CN109087641A - Intelligent sound box, instruction input device and its safe early warning method, device - Google Patents
Intelligent sound box, instruction input device and its safe early warning method, device Download PDFInfo
- Publication number
- CN109087641A CN109087641A CN201810980451.4A CN201810980451A CN109087641A CN 109087641 A CN109087641 A CN 109087641A CN 201810980451 A CN201810980451 A CN 201810980451A CN 109087641 A CN109087641 A CN 109087641A
- Authority
- CN
- China
- Prior art keywords
- instruction
- target
- early warning
- target word
- command
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004590 computer program Methods 0.000 claims description 19
- 230000003993 interaction Effects 0.000 abstract description 6
- 230000005540 biological transmission Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
This application discloses a kind of intelligent sound box, instruction input device and its safe early warning methods, device, it is related to field of human-computer interaction, for solving the problems, such as that obtaining user's request by voice is easy to cause information leakage, this method comprises: obtaining target instruction target word using instruction input device, judge whether target instruction target word is dangerous command, if target instruction target word is dangerous command, corresponding early warning information is played.From the above, it can be seen that, the present invention is by obtaining the instruction of user for the instruction input device of acquisition instructions, after getting instruction safety check can be carried out to instruction, if instruction is dangerous command, then instruction will not further be sent request as safety command, but play corresponding early warning, prompt the input instruction of user's specification, to prevent dangerous command, the problem of phonetic order reveals privacy information is avoided.
Description
Technical field
The present invention relates to field of human-computer interaction, in particular to a kind of intelligent sound box, instruction input device and its safe early warning side
Method, device.
Background technique
Recently, with the development of science and technology, the artificial intelligence epoch have arrived, human-computer interaction device also comes into being, for
Promote the progress of society while people provide convenient.
The one kind of intelligent sound box as human-computer interaction device can be interacted in a manner of voice dialogue with user, from
And the available desired information of user, in the prior art, intelligent sound box gets the phonetic order of user, and instruction is sent out
It send to server, after the request content of server return instruction, using intelligent sound box playing request content, but it is this by adopting
Collect the mode that voice obtains user information, having greatly may be lack of standardization or dangerous because of instruction, so as to cause user information
Leakage, causes danger.In consideration of it, providing one kind to ensure that information is not leaked method is that those skilled in the art are urgently to be resolved
The technical issues of.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of intelligent sound box, instruction input device and its safe early warning method,
Device can carry out safety check to it after getting phonetic order, avoid the safety of information leakage.Its concrete scheme is such as
Under:
In a first aspect, being applied to intelligent sound box the invention discloses a kind of safe early warning method, comprising:
Target instruction target word is obtained using instruction input device;
Judge whether the target instruction target word is dangerous command;
If the target instruction target word is dangerous command, corresponding early warning information is played.
It is optionally, described to judge whether the target instruction target word is dangerous command, comprising:
Judge whether the target instruction target word is dangerous command by presetting offline alarm command library.
It is optionally, described to judge whether the target instruction target word is dangerous command, comprising:
Judge whether the target instruction target word is dangerous command by presetting offline alarm command library;
If it is, determining the target instruction target word for dangerous command;
If it is not, then judging whether the target instruction target word is that danger refers to by the default online alarm command library in server
It enables, if it is, determining the target instruction target word for dangerous command.
Optionally, the default line off instruction library is the instruction database positioned at the intelligent sound box or described instruction input device.
Optionally, the safe early warning method further include:
It presets online alarm command library using described and presets offline alarm command library to described and be updated.
Second aspect, the invention discloses a kind of safe early warning methods, are applied to instruction input device, comprising:
Obtain target instruction target word;
Judge whether the target instruction target word is dangerous command by local default offline alarm command library;
If the target instruction target word is dangerous command, the corresponding early warning information of the target instruction target word is sent to intelligence
Speaker plays out.
The third aspect, the invention discloses a kind of safety early warning devices, are applied to intelligent sound box, comprising:
First obtains module, for obtaining target instruction target word using instruction input device;
First judgment module, for judging whether the target instruction target word is dangerous command;
Early warning playing module plays corresponding early warning information if being dangerous command for the target instruction target word.
Fourth aspect, the invention discloses a kind of safety early warning devices, are applied to instruction input device, comprising:
Second obtains module, for obtaining target instruction target word;
Second judgment module, for judging whether the target instruction target word is danger by local default offline alarm command library
Danger instruction;
Early warning sending module, if being dangerous command for the target instruction target word, by the corresponding early warning of the target instruction target word
Prompt information is sent to intelligent sound box and plays out.
5th aspect, the invention discloses a kind of intelligent sound boxes, comprising:
Memory, for storing computer program;
Processor, the step of aforementioned disclosed safe early warning method is realized when for executing the computer program.
6th aspect, the invention discloses a kind of instruction input devices, comprising:
Memory, for storing computer program;
Processor, the step of aforementioned disclosed safe early warning method is realized when for executing the computer program.
As it can be seen that the present invention, which passes through, obtains target instruction target word using instruction input device, judge whether target instruction target word is dangerous command,
If target instruction target word is dangerous command, corresponding early warning information is played.From the foregoing, it will be observed that the present invention is by being used for acquisition instructions
Instruction input device obtain user instruction, get instruction after can to instruction carry out safety check, if instruction be that danger refers to
It enables, then plays early warning, the input instruction that user can be prompted to standardize prevents dangerous command, so as to avoid phonetic order
The problem of revealing privacy information.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of safe early warning method flow chart disclosed by the invention;
Fig. 2 is a kind of safe early warning method flow chart disclosed by the invention;
Fig. 3 is a kind of safety early warning device structural schematic diagram disclosed by the invention;
Fig. 4 is a kind of safety early warning device structural schematic diagram disclosed by the invention;
Fig. 5 is a kind of specific intelligent sound box hardware structural diagram disclosed by the invention;
Fig. 6 is a kind of specific instruction input device hardware structural diagram disclosed by the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In the prior art, intelligent sound box is transmitted in server acquisition request by collecting the phonetic order of user
Hold, it is this acquisition voice obtain user information by way of may result in user information leakage, for this purpose, the present invention by pair
The instruction got is judged, is carried out early warning prompting to dangerous command, is avoided the danger of information leakage.
As shown in Figure 1, being applied to intelligent sound box, this method packet the embodiment of the invention discloses a kind of safe early warning method
It includes:
Step S101: target instruction target word is obtained using instruction input device;
In the present embodiment, the phonetic order that target instruction target word can issue for user is set using the recording in instruction input device
Standby unit obtains target instruction target word, is specifically as follows: being believed using the voice that the microphone in instruction input device collects user's sending
Breath, wherein described instruction input device can be set in intelligent sound box.
Preferably, it using instruction input device as individual equipment, is separated from intelligent sound box, acquires voice as a result,
The function that the function of instruction and intelligent sound box play voice separates, in sending instruction process user at a distance from intelligent sound box not
It is restricted again, user can carry instruction input device, facilitate voice input, and greatly improve voice collecting
Accuracy.
In addition, target instruction target word is sent to voice solution after the present embodiment gets target instruction target word using instruction input device
Unit is analysed, after speech analysis unit receives target instruction target word, target instruction target word can be parsed, is by target instruction target word analysis processing
Specific voice command data is identified and is handled convenient for subsequent data.Specifically, the speech analysis unit can be located at and refer to
It enables in input device, can also be located in intelligent sound box.
Step S102: judge whether the target instruction target word is dangerous command;
It is understood that being sent voice command data to after above-mentioned speech analysis unit parses target instruction target word
Alarm command unit, there is preset offline alarm command library in alarm command unit, and the offline alarm command library can be
It is imported in advance from interface or from the alarm command library that server is downloaded, the alarm command library includes that the possibility found at present is let out
Reveal all instructions of privacy.Specifically, alarm command unit can be located in instruction input device, can also be located at intelligent sound box
It is interior.
It is described to judge whether the target instruction target word is dangerous command detailed process are as follows: to judge target instruction target word in the present embodiment
Whether show to preserve current target in offline alarm command library if successful match with offline alarm command storehouse matching
Instruction, target instruction target word is dangerous command.
Step S103: if the target instruction target word is dangerous command, corresponding early warning information is played.
In the present embodiment, if the target instruction target word is dangerous command, corresponding early warning information is played.It is a kind of specific
Embodiment are as follows: alarm command unit is located in intelligent sound box, determines current target instruction target word for danger by alarm command unit
After the instruction of danger, it will be taken out in offline alarm command library with the alarm command of current goal instructions match, and be sent to intelligent sound
The audio output apparatus unit of case plays out.Another specific embodiment are as follows: alarm command unit is located at instruction input device
It is interior, it, will be in offline alarm command library and currently after determining current target instruction target word for dangerous command by alarm command unit
The matched alarm command of target instruction target word is taken out, and the wireless device unit being sent in instruction input device instructs the nothing in input device
Alarm command corresponding with target instruction target word is sent to the wireless device unit of intelligent sound box by line unit again, is further sent
Audio output apparatus unit to intelligent sound box plays out.
In addition, in the present embodiment, when the target instruction target word and the failure of offline alarm command storehouse matching, then by target instruction target word
Send the radio network unit of intelligent sound box.
In a specific embodiment, alarm command unit be located at instruction input device in, when the target instruction target word with from
When line alarm command storehouse matching fails, the target instruction target word is sent to the wireless device unit in instruction input device, passes through finger
It enables the wireless device unit in input device be sent to the wireless device unit of intelligent sound box, receives target in wireless device unit
After instruction, target instruction target word is further sent to the radio network unit of intelligent sound box.
It should be pointed out that instruct input device and intelligent sound box by the way of wireless data transmission in the present embodiment, tool
Body can pass through conventional Bluetooth, 4G, GPRS (General Packet Radio Service, general packet radio service skill
Art), any one or any combination in BLE (bluetooth low energy consumption technologies) mode carry out data transmission, in specific implementation process
In can also use other modes, such as wire communication mode.
In another embodiment specific implementation mode, alarm command unit is located in intelligent sound box, when the target instruction target word with from
When line alarm command storehouse matching fails, the target instruction target word is sent to the radio network unit of intelligent sound box.
Further, after the radio network unit of the intelligent sound box receives target instruction target word, target instruction target word is sent
To server.
In a specific embodiment, the request results of target instruction target word are directly returned to the nothing of intelligent sound box by server
Line network unit is set the audio output that the request results of the target instruction target word are sent to intelligent sound box by radio network unit
Standby unit plays out, and completes primary interaction.
In another embodiment specific implementation mode, server can carry out second to target instruction target word after getting target instruction target word
Secondary judgement.Specific deterministic process are as follows: judge the target instruction target word whether in server on-line early warning instruct storehouse matching, if
It fails to match, then current target instruction target word is safety command, and the request results of the target instruction target word are sent to intelligence by server
The request results of the target instruction target word are sent to the sound of intelligent sound box by radio network unit by the radio network unit of speaker
Frequency output equipment unit plays out.
Further, if successful match, current target instruction target word be dangerous command, by on-line early warning instruction database with
The corresponding alarm command of the target instruction target word is sent to the radio network unit of intelligent sound box, is further sent to alarm command list
Alarm command update is saved in offline alarm command library by member.
It is understood that importing in advance or the instruction database downloaded is in alarm command library offline, in the server that compares
On-line early warning instruction database may relatively lag behind, and the present embodiment carries out secondary judgement to target instruction target word using server, avoid
Offline test leakage of the alarm command library to dangerous command, while also having updated offline alarm command library.
It should be noted that in the specific implementation process, updates offline alarm command library and not only can use server and exist
To the mode for updating instruction database after the secondary judgement of target instruction target word, it can also actively be sent and be examined to server from alarm command unit
It surveys and updates request, if there is update in online alarm command library in discovery server, offline alarm command library is automatically updated, to reach
To real-time update, more accurate safety check effect is further obtained.In order to guarantee the real-time update in offline alarm command library, this
Embodiment can also be according to preset update RQ cycle, and regularly whether the on-line early warning instruction database in detection service device has more
Newly, the update RQ cycle can set manually or be set automatically by system, for example, it is assumed that the present embodiment is above-mentioned preset
Updating RQ cycle is 3 hours, then the present embodiment can be every the on-line early warning instruction database in the server of detection in 3 hours
It is no to have update.
As it can be seen that the present invention, which passes through, obtains target instruction target word using instruction input device, judge whether target instruction target word is dangerous command,
If target instruction target word is dangerous command, corresponding early warning information is played.From the foregoing, it will be observed that the present invention is by being used for acquisition instructions
Instruction input device obtain user instruction, get instruction after can carry out safety check to it, if instruction be dangerous command,
Then instruction will not further be sent request as safety command, but play corresponding early warning, user can be prompted to standardize
Input instruction, to prevent dangerous command, the problem of avoiding phonetic order leakage privacy information.
As shown in Fig. 2, being applied to instruction input device, this method the embodiment of the invention discloses a kind of safe early warning method
Include:
Step S201: target instruction target word is obtained;
In the present embodiment, the phonetic order that target instruction target word can issue for user is set using the recording in instruction input device
Standby unit obtains target instruction target word, is specifically as follows: being believed using the voice that the microphone in instruction input device collects user's sending
Breath.
After the present embodiment gets target instruction target word using instruction input device, target instruction target word is sent to speech analysis list
Member after speech analysis unit receives target instruction target word, can parse target instruction target word, and it is specific that target instruction target word analysis, which is handled,
Voice command data, convenient for subsequent data identify and handle.
It should be pointed out that instruction input device and intelligent sound box can pass through wire communication or wireless telecommunications, it is preferred that this
Instruct input device and intelligent sound box by the way of wireless data transmission in embodiment, specifically can by conventional Bluetooth, 4G,
Any one or any combination in GPRS, BLE mode carry out data transmission, and user can carry instruction input device at any time, with
When issue phonetic order, break through the distance between user and intelligent sound box in use process and limit, and short distance refers to
Order also improves the accuracy of acquisition instructions.
Step S202: judge whether the target instruction target word is dangerous command by local default offline alarm command library;
In the present embodiment, after above-mentioned speech analysis unit parses target instruction target word, finger is sent voice command data to
The alarm command unit in input device is enabled, there is preset offline alarm command library, the offline early warning in alarm command unit
Instruction database can be for from interface importing or from the alarm command library that server is downloaded, the alarm command library includes current institute in advance
It was found that possibility leakage privacy all instructions.
About it is described judge the target instruction target word whether be dangerous command detailed process can with reference to previous embodiment,
This is repeated no more.
Step S203: if the target instruction target word is dangerous command, by the corresponding early warning information of the target instruction target word
Intelligent sound box is sent to play out.
It is understood that after determining current target instruction target word for dangerous command by alarm command unit, it will be offline
It is taken out in alarm command library with the alarm command of current goal instructions match, and is sent to the audio output apparatus list of intelligent sound box
Member plays out, detailed process are as follows: will take out, sends with the alarm command of current goal instructions match in offline alarm command library
Wireless device unit to instruction input device, instructs the wireless device unit in input device that will send again with the alarm command
To the wireless device unit of intelligent sound box, the audio output apparatus unit for being further transmitted to intelligent sound box is played out.
It should be pointed out that when the target instruction target word and offline alarm command storehouse matching fail, by the target instruction target word
The wireless device unit being sent in instruction input device is sent to intelligent sound box by the wireless device unit in instruction input device
Wireless device unit target instruction target word is further sent to intelligent sound box after wireless device unit receives target instruction target word
Radio network unit.
In a specific embodiment, the request results of target instruction target word are directly returned to the nothing of intelligent sound box by server
Line network unit is set the audio output that the request results of the target instruction target word are sent to intelligent sound box by radio network unit
Standby unit plays out, and completes primary interaction.
In another embodiment specific implementation mode, server can carry out second to target instruction target word after getting target instruction target word
Secondary judgement.Specific deterministic process are as follows: judge the target instruction target word whether in server on-line early warning instruct storehouse matching, if
It fails to match, then current target instruction target word is safety command, and the request results of the target instruction target word are sent to intelligence by server
The request results of the target instruction target word are sent to the sound of intelligent sound box by radio network unit by the radio network unit of speaker
Frequency output equipment unit plays out;If successful match, current target instruction target word is dangerous command, and on-line early warning is instructed
Alarm command corresponding with the target instruction target word is sent to the radio network unit of intelligent sound box in library, and intelligent sound box receives pre-
By the wireless device unit by the wireless device unit of intelligent sound box via instruction input device after alert instruction, it is sent to instruction record
Enter the alarm command unit in device, offline alarm command library, which receives, to be saved, to update offline alarm command library.
It should be noted that in the specific implementation process, not only can by server to the secondary judgement of target instruction target word after
Offline alarm command library is updated, can also actively to server send detection update request, if discovery server in
There is update in line alarm command library, then automatically updates instruction database, to reach realization real-time update, obtains more accurately detection effect
Fruit.
In the present embodiment, instruction input device first gets target instruction target word;Sentenced by local default offline alarm command library
Whether disconnected target instruction target word is dangerous command;If target instruction target word is dangerous command, by the corresponding early warning information of target instruction target word
Intelligent sound box is sent to play out.From the foregoing, it will be observed that the present invention acquires phonetic order by instruction input device, by traditional intelligence
Voice being acquired in speaker to separate with the function of playing voice, instruction input device and intelligent sound box use wireless way for transmitting data,
User be not restricted at a distance from intelligent sound box during issuing phonetic order;And instruct input device to instruct into
Row acquisition, parsing, early warning verification, all processes be in off-line state progress, therefore user instruction lack of standardization or uneasiness all referring to
Enabling will not be via Internet communication, to achieve the purpose that privacy of user is avoided to reveal.
In addition, it is applied to intelligent sound box the embodiment of the invention also discloses a kind of safety early warning device, it is shown in Figure 3,
Device includes:
First obtains module 100, for obtaining target instruction target word using instruction input device;
First judgment module 200, for judging whether the target instruction target word is dangerous command;
Early warning playing module 300 plays corresponding early warning letter if being dangerous command for the target instruction target word
Breath.
The safety early warning device of the present embodiment is for realizing safe early warning method above-mentioned, therefore in safety early warning device
Specific embodiment can be found in the description of the various pieces embodiment of safe early warning method hereinbefore, and details are not described herein.
In addition, being applied to instruction input device, referring to fig. 4 institute the embodiment of the invention also discloses a kind of safety early warning device
Show, device includes:
Second obtains module 400, for obtaining target instruction target word;
Second judgment module 500, for whether judging the target instruction target word by local default offline alarm command library
For dangerous command;
Early warning sending module 600, it is if being dangerous command for the target instruction target word, the target instruction target word is corresponding pre-
Alert prompt information is sent to intelligent sound box and plays out.
The safety early warning device of the present embodiment is for realizing safe early warning method above-mentioned, therefore in safety early warning device
Specific embodiment can be found in the description of the various pieces embodiment of safe early warning method hereinbefore, and details are not described herein.
In addition, the embodiment of the invention also provides a kind of intelligent sound box, including processor 11 and memory 12, wherein institute
It states when processor 11 executes the computer program saved in the memory 12 and performs the steps of
Target instruction target word is obtained using instruction input device;Judge whether the target instruction target word is dangerous command;If the target
Instruction is dangerous command, then plays corresponding early warning information.
In the present embodiment, the processor 11 can be specifically real when executing the computer program saved in the memory 12
Existing following steps:
Judge whether the target instruction target word is dangerous command by presetting offline alarm command library;If it is, determining institute
Stating target instruction target word is dangerous command;If it is not, then judging that the target refers to by the default online alarm command library in server
Whether be dangerous command, if it is, determining the target instruction target word for dangerous command if enabling.
Further, shown in Figure 5, the intelligent sound box in the present embodiment can also include:
Input interface 13, for obtaining the computer program of extraneous importing, and the computer program that will acquire save to
In the memory 12, it can be also used for the various instructions and parameter that obtain extraneous terminal device transmission, and be transmitted to processor
In 11, so that processor 11 is handled accordingly using above-mentioned various instructions and parametric evolving.In the present embodiment, the input interface
13, which can specifically include but be not limited to USB interface, serial line interface, speech input interface, fingerprint input interface, hard disk, reads interface
Deng.
Output interface 14, the various data for generating processor 11 are exported to coupled terminal device, so as to
The various data of the generation of processor 11 can be got in other terminal devices being connected with output interface 14.In the present embodiment,
The output interface 14 can specifically include but be not limited to USB interface, serial line interface etc..
Wireless device unit 15, for realizing with external equipment establish communicate to connect, specific connection type may include but
It is not limited to BLE, conventional Bluetooth.
Radio network unit 16 connect for realizing telecommunication is established with external server, obtains extraneous terminal and sends
Data, be then forwarded to processor 11 and be analyzed and processed, in addition, the various knots that processor 11 can also will obtain after processing
Fruit is sent to preset various data receivers by radio network unit 16.
Display unit 17, the data for sending over to processor 11 are shown.
Audio output apparatus unit 18, the voice for sending over to processor 11 play out.
In addition, the embodiment of the invention also provides a kind of instruction input device, including processor 21 and memory 22, wherein
The processor 21 performs the steps of when executing the computer program saved in the memory 22
Obtain target instruction target word;Judge whether the target instruction target word is that danger refers to by local default offline alarm command library
It enables;If the target instruction target word is dangerous command, the corresponding early warning information of the target instruction target word is sent to intelligent sound box
It plays out
Further, shown in Figure 6, the instruction input device in the present embodiment can also include:
Input interface 23, for obtaining the computer program of extraneous importing, and the computer program that will acquire save to
In the memory 22, it can be also used for the various instructions and parameter that obtain extraneous terminal device transmission, and be transmitted to processor
In 21, so that processor 21 is handled accordingly using above-mentioned various instructions and parametric evolving.In the present embodiment, the input interface
23, which can specifically include but be not limited to USB interface, serial line interface, speech input interface, fingerprint input interface, hard disk, reads interface
Deng.
Output interface 24, the various data for generating processor 21 are exported to coupled terminal device, so as to
The various data of the generation of processor 21 can be got in other terminal devices being connected with output interface 24.In the present embodiment,
The output interface 24 can specifically include but be not limited to USB interface, serial line interface etc..
Recoding unit 25, for obtaining voice data;Wherein, the voice data got can be directly transferred to the place
It manages device 21 and carries out relevant treatment.
Speech analysis unit 26, for voice data to be parsed into specific director data.
Alarm command unit 27, for carrying out safety check to director data.
Wireless device unit 28, for realizing with external equipment establish communicate to connect, specific connection type may include but
It is not limited to BLE (bluetooth low energy consumption technologies), conventional Bluetooth.
Display unit 29, the data for sending over to processor 21 are shown.
In addition, the embodiment of the invention also discloses a kind of safety pre-warning system, including aforementioned disclosed intelligent sound box and
Aforementioned disclosed instruction input device, can be with reference to public in previous embodiment about above-mentioned intelligent sound box and instruction typing implement body
The corresponding contents opened, are no longer repeated herein.
In addition, the embodiment of the invention also discloses a kind of computer readable storage mediums, for saving computer program,
In, when the computer program is executed by processor, realize the safety for being applied to intelligent sound box as disclosed in previous embodiment
Method for early warning.
Specific steps about the above method can no longer carry out herein with reference to corresponding contents disclosed in previous embodiment
It repeats.
In addition, the embodiment of the invention also discloses a kind of computer readable storage mediums, for saving computer program,
In, when the computer program is executed by processor, realize the peace for being applied to instruction input device as disclosed in previous embodiment
Full method for early warning.
Specific steps about the above method can no longer carry out herein with reference to corresponding contents disclosed in previous embodiment
It repeats.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above to intelligent sound box provided by the present invention, instruction input device and its safe early warning method, device, storage medium
It is described in detail, used herein a specific example illustrates the principle and implementation of the invention, the above reality
The explanation for applying example is merely used to help understand method and its core concept of the invention;Meanwhile for the general technology of this field
Personnel, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this theory
Bright book content should not be construed as limiting the invention.
Claims (10)
1. a kind of safe early warning method, which is characterized in that be applied to intelligent sound box, comprising:
Target instruction target word is obtained using instruction input device;
Judge whether the target instruction target word is dangerous command;
If the target instruction target word is dangerous command, corresponding early warning information is played.
2. safe early warning method according to claim 1, which is characterized in that described to judge whether the target instruction target word is danger
Danger instruction, comprising:
Judge whether the target instruction target word is dangerous command by presetting offline alarm command library.
3. safe early warning method according to claim 1, which is characterized in that described to judge whether the target instruction target word is danger
Danger instruction, comprising:
Judge whether the target instruction target word is dangerous command by presetting offline alarm command library;
If it is, determining the target instruction target word for dangerous command;
If it is not, then judge whether the target instruction target word is dangerous command by the default online alarm command library in server,
If it is, determining the target instruction target word for dangerous command.
4. safe early warning method according to claim 2 or 3, which is characterized in that the default line off instruction library be positioned at
The instruction database of the intelligent sound box or described instruction input device.
5. safe early warning method according to claim 3, which is characterized in that further include:
It presets online alarm command library using described and presets offline alarm command library to described and be updated.
6. a kind of safe early warning method, which is characterized in that be applied to instruction input device, comprising:
Obtain target instruction target word;
Judge whether the target instruction target word is dangerous command by local default offline alarm command library;
If the target instruction target word is dangerous command, the corresponding early warning information of the target instruction target word is sent to intelligent sound box
It plays out.
7. a kind of safety early warning device, which is characterized in that be applied to intelligent sound box, comprising:
First obtains module, for obtaining target instruction target word using instruction input device;
First judgment module, for judging whether the target instruction target word is dangerous command;
Early warning playing module plays corresponding early warning information if being dangerous command for the target instruction target word.
8. a kind of safety early warning device, which is characterized in that be applied to instruction input device, comprising:
Second obtains module, for obtaining target instruction target word;
Second judgment module, for judging whether the target instruction target word is that danger refers to by local default offline alarm command library
It enables;
Early warning sending module, if being dangerous command for the target instruction target word, by the corresponding early warning of the target instruction target word
Information is sent to intelligent sound box and plays out.
9. a kind of intelligent sound box characterized by comprising
Memory, for storing computer program;
Processor, realizing the safe early warning method as described in any one of claim 1 to 5 when for executing the computer program
Step.
10. a kind of instruction input device characterized by comprising
Memory, for storing computer program;
Processor, the step of safe early warning method as claimed in claim 6 is realized when for executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810980451.4A CN109087641A (en) | 2018-08-27 | 2018-08-27 | Intelligent sound box, instruction input device and its safe early warning method, device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810980451.4A CN109087641A (en) | 2018-08-27 | 2018-08-27 | Intelligent sound box, instruction input device and its safe early warning method, device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109087641A true CN109087641A (en) | 2018-12-25 |
Family
ID=64794854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810980451.4A Pending CN109087641A (en) | 2018-08-27 | 2018-08-27 | Intelligent sound box, instruction input device and its safe early warning method, device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109087641A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109981252A (en) * | 2019-03-12 | 2019-07-05 | 中国科学院信息工程研究所 | A kind of artificial intelligence process device safety enhancing system and method based on critical path encryption |
CN111312230A (en) * | 2019-11-27 | 2020-06-19 | 南京创维信息技术研究院有限公司 | Voice interaction monitoring method and device for voice conversation platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103516915A (en) * | 2012-06-27 | 2014-01-15 | 百度在线网络技术(北京)有限公司 | Method, system and device for replacing sensitive words in call process of mobile terminal |
CN106340296A (en) * | 2016-10-20 | 2017-01-18 | 努比亚技术有限公司 | Voice verification code protection device, method and mobile terminal |
CN106549954A (en) * | 2016-11-01 | 2017-03-29 | 乐视控股(北京)有限公司 | Method of speech processing and device |
CN106997764A (en) * | 2016-01-26 | 2017-08-01 | 阿里巴巴集团控股有限公司 | A kind of instant communicating method and instantaneous communication system based on speech recognition |
CN108111538A (en) * | 2018-01-25 | 2018-06-01 | 芜湖应天光电科技有限责任公司 | Smart projector speech control system and its method based on sound groove recognition technology in e |
-
2018
- 2018-08-27 CN CN201810980451.4A patent/CN109087641A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103516915A (en) * | 2012-06-27 | 2014-01-15 | 百度在线网络技术(北京)有限公司 | Method, system and device for replacing sensitive words in call process of mobile terminal |
CN106997764A (en) * | 2016-01-26 | 2017-08-01 | 阿里巴巴集团控股有限公司 | A kind of instant communicating method and instantaneous communication system based on speech recognition |
CN106340296A (en) * | 2016-10-20 | 2017-01-18 | 努比亚技术有限公司 | Voice verification code protection device, method and mobile terminal |
CN106549954A (en) * | 2016-11-01 | 2017-03-29 | 乐视控股(北京)有限公司 | Method of speech processing and device |
CN108111538A (en) * | 2018-01-25 | 2018-06-01 | 芜湖应天光电科技有限责任公司 | Smart projector speech control system and its method based on sound groove recognition technology in e |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109981252A (en) * | 2019-03-12 | 2019-07-05 | 中国科学院信息工程研究所 | A kind of artificial intelligence process device safety enhancing system and method based on critical path encryption |
CN111312230A (en) * | 2019-11-27 | 2020-06-19 | 南京创维信息技术研究院有限公司 | Voice interaction monitoring method and device for voice conversation platform |
CN111312230B (en) * | 2019-11-27 | 2023-10-20 | 南京创维信息技术研究院有限公司 | Voice interaction monitoring method and device for voice conversation platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6828001B2 (en) | Voice wakeup method and equipment | |
US10832686B2 (en) | Method and apparatus for pushing information | |
CN107818798B (en) | Customer service quality evaluation method, device, equipment and storage medium | |
CN109243432A (en) | Speech processing method and the electronic equipment for supporting the speech processing method | |
CN105489221B (en) | A kind of audio recognition method and device | |
US11501028B2 (en) | Electronic device, audio device, electronic device control method and storage medium | |
WO2018195185A1 (en) | Multi-user authentication on a device | |
CN108428446A (en) | Audio recognition method and device | |
US20130317825A1 (en) | Deriving geographic distribution of physiological or psychological conditions of human speakers while reserving personal privacy | |
CN104160441A (en) | Speaker verification in a health monitoring system | |
CN107506166A (en) | Information cuing method and device, computer installation and readable storage medium storing program for executing | |
CN110782962A (en) | Hearing language rehabilitation device, method, electronic equipment and storage medium | |
CN112634897B (en) | Equipment awakening method and device, storage medium and electronic device | |
CN104538034A (en) | Voice recognition method and system | |
CN103635962A (en) | Voice recognition system, recognition dictionary logging system, and audio model identifier series generation device | |
CN109087641A (en) | Intelligent sound box, instruction input device and its safe early warning method, device | |
CN108877813A (en) | The methods, devices and systems of man-machine identification | |
CN109729067A (en) | Voice punch card method, device, equipment and computer storage medium | |
CN109671234A (en) | A kind of alarm method and device of monitoring device | |
WO2015102082A1 (en) | Terminal device, program, and server device for providing information according to user data input | |
KR20130108173A (en) | Question answering system using speech recognition by radio wire communication and its application method thereof | |
CN106535195A (en) | Authentication method and device, and network connection method and system | |
CN108837273A (en) | A kind of control method for playing back and terminal device of assisting sleep | |
CN112116925A (en) | Emotion recognition method and device, terminal equipment, server and storage medium | |
JP6427377B2 (en) | Equipment inspection support device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |