CN201503630U - Voice Security Device - Google Patents

Abstract

The utility model discloses a voice security device, which is composed of an outer box with a power input interface and a communication interface and a built-in voice alarm system, which also includes: a voice input unit for inputting voice information; The voice alarm system consists of a voice recognition module, a data processing and transmission module and a power supply module, wherein the voice recognition module is used for voice learning data storage and voice recognition input; the data processing and transmission module is used for voice data transmission and processing; The power supply module is used to provide power to the above units; the voice recognition module is bidirectionally connected to the data processing and transmission module through the data bus; the data processing and transmission module is connected to the upper computer control center through the communication interface. It is used in building safety monitoring, and can reduce the loss caused by safety violations or some emergencies to a certain extent through convenient and quick voice alarm, and increase the sense of security of residents.

Description

Voice Security Device

technical field

The utility model belongs to safety protection equipment, in particular to a safety protection facility for speech recognition.

Background technique

At present, speech recognition technology mainly focuses on the feature extraction, model building, recognition algorithm and language processing technology of speech recognition. The research and development of speech recognition application technology is mainly concentrated in the field of communication, while the development of application technology in other fields is less, such as building Intelligent control, there are not many products in China that really use voice recognition technology in building intelligent control. Building intelligence is the use of high-tech to monitor the equipment in the building, manage information resources, and provide users with information services. It is the crystallization of building technology adapting to the requirements of modern society informatization. With the rapid development of high technology such as computers, intelligent building construction has also embarked on a high-speed development track. People's expectations for an economical, comfortable, efficient and safe environment are getting higher and higher. Using the advantages of voice alarm and SI technology to provide users with security It will be people's expectation to minimize the loss caused by sudden danger and illness.

In addition, the application level of speech recognition technology in China is relatively low at present. In addition to the communication field, it is basically used in low-end smart toys, lighting control, etc., and has not really given full play to the advantages of speech recognition technology. Therefore, speech recognition technology is widely used in buildings. There will be broad prospects in security monitoring.

In recent years, with the continuous improvement of living standards, people's safety awareness is also increasing day by day. How can the living quarters ensure the safety of residents to the greatest extent, and when the safety of residents is violated, they can get alarm information in time and reach the scene? Ways to remove their dangers have become an urgent problem to be solved at present. We often see from the Internet that some criminals enter the house to commit crimes such as theft, robbery, and murder. Although the victim speaks out and resists vigorously, he still fails to call for rescue. When he finds out, everything is too late; It is found that there is a fire, the smoke is full, and the person concerned has lost his way and cannot call the police; or the lonely old man with limited mobility suddenly feels unwell, and when he gets to the phone, he is out of control; all of this is because he cannot call the police or The tragedy caused by the untimely alarm.

At present, the main problem of the products in the similar speech recognition technology market in the market is: the recognition ability is not very perfect, and it is easy to cause false positives or false positives.

Contents of the invention

The purpose of this utility model is to provide a voice security device, which can reduce the loss caused by security violations or some emergencies (fires, sudden illnesses, etc.) to a certain extent through convenient and quick voice alarms, increasing the Residents' sense of security.

In order to achieve the above object, the utility model takes the following design scheme:

A voice security device is composed of an outer box with a power input interface and a communication interface and a built-in voice alarm system, which also includes:

an input voice unit for inputting voice information;

The built-in voice alarm system is composed of a voice recognition module, a data processing transmission module and a power supply module, wherein

Speech recognition module, used for speech learning data storage and speech recognition input;

The data processing and transmission module is used for the transmission and processing of voice data;

A power module, used to provide power to the above units;

The voice recognition module is bidirectionally connected to the data processing and transmission module through the data bus; the data processing and transmission module is connected to the upper computer control center through the communication interface.

The voice security device also has a learning control port.

Described speech recognition module is made up of microphone amplifier and AD sampling circuit unit and data storage circuit unit, bus data circuit unit; Described data processing transmission module is made up of central processing unit CPU and reset circuit unit, communication circuit unit, bus data circuit unit composition.

The voice alarm of the voice security equipment of the utility model does not need to be contacted, and only needs to say a few simple words to alarm. The voice template can be recorded according to one's own situation. What do you want to do?" or other sentences (preferably words that are not often spoken) are used as templates. When the parties encounter danger, they can say these words to call the police. In addition, the speech recognition algorithm is relatively mature, the recognition rate for small vocabulary is also very high, and the response speed is fast, so it is more convenient and fast, and it is also very safe and reliable. positive meaning.

The utility model has the advantages of:

1. Easy to use: No hand movements are required, especially suitable for the elderly and children with limited mobility, and the alarm is more concealed and timely.

2. The alarm is accurate and reliable: the current alarm recognition rate can reach more than 95%, and the false alarm rate is less than 1%.

3. Opened up a new field of voice alarm, because the application of voice recognition technology in building intelligence is very little at present, and it is still in the exploratory stage in China, so the research results have extensive promotion value.

Description of drawings

Fig. 1 is the structural representation of the utility model voice security equipment

Fig. 2 is the electrical schematic diagram of an embodiment of the voice recognition module of the voice security equipment

Figure 3 is the electrical schematic diagram of the data processing and transmission module of the voice security equipment

Figure 4 is the electrical schematic diagram of the power module of the voice security equipment

Figure 5 is a schematic diagram of the interface of the upper computer software of the voice security equipment

Below in conjunction with accompanying drawing and specific embodiment the utility model is described further:

Detailed ways

The voice security device of the utility model is composed of an outer box with a power input interface and a communication interface and a built-in voice alarm system. Referring to Fig. 1, the core technology of the voice security equipment of the present invention is mainly composed of voice recognition module 1, data processing and transmission module 2, power supply module 3 and upper computer control center 4.

As shown in Fig. 2, described voice recognition module 1 is used for voice learning, data storage and recognition input to voice, and wherein this module includes microphone amplifier U6, AD sampling circuit unit, data storage circuit unit U4 and bus data circuit unit, U5 is the horn.

The speech recognition module is set with a learning control port and a working control port. When the external learning control port of the speech recognition module 1 was connected (the EN pin of the speech recognition module was connected to the ground wire), the speech recognition module was in the learning state, and the speech recognition module prompted the input of corresponding voice alarm sentences through the U5 loudspeaker, continuously After learning 5 alarm commands, it will end automatically. When the external learning control port is disconnected (that is, the EN pin of the speech recognition module is suspended), the speech recognition module is in the working state, and if the external voice signal has an alarm command matching the learned sentence, the speech recognition module passes the data bus D0- D3 notifies the data processing transmission module.

The user can store 4 alarm passwords in advance, such as: fire alarm, bandit alarm, medical alarm, and disarming the police; the voice processing module uses an external microphone or other media devices to input voice or word content, and after the internal microphone amplifier is accurately amplified, the voice signal The content is digitized by the A/D converter, and the internal sound effect processor samples and stores the features in the digitized speech or words.

When a similar alarm situation occurs during the user's use, just call out the type of alarm that occurred. The input voice is sampled by the sound processor feature, and compared with the sampling feature of the target word stored in the internal, it must be exactly the same The selected recognized target word matches, and the result is output signal.

The above functions can be realized by using the TS-H001 speech recognition module produced and sold by Xiamen Tiancong Software Co., Ltd.

Figure 3 shows the circuit schematic diagram of the data processing and transmission module 2 of the voice security equipment, which includes: a reset circuit unit composed of central CPU units U1, R1 and C1 and a 485 serial communication circuit unit U3. When the data processing and transmission module is powered on, the system resets through R1 and C1, the circuit starts U1, and the system starts to work. If U1 receives an alarm command from the voice recognition module through the data bus D0-D3, U1 sends an alarm command notification through U3 Central control software. The central control software can also send commands through the serial port of the computer to query the current status of the voice recognition module through U3 to U1.

Fig. 4 is a schematic diagram of the principle of the power supply used in the embodiment of the utility model. This circuit transforms the mains 220V through T1, BR rectifies, E1 filters, and stabilizes the voltage with the voltage regulator chip P1 to form a DC 5V power supply. The commercially available GX-051A power supply module (parameters: INPUT: AC100-240V-50/60HZ; OUTPUT: DC5V 1000mA) can be directly used.

As shown in Figure 5, it is the host computer software independently designed by the inventor of the present application: including user management information, real-time alarm display, historical alarm query, community map display, etc. The user management information mainly displays the detailed information of all users controlled by the software; the map information mainly displays the relative geographical location of the current users, which is convenient for timely handling when an alarm occurs; the alarm information provides the type of alarm that the current user has occurred. Real-time alarm information displays the content of the current alarm. All alarms are stored in the database for easy reference, and can also be printed out as historical alarm information.

The working principle of the voice security equipment of the utility model:

The voice processing module uses an external microphone or other media devices to input voice or words, and after being accurately amplified by the internal microphone amplifier, the content of the voice signal is digitized by the A/D converter, and the internal sound processor converts the digitized voice or words Features are sampled and stored.

After entering the speech recognition operation mode, the input speech is sampled by the sound processor feature, and compared with the sampling feature of the target word stored in the interior, it must be exactly matched with the selected target word for recognition, and the result is the output signal.

Speech recognition is the front-end sensor of the system, processing whether the user has an alarm, and if the alarm is what kind of alarm, according to the type of alarm, the staff on duty at the center can confirm and take corresponding measures to deal with it.

The signal output by the voice module is sent to the microprocessor, and the microprocessor identifies what kind of alarm it is according to the obtained signal, and then reports it to the control center through serial port communication.

The working process of the voice security device of the utility model is: when an alarm situation occurs, the voice recognition module 1 recognizes the matching alarm voice type, and notifies the data processing and transmission module 2 through the data bus, and the data processing and transmission module obtains the alarm command and passes the data transmission Notify the upper computer control center, the main control computer can realize the sound/light alarm to notify the duty personnel under the judgment and command of the monitoring program. According to the type of alarm, the center staff on duty confirmed to take corresponding measures to deal with it.

Claims (6)

1. a voice security protection equipment is made up of outer box that has power input interface and communication interface and built-in phonetic warning system, it is characterized in that also including:

One input voice unit is used to import voice messaging;

Described built-in phonetic warning system is made up of sound identification module, data processing transport module and power module, wherein

Sound identification module is used for the phonetic study data storage and to the identification of voice input;

The data processing transport module is used for transmission and processing to speech data;

Power module is used for providing power supply to above-mentioned each unit;

Described sound identification module is connected with the data processing transport module is two-way by data bus; The data processing transport module is connected with the PC control center by communication interface.

2. voice security protection equipment according to claim 1 is characterized in that: described sound identification module is made up of amplifier of microphone, AD sample circuit unit, inner sound effect processor and data storage circuitry unit; Described amplifier of microphone is numerical information with the output of the voice messaging processing and amplifying that collects through AD sample circuit cell translation, is sampled by the feature of inner sound effect processor in will this digitized voice words and expressions and is stored in the data storage circuitry unit.

3. voice security protection equipment according to claim 2 is characterized in that: described sound identification module is set with Learning Control port and work control port.

4. voice security protection equipment according to claim 1 is characterized in that: described communication interface is 485 communication interfaces.

5. voice security protection equipment according to claim 1 is characterized in that: described sound identification module adopts the TS-H001 sound identification module.

6. voice security protection equipment according to claim 2 is characterized in that: described input voice unit is a microphone.

Images