[0036] The embodiment of the present invention provides an anti-terrorism early warning method and device based on telephone monitoring, which can accurately identify the identity of the monitored person and realize the anti-terrorism early warning.
[0037] In order to make the objectives, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
[0038] See figure 1 , An embodiment of an anti-terrorism early warning method based on telephone monitoring provided by the present invention includes:
[0039] 101. Obtain the call voice of the monitored user;
[0040] 102. Extract the voiceprint information to be inspected in the call voice, and compare the voiceprint information to be inspected with the preset voiceprint information in the voiceprint library. The preset voiceprint information is that of the target suspect in the preset case. Voiceprint information of pre-recorded voice;
[0041] 103. After determining that the monitored user is the target suspect based on the comparison result, extract the voice content in the call voice through semantic recognition technology to determine whether the voice content is related to the preset case, and if so, execute an early warning.
[0042] The embodiment of the present invention provides an anti-terrorism early warning method based on telephone monitoring, including: acquiring the voice of the monitored user; extracting the voiceprint information to be inspected in the voice of the call, and combining the voiceprint information to be inspected with the voiceprint information in the voiceprint library The preset voiceprint information is compared. The preset voiceprint information is the voiceprint information of the pre-recorded voice of the target suspect in the preset case; after the monitored user is determined as the target suspect according to the comparison result, the semantics The recognition technology extracts the voice content in the call voice, determines whether the voice content is related to a preset case, and if so, executes an early warning. The present invention determines whether the monitored user is the target suspect through voiceprint recognition, and if so, extracts the voice content through semantic recognition, thereby determining the case involved in the target suspect, realizing anti-terrorism early warning in time, and reducing manual operations , Improve the efficiency and accuracy of case monitoring.
[0043] The above is an embodiment of the anti-terrorism early warning method based on telephone monitoring provided by the present invention. The following will describe another embodiment of the anti-terrorist early warning method based on telephone monitoring provided by the present invention.
[0044] See figure 2 , Another embodiment of the anti-terrorism early warning method based on telephone monitoring provided by the present invention includes:
[0045] 201. Obtain the pre-recorded voice of the target suspect related to the preset case;
[0046] In this embodiment, in order to be able to determine whether the monitored user is a target suspect through the voiceprint recognition technology, a voiceprint database needs to be established. It is understandable that various voiceprints are stored in the voiceprint library, and each voiceprint corresponds to the voice characteristics of each person. Therefore, the pre-recorded voices of the target suspects related to the case can be collected first to establish the voice. Pattern library.
[0047] 202. Extract the voice information of the pre-recorded voice of each target suspect, and determine whether the voice information of the pre-recorded voice meets the standard, if so, extract the voiceprint information in the pre-recorded voice as the preset voiceprint information of the target suspect, if If not, perform 201 again.
[0048] Then it is judged whether the voice information in the pre-recorded voice of the target suspect meets the standard. Specifically, the voice information in this embodiment includes: signal-to-noise ratio, effective duration, and energy.
[0049] The process of judging whether the voice information of the pre-recorded voice meets the standard can be:
[0050] Judge whether the signal-to-noise ratio, effective duration and energy of the pre-recorded speech are within the corresponding preset standard range. For example, the preset standard range of the signal-to-noise ratio can be greater than 6DB, and the preset standard range of energy (speech amplitude) is 1000~30000.
[0051] In this embodiment, the effective duration of the pre-recorded voice specifically includes: the effective duration of random numbers in the pre-recorded voice, the effective duration of any phrase in the pre-recorded voice, the effective duration of any long sentence in the quotation voice, and the fixed short duration in the pre-recorded voice. The effective duration of the sentence. Specifically, the standard for random numbers is greater than 1.2 seconds, the standard for arbitrary short sentences is greater than 1.8 seconds, the standard for arbitrary long sentences is greater than 16 seconds, and the standard for fixed phrases is greater than 0.8 seconds.
[0052] It should be noted that if a pre-recorded voice of a target suspect A meets the above criteria (if not, the pre-recorded voice will be re-recorded until the criteria is met), then the voiceprint can be extracted and the obtained voiceprint The information is used as the preset voiceprint information of the target suspect A and stored in the voiceprint library. In the same way, all target suspects related to the preset case can perform the above process, so that the voiceprint database contains the preset voiceprint information of all suspects related to the case.
[0053] 203. Obtain the call voice of the monitored user;
[0054] In this embodiment, the conversation voice of the monitored user can be obtained in real time.
[0055] 204. Extract the effective human voice voice in the call voice through endpoint detection, and then perform noise reduction to obtain the preprocessed call voice;
[0056] After the conversation voice of the monitored user is obtained, it can be preprocessed. Specifically, the preprocessing process may be to extract the effective human voice voice part of the call voice through endpoint detection, and then perform noise reduction processing on it to obtain the preprocessed call voice. It should be noted that the noise reduction algorithm used in the noise reduction process is a well-known technology of those skilled in the art, and no specific explanation is given here.
[0057] 205. Extract the voiceprint information to be verified from the preprocessed call voice, and compare the voiceprint information to be verified with the preset voiceprint information in the voiceprint library. The preset voiceprint information is in the preset case, Voiceprint information of the pre-recorded voice of the target suspect;
[0058] After preprocessing the call voice of the monitored user, the voiceprint information in the voice can be extracted, and the voiceprint information to be tested can be compared with the preset voiceprint information in the voiceprint library. As a result, it is determined whether the monitored user is the target suspect.
[0059] 206. After determining that the monitored user is the target suspect based on the comparison result, extract the voice content in the call voice through semantic recognition technology to determine whether the voice content is related to a preset case, and if so, execute an early warning.
[0060] If there is preset voiceprint information in the voiceprint database that is consistent with the voiceprint information to be tested, the monitored user can be determined as the target suspect corresponding to the preset voiceprint information, and then the monitored user can be extracted through semantic recognition technology The content in the call voice is judged whether the content is related to the preset case, and if it is, an early warning can be given. Specifically, the specific operation of the early warning may be to highlight the monitored user and give voice reminders at the same time, such as highlighting the monitored user as a suspect on the display screen and simultaneously playing it through sound.
[0061] The present invention determines whether the monitored user is the target suspect through voiceprint recognition, and if so, extracts the voice content through semantic recognition, thereby determining the case involved in the target suspect, realizing anti-terrorism early warning in time, and reducing manual operations , Improve the efficiency and accuracy of case monitoring.
[0062] The above is a detailed description of the anti-terrorism early warning method based on telephone monitoring provided by the present invention. The structure and connection mode of the anti-terrorism early warning device based on telephone monitoring provided by the present invention will be introduced below, please refer to image 3 An embodiment of an anti-terrorism early warning device based on telephone monitoring provided by the present invention includes:
[0063] The obtaining module 301 is used to obtain the call voice of the monitored user;
[0064] The comparison module 302 is used to extract the voiceprint information to be verified in the call voice, and compare the voiceprint information to be verified with the preset voiceprint information in the voiceprint library, and the preset voiceprint information is in the preset case , The voiceprint information of the pre-recorded voice of the target suspect;
[0065] The early warning module 303 is configured to extract the voice content of the call voice through semantic recognition technology after determining that the monitored user is the target suspect according to the comparison result, and determine whether the voice content is related to the preset case, and if so, execute the early warning.
[0066] The anti-terrorism early warning device based on telephone monitoring provided by the present invention further includes:
[0067] The pre-recorded module is used to obtain the pre-recorded voice of the target suspect related to the preset case;
[0068] The judgment module is used to extract the voice information of the pre-recorded voice of each target suspect, and determine whether the voice information of the pre-recorded voice meets the standard, if so, extract the voiceprint information in the pre-recorded voice as the preset voiceprint of the target suspect If not, then trigger the pre-recording module again.
[0069] Optionally, the voice information includes: signal-to-noise ratio, effective duration, and energy.
[0070] Optionally, the judgment module is also used to extract the voice information of the pre-recorded voice of each target suspect, and determine whether the signal-to-noise ratio, effective duration and energy of the pre-recorded voice are within the corresponding preset standard range, if so, extract The voiceprint information in the pre-recorded voice is used as the preset voiceprint information of the target suspect. If not, the pre-recording module is triggered again.
[0071] Optionally, the effective duration of the pre-recorded voice specifically includes: the effective duration of the random number in the pre-recorded voice, the effective duration of any phrase in the pre-recorded voice, the effective duration of any long sentence in the quotation voice, and the fixed short sentence in the pre-recorded voice The effective length of time.
[0072] Optionally, the anti-terrorism early warning device based on telephone monitoring provided by the present invention further includes:
[0073] The preprocessing module is used to extract the effective vocal voice in the call voice through endpoint detection, and then perform noise reduction to obtain the preprocessed call voice;
[0074] The comparison module is also used to extract the voiceprint information to be inspected in the preprocessed call voice, and compare the voiceprint information to be inspected with the preset voiceprint information in the voiceprint library. The preset voiceprint information is In the case, the voiceprint information of the pre-recorded voice of the target suspect.
[0075] Optionally, the execution warning is specifically: highlighting the monitored user and giving a voice reminder at the same time.
[0076] Another embodiment of an anti-terrorism early warning device based on telephone monitoring of the present invention includes: a memory, and a processor coupled to the memory;
[0077] The processor is configured to execute the anti-terrorism warning method based on telephone monitoring as described in any one of the above based on instructions stored in the memory device.
[0078] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described system, device, and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.
[0079] In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
[0080] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
[0081] In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
[0082] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes.
[0083] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions recorded in the embodiments are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.