阅读说明：本技术 一种语音控制物业管理的方法、系统、设备及介质 (Method, system, equipment and medium for voice control property management ) 是由 鲍玟浠 于 2021-09-10 设计创作，主要内容包括：本发明提出了一种语音控制物业管理的方法、系统、设备及介质,涉及语音控制技术领域。包括利用客户端设备采集多个用于控制物业管理的原始语音信息,提取语音脉冲序列中的语音特征矢量,并量化成标准语音特征矢量；在客户端设备上和后台终端均设置隐马尔可夫模型对多次提取的标准语音特征矢量进行概率统计,得出最佳标准语音特征矢量；将最佳标准语音特征矢量与对比语音矢量进行比较,若最佳标准语音特征矢量与任一对比语音矢量相匹配,向对比语音矢量对应的控制设备发送启动信号；反之则不发送启动信号。其能够采用声音控制的方法,迅速地使对应的控制设备在接收到语音信息后进行对应的控制,节约了寻找的时间,由此提高了便捷性。(The invention provides a method, a system, equipment and a medium for controlling property management by voice, and relates to the technical field of voice control. The method comprises the steps that a plurality of original voice messages for controlling property management are collected by client equipment, voice feature vectors in a voice pulse sequence are extracted, and the voice feature vectors are quantized into standard voice feature vectors; hidden Markov models are arranged on the client equipment and the background terminal to carry out probability statistics on the standard voice feature vectors extracted for multiple times, so that the optimal standard voice feature vector is obtained; comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent. The voice control method can be adopted, corresponding control equipment can be rapidly controlled after receiving voice information, searching time is saved, and convenience is improved.)

1. A method for voice-controlled property management is characterized by comprising

Acquiring a plurality of original voice messages for controlling property management by using client equipment, and converting any original voice message into a voice pulse sequence by using an acoustic-electric converter for transmission;

after filtering an interference signal of any one voice pulse sequence, extracting a voice feature vector in the voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector;

establishing a local hidden Markov model on the client equipment, and setting a terminal hidden Markov model at a background terminal; when the client device is not connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the local hidden Markov model to obtain the optimal standard voice feature vector; when the client equipment is connected with a background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the terminal hidden Markov model to obtain the optimal standard voice feature vector;

presetting a voice template library, and storing a comparison voice vector for controlling the related operation of property management in the voice template library;

comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

2. The method of claim 1, wherein the step of extracting the speech feature vectors in the speech pulse sequence comprises:

extracting each frame of the voice pulse sequence, carrying out Fourier transform on each frame of the voice pulse sequence to obtain a voice frequency spectrum, carrying out triangular filtering conversion according to the voice frequency spectrum to obtain a Mel frequency cepstrum, and storing the obtained Mel frequency cepstrum as a voice feature vector.

3. The method of claim 1, wherein the step of comparing the best standard speech feature vector with the comparison speech vector comprises:

and respectively calculating the Euclidean distance corresponding to each frame of the standard voice feature vector and the comparison feature vector by using a dynamic time warping algorithm, if the Euclidean distance corresponding to two adjacent frames is within a preset range, determining that the standard voice feature vector is matched with the comparison feature vector, otherwise, determining that the standard voice feature vector is not matched with the comparison feature vector.

4. The method of claim 3, wherein the plurality of comparison feature vectors in the speech template library correspond to a control device for controlling property management.

5. The method according to claim 1, further comprising the background terminal saving the extracted standard speech feature vector of the client device to a storage unit by using the internet, and saving the standard speech feature vector adapted to the comparison speech vector as a new comparison speech vector to the speech template library.

6. The method of claim 5, further comprising the backend terminal updating the voice template library of the client device in real-time via the internet.

7. The method of claim 1, wherein the step of not sending the activation signal is further followed by the step of not sending the activation signal: and playing preset voice for prompting the unrecognized voice by using the player, and re-collecting the voice information, and stopping working when the voice information is not collected again within the preset time.

8. A system for voice-controlled property management, comprising:

the system comprises an acquisition module, a property management module and a voice pulse sequence module, wherein the acquisition module is used for acquiring a plurality of original voice information for controlling property management by using client equipment and converting any original voice information into a voice pulse sequence by using an acoustic-electric converter for transmission;

the conversion module is used for extracting a voice feature vector in the voice pulse sequence after filtering an interference signal of any voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector;

the screening identification module is used for establishing a local hidden Markov model on the client equipment and setting a terminal hidden Markov model at a background terminal; when the client device is not connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the local hidden Markov model to obtain the optimal standard voice feature vector; when the client equipment is connected with a background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the terminal hidden Markov model to obtain the optimal standard voice feature vector;

the model presetting module is used for presetting a voice template library and storing a comparison voice vector for controlling the related operation of property management in the voice template library;

the judging module is used for comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

9. An electronic device comprising at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete mutual communication through the data bus; the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.

Technical Field

The invention relates to the technical field of voice control, in particular to a method, a system, equipment and a medium for voice control property management.

Background

Due to the continuous improvement of the living standard and the living quality of people, the safety requirements of the current resident on the living are also the rising ship height, and the living safety is the primary task of the current property management. Under this trend, the importance of property management of smart cells is increasingly highlighted. For operations in property management such as a gas switch, a water-power switch and the like of each household, various switches need to be searched in the prior art, and due to the fact that the number of the switches is large and the types are complicated, management is time-consuming and labor-consuming, a property management method capable of being directly controlled through voice is needed.

Disclosure of Invention

The invention aims to provide a method for controlling property management by voice, which can adopt a voice control method to quickly enable corresponding control equipment to carry out corresponding control after receiving voice information, thereby saving the searching time and improving the convenience.

The embodiment of the invention is realized by the following steps:

in a first aspect, an embodiment of the present application provides a method for controlling property management by voice, which includes acquiring, by a client device, a plurality of pieces of original voice information for controlling property management, and converting any one of the pieces of original voice information into a voice pulse sequence by using an acousto-electric converter for transmission; after filtering an interference signal of any one voice pulse sequence, extracting a voice feature vector in the voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector; establishing a local hidden Markov model on the client equipment, and setting a terminal hidden Markov model at a background terminal; when the client device is not connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the local hidden Markov model to obtain the optimal standard voice feature vector; when the client equipment is connected with a background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the terminal hidden Markov model to obtain the optimal standard voice feature vector; presetting a voice template library, and storing a comparison voice vector for controlling the related operation of property management in the voice template library; comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

Based on the first aspect, in some embodiments of the present invention, the step of extracting the speech feature vector in the speech pulse sequence includes: extracting each frame of the voice pulse sequence, carrying out Fourier transform on each frame of the voice pulse sequence to obtain a voice frequency spectrum, carrying out triangular filtering conversion according to the voice frequency spectrum to obtain a Mel frequency cepstrum, and storing the obtained Mel frequency cepstrum as a voice feature vector.

Based on the first aspect, in some embodiments of the invention, the step of comparing the best standard speech feature vector with the comparison speech vector comprises: and respectively calculating the Euclidean distance corresponding to each frame of the standard voice feature vector and the comparison feature vector by using a dynamic time warping algorithm, if the Euclidean distance corresponding to two adjacent frames is within a preset range, determining that the standard voice feature vector is matched with the comparison feature vector, otherwise, determining that the standard voice feature vector is not matched with the comparison feature vector.

Based on the first aspect, in some embodiments of the present invention, the plurality of comparison feature vectors in the speech template library correspond to a control device for controlling property management.

Based on the first aspect, in some embodiments of the present invention, the backend terminal further stores the extracted standard speech feature vector of the client device to a storage unit by using the internet, and stores the standard speech feature vector adapted to the comparison speech vector therein as a new comparison speech vector to the speech template library.

Based on the first aspect, in some embodiments of the present invention, the method further includes updating, by the backend terminal, the speech template library of the client device in real time through the internet.

Based on the first aspect, in some embodiments of the present invention, the step of not sending the start signal further includes: and playing preset voice for prompting the unrecognized voice by using the player, and re-collecting the voice information, and stopping working when the voice information is not collected again within the preset time.

In a second aspect, an embodiment of the present application provides a system for controlling property management by voice, which includes an acquisition module, configured to acquire, by using a client device, a plurality of original voice information for controlling property management, and convert any of the original voice information into a voice pulse sequence by using an acousto-electric converter for transmission;

the conversion module is used for extracting a voice feature vector in the voice pulse sequence after filtering an interference signal of any voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector;

the screening identification module is used for establishing a local hidden Markov model on the client equipment and setting a terminal hidden Markov model at a background terminal; when the client device is not connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the local hidden Markov model to obtain the optimal standard voice feature vector; when the client equipment is connected with a background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the terminal hidden Markov model to obtain the optimal standard voice feature vector;

the model presetting module is used for presetting a voice template library and storing a comparison voice vector for controlling the related operation of property management in the voice template library;

the judging module is used for comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

In a third aspect, an embodiment of the present application provides an electronic device, which includes at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete mutual communication through the data bus; the memory stores program instructions executable by the processor, which are invoked by the processor to perform a method of voice-controlled property management.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements a method for voice-controlled property management.

Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:

a method for controlling property management by voice is invented, in view of the fact that the number of users is large in property management and the number of switch types needing property management is large, and therefore the method for controlling property by voice is adopted, corresponding switches can be rapidly controlled after voice information is received, and convenience is improved. For the collection of sound information, a mature mode in the prior art is adopted, namely, a recorder or a recording pen is used for recording sound, then a sound-electricity converter is used for converting the sound into a voice pulse sequence, and the voice pulse sequence is transmitted by using an electric signal mode. Because current noise or other interference is accompanied in the process of recording the sound signal, the invention adopts a notch filter, and in view of the sound with the most sensitive sound frequency range of human ears between 1KHZ and 3KHZ, the invention filters the signals corresponding to the sound with the frequency less than 1KHZ and greater than 3 KHZ. And simultaneously, extracting a voice feature vector from the filtered voice pulse sequence, and quantizing the voice feature vector into a standard voice feature vector. Establishing a hidden Markov model which is mainly used for carrying out probability statistics on the standard voice feature vector to obtain the optimal standard voice feature vector; the hidden Markov models are arranged on the client device and the background terminal, and are mainly used for avoiding the problem that the client device cannot communicate with the background terminal in real time when the network is disconnected, so that the client device cannot be used. Setting a local hidden Markov model on the client equipment to carry out probability statistics on the multiple extracted standard speech feature vectors to obtain the optimal standard speech feature vector; and arranging a terminal hidden Markov model on the background terminal to carry out probability statistics on the standard voice feature vectors extracted for multiple times to obtain the optimal standard voice feature vector. The method comprises the steps that standard voice feature vectors are received at a client side and a background terminal, the standard voice feature vectors need to be judged, the judged operation needs to be compared, and therefore a voice template library is set, and compared voice vectors which are used for controlling related operations of property management in a relevant mode are set in the voice template library. After the control equipment for property management receives the voice information, for example, the user sends out 'turn on 104 room gas switch', and after the control equipment confirms the voice matching, the control equipment turns on 104 room gas switch, so that the voice control property management is completed, and the convenience is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

FIG. 1 is a flow chart of a method for voice-controlled property management in accordance with the present invention;

FIG. 2 is another flow chart of a method for voice-controlled property management in accordance with the present invention;

FIG. 3 is a flowchart of a method for voice-controlled property management according to the present invention;

FIG. 4 is a flow chart illustrating the structure of a voice-controlled property management system according to the present invention;

fig. 5 is a schematic flow chart of a structure of an electronic device according to the present invention.

Icon: 1. an acquisition module; 2. a conversion module; 3. a screening identification module; 4. a model presetting module; 5. a judgment module; 6. a processor; 7. a memory; 8. a data bus.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

It is noted that, herein, relational terms such as first and second, and the like may be 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. Also, 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings or orientations or positional relationships conventionally found in use of products of the application, and are used only for convenience in describing the present application and for simplification of description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application.

In the description of the present application, it is also to be noted that, unless otherwise explicitly specified or limited, the terms "disposed" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the individual features of the embodiments can be combined with one another without conflict.

Example 1

Referring to fig. 1, in view of the fact that the number of users in property management is large and the number of types of switches requiring property management is large, the method of voice control is adopted in the present invention, and the corresponding switches can be rapidly controlled after receiving voice information, thereby improving convenience.

S101: the method comprises the steps that a plurality of original voice messages for controlling property management are collected by client equipment, and any original voice message is converted into a voice pulse sequence by an acoustic-electric converter to be transmitted;

for the collection of sound information, a mature mode in the prior art is adopted, namely, a recorder or a recording pen is used for recording sound, then a sound-electricity converter is used for converting the sound into a voice pulse sequence, and the voice pulse sequence is transmitted by using an electric signal mode.

S102: after filtering an interference signal from any voice pulse sequence, extracting a voice feature vector in the voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector;

because current noise or other interference is accompanied in the process of recording the sound signal, the invention adopts a notch filter, and in view of the sound with the most sensitive sound frequency range of human ears between 1KHZ and 3KHZ, the invention filters the signals corresponding to the sound with the frequency less than 1KHZ and greater than 3 KHZ. And simultaneously, extracting a voice feature vector from the filtered voice pulse sequence, and quantizing the voice feature vector into a standard voice feature vector.

S103: establishing a local hidden Markov model on client equipment, and setting a terminal hidden Markov model at a background terminal; when the client equipment is not connected with the background terminal through the Internet, carrying out probability statistics on the repeatedly extracted standard speech feature vectors by using a local hidden Markov model to obtain the optimal standard speech feature vectors; when the client device is connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using a terminal hidden Markov model to obtain the optimal standard voice feature vector;

establishing a hidden Markov model which is mainly used for carrying out probability statistics on the standard voice feature vector to obtain the optimal standard voice feature vector; the hidden Markov models are arranged on the client device and the background terminal, and are mainly used for avoiding the problem that the client device cannot communicate with the background terminal in real time when the network is disconnected, so that the client device cannot be used. Setting a local hidden Markov model on the client equipment to carry out probability statistics on the multiple extracted standard speech feature vectors to obtain the optimal standard speech feature vector; and arranging a terminal hidden Markov model on the background terminal to carry out probability statistics on the standard voice feature vectors extracted for multiple times to obtain the optimal standard voice feature vector.

S104: presetting a voice template library, and storing a comparison voice vector for controlling the related operation of property management in the voice template library;

the method comprises the steps that standard voice feature vectors are received at a client side and a background terminal, the standard voice feature vectors need to be judged, the judged operation needs to be compared, and therefore a voice template library is set, and compared voice vectors which are used for controlling related operations of property management in a relevant mode are set in the voice template library.

S105: comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

After the control equipment for property management receives the voice information, for example, the user sends out 'turn on 104 room gas switch', and after the control equipment confirms the voice matching, the control equipment turns on 104 room gas switch, so that the voice control property management is completed, and the convenience is improved.

In some embodiments of the present invention, the step of extracting the speech feature vector in the speech pulse sequence comprises:

extracting each frame of the voice pulse sequence, carrying out Fourier transform on each frame of the voice pulse sequence to obtain a voice frequency spectrum, carrying out triangular filtering conversion according to the voice frequency spectrum to obtain a Mel frequency cepstrum, and storing the obtained Mel frequency cepstrum as a voice feature vector.

In some embodiments of the present invention, features in the speech pulse sequence are extracted, which cannot be directly recognized on the pulse sequence signal, so that the speech pulse sequence is visualized, that is, each frame of the pulse sequence signal is converted into a speech spectrum by fourier transform, and a mel-frequency cepstrum is obtained by performing triangular filtering on a vector corresponding to the speech pulse sequence on the speech spectrum, so that a final speech feature vector can be obtained.

In some embodiments of the present invention, the step of comparing the best standard speech feature vector with the comparison speech vector comprises:

and respectively calculating the Euclidean distance corresponding to each frame of the standard voice feature vector and the comparison feature vector by using a dynamic time warping algorithm, if the Euclidean distance corresponding to two adjacent frames is within a preset range, determining that the standard voice feature vector is matched with the comparison feature vector, otherwise, determining that the standard voice feature vector is not matched with the comparison feature vector.

In some embodiments of the present invention, in the process of comparing the optimal standard speech feature vector with the comparison speech vector, the similarity of the shapes of the optimal standard speech feature vector and the comparison speech vector is usually adopted, but since a computer cannot visually compare the optimal standard speech feature vector with the comparison speech vector like a human being, the euclidean distance of each frame is calculated by using a dynamic time warping algorithm, wherein the euclidean distance of two adjacent frames is in an interval of a difference value between-2 MM and 3MM, and the standard speech feature vector and the comparison feature vector are judged to be matched, otherwise, the euclidean distance is not matched.

In some embodiments of the invention, the plurality of comparison feature vectors in the speech template library correspond to a control device that controls property management.

In some embodiments of the present invention, in order to make the adaptation as much as possible in view of the fact that in real life, there are multiple dialects in addition to mandarin, the present implementation saves the multiple dialects as comparison feature vectors into a speech template library, and associates the comparison feature vectors of the same semantic meaning with the same control device that controls property management, thereby improving the adaptation.

Referring to fig. 2, in some embodiments of the invention, S106: the background terminal stores the extracted standard voice feature vector of the client device to a storage unit by using the Internet, and stores the standard voice feature vector matched with the comparison voice vector as a new comparison voice vector to a voice template library.

In some embodiments of the present invention, since the voices of different speakers are different, in order to avoid matching errors as much as possible, the standard speech feature vectors of all users of the client device connected to the background terminal are stored each time, and the background terminal is used as a new comparison speech vector, so that matching is more accurate.

Referring to fig. 3, in some embodiments of the invention, S107: the method also comprises the step that the background terminal updates the voice template library of the client equipment in real time through the Internet.

In some embodiments of the present invention, in order to further improve the matching accuracy in an offline situation, the new comparison speech vector in the background terminal is synchronized to the client device by using the internet, and the speech template library is updated in real time.

In some embodiments of the present invention, the step of not sending the start signal otherwise further includes: and playing preset voice for prompting the unrecognized voice by using the player, and re-collecting the voice information, and stopping working when the voice information is not collected again within the preset time.

In some embodiments of the present invention, when the property manager operates the control device, if the control device is not successfully started, the real-time reminding should be performed, and the specific implementation manner is to play a preset voice for reminding that the control device is not recognized by using a player, where the preset voice is, for example: the method comprises the steps of 'unable to identify your command, please repeat the command', and the like, and simultaneously collecting voice information again; and if no voice information is collected again within 5 minutes, the voice recognition device judges that no command is issued and stops working.

Example 2

Referring to fig. 4, a system for voice-controlled property management according to an embodiment of the present application includes

The system comprises an acquisition module 1, a property management module and a voice processing module, wherein the acquisition module 1 is used for acquiring a plurality of original voice information for controlling property management by using client equipment, and converting any original voice information into a voice pulse sequence by using an acoustic-electric converter for transmission;

the conversion module 2 is used for extracting a voice feature vector in the voice pulse sequence after filtering an interference signal from any voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector;

the screening and identifying module 3 is used for establishing a local hidden Markov model on the client equipment and setting a terminal hidden Markov model at a background terminal; when the client equipment is not connected with the background terminal through the Internet, carrying out probability statistics on the repeatedly extracted standard speech feature vectors by using a local hidden Markov model to obtain the optimal standard speech feature vectors; when the client device is connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using a terminal hidden Markov model to obtain the optimal standard voice feature vector;

the model presetting module 4 is used for presetting a voice template library and storing a comparison voice vector for controlling the related operation of property management in the voice template library;

the judging module 5 is used for comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

Example 3

Referring to fig. 5, an electronic device provided in the embodiment of the present application includes at least one processor 6, at least one memory 7, and a data bus 8; wherein: the processor 6 and the memory 7 complete mutual communication through a data bus 8; the memory 7 stores program instructions executable by the processor 6, the processor 6 calling the program instructions to perform a method of voice-controlled property management. For example, the following steps are realized:

acquiring a plurality of original voice messages for controlling property management by using client equipment, and converting any original voice message into a voice pulse sequence by using an acoustic-electric converter for transmission; after filtering an interference signal of any one voice pulse sequence, extracting a voice feature vector in the voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector; establishing a local hidden Markov model on the client equipment, and setting a terminal hidden Markov model at a background terminal; when the client device is not connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the local hidden Markov model to obtain the optimal standard voice feature vector; when the client equipment is connected with a background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the terminal hidden Markov model to obtain the optimal standard voice feature vector; presetting a voice template library, and storing a comparison voice vector for controlling the related operation of property management in the voice template library; comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

The MEMORY 7 may be, but is not limited to, a RANDOM ACCESS MEMORY 7 (RAM), a READ ONLY MEMORY (READ ONLY MEMORY, ROM), a PROGRAMMABLE READ ONLY MEMORY (PROGRAMMABLE READ-ONLY MEMORY, PROM), an ERASABLE READ ONLY MEMORY (EPROM), an electrically ERASABLE READ ONLY MEMORY (EEPROM), and the like.

The processor 6 may be an integrated circuit chip having signal processing capabilities. The PROCESSOR 6 may be a general-purpose PROCESSOR, including a CENTRAL PROCESSING UNIT (CPU), a NETWORK PROCESSOR (NP), etc.; it may also be a digital signal processor (DIGITAL SIGNAL PROCESSING, DSP), an APPLICATION Specific Integrated CIRCUIT (ASIC), a FIELD PROGRAMMABLE gate array (FIELD-PROGRAMMABLE GATE ARRAY, FPGA) or other PROGRAMMABLE logic device, discrete gate or transistor logic device, discrete hardware component.

Example 4

A computer-readable storage medium is provided for embodiments of the present application, on which a computer program is stored, which, when being executed by a processor 6, carries out a method for voice-controlled property management. For example, the following steps are realized:

acquiring a plurality of original voice messages for controlling property management by using client equipment, and converting any original voice message into a voice pulse sequence by using an acoustic-electric converter for transmission; after filtering an interference signal of any one voice pulse sequence, extracting a voice feature vector in the voice pulse sequence, and quantizing the extracted voice feature vector into a standard voice feature vector; establishing a local hidden Markov model on the client equipment, and setting a terminal hidden Markov model at a background terminal; when the client device is not connected with the background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the local hidden Markov model to obtain the optimal standard voice feature vector; when the client equipment is connected with a background terminal through the Internet, carrying out probability statistics on the standard voice feature vectors extracted for multiple times by using the terminal hidden Markov model to obtain the optimal standard voice feature vector; presetting a voice template library, and storing a comparison voice vector for controlling the related operation of property management in the voice template library; comparing the optimal standard voice feature vector with the comparison voice vector, and if the optimal standard voice feature vector is matched with any comparison voice vector, sending a starting signal to the control equipment corresponding to the comparison voice vector; otherwise, the starting signal is not sent.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a READ-ONLY MEMORY (ROM), a RANDOM ACCESS MEMORY (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.