CN112800772A - Automatic danger early warning method and system of law enforcement recorder - Google Patents

Automatic danger early warning method and system of law enforcement recorder Download PDF

Info

Publication number
CN112800772A
CN112800772A CN202110027079.7A CN202110027079A CN112800772A CN 112800772 A CN112800772 A CN 112800772A CN 202110027079 A CN202110027079 A CN 202110027079A CN 112800772 A CN112800772 A CN 112800772A
Authority
CN
China
Prior art keywords
law enforcement
voice
loudness
tone
site
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
Application number
CN202110027079.7A
Other languages
Chinese (zh)
Inventor
张冠峰
张冠华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Tianlong Century Technology Development Co ltd
Original Assignee
Shenzhen Tianlong Century Technology Development Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Tianlong Century Technology Development Co ltd filed Critical Shenzhen Tianlong Century Technology Development Co ltd
Priority to CN202110027079.7A priority Critical patent/CN112800772A/en
Publication of CN112800772A publication Critical patent/CN112800772A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51Speech 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
    • G10L25/63Speech 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 for estimating an emotional state

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Hospice & Palliative Care (AREA)
  • Development Economics (AREA)
  • Acoustics & Sound (AREA)
  • Child & Adolescent Psychology (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention relates to a danger automatic early warning method and a system of a law enforcement recorder, wherein the method comprises the steps of acquiring initial voice information of a current law enforcement site in real time; according to the initial voice information, performing emotion analysis on related personnel of the current law enforcement site to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel; and judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold value, if so, generating a law enforcement alarm instruction and sending the law enforcement alarm instruction to a law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel. The invention can realize automatic early warning for potential danger under the complex law enforcement situation, thereby improving the personal safety of related personnel on the law enforcement site and promoting harmonious law enforcement.

Description

Automatic danger early warning method and system of law enforcement recorder
Technical Field
The invention relates to the technical field of law enforcement recording, in particular to a method and a system for automatically early warning danger of a law enforcement recorder.
Background
At present, in public inspection law enforcement field, law enforcement record appearance is indispensable equipment, small, conveniently carry, powerful moreover. In recent years, there have been many other industries or fields that are increasingly using law enforcement recorders, such as the city management, traffic, rail, factory, gas station, and construction industries, among others. The law enforcement recorder is mainly used for recording real-time evidences, and the traditional law enforcement recorder has the functions of shooting, photographing, voice recording and talkback, can record and record the field environment in the law enforcement process in real time, acts in a word and restores the real situation of the field.
In a law enforcement scene, a law enforcement person often warns of a mouth and a law enforcement person and is easily trapped in a dangerous law enforcement scene, the law enforcement effect is influenced, the personal safety of related personnel in the law enforcement scene is threatened, the conventional law enforcement recorder is mostly used for recording evidence in the law enforcement scene, but corresponding early warning or reminding cannot be made aiming at a complex law enforcement environment, for example, in the process of city management in a street, the risk of contradiction upgrading and even life threat exists, the conventional law enforcement recorder only can record the law enforcement scene at that time, and the function of automatic early warning to the law enforcement person under a dangerous condition cannot be realized, so the inventor considers that the conventional law enforcement recorder has certain defects in the aspect of automatic early warning, and needs further improvement.
Disclosure of Invention
In order to overcome the defects of the prior art, the application provides an automatic danger early warning method and system of a law enforcement recorder, which can realize automatic early warning for potential dangers under the complex law enforcement situation, thereby improving the personal safety of related personnel at the law enforcement site and promoting harmonious law enforcement.
The above object of the present invention is achieved by the following technical solutions:
a danger automatic early warning method of a law enforcement recorder is applied to interaction between a server and the law enforcement recorder, and comprises the following steps:
acquiring initial voice information of a current law enforcement site in real time;
according to the initial voice information, performing emotion analysis on related personnel of the current law enforcement site to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
and judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold value, if so, generating a law enforcement alarm instruction and sending the law enforcement alarm instruction to a law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
By adopting the technical scheme, the initial voice information of the current law enforcement site is acquired through the law enforcement recorder, the server is used for analyzing the emotional characteristics of the relevant personnel of the law enforcement site in real time on the initial voice information, the danger coefficient of the current law enforcement site is determined, the danger coefficient is compared with the preset danger coefficient threshold, and warning reminding is carried out aiming at the condition that the danger coefficient is greater than the preset danger coefficient threshold, so that the situation that law enforcement personnel are high in the site law enforcement atmosphere danger and have the risk of occurrence of personal safety events is reminded, the law enforcement personnel can regulate and control the environment of the law enforcement site, the personal safety of the law enforcement personnel and the personnel to be enforced is improved, and harmonious law enforcement is promoted.
Optionally, performing emotion analysis on related personnel of the current law enforcement site according to the initial voice information to obtain a risk coefficient of the current law enforcement site, including:
performing voice preprocessing on the initial voice information, and taking the initial voice information corresponding to the voice preprocessed information as intermediate voice information;
extracting the characteristics of the intermediate voice information to obtain a tone characteristic time sequence and a loudness characteristic time sequence, wherein the tone characteristic represents the pronunciation frequency of words and sentences, and the loudness characteristic represents the pronunciation amplitude of words and sentences;
calculating the voice danger coefficient of the current law enforcement site by utilizing a similarity measurement method and a preset voice threshold according to the tone characteristic time sequence and the loudness characteristic time sequence;
matching according to the tone characteristic time sequence and a preset identification word frequency database, counting the word frequency of the successfully matched identification words, and determining the semantic risk coefficient of the current law enforcement site according to the word frequency;
and calculating the risk coefficient of the current law enforcement site according to different weight proportions according to the voice risk coefficient and the semantic risk coefficient.
By adopting the technical scheme, the voice danger coefficient of the law enforcement site is obtained by carrying out voice analysis on the voice information, and the semantic danger coefficient of the law enforcement site is obtained by carrying out semantic analysis on the voice information, so that the danger coefficient of the law enforcement site is obtained according to the voice danger coefficient and the semantic danger coefficient, the danger degree of the law enforcement site atmosphere is further reflected, the warning prompt is favorably carried out on law enforcement personnel, and harmonious law enforcement is promoted. In addition, intermediate voice information is obtained by preprocessing the initial voice information, so that the voice is conveniently analyzed; the voice recognition method has the advantages that the characteristic extraction is carried out on the intermediate voice information, the tone characteristic time sequence and the loudness characteristic time sequence are obtained, the analysis of the speaking voice characteristics of the law enforcement site is facilitated, the semantic analysis is carried out through the tone characteristic time sequence, and therefore whether over-excited marker words exist in the semantics of the law enforcement site or not is conveniently analyzed, and the semantic risk degree of the law enforcement site is determined.
Optionally, the voice threshold includes a tone threshold and a loudness threshold, and the voice risk coefficient of the current law enforcement site is calculated by using a similarity measure method and a preset voice threshold according to the tone feature timing and the loudness feature timing, including:
acquiring a real-time tone characteristic value from a tone characteristic time sequence, calculating the tone similarity between the real-time tone characteristic value and a preset tone threshold value by using a similarity measurement method, acquiring a real-time loudness characteristic value from a loudness characteristic time sequence, and calculating the loudness similarity between the real-time loudness characteristic value and the preset loudness threshold value;
and calculating the voice similarity according to different weight proportions according to the tone similarity and the loudness similarity, and taking the voice similarity as a voice risk coefficient.
By adopting the technical scheme, the tone similarity and the loudness similarity are simultaneously calculated, and the voice similarity is determined according to different weight ratios and is used as the voice danger coefficient, so that the emotional characteristics of the related personnel on the law enforcement site are obtained through audio analysis, and the warning prompt on the law enforcement site is facilitated.
Optionally, the tagged word frequency database stores pronunciation frequencies of tagged words, where the tagged words refer to words and sentences with contradictory enlightenment, the tone feature time sequence is matched with a preset tagged word frequency database, the tagged word frequency with successful matching is counted, and semantic risk coefficients of the current law enforcement site are determined according to the word frequency, where the semantic risk coefficients include:
acquiring a real-time tone characteristic value from a tone characteristic time sequence, matching the real-time tone characteristic value with an identification word frequency database, and counting the accumulated times of the occurrence of identification words in the tone characteristic time sequence to be used as word frequency;
and calculating the ratio of the word frequency to a preset word frequency threshold value, and acquiring a calculation result as a semantic risk coefficient.
By adopting the technical scheme, the real-time tone characteristic value and the identification word frequency database are matched, so that whether the speech of the overstimulation dispute exists can be analyzed, the accumulated times of the identification words appearing in the tone characteristic time sequence are counted and used as word frequency, and the ratio of the word frequency to a preset word frequency threshold value is calculated, so that the semantic risk coefficient of a law enforcement site is conveniently determined, the warning prompt of the law enforcement site is facilitated, and the harmonious law enforcement is promoted.
Optionally, the initial voice information is subjected to voice preprocessing, including voice framing, pre-emphasis, windowing, and FFT transformation.
By adopting the technical scheme, the initial voice information is divided into small sections of voices by voice framing, so that voice analysis is facilitated; pre-emphasis processing is utilized, so that low-frequency interference in initial voice information can be filtered, a high-frequency part is improved, and voice analysis is facilitated; windowing is utilized to help increase the intelligibility of the speech signal; the voice time domain signal is converted into a frequency domain signal by using FFT (fast Fourier transform), so that the signal is decomposed, the subsequent calculation amount is reduced, and the efficiency of preprocessing the initial voice information is improved.
Optionally, the performing feature extraction on the intermediate speech information to obtain a pitch feature timing sequence and a loudness feature timing sequence includes:
and (3) extracting the characteristics of the intermediate voice information by using a wavelet transform method, and acquiring a tone characteristic time sequence and a loudness characteristic time sequence.
By adopting the technical scheme, the intermediate voice information is subjected to feature extraction through a wavelet transform method, and the tone feature time sequence and the loudness feature time sequence can be quickly acquired, so that the analysis of the audio features of the voice information is facilitated, meanwhile, the tone feature time sequence is facilitated to be analyzed for the semantic features of the voice information, and the analysis of the dangerous degree of a law enforcement site at multiple angles is facilitated.
Optionally, judging whether the current law enforcement site needs to be warned according to the risk coefficient and a preset risk coefficient threshold, including:
if the risk coefficient is larger than or equal to the risk coefficient threshold value, determining that the current law enforcement site needs to be warned; and if the risk coefficient is smaller than the risk coefficient threshold value, determining that no alarm is needed in the current law enforcement site.
By adopting the technical scheme, the danger coefficient is compared with the preset danger coefficient threshold value, so that whether the current law enforcement site needs to give an alarm to law enforcement personnel can be quickly judged.
The second aim of the invention is realized by the following technical scheme:
a hazard automatic early warning system for a law enforcement recorder, the system comprising:
the information acquisition module is used for acquiring initial voice information of a current law enforcement site in real time;
the analysis module is used for carrying out emotion analysis on related personnel of the current law enforcement site according to the initial voice information to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
and the judgment warning module is used for judging whether the current law enforcement site needs to be warned according to the danger coefficient and a preset danger coefficient threshold value, if so, generating a law enforcement warning instruction and sending the law enforcement warning instruction to the law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
By adopting the technical scheme, the initial voice information of the current law enforcement site is acquired through the law enforcement recorder, the server is used for analyzing the emotional characteristics of the relevant personnel of the law enforcement site in real time, the risk coefficient of the current law enforcement site is determined, the risk coefficient is compared with the preset risk coefficient threshold, and the warning reminding is carried out aiming at the condition that the risk coefficient is greater than the preset risk coefficient threshold, so that the law enforcement personnel is reminded of high risk of law enforcement atmosphere, the risk of occurrence of personal safety events exists, the law enforcement personnel can adjust the environment of the law enforcement site, the personal safety of the law enforcement personnel is improved, and the harmonious law enforcement is promoted.
Optionally, the analysis module includes:
the preprocessing submodule is used for carrying out voice preprocessing on the initial voice information and taking the initial voice information corresponding to the voice preprocessed information as intermediate voice information;
the characteristic extraction submodule is used for extracting the characteristics of the intermediate voice information and acquiring a tone characteristic time sequence and a loudness characteristic time sequence, wherein the tone characteristic represents word and sentence pronunciation frequency, and the loudness characteristic represents word and sentence pronunciation amplitude;
the voice analysis submodule is used for calculating a voice danger coefficient of the current law enforcement site by utilizing a similarity measurement method and a preset voice threshold according to the tone characteristic time sequence and the loudness characteristic time sequence;
the semantic analysis submodule is used for matching according to the tone characteristic time sequence and a preset identification word frequency database, counting the word frequency of the successfully matched identification words, and determining the semantic risk coefficient of the current law enforcement site according to the word frequency;
and the calculation submodule is used for calculating the risk coefficient of the current law enforcement site according to different weight proportions according to the voice risk coefficient and the semantic risk coefficient.
By adopting the technical scheme, the voice danger coefficient of the law enforcement site is obtained by carrying out voice analysis on the voice information, and the semantic danger coefficient of the law enforcement site is obtained by carrying out semantic analysis on the voice information, so that the danger coefficient of the law enforcement site is obtained according to the voice danger coefficient and the semantic danger coefficient, the danger degree of the law enforcement site atmosphere is further reflected, the warning prompt is favorably carried out on law enforcement personnel, and harmonious law enforcement is promoted. In addition, intermediate voice information is obtained by preprocessing the initial voice information, so that the voice is conveniently analyzed; the voice recognition method has the advantages that the characteristic extraction is carried out on the intermediate voice information, the tone characteristic time sequence and the loudness characteristic time sequence are obtained, the analysis of the speaking voice characteristics of the law enforcement site is facilitated, the semantic analysis is carried out through the tone characteristic time sequence, and therefore whether over-excited marker words exist in the semantics of the law enforcement site or not is conveniently analyzed, and the semantic risk degree of the law enforcement site is determined.
Optionally, the voice analysis sub-module includes:
the first similarity calculation unit is used for acquiring a real-time tone characteristic value from a tone characteristic time sequence, calculating the tone similarity between the real-time tone characteristic value and a preset tone threshold value by using a similarity measurement method, acquiring a real-time loudness characteristic value from a loudness characteristic time sequence, and calculating the loudness similarity between the real-time loudness characteristic value and the preset loudness threshold value;
and the second similarity calculation unit is used for calculating the voice similarity according to the tone similarity and the loudness similarity and different weight proportions and taking the voice similarity as a voice risk coefficient.
By adopting the technical scheme, the tone similarity and the loudness similarity are simultaneously calculated, and the voice similarity is determined according to different weight ratios and is used as the voice danger coefficient, so that the emotional characteristics of the related personnel on the law enforcement site are obtained through audio analysis, and the warning prompt on the law enforcement site is facilitated.
The third object of the invention is realized by the following technical scheme:
computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method for automatic pre-warning of a hazard of a law enforcement recorder when executing the computer program.
The fourth object of the invention is realized by the following technical scheme:
a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method for automatic pre-warning of risks of a law enforcement recorder.
In summary, the invention includes at least one of the following beneficial technical effects:
1. according to the method, the initial voice information of the current law enforcement site is acquired through the law enforcement recorder, the server is used for analyzing the emotional characteristics of relevant personnel of the law enforcement site in real time, the danger coefficient of the current law enforcement site is determined, the danger coefficient is compared with the preset danger coefficient threshold, and warning reminding is performed on the condition that the danger coefficient is larger than the preset danger coefficient threshold, so that the danger of the law enforcement personnel on the site is reminded to be higher, the risk of personal safety events is generated, the law enforcement personnel can regulate and control the environment of the law enforcement site, the personal safety of the law enforcement personnel and the personnel to be enforced is improved, and harmonious law enforcement is promoted.
2. This application is through carrying out speech analysis to speech information, obtains the on-the-spot pronunciation danger coefficient of law enforcement, through carrying out semantic analysis to speech information, obtains the on-the-spot semantic danger coefficient of law enforcement to according to pronunciation danger coefficient and semantic danger coefficient, obtain the on-the-spot danger coefficient of law enforcement, and then reflect the danger degree of the on-the-spot atmosphere of law enforcement, help reporting an emergency and asking for help to the law enforcement personnel to report an emergency and ask for help harmonious law enforcement.
3. According to the method and the device, the tone similarity and the loudness similarity are calculated simultaneously, the voice similarity is determined according to different weight ratios and is used as the voice danger coefficient, so that the emotional characteristics of related personnel on the law enforcement site are obtained through audio analysis, and warning prompt on the law enforcement site is facilitated.
4. According to the method and the device, the real-time tone characteristic value and the identification word frequency database are matched, whether the speech of the overstimulation dispute exists can be analyzed, the accumulated times of the identification words appearing in the tone characteristic time sequence are counted and used as the word frequency, and the word frequency and the preset word frequency threshold value are subjected to ratio calculation, so that the semantic risk coefficient of a law enforcement site is determined conveniently, the warning prompt of the law enforcement site is facilitated, and the harmonious law enforcement is promoted.
Drawings
FIG. 1 is a flow chart of an implementation of a method for automatic early warning of a hazard of a law enforcement recorder according to an embodiment of the present application;
FIG. 2 is a flowchart of an implementation of step S20 of an automatic pre-warning method for a law enforcement recorder according to an embodiment of the present application;
FIG. 3 is a functional block diagram of an automatic hazard warning system for a law enforcement recorder in accordance with an embodiment of the present application;
FIG. 4 is a functional block diagram of a computer device according to an embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
in this embodiment, as shown in fig. 1, the application discloses a method for automatically warning a danger of a law enforcement recorder, which is applied to an interaction between a server and the law enforcement recorder, and the method includes:
s10: and acquiring initial voice information of the current law enforcement site in real time.
In this embodiment, the current law enforcement scene refers to the scene where law enforcement personnel are enforcing law; the initial voice information refers to original voice information acquired by a law enforcement recorder at a law enforcement site.
Specifically, when a law enforcement officer performs law enforcement on a law enforcement site, a law enforcement recorder is opened, voice recording is performed on the current law enforcement site by using the law enforcement recorder, the real-time acquired voice signal is transmitted to a server by the law enforcement recorder, the server acquires the voice signal for digital-to-analog conversion, and the voice signal corresponding to the digital-to-analog conversion is used as initial voice information. In addition, the law enforcement recorder of the embodiment can also be used for video shooting of the current law enforcement site and talkback among law enforcement personnel.
S20: and performing emotion analysis on related personnel of the current law enforcement site according to the initial voice information to acquire the risk coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel.
In this embodiment, the risk factor refers to the possibility that a dangerous event may occur at the current law enforcement site.
Specifically, there are law enforcement personnel and the personnel that are enforced on the current law enforcement scene, according to the initial speech information who obtains, carry out emotion analysis to law enforcement personnel and the initial speech information of the personnel that are enforced, thereby the analysis obtains the possibility that there is the dangerous condition in the current law enforcement scene, in this embodiment, dangerous condition such as taking place and beating, personal attack and so on threaten the incident of personal safety.
As shown in fig. 2, the following describes in detail the implementation manner of step S20 in this embodiment:
s201: and carrying out voice preprocessing on the initial voice information, and taking the initial voice information corresponding to the voice preprocessed information as intermediate voice information.
In this embodiment, the intermediate voice information refers to voice information obtained by preprocessing the initial voice information.
Specifically, the server performs voice preprocessing on the acquired initial voice information, where the voice preprocessing may adopt voice framing, pre-emphasis, windowing, and FFT (fast fourier transform), and takes the voice information after the preprocessing as intermediate voice information. In the embodiment, the initial voice information is divided into small segments of voice by voice framing, so that voice analysis is facilitated; pre-emphasis processing is utilized, so that low-frequency interference in initial voice information can be filtered, a high-frequency part is improved, and voice analysis is facilitated; windowing is utilized to help increase the intelligibility of the speech signal; the voice time domain signal is converted into a frequency domain signal by using FFT (fast Fourier transform), so that the signal is decomposed, the subsequent calculation amount is reduced, and the efficiency of preprocessing the initial voice information is improved.
S202: and performing feature extraction on the intermediate voice information to acquire a tone feature time sequence and a loudness feature time sequence, wherein the tone feature represents the pronunciation frequency of the words and sentences, and the loudness feature represents the pronunciation amplitude of the words and sentences.
In this embodiment, the acoustic feature timing refers to a frequency feature timing obtained by framing the intermediate speech information; the loudness characteristic time sequence refers to the amplitude characteristic time sequence after the intermediate voice information is framed.
Specifically, the wavelet transform method may be used to perform feature extraction on the intermediate speech information, and obtain a pitch feature timing and a loudness feature timing.
S203: and calculating the voice danger coefficient of the current law enforcement site by utilizing a similarity measurement method and a preset voice threshold according to the tone characteristic time sequence and the loudness characteristic time sequence.
In the present embodiment, the voice threshold is an alarm threshold set for a voice feature; the voice risk coefficient refers to the possibility that the current law enforcement scene is dangerous through voice analysis. In the present embodiment, the speech threshold includes a pitch threshold and a loudness threshold.
The following describes in detail the way in which the speech risk factor of the current law enforcement situation is calculated:
and acquiring a real-time tone characteristic value from the tone characteristic time sequence, calculating the tone similarity between the real-time tone characteristic value and a preset tone threshold value by using a similarity measurement method, acquiring a real-time loudness characteristic value from the loudness characteristic time sequence, and calculating the loudness similarity between the real-time loudness characteristic value and the preset loudness threshold value.
And calculating the voice similarity according to different weight proportions according to the tone similarity and the loudness similarity, and taking the voice similarity as a voice risk coefficient.
In the present embodiment, the tone threshold is an alarm threshold set for the tone characteristic; the loudness threshold is an alert threshold set for loudness; tone similarity refers to the probability that a tone in voice information in a law enforcement scene reaches an alarm; loudness similarity refers to the likelihood of loudness in voice messages reaching an alert in law enforcement situations.
Specifically, according to the tone feature time sequence, a real-time tone feature value is obtained from the tone feature time sequence, then the tone similarity between the real-time tone feature value and the tone threshold value is calculated by using a similarity measurement method, meanwhile, a real-time loudness feature value is obtained from the loudness feature time sequence, and the loudness similarity between the real-time loudness feature value and the loudness threshold value is calculated by using the similarity measurement method. In this embodiment, the euclidean distance method may be used to perform the similarity metric calculation.
Further, the voice similarity is calculated according to different weight ratios of the pitch similarity and the loudness similarity, and is used as a voice risk coefficient, in the embodiment, the weight ratios of the pitch similarity and the loudness similarity are both set to be 0.5, and in other embodiments, the weight ratio can be adaptively adjusted according to actual conditions.
S204: and matching according to the tone characteristic time sequence and a preset identification word frequency database, counting the word frequency of the successfully matched identification words, and determining the semantic risk coefficient of the current law enforcement site according to the word frequency.
In this embodiment, the tagged word frequency database stores the pronunciation frequency of tagged words, where the tagged words refer to words and sentences with contradictory enlightenment; the word frequency of the identification words refers to the frequency of the accumulated occurrence of the identification words in the tone characteristic time sequence; semantic risk factors refer to the likelihood of a risk present at the current law enforcement site through analysis of voice content.
The implementation of determining the semantic risk factor of a current law enforcement site is described in detail below:
and acquiring a real-time tone characteristic value from the tone characteristic time sequence, matching the real-time tone characteristic value with the identification word frequency database, and counting the accumulated times of the occurrence of the identification words in the tone characteristic time sequence to be used as word frequency.
And calculating the ratio of the word frequency to a preset word frequency threshold value, and acquiring a calculation result as a semantic risk coefficient.
In this embodiment, the word frequency threshold refers to a maximum occurrence number preset for the identified word; the identifying words may be contradictory inspirations or abusive words, such as "fines", "try-you-go", and abusive words. And storing the pronunciation frequency of the identified words in a database. Matching the real-time tone characteristic value with a tag word frequency database, counting the times of accumulating tag words, wherein the tag words are not limited in kind, then taking the counted times as word frequency, calculating the ratio of the word frequency to a preset word frequency threshold value, for example, the word frequency is 8 times, the preset word frequency threshold value is 10 times, the ratio calculation result is 0.8, further, taking the ratio calculation result as a semantic risk coefficient, in this embodiment, the word frequency threshold value can be properly adjusted according to the voice time length in the actual law enforcement site.
S205: and calculating the risk coefficient of the current law enforcement site according to different weight proportions according to the voice risk coefficient and the semantic risk coefficient.
Specifically, the risk coefficient of the current law enforcement site is obtained by calculating the voice risk coefficient and the semantic risk coefficient according to different weight proportions, in this embodiment, both the voice risk coefficient and the semantic risk coefficient may be set to 0.5, and in other embodiments, the weight proportion may be adaptively adjusted according to actual conditions.
S30: and judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold, if so, generating a law enforcement alarm instruction and sending the law enforcement alarm instruction to a law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
In this embodiment, the risk factor threshold refers to a threshold set for whether or not a risk alarm is performed on the law enforcement site.
Specifically, comparing the calculated risk coefficient with a preset risk coefficient threshold value, specifically: if the risk coefficient is larger than or equal to the risk coefficient threshold value, determining that the current law enforcement site needs to be warned; and if the risk coefficient is smaller than the risk coefficient threshold value, determining that no alarm is needed on the current law enforcement site. For example, the risk factor threshold is set to 70%, and when the risk factor is 80%, it can be determined that the current law enforcement site needs to be warned.
Furthermore, if the current law enforcement site needs to give an alarm, a law enforcement alarm instruction is generated and sent to the law enforcement recorder, so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel, the law enforcement personnel coordinate the law enforcement site, law enforcement harmony is promoted, and the possibility of personal safety events is reduced.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two:
in one embodiment, an automatic danger early warning system of a law enforcement recorder is provided, and the automatic danger early warning system of the law enforcement recorder corresponds to the automatic danger early warning method of the law enforcement recorder in the embodiment one to one. As shown in fig. 3, the automatic danger early warning system of the law enforcement recorder includes an information acquisition module, an analysis module, and a judgment and alarm module. The functional modules are explained in detail as follows:
the information acquisition module is used for acquiring initial voice information of a current law enforcement site in real time;
the analysis module is used for carrying out emotion analysis on related personnel of the current law enforcement site according to the initial voice information to obtain the risk coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
and the judgment warning module is used for judging whether the current law enforcement site needs to be warned according to the danger coefficient and a preset danger coefficient threshold value, and if so, generating a law enforcement warning instruction and sending the law enforcement warning instruction to the law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
Optionally, the analysis module includes:
the preprocessing submodule is used for carrying out voice preprocessing on the initial voice information and taking the initial voice information corresponding to the voice preprocessed information as intermediate voice information;
the characteristic extraction submodule is used for extracting the characteristics of the intermediate voice information and acquiring a tone characteristic time sequence and a loudness characteristic time sequence, wherein the tone characteristic represents word and sentence pronunciation frequency, and the loudness characteristic represents word and sentence pronunciation amplitude;
the voice analysis submodule is used for calculating a voice danger coefficient of a current law enforcement site by utilizing a similarity measurement method and a preset voice threshold according to the tone characteristic time sequence and the loudness characteristic time sequence;
the semantic analysis submodule is used for matching according to the tone characteristic time sequence and a preset identification word frequency database, counting the word frequency of the successfully matched identification words and determining the semantic risk coefficient of the current law enforcement site according to the word frequency;
and the calculation submodule is used for calculating the risk coefficient of the current law enforcement site according to different weight proportions according to the voice risk coefficient and the semantic risk coefficient.
Optionally, the voice analysis sub-module includes:
the first similarity calculation unit is used for acquiring a real-time tone characteristic value from a tone characteristic time sequence, calculating the tone similarity between the real-time tone characteristic value and a preset tone threshold value by using a similarity measurement method, acquiring a real-time loudness characteristic value from a loudness characteristic time sequence, and calculating the loudness similarity between the real-time loudness characteristic value and the preset loudness threshold value;
and the second similarity calculation unit is used for calculating the voice similarity according to the tone similarity and the loudness similarity and different weight proportions and taking the voice similarity as a voice risk coefficient.
Optionally, the semantic analysis sub-module includes:
the matching unit is used for acquiring a real-time tone characteristic value from the tone characteristic time sequence, matching the real-time tone characteristic value with the identification word frequency database, and counting the accumulated times of the occurrence of the identification words in the tone characteristic time sequence and taking the accumulated times as word frequency;
and the ratio calculation unit is used for calculating the ratio of the word frequency to a preset word frequency threshold value, acquiring a calculation result and taking the calculation result as a semantic risk coefficient.
Optionally, the preprocessing sub-module includes:
and the preprocessing unit is used for performing voice preprocessing on the initial voice information, and comprises voice framing, pre-emphasis, windowing and FFT (fast Fourier transform).
Optionally, the feature extraction sub-module includes:
and the characteristic extraction unit is used for extracting the characteristics of the intermediate voice information by using a wavelet transform method and acquiring the tone characteristic time sequence and the loudness characteristic time sequence.
Optionally, the judging and warning module includes:
the judgment unit is used for determining that the current law enforcement site needs to be warned if the risk coefficient is greater than or equal to the risk coefficient threshold; and if the risk coefficient is smaller than the risk coefficient threshold value, determining that no alarm is needed on the current law enforcement site.
For the specific limitations of the automatic hazard warning system of the law enforcement recorder, reference may be made to the above limitations of the automatic hazard warning method of the law enforcement recorder, which are not described herein again. The modules in the automatic danger early warning system of the law enforcement recorder can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Example three:
in one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as initial speech information, intermediate speech information, pitch characteristic timing, loudness characteristic timing and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize the automatic danger early warning method of the law enforcement recorder, and the processor executes the computer program to realize the following steps:
s10: acquiring initial voice information of a current law enforcement site in real time;
s20: according to the initial voice information, performing emotion analysis on related personnel of the current law enforcement site to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
s30: and judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold, if so, generating a law enforcement alarm instruction and sending the law enforcement alarm instruction to a law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
Example four:
in one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s10: acquiring initial voice information of a current law enforcement site in real time;
s20: according to the initial voice information, performing emotion analysis on related personnel of the current law enforcement site to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
s30: and judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold, if so, generating a law enforcement alarm instruction and sending the law enforcement alarm instruction to a law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims (10)

1. A danger automatic early warning method of a law enforcement recorder is applied to interaction between a server and the law enforcement recorder, and is characterized by comprising the following steps:
acquiring initial voice information of a current law enforcement site in real time;
according to the initial voice information, performing emotion analysis on related personnel of the current law enforcement site to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
and judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold value, if so, generating a law enforcement alarm instruction and sending the law enforcement alarm instruction to a law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
2. The automatic pre-warning method for danger of law enforcement recorder according to claim 1,
according to the initial voice information, emotion analysis is carried out on related personnel of the current law enforcement site, and the risk coefficient of the current law enforcement site is obtained, wherein the emotion analysis comprises the following steps:
performing voice preprocessing on the initial voice information, and taking the initial voice information corresponding to the voice preprocessed information as intermediate voice information;
extracting the characteristics of the intermediate voice information to obtain a tone characteristic time sequence and a loudness characteristic time sequence, wherein the tone characteristic represents the pronunciation frequency of words and sentences, and the loudness characteristic represents the pronunciation amplitude of words and sentences;
calculating the voice danger coefficient of the current law enforcement site by utilizing a similarity measurement method and a preset voice threshold according to the tone characteristic time sequence and the loudness characteristic time sequence;
matching according to the tone characteristic time sequence and a preset identification word frequency database, counting the word frequency of the successfully matched identification words, and determining the semantic risk coefficient of the current law enforcement site according to the word frequency;
and calculating the risk coefficient of the current law enforcement site according to different weight proportions according to the voice risk coefficient and the semantic risk coefficient.
3. The method for automatic pre-warning of danger of law enforcement recorder according to claim 2, wherein the voice threshold comprises a tone threshold and a loudness threshold, and the calculation of the voice danger coefficient of the current law enforcement site by using a similarity measure method and a preset voice threshold according to the tone feature timing and the loudness feature timing comprises:
acquiring a real-time tone characteristic value from a tone characteristic time sequence, calculating the tone similarity between the real-time tone characteristic value and a preset tone threshold value by using a similarity measurement method, acquiring a real-time loudness characteristic value from a loudness characteristic time sequence, and calculating the loudness similarity between the real-time loudness characteristic value and the preset loudness threshold value;
and calculating the voice similarity according to different weight proportions according to the tone similarity and the loudness similarity, and taking the voice similarity as a voice risk coefficient.
4. The automatic pre-warning method for danger of law enforcement recorder according to claim 2,
the identification word frequency database is used for storing pronunciation frequency of identification words, wherein the identification words refer to words and sentences with contradictory enlightenment, the tone characteristic time sequence is matched with the preset identification word frequency database, the identification word frequency which is successfully matched is counted, and the semantic risk coefficient of the current law enforcement site is determined according to the word frequency, and the method comprises the following steps:
acquiring a real-time tone characteristic value from a tone characteristic time sequence, matching the real-time tone characteristic value with an identification word frequency database, and counting the accumulated times of the occurrence of identification words in the tone characteristic time sequence to be used as word frequency;
and calculating the ratio of the word frequency to a preset word frequency threshold value, and acquiring a calculation result as a semantic risk coefficient.
5. The automatic pre-warning method for danger of law enforcement recorder according to claim 4, wherein,
and performing voice preprocessing on the initial voice information, wherein the voice preprocessing comprises voice framing, pre-emphasis, windowing and FFT (fast Fourier transform).
6. The automatic pre-warning method for danger of law enforcement recorder according to claim 4, wherein,
carrying out feature extraction on the intermediate voice information to obtain a tone feature time sequence and a loudness feature time sequence, wherein the method comprises the following steps:
and (3) extracting the characteristics of the intermediate voice information by using a wavelet transform method, and acquiring a tone characteristic time sequence and a loudness characteristic time sequence.
7. The automatic pre-warning method for danger of law enforcement recorder according to claim 1,
judging whether the current law enforcement site needs to give an alarm or not according to the risk coefficient and a preset risk coefficient threshold value, wherein the judgment comprises the following steps:
if the risk coefficient is larger than or equal to the risk coefficient threshold value, determining that the current law enforcement site needs to be warned; and if the risk coefficient is smaller than the risk coefficient threshold value, determining that no alarm is needed in the current law enforcement site.
8. An automatic hazard warning system for a law enforcement recorder, the system comprising:
the information acquisition module is used for acquiring initial voice information of a current law enforcement site in real time;
the analysis module is used for carrying out emotion analysis on related personnel of the current law enforcement site according to the initial voice information to obtain a danger coefficient of the current law enforcement site, wherein the related personnel comprise law enforcement personnel and law enforcement personnel;
and the judgment warning module is used for judging whether the current law enforcement site needs to be warned according to the danger coefficient and a preset danger coefficient threshold value, if so, generating a law enforcement warning instruction and sending the law enforcement warning instruction to the law enforcement recorder so that the law enforcement recorder sends a danger early warning prompt to law enforcement personnel.
9. The automatic hazard warning system for a law enforcement recorder according to claim 8 wherein the analysis module comprises:
the preprocessing submodule is used for carrying out voice preprocessing on the initial voice information and taking the initial voice information corresponding to the voice preprocessed information as intermediate voice information;
the characteristic extraction submodule is used for extracting the characteristics of the intermediate voice information and acquiring a tone characteristic time sequence and a loudness characteristic time sequence, wherein the tone characteristic represents word and sentence pronunciation frequency, and the loudness characteristic represents word and sentence pronunciation amplitude;
the voice analysis submodule is used for calculating a voice danger coefficient of the current law enforcement site by utilizing a similarity measurement method and a preset voice threshold according to the tone characteristic time sequence and the loudness characteristic time sequence;
the semantic analysis submodule is used for matching according to the tone characteristic time sequence and a preset identification word frequency database, counting the word frequency of the successfully matched identification words, and determining the semantic risk coefficient of the current law enforcement site according to the word frequency;
and the calculation submodule is used for calculating the risk coefficient of the current law enforcement site according to different weight proportions according to the voice risk coefficient and the semantic risk coefficient.
10. The automatic hazard warning system for a law enforcement recorder according to claim 8 wherein the voice analysis sub-module comprises:
the first similarity calculation unit is used for acquiring a real-time tone characteristic value from a tone characteristic time sequence, calculating the tone similarity between the real-time tone characteristic value and a preset tone threshold value by using a similarity measurement method, acquiring a real-time loudness characteristic value from a loudness characteristic time sequence, and calculating the loudness similarity between the real-time loudness characteristic value and the preset loudness threshold value;
and the second similarity calculation unit is used for calculating the voice similarity according to the tone similarity and the loudness similarity and different weight proportions and taking the voice similarity as a voice risk coefficient.
CN202110027079.7A 2021-01-09 2021-01-09 Automatic danger early warning method and system of law enforcement recorder Pending CN112800772A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110027079.7A CN112800772A (en) 2021-01-09 2021-01-09 Automatic danger early warning method and system of law enforcement recorder

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110027079.7A CN112800772A (en) 2021-01-09 2021-01-09 Automatic danger early warning method and system of law enforcement recorder

Publications (1)

Publication Number Publication Date
CN112800772A true CN112800772A (en) 2021-05-14

Family

ID=75809577

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110027079.7A Pending CN112800772A (en) 2021-01-09 2021-01-09 Automatic danger early warning method and system of law enforcement recorder

Country Status (1)

Country Link
CN (1) CN112800772A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113612953A (en) * 2021-08-11 2021-11-05 深圳中维安科技有限公司 Multi-device remote transmission control method and system
CN115587216A (en) * 2022-12-13 2023-01-10 广州电力工程监理有限公司 Calibration software management method, system and medium for supervision witness recorder

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108694958A (en) * 2018-04-26 2018-10-23 广州国音科技有限公司 A kind of security alarm method and device
CN110401792A (en) * 2019-08-27 2019-11-01 青岛卡铺信息有限公司 A kind of comprehensive law enforcement recorder and its supervisory systems
CN112037820A (en) * 2019-05-16 2020-12-04 杭州海康威视数字技术股份有限公司 Security alarm method, device, system and equipment

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108694958A (en) * 2018-04-26 2018-10-23 广州国音科技有限公司 A kind of security alarm method and device
CN112037820A (en) * 2019-05-16 2020-12-04 杭州海康威视数字技术股份有限公司 Security alarm method, device, system and equipment
CN110401792A (en) * 2019-08-27 2019-11-01 青岛卡铺信息有限公司 A kind of comprehensive law enforcement recorder and its supervisory systems

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113612953A (en) * 2021-08-11 2021-11-05 深圳中维安科技有限公司 Multi-device remote transmission control method and system
CN115587216A (en) * 2022-12-13 2023-01-10 广州电力工程监理有限公司 Calibration software management method, system and medium for supervision witness recorder
CN115587216B (en) * 2022-12-13 2023-08-22 广州电力工程监理有限公司 Calibration software management method, system and medium for supervision witness recorder

Similar Documents

Publication Publication Date Title
WO2020177380A1 (en) Voiceprint detection method, apparatus and device based on short text, and storage medium
CN108694958B (en) Security alarm method and device
US20190279298A1 (en) Information auditing method, apparatus, electronic device and computer readable storage medium
US20070299671A1 (en) Method and apparatus for analysing sound- converting sound into information
CN109616140B (en) Abnormal sound analysis system
CN112800772A (en) Automatic danger early warning method and system of law enforcement recorder
US11322159B2 (en) Caller identification in a secure environment using voice biometrics
WO2021042537A1 (en) Voice recognition authentication method and system
CN108831456B (en) Method, device and system for marking video through voice recognition
CN110839112A (en) Problem voice detection method and device
CN109801638B (en) Voice verification method, device, computer equipment and storage medium
CN112328994A (en) Voiceprint data processing method and device, electronic equipment and storage medium
AU2005100274A4 (en) Method and apparatus for analyising sound
US20220224792A1 (en) Caller identification in a secure environment using voice biometrics
CN113223558B (en) Audio data silencing method and device, electronic equipment and storage medium
CN114610840A (en) Sensitive word-based accounting monitoring method, device, equipment and storage medium
CN111179936A (en) Call recording monitoring method
CN109634554B (en) Method and device for outputting information
CN113112992B (en) Voice recognition method and device, storage medium and server
CN115132188A (en) Early warning method and device based on voice recognition, terminal equipment and storage medium
CN106559759B (en) Method and device for intercepting multimedia message in mobile equipment
CN114171057A (en) Transformer event detection method and system based on voiceprint
CN113810548A (en) Intelligent call quality inspection method and system based on IOT
CN112967712A (en) Synthetic speech detection method based on autoregressive model coefficient
CN111986681A (en) Warehouse supervision management system

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

Application publication date: 20210514

RJ01 Rejection of invention patent application after publication