CN111312282A - Health state determination method and device based on voice information - Google Patents
Health state determination method and device based on voice information Download PDFInfo
- Publication number
- CN111312282A CN111312282A CN202010099877.6A CN202010099877A CN111312282A CN 111312282 A CN111312282 A CN 111312282A CN 202010099877 A CN202010099877 A CN 202010099877A CN 111312282 A CN111312282 A CN 111312282A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- preset time
- user
- voice
- preset
- 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
- 230000036541 health Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 78
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 238000012544 monitoring process Methods 0.000 claims abstract description 38
- 238000000605 extraction Methods 0.000 claims abstract description 26
- 230000003862 health status Effects 0.000 claims description 46
- 238000004891 communication Methods 0.000 claims description 19
- 201000010099 disease Diseases 0.000 claims description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000007635 classification algorithm Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 206010068319 Oropharyngeal pain Diseases 0.000 description 1
- 201000007100 Pharyngitis Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000000994 depressogenic effect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
-
- 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
-
- 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
- G10L25/66—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 for extracting parameters related to health condition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application discloses a health state determination method and device based on voice information. After acquiring voice signals of a user in a preset time period, wherein the preset time period comprises at least two preset time slots, performing signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time period; and analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal. The method can identify and evaluate the health state by utilizing the long-time voice signal, and improves the practicability and accuracy of monitoring.
Description
Technical Field
The present application relates to the field of intelligent voice interaction technologies, and in particular, to a method and an apparatus for determining a health status based on voice information.
Background
Along with the high-speed development of market economy, the pace of life of people is also faster and faster, and people are often busy in various works and pay for, resulting in excessive mental stress and irregular life style of people, thereby causing the sub-health state of human bodies. Because the sound contains rich biomedical information and has the advantages of directness, non-invasiveness, automation and the like, the sound attracts wide attention in the aspects of semantic understanding, health analysis and the like.
However, the inventor finds that the current monitoring system can only perform short-term monitoring on whether the user has diseases such as sore throat or cough and the like and perform short-term monitoring on whether the user has abnormal emotion, that is, the current monitoring system cannot perform long-term monitoring and is low in accuracy.
Disclosure of Invention
The embodiment of the application provides a health state determination method and device based on voice information, which solve the problems in the prior art and improve the monitoring accuracy.
In a first aspect, a health status determination method based on voice information is provided, and the method may include:
acquiring a voice signal of a user in a preset time period, wherein the preset time period comprises at least two preset time slots;
performing signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time period;
and analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal.
In an optional implementation, acquiring a voice signal of a user within a preset time period includes:
collecting a multi-channel voice signal of a user in a preset time period;
and processing the acquired multi-channel voice signals by adopting a multi-channel voice enhancement algorithm to acquire the voice signals of the user in a preset time period.
In an optional implementation, performing signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time slot includes:
performing signal feature extraction on the voice signals in the at least two preset time slots to acquire sub voice signal features corresponding to the at least two preset time slots;
and comprehensively analyzing the sub-voice signal characteristics corresponding to the at least two preset time slots by adopting a preset analysis algorithm to obtain the voice signal characteristics of the preset time slot.
In an optional implementation, after determining the health status of the user corresponding to the acquired voice signal, the method further includes:
and sending an evaluation report of the health state of the user to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
In an optional implementation, the analyzing the voice signal features by using a preset feature analysis algorithm to determine the user health status corresponding to the obtained voice signal includes:
analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm to obtain voice signal characteristic values corresponding to the voice signal characteristics;
and determining the health state of the user corresponding to the acquired voice signal according to the voice signal characteristic value and a preset disease characteristic threshold value.
In an alternative implementation, the speech signal feature includes at least one of a speech pause feature, a speech rate feature, and a pitch frequency feature.
In an optional implementation, the predetermined feature analysis algorithm includes a linear discriminant analysis algorithm, a principal component analysis algorithm, a least squares algorithm, a bayesian classification algorithm, a support vector machine algorithm, a gaussian mixture algorithm, and a deep neural network algorithm.
In an optional implementation, after determining the health status of the user corresponding to the acquired voice signal, the method further includes:
searching a customized service corresponding to the user health state determined in a stored preset service library, wherein the preset service library is used for storing the mapping relation between different user health states and different customized services;
and executing the customized service.
In a second aspect, a health status determination apparatus based on voice information is provided, which may include: an acquisition unit, an extraction unit and a determination unit;
the acquiring unit is used for acquiring a voice signal of a user in a preset time period, wherein the preset time period comprises at least two preset time slots;
the extraction unit is used for extracting the signal characteristics of the voice signals in the at least two preset time slots to obtain the voice signal characteristics of the preset time slot;
the determining unit is configured to analyze the voice signal features by using a preset feature analysis algorithm, and determine a user health state corresponding to the acquired voice signal.
In an optional implementation, the apparatus further comprises an acquisition unit;
the acquisition unit is used for acquiring a multi-channel voice signal of a user in a preset time period;
the acquisition unit is further configured to process the acquired multi-channel speech signals by using a multi-channel speech enhancement algorithm, and acquire the speech signals of the user within a preset time period.
In an optional implementation, the extracting unit is specifically configured to perform signal feature extraction on the voice signals in the at least two preset time slots, and obtain sub-voice signal features corresponding to the at least two preset time slots;
and comprehensively analyzing the sub-voice signal characteristics corresponding to the at least two preset time slots by adopting a preset analysis algorithm to obtain the voice signal characteristics of the preset time slot.
In an alternative implementation, the apparatus further comprises a transmitting unit;
and the sending unit is used for sending the evaluation report of the health state of the user to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
In an optional implementation, the determining unit is specifically configured to analyze the voice signal feature by using a preset feature analysis algorithm to obtain a voice signal feature value corresponding to the voice signal feature;
and determining the user health state corresponding to the acquired voice signal according to the voice signal characteristic value and a preset disease characteristic threshold value.
In an alternative implementation, the speech signal feature includes at least one of a speech pause feature, a speech rate feature, and a pitch frequency feature.
In an optional implementation, the predetermined feature analysis algorithm includes a linear discriminant analysis algorithm, a principal component analysis algorithm, a least squares algorithm, a bayesian classification algorithm, a support vector machine algorithm, a gaussian mixture algorithm, and a deep neural network algorithm.
In an alternative implementation, the apparatus further comprises a lookup unit and an execution unit;
the searching unit is used for searching the customized service corresponding to the user health state determined in a stored preset service library, and the preset service library is used for storing the mapping relation between different user health states and different customized services;
the execution unit is used for executing the customized service.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor adapted to perform the method steps of any of the above first aspects when executing a program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, having stored therein a computer program which, when executed by a processor, performs the method steps of any of the above first aspects.
According to the health state determining method based on the voice information, provided by the embodiment of the invention, after the voice signals of the user in the preset time period are obtained, the preset time period comprises at least two preset time slots, signal feature extraction is carried out on the voice signals in the at least two preset time slots, and the voice signal features of the preset time period are obtained; and analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal. The method can identify and evaluate the health state by utilizing the long-time voice signal, and improves the practicability and accuracy of monitoring.
Drawings
Fig. 1 is a schematic structural diagram of a health status determining system based on voice information according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a health status determining apparatus according to an embodiment of the present invention;
fig. 3 is a schematic flow structure diagram of a health status determining method based on voice information according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a health status determining apparatus based on voice information according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without any creative effort belong to the protection scope of the present application.
The health status determining apparatus of the health status determining method based on voice information provided in the embodiment of the present application may be applied only to the terminal device, may be applied only to the server, and may also be applied to the system shown in fig. 1, where the system may include the terminal device and the server.
If the health status determination apparatus is only applied to the terminal device, the terminal device may be a User Equipment (UE) such as a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a Personal Digital Assistant (PDA), a tablet computer (PAD), etc., having a voice acquisition apparatus and a relatively high computing power, a smart speaker, a handheld device, a vehicle-mounted device, a wearable device, a computing device, or other processing devices connected to a wireless modem, a Mobile Station (MS), etc.
If the health status determination device is only applied to the server, the server may be an application server with a voice acquisition device or a cloud server.
If the health status determination device is applied to the system, the terminal device needs to have a voice acquisition device, and a communication connection is established between the terminal device and the server.
As shown in fig. 2, the health status determining device may include a voice collecting device, a voice signal preprocessing device, a voice signal feature extracting device and a health status recognizing device;
specifically, the voice acquisition device is used for acquiring a multi-channel voice signal of a monitored user within a preset time period; the preset time period may be 24 hours, one week, or one month.
The voice signal preprocessing device is used for processing the acquired multi-channel voice signals by adopting a voice signal processing algorithm to acquire the voice signals of the user in a preset time period, namely the single-channel voice signals, wherein the preset time period can comprise at least two preset time slots.
The voice signal feature extraction device is used for extracting signal features of voice signals in at least two preset time slots, and after the voice signals are imaged, the voice signals are subjected to signal feature extraction frame by taking each preset time slot as a frame, so that the voice signal features in the preset time period are obtained. The preset time slot may be a voice signal within 1 min.
The health state recognition device is used for analyzing the voice signal features by adopting a preset feature analysis algorithm and determining the health state of the user corresponding to the acquired voice signal;
the health state recognition device can analyze the extracted voice signal features by adopting a preset feature analysis algorithm to obtain voice signal feature values corresponding to the voice signal features, and determine the user health state corresponding to the multi-channel voice signals according to the size of the voice signal feature values.
Optionally, the evaluation report sending device can be further included;
and the evaluation report sending device is used for sending an evaluation report of the health state of the user to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
The monitoring users can comprise other family members of the monitored users, main doctors, the detected users and other people needing to monitor the health conditions of the monitored users.
It should be noted that, the attending physician can follow up and monitor the disease condition of the monitored user, such as the disease development trend, the chronic disease recovery condition, etc., according to the evaluation report of the health status of the monitored user.
The evaluation report sending device in the health status recognition device may send the evaluation report of the health status to the mobile phone of the monitoring user or the smart speaker of the monitoring user, so as to display the corresponding evaluation report to the monitoring user.
Further, the health status recognition device may be further configured to search for a customized service corresponding to the determined user health status in a stored preset service library, where the preset service library is configured to store mapping relationships between different user health statuses and different customized services, so as to execute the customized service. The customized services may include at least one of recommended music, recipes, advertisements, dressing reminders, climate change reminders, health encyclopedias, medical recommendations, and the like.
It should be noted that, in order to protect the privacy of the user, the monitored user may trigger the health status identification device to start monitoring or trigger the health status identification device to stop monitoring by himself or herself.
Fig. 3 is a flowchart illustrating a health status determining method based on voice information according to an embodiment of the present invention. As shown in fig. 3, the method may include:
step 310, acquiring a voice signal of a user in a preset time period.
Specifically, the preset time period may be 24 hours, one week, or one month.
The voice signal in the implementation mode is a single-channel voice signal which can be acquired by a microphone consisting of a single acoustic sensor; or after a voice acquisition device consisting of a plurality of acoustic sensors acquires a multi-channel voice signal, the acquired multi-channel voice signal is processed by adopting a multi-channel voice enhancement algorithm to acquire the multi-channel voice signal.
The preset time period may include at least two preset time slots. Such as a preset time slot may be a 1min period.
And step 320, performing signal feature extraction on the voice signals in at least two preset time slots to obtain voice signal features of a preset time period.
And performing signal feature extraction on the voice signals in the at least two preset time slots to acquire sub-voice signal features corresponding to the at least two preset time slots, namely acquiring the corresponding sub-voice signal feature from the voice signal of each preset time slot.
And then, comprehensively analyzing the sub-voice signal characteristics corresponding to at least two preset time slots by adopting a preset analysis algorithm to obtain the voice signal characteristics of the preset time slot.
The speech signal characteristics may include at least one of Mel Frequency Cepstral Coefficients (MFCCs) characteristics, signal spectral energy value characteristics, zero-crossing rate characteristics, formant characteristics, speech pause characteristics, speech rate characteristics, pitch Frequency characteristics, and the like. The voice pause characteristics represent the voice pause times and pause duration in the voice signals in a preset time period; the speech speed feature represents the size of the speed of each syllable appearing in the voice signal in a preset time period; the pitch frequency characteristic represents the pitch frequency in the voice signal in a preset time period;
for example, following a follow-up survey of a depression patient, the voice of the depression patient is characterized by: the speech speed characteristic is slower speech speed, the speech pause characteristic is more pause times, long pause time, the pitch frequency characteristic is the change reduction of the speech characteristic, the lack of voice suppression and pause frustration, the stiff voice and the like; breath sounds were more pronounced in depressed individuals compared to normal individuals; less change in the frequency of sound in patients with depression; the frequency spectrum characteristics are also related to the depression degree of the patient, and the research finds that the change degrees of the sound spectrum energy are below 500Hz and 500-1000 Hz.
If the voice signal feature of the preset time slot is the voice pause feature, the voice pause feature is the sum of the number of the time slots without the voice signal in the sub-voice signal features corresponding to the at least two preset time slots and the average time slot without the voice signal;
if the speech signal feature of the preset time period is a speech rate feature, in order to improve the accuracy of the speech rate feature, the speech rate feature may also be an average speech rate in the sub-speech signal features corresponding to at least two preset time slots.
If the voice signal feature of the preset time slot is the pitch frequency feature, in order to improve the accuracy of the pitch frequency feature, the pitch frequency feature is an average pitch frequency in the sub-voice signal features corresponding to at least two preset time slots.
Therefore, accurate voice pause characteristics, pitch frequency characteristics, speech speed characteristics and the like are difficult to acquire from the voice signal monitored in the short term in the prior art.
Compared with the short-term monitoring voice signals in the prior art, the voice signals monitored for a long time can extract the change characteristics of the voice frequency, the change characteristics of the sound spectrum energy and the like of the monitored user from the voice signals monitored for a long time, namely, the voice signals monitored for a long time can extract the voice signal characteristics of the voice signals monitored for a short time, and can also extract some voice signal characteristics which cannot be extracted from the voice signals monitored for a short time, so that the monitoring accuracy is improved.
It should be noted that, since the signal feature extraction algorithm for extracting the speech signal features can be performed by using the existing feature extraction algorithm, the embodiment of the present invention is not limited herein.
And 330, analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal.
Specifically, a preset feature analysis algorithm is adopted to analyze the extracted voice signal features to obtain voice signal feature values corresponding to the voice signal features;
and then, determining the health state of the user corresponding to the multi-channel voice signal according to the voice signal characteristic value and a preset disease characteristic threshold value.
For example, if the voice signal characteristic value is always higher than a preset disease characteristic threshold value of a certain disease according to the sequence of the preset time slots, it indicates that the monitored user suffers from the disease within a preset time period;
if the voice signal characteristic value is higher than a preset disease characteristic threshold value of a certain disease and then lower than the preset disease characteristic threshold value of the disease according to the sequence of the preset time slots, it indicates that the monitored user is in a rehabilitation state within a preset time period.
The preset feature Analysis algorithm may include a linear discriminant Analysis algorithm, a Principal Component Analysis (PCA), a least square algorithm, a bayesian classification algorithm, a support vector machine algorithm, a gaussian mixture algorithm, a deep neural network algorithm, and the like.
Optionally, the health status determining device may train the recognition model by using a preset feature analysis algorithm; the recognition model may include a linear discriminant analysis model, a principal component analysis model, a least square model, a bayesian classification model, a support vector machine model, a gaussian mixture model, a deep neural network model, and the like.
And then, analyzing the extracted voice signal characteristics by using the trained recognition model, and determining the health state of the monitored user in a preset time period.
Optionally, after determining the user health status corresponding to the acquired voice signal, the evaluation report of the user health status may be sent to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
Optionally, after the user health state corresponding to the acquired voice signal is determined, a customized service corresponding to the determined user health state in a stored preset service library may be searched, where the preset service library is used to store mapping relationships between different user health states and different customized services, and execute corresponding customized services.
According to the health state determining method based on the voice information, provided by the embodiment of the invention, after the voice signals of the user in the preset time period are obtained, the preset time period comprises at least two preset time slots, signal feature extraction is carried out on the voice signals in the at least two preset time slots, and the voice signal features of the preset time period are obtained; and analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal. The method can identify and evaluate the health state by utilizing the long-time voice signal, and improves the practicability and accuracy of monitoring.
Corresponding to the foregoing method, an embodiment of the present invention further provides a health status determining apparatus based on voice information, and as shown in fig. 4, the apparatus may include: an acquisition unit 410, an extraction unit 420, and a determination unit 430;
an obtaining unit 410, configured to obtain a voice signal of a user in a preset time period, where the preset time period includes at least two preset time slots;
an extracting unit 420, configured to perform signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time period;
the determining unit 430 is configured to analyze the voice signal features by using a preset feature analysis algorithm, and determine a user health status corresponding to the obtained voice signal.
In an optional implementation, the apparatus further comprises an acquisition unit 440;
the acquisition unit 440 is used for acquiring a multi-channel voice signal of a user within a preset time period;
the obtaining unit 410 is further configured to process the collected multi-channel speech signal by using a multi-channel speech enhancement algorithm, and obtain a speech signal of the user within a preset time period.
In an optional implementation, the extracting unit 420 is specifically configured to perform signal feature extraction on the voice signals in the at least two preset time slots, and obtain sub-voice signal features corresponding to the at least two preset time slots;
and comprehensively analyzing the sub-voice signal characteristics corresponding to the at least two preset time slots by adopting a preset analysis algorithm to obtain the voice signal characteristics of the preset time slot.
In an optional implementation, the apparatus further comprises a sending unit 450;
the sending unit 450 is configured to send an evaluation report of the health status of the user to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
In an optional implementation, the determining unit 430 is specifically configured to analyze the voice signal feature by using a preset feature analysis algorithm to obtain a voice signal feature value corresponding to the voice signal feature;
and determining the user health state corresponding to the acquired voice signal according to the voice signal characteristic value and a preset disease characteristic threshold value.
In an alternative implementation, the speech signal feature includes at least one of a zero-crossing rate feature, a formant feature, a speech pause feature, a speech rate feature, and a pitch frequency feature.
In an optional implementation, the predetermined feature analysis algorithm includes a linear discriminant analysis algorithm, a principal component analysis algorithm, a least squares algorithm, a bayesian classification algorithm, a support vector machine algorithm, a gaussian mixture algorithm, and a deep neural network algorithm.
In an alternative implementation, the apparatus further comprises a lookup unit 460 and an execution unit 470;
a searching unit 460, configured to search for a customized service corresponding to the user health status determined in a stored preset service library, where the preset service library is used to store mapping relationships between different user health statuses and different customized services;
an executing unit 470, configured to execute the customized service.
The functions of the functional units of the health status determining apparatus based on voice information provided in the above embodiments of the present invention may be implemented by the above method steps, and therefore, detailed working processes and beneficial effects of the units in the health status determining apparatus based on voice information provided in the embodiments of the present invention are not repeated herein.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 510, a communication interface 520, a memory 530 and a communication bus 540, where the processor 510, the communication interface 520, and the memory 530 complete mutual communication through the communication bus 540.
A memory 530 for storing a computer program;
the processor 510, when executing the program stored in the memory 530, implements the following steps:
acquiring a voice signal of a user in a preset time period, wherein the preset time period comprises at least two preset time slots;
performing signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time period;
and analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal.
In an optional implementation, acquiring a voice signal of a user within a preset time period includes:
collecting a multi-channel voice signal of a user in a preset time period;
and processing the acquired multi-channel voice signals by adopting a multi-channel voice enhancement algorithm to acquire the voice signals of the user in a preset time period.
In an optional implementation, performing signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time slot includes:
performing signal feature extraction on the voice signals in the at least two preset time slots to acquire sub voice signal features corresponding to the at least two preset time slots;
and comprehensively analyzing the sub-voice signal characteristics corresponding to the at least two preset time slots by adopting a preset analysis algorithm to obtain the voice signal characteristics of the preset time slot.
In an optional implementation, after determining the health status of the user corresponding to the acquired voice signal, the method further includes:
and sending an evaluation report of the health state of the user to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
In an optional implementation, the analyzing the voice signal features by using a preset feature analysis algorithm to determine the user health status corresponding to the obtained voice signal includes:
analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm to obtain voice signal characteristic values corresponding to the voice signal characteristics;
and determining the health state of the user corresponding to the acquired voice signal according to the voice signal characteristic value and a preset disease characteristic threshold value.
In an alternative implementation, the speech signal feature includes at least one of a speech pause feature, a speech rate feature, and a pitch frequency feature.
In an optional implementation, the predetermined feature analysis algorithm includes a linear discriminant analysis algorithm, a principal component analysis algorithm, a least squares algorithm, a bayesian classification algorithm, a support vector machine algorithm, a gaussian mixture algorithm, and a deep neural network algorithm.
In an optional implementation, after determining the health status of the user corresponding to the acquired voice signal, the method further includes:
searching a customized service corresponding to the user health state determined in a stored preset service library, wherein the preset service library is used for storing the mapping relation between different user health states and different customized services;
and executing the customized service.
The aforementioned communication bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Since the implementation and the beneficial effects of the problem solving of each device of the electronic device in the above embodiment can be realized by referring to each step in the embodiment shown in fig. 3, detailed working processes and beneficial effects of the electronic device provided by the embodiment of the present invention are not described herein again.
In yet another embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions that, when executed on a computer, cause the computer to execute the health status determination method based on voice information as described in any one of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method for determining a health status based on speech information as described in any of the above embodiments.
As will be appreciated by one of skill in the art, the embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the true scope of the embodiments of the present application.
It is apparent that those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the embodiments of the present application and their equivalents, the embodiments of the present application are also intended to include such modifications and variations.
Claims (11)
1. A method for determining a health status based on voice information, the method comprising:
acquiring a voice signal of a user in a preset time period, wherein the preset time period comprises at least two preset time slots;
performing signal feature extraction on the voice signals in the at least two preset time slots to obtain voice signal features of the preset time period;
and analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm, and determining the health state of the user corresponding to the acquired voice signal.
2. The method of claim 1, wherein obtaining the voice signal of the user within the preset time period comprises:
collecting a multi-channel voice signal of a user in a preset time period;
and processing the acquired multi-channel voice signals by adopting a multi-channel voice enhancement algorithm to obtain the voice signals of the user in a preset time period.
3. The method of claim 1, wherein performing signal feature extraction on the voice signals in the at least two preset time slots to obtain the voice signal features of the preset time period comprises:
performing signal feature extraction on the voice signals in the at least two preset time slots to acquire sub voice signal features corresponding to the at least two preset time slots;
and comprehensively analyzing the sub-voice signal characteristics corresponding to the at least two preset time slots by adopting a preset analysis algorithm to obtain the voice signal characteristics of the preset time slot.
4. The method of claim 1, wherein after determining the user health status corresponding to the acquired voice signal, the method further comprises:
and sending an evaluation report of the health state of the user to the corresponding monitoring user according to the user identifier of at least one monitoring user in the stored monitoring group information.
5. The method of claim 1, wherein analyzing the speech signal features using a predetermined feature analysis algorithm to determine the user health status corresponding to the obtained speech signal comprises:
analyzing the voice signal characteristics by adopting a preset characteristic analysis algorithm to obtain voice signal characteristic values corresponding to the voice signal characteristics;
and determining the health state of the user corresponding to the acquired voice signal according to the voice signal characteristic value and a preset disease characteristic threshold value.
6. The method of claim 1 or 5, wherein the speech signal features include at least one of speech pause features, speech rate features, and pitch frequency features.
7. The method of claim 1, wherein the predetermined feature analysis algorithm comprises a linear discriminant analysis algorithm, a principal component analysis algorithm, a least squares algorithm, a bayesian classification algorithm, a support vector machine algorithm, a gaussian mixture algorithm, and a deep neural network algorithm.
8. The method of claim 1, wherein after determining the user health status corresponding to the acquired voice signal, the method further comprises:
searching a customized service corresponding to the user health state determined in a stored preset service library, wherein the preset service library is used for storing the mapping relation between different user health states and different customized services;
and executing the customized service.
9. A health status determination apparatus based on voice information, the apparatus comprising: an acquisition unit, an extraction unit and a determination unit;
the acquiring unit is used for acquiring a voice signal of a user in a preset time period, wherein the preset time period comprises at least two preset time slots;
the extraction unit is used for extracting the signal characteristics of the voice signals in the at least two preset time slots to obtain the voice signal characteristics of the preset time slot;
the determining unit is configured to analyze the voice signal features by using a preset feature analysis algorithm, and determine a user health state corresponding to the acquired voice signal.
10. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-8 when executing a program stored on a memory.
11. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010099877.6A CN111312282A (en) | 2020-02-18 | 2020-02-18 | Health state determination method and device based on voice information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010099877.6A CN111312282A (en) | 2020-02-18 | 2020-02-18 | Health state determination method and device based on voice information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111312282A true CN111312282A (en) | 2020-06-19 |
Family
ID=71148394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010099877.6A Pending CN111312282A (en) | 2020-02-18 | 2020-02-18 | Health state determination method and device based on voice information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111312282A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033492A (en) * | 2015-03-12 | 2016-10-19 | 联想(北京)有限公司 | An information processing method and an electronic apparatus |
| US20180366143A1 (en) * | 2017-06-19 | 2018-12-20 | International Business Machines Corporation | Sentiment analysis of mental health disorder symptoms |
| CN109493885A (en) * | 2018-11-13 | 2019-03-19 | 平安科技（深圳）有限公司 | Psychological condition assessment and adjusting method, device and storage medium, server |
| CN110136743A (en) * | 2019-04-04 | 2019-08-16 | 平安科技（深圳）有限公司 | Monitoring method of health state, device and storage medium based on sound collection |
-
2020
- 2020-02-18 CN CN202010099877.6A patent/CN111312282A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033492A (en) * | 2015-03-12 | 2016-10-19 | 联想(北京)有限公司 | An information processing method and an electronic apparatus |
| US20180366143A1 (en) * | 2017-06-19 | 2018-12-20 | International Business Machines Corporation | Sentiment analysis of mental health disorder symptoms |
| CN109493885A (en) * | 2018-11-13 | 2019-03-19 | 平安科技（深圳）有限公司 | Psychological condition assessment and adjusting method, device and storage medium, server |
| CN110136743A (en) * | 2019-04-04 | 2019-08-16 | 平安科技（深圳）有限公司 | Monitoring method of health state, device and storage medium based on sound collection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806089B1 (en) | Mixed speech recognition method and apparatus, and computer readable storage medium | |
| Hassan et al. | COVID-19 detection system using recurrent neural networks | |
| Zhang et al. | Pdvocal: Towards privacy-preserving parkinson's disease detection using non-speech body sounds | |
| San-Segundo et al. | Feature extraction from smartphone inertial signals for human activity segmentation | |
| WO2019104890A1 (en) | Fraud identification method and device combining audio analysis and video analysis and storage medium | |
| Ghosh et al. | Recognizing human activities from smartphone sensor signals | |
| US20180018974A1 (en) | System and method for detecting tantrums | |
| CN109460752B (en) | Emotion analysis method and device, electronic equipment and storage medium | |
| CN109800720B (en) | Emotion recognition model training method, emotion recognition device, equipment and storage medium | |
| US10806393B2 (en) | System and method for detection of cognitive and speech impairment based on temporal visual facial feature | |
| CN110634472B (en) | Speech recognition method, server and computer readable storage medium | |
| Feng et al. | Tiles audio recorder: an unobtrusive wearable solution to track audio activity | |
| WO2014062441A1 (en) | Screening for neurologial disease using speech articulation characteristics | |
| CN112016367A (en) | Emotion recognition system and method and electronic equipment | |
| Pillos et al. | A Real-Time Environmental Sound Recognition System for the Android OS. | |
| CN106504773B (en) | Wearable device and voice and activity monitoring system | |
| CN110505504B (en) | Video program processing method and device, computer equipment and storage medium | |
| WO2019119279A1 (en) | Method and apparatus for emotion recognition from speech | |
| US20180240458A1 (en) | Wearable apparatus and method for vocabulary measurement and enrichment | |
| KR20210006419A (en) | Generating and storing health-related information | |
| CN110946554A (en) | Cough type identification method, device and system | |
| US20210027777A1 (en) | Method for monitoring phonation and system thereof | |
| CN115862868A (en) | Psychological assessment system, psychological assessment platform, electronic device and storage medium | |
| CN109841221A (en) | Parameter adjusting method, device and body-building equipment based on speech recognition | |
| Usman et al. | Heart rate detection and classification from speech spectral features using machine learning |
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: 20200619 |
|
| RJ01 | Rejection of invention patent application after publication |