CN116487050A - Human health monitoring method, device and computer equipment - Google Patents
Human health monitoring method, device and computer equipment Download PDFInfo
- Publication number
- CN116487050A CN116487050A CN202310738119.8A CN202310738119A CN116487050A CN 116487050 A CN116487050 A CN 116487050A CN 202310738119 A CN202310738119 A CN 202310738119A CN 116487050 A CN116487050 A CN 116487050A
- Authority
- CN
- China
- Prior art keywords
- user
- monitored
- model
- health monitoring
- database
- 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.)
- Granted
Links
- 230000036541 health Effects 0.000 title claims abstract description 218
- 238000012544 monitoring process Methods 0.000 title claims abstract description 214
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013507 mapping Methods 0.000 claims description 36
- 230000009467 reduction Effects 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 210000000577 adipose tissue Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Acoustics & Sound (AREA)
- Epidemiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a human health monitoring method, a device and computer equipment, which comprise the following steps: acquiring face images of a user to be monitored, carrying out face recognition, and acquiring user information of the user to be monitored; acquiring the health type to be monitored of the user to be monitored; searching a health monitoring initial model matched with the health type to be monitored in a database; matching a model parameter set of the health monitoring initial model according to user information of a user to be monitored; updating model parameters of the health monitoring initial model into optimal parameters in the model parameter set to obtain a corresponding health monitoring model; and inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored. In the invention, corresponding model parameter sets are matched according to different users to be monitored, so that corresponding health monitoring models are updated and obtained for health monitoring.
Description
Technical Field
The present invention relates to the field of facial image recognition technology, and in particular, to a method and apparatus for monitoring human health, and a computer device.
Background
With the attention of users to self health, more and more users can perform timed health monitoring, and physiological information of the users can be collected through special instrument equipment during health monitoring, and further analysis is performed by adopting a health monitoring model, so that health monitoring results of the users are obtained.
The inventor finds that when human health monitoring is performed at present, the same health monitoring model is generally adopted for all users, and different monitoring cannot be performed for different users, so that the detection accuracy is not improved; this is because, when the information of the age group, sex, etc. of the users is different, the corresponding health judgment criteria will also be different.
Disclosure of Invention
The invention mainly aims to provide a human health monitoring method, a human health monitoring device and computer equipment, and aims to overcome the defect that a target cannot conduct differential health monitoring aiming at different users.
In order to achieve the above object, the present invention provides a human health monitoring method, comprising the steps of:
judging whether the user to be monitored is a new user, if so, collecting physiological information of the user to be monitored; wherein the physiological information is collected by a plurality of sensors;
Acquiring a face image of the user to be monitored, and carrying out face recognition on the face image by adopting a preset image detection model to acquire user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality;
acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored;
searching a health monitoring initial model matched with the health type to be monitored in a database; wherein the health monitoring initial model is an initial model for detecting the health type;
according to the user information of the user to be monitored, matching the model parameter set of the health monitoring initial model; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model;
updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model;
and inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored.
Further, the step of determining whether the user to be monitored is a new user includes:
sending out a voice prompt to inquire whether the user to be monitored is a new user;
receiving voice information fed back by a user to be monitored, carrying out voice recognition on the voice information by adopting a preset recognition model, acquiring a feedback text of the user to be monitored, and judging whether the user to be monitored is a new user or not based on the feedback text; the recognition model is a deep learning model which is obtained through pre-training.
Further, the recognition model comprises a noise reduction model and a voice recognition model;
the training process of the noise reduction model comprises the following steps:
collecting pure user voices of a plurality of users;
mixing the pure user voice with a preset background sound to obtain a mixed voice;
extracting the characteristics of the mixed voice to obtain corresponding first voice characteristics; extracting the characteristics of the pure user voice to obtain a corresponding second voice characteristic;
calculating a first ratio of the first speech feature to the second speech feature;
inputting the first voice characteristic into an initial noise reduction model for prediction, and obtaining a corresponding second ratio by prediction;
And calculating the approximation degree of the first ratio and the second ratio based on a loss function in the initial noise reduction model, and iteratively training the initial noise reduction model until the approximation degree is not changed, so as to obtain a trained noise reduction model.
Further, after the step of determining whether the user to be monitored is a new user, the method further includes:
if the user to be monitored is not a new user, matching a unique identification code corresponding to the user to be monitored in a database; wherein the unique identification code comprises a plurality of characters;
identifying the identifier of the unique identification code, and detecting the identifier included in the unique identification code;
judging whether the identifier is positioned at a designated position of the unique identification code; if the identifier is located, the identifier is used as a target identifier;
matching a target identification code segmentation mode corresponding to the target identifier in a database; wherein, the database is pre-stored with the corresponding relation between the identifier and the dividing mode of the identifier code;
removing the target identifier in the unique identification code to obtain a removed identification code;
dividing the eliminating identification codes based on the target identification code dividing mode to obtain a plurality of target character combinations;
Matching health monitoring models corresponding to the target character combinations in a database; wherein, different target character combinations correspond to different health monitoring models;
and acquiring physiological information of the user to be monitored, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and acquiring a corresponding monitoring result as a human health monitoring result of the user to be monitored.
Further, the step of inputting the physiological information of the user to be monitored into the health monitoring model to monitor, and obtaining a corresponding monitoring result, after the step of serving as the human health monitoring result of the user to be monitored, includes:
generating a plurality of character combinations, and binding the character combinations with the health monitoring model and storing the character combinations in a database;
acquiring a random target identifier from a database, and acquiring a splicing mode corresponding to the target identifier; the database is pre-stored with the corresponding relation between the target identifier and the splicing mode;
splicing the character combinations according to the splicing mode to obtain spliced character combinations; adding the target identifier at the appointed position of the spliced character combination to obtain an identification code;
Judging whether the identification code exists in the database, and if not, taking the identification code as the unique identification code of the user to be monitored.
Further, the user information of the user to be monitored comprises Chinese names, wherein the names comprise surnames and names, and the number of the character combinations is three; the step of generating a plurality of character combinations includes:
acquiring pinyin characteristics, stroke characteristics and radical characteristics of the surnames and the names;
based on the pinyin characteristics of the surnames and the people names, matching corresponding first generation rules in a database, and generating corresponding first characters by adopting the first generation rules;
based on the stroke characteristics of the surnames and the person names, matching corresponding second generation rules in a database, and generating corresponding second characters by adopting the second generation rules;
based on the radical characteristics of the surnames and the person names, matching corresponding third generation rules in a database, and generating corresponding third characters by adopting the third generation rules;
acquiring a first rule symbol, a second rule symbol and a third rule symbol which respectively correspond to the first generation rule, the second generation rule and the third generation rule in a database;
Combining the first character with the first rule symbol to obtain a first character combination; combining the second character with the second rule symbol to obtain a second character combination; combining the third character with the third rule symbol to obtain a third character combination; the first character combination, the second character combination and the third character combination are three generated character combinations.
Further, the step of matching corresponding first generation rules in the database based on the pinyin characteristics of the surnames and the people's names and adopting the first generation rules to generate corresponding first characters comprises the following steps:
based on the pinyin characteristics of the surnames, matching corresponding first generation rules in a database; wherein, the database stores the corresponding relation between the pinyin characteristics and the generation rules; the pinyin characteristics of the surname comprise pinyin; the pinyin characteristics of the name comprise initial consonant characteristics, final characteristics and tone characteristics; the first generation rule is a mapping relation table of initial consonant characteristics, final sound characteristics and tone characteristics and mapping characters respectively;
mapping the initial consonant feature into a first mapping character, mapping the final feature into a second mapping character and mapping the tone feature into a third mapping character based on the first generation rule;
Splicing the first mapping character, the second mapping character and the third mapping character once to obtain spliced characters;
based on the pinyin characteristics of the surnames, matching corresponding coding tables in a database; wherein, the database stores the mapping relation between the phonetic feature and the coding table;
and encoding the spliced character based on the encoding table to obtain the first character.
The invention also provides a human health monitoring device, comprising:
the judging unit is used for judging whether the user to be monitored is a new user or not, and if so, the physiological information of the user to be monitored is acquired; wherein the physiological information is collected by a plurality of sensors;
the acquisition unit is used for acquiring the face image of the user to be monitored, carrying out face recognition on the face image by adopting a preset image detection model, and acquiring user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality;
the acquisition unit is used for acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored;
the searching unit is used for searching a health monitoring initial model matched with the health type to be monitored in the database; wherein the health monitoring initial model is an initial model for detecting the health type;
The matching unit is used for matching the model parameter set of the health monitoring initial model according to the user information of the user to be monitored; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model;
the updating unit is used for updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model;
and the monitoring unit is used for inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result which is used as the human health monitoring result of the user to be monitored.
Further, the judging unit is further configured to:
if the user to be monitored is not a new user, matching a unique identification code corresponding to the user to be monitored in a database; wherein the unique identification code comprises a plurality of characters;
identifying the identifier of the unique identification code, and detecting the identifier included in the unique identification code;
judging whether the identifier is positioned at a designated position of the unique identification code; if the identifier is located, the identifier is used as a target identifier;
Matching a target identification code segmentation mode corresponding to the target identifier in a database; wherein, the database is pre-stored with the corresponding relation between the identifier and the dividing mode of the identifier code;
removing the target identifier in the unique identification code to obtain a removed identification code;
dividing the eliminating identification codes based on the target identification code dividing mode to obtain a plurality of target character combinations;
matching health monitoring models corresponding to the target character combinations in a database; wherein, different target character combinations correspond to different health monitoring models;
and acquiring physiological information of the user to be monitored, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and acquiring a corresponding monitoring result as a human health monitoring result of the user to be monitored.
The invention also provides a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of any of the methods described above when the computer program is executed.
The invention provides a human health monitoring method, a device and computer equipment, which comprise the following steps: judging whether the user to be monitored is a new user, if so, collecting physiological information of the user to be monitored; wherein the physiological information is collected by a plurality of sensors; acquiring a face image of the user to be monitored, and carrying out face recognition on the face image by adopting a preset image detection model to acquire user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality; acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored; searching a health monitoring initial model matched with the health type to be monitored in a database; wherein the health monitoring initial model is an initial model for detecting the health type; according to the user information of the user to be monitored, matching the model parameter set of the health monitoring initial model; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model; updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model; and inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored. According to the invention, corresponding model parameter sets are matched according to different users to be monitored, so that corresponding health monitoring models are updated for health monitoring, and differentiated health monitoring can be performed according to different users.
Drawings
FIG. 1 is a schematic diagram showing steps of a method for monitoring human health in an embodiment of the invention;
FIG. 2 is a block diagram of a human health monitoring device according to an embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, in one embodiment of the present invention, a method for monitoring human health is provided, which includes the following steps:
step S1, judging whether a user to be monitored is a new user, if so, collecting physiological information of the user to be monitored; wherein the physiological information is collected by a plurality of sensors;
step S2, acquiring a face image of the user to be monitored, and carrying out face recognition on the face image by adopting a preset image detection model to acquire user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality;
Step S3, obtaining the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored;
step S4, searching a health monitoring initial model matched with the health type to be monitored in a database; wherein the health monitoring initial model is an initial model for detecting the health type;
step S5, matching the model parameter set of the health monitoring initial model according to the user information of the user to be monitored; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model;
step S6, updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model;
and S7, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored.
In this embodiment, the above scheme is applied to the health monitoring for the difference of the users to be monitored, so as to improve the effect of health monitoring.
As described in the step S1, the user to be monitored may be a new user for health monitoring for the first time, or may be an old user for health monitoring for multiple times; for a new user, the database will typically not store the corresponding information corresponding to the new user and the corresponding health monitoring model. Therefore, in this embodiment, corresponding information acquisition and generation of the health monitoring model are required. Firstly, physiological information of a user to be monitored needs to be acquired through a plurality of sensors, wherein the sensors comprise various physiological sensors, such as a heart rate sensor, a body fat sensor, a muscle signal acquisition sensor and the like, and the detailed description is omitted.
As described in the above step S2, the health monitoring standard of the user is affected due to the age, sex, nationality and other factors of the user to be monitored; therefore, the information of the user needs to be acquired, and because the user is a new user and the database has no corresponding user information, the face image of the user to be monitored can be acquired, the face image is identified by adopting an image detection model obtained by training in advance, and the user information of the user to be monitored is acquired, wherein the user information comprises age, gender and nationality.
As described in the above step S3, the health monitoring needs of different users are different, and thus the health type to be monitored will also be different, for example, some users need to monitor heart functions; while some users only need to monitor metabolic efficiency, etc. Obviously, when the health types to be monitored are different, different health monitoring models should be used for monitoring.
As described in step S4, the corresponding relationship between the health type and the health monitoring initial model is stored in the database, so that the corresponding health monitoring initial model can be found in the database according to the health type to be monitored by the user to be monitored; it will be appreciated that the above-described health monitoring initial model is an initial model for detecting the above-described health type, and although health monitoring is possible, monitoring is not effective because model parameters are not updated.
In order to improve the monitoring effect of the health monitoring initial model, as described in the step S5, a model parameter set of the health monitoring initial model needs to be matched according to the user information of the user to be monitored; the model parameter set includes a set of optimal parameters of each health monitoring initial model, and the model parameter set is a set formed by training optimal model parameters obtained by the corresponding health monitoring initial model based on training data in advance.
Finally, as described in the above steps S6 to S7, updating the model parameters of the health monitoring initial model to the optimal parameters in the model parameter set to obtain a corresponding health monitoring model; and inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored. Therefore, the method and the device realize the adaptive monitoring by adopting different health monitoring models according to different users, not only can monitor the health of the users differently, but also are beneficial to the targeted health monitoring, and the health monitoring effect is improved.
In an embodiment, the step of determining whether the user to be monitored is a new user includes:
sending out a voice prompt to inquire whether the user to be monitored is a new user;
receiving voice information fed back by a user to be monitored, carrying out voice recognition on the voice information by adopting a preset recognition model, acquiring a feedback text of the user to be monitored, and judging whether the user to be monitored is a new user or not based on the feedback text; the recognition model is a deep learning model which is obtained through pre-training. In this embodiment, a voice answering mode is adopted to obtain information about whether the user to be monitored is a new user.
In one embodiment, the recognition model includes a noise reduction model and a speech recognition model;
the training process of the noise reduction model comprises the following steps:
collecting pure user voices of a plurality of users;
mixing the pure user voice with a preset background sound to obtain a mixed voice;
extracting the characteristics of the mixed voice to obtain corresponding first voice characteristics; extracting the characteristics of the pure user voice to obtain a corresponding second voice characteristic;
calculating a first ratio of the first speech feature to the second speech feature;
inputting the first voice characteristic into an initial noise reduction model for prediction, and obtaining a corresponding second ratio by prediction;
and calculating the approximation degree of the first ratio and the second ratio based on a loss function in the initial noise reduction model, and iteratively training the initial noise reduction model until the approximation degree is not changed, so as to obtain a trained noise reduction model.
In this embodiment, the noise reduction model is obtained based on the mode of the training model, and the noise reduction capability of the initial noise reduction model is trained by adopting a mode of comparing pure user voice with mixed voice; the pure user voice is voice without background sound, and the mixed voice is voice obtained by mixing the pure user voice with preset background sound; it will be appreciated that when the noise reduction effect of the initial noise reduction model is optimal, the effect of the background sound should be filtered out; therefore, the feature extraction can be respectively carried out on the mixed voices to obtain corresponding first voice features; extracting the characteristics of the pure user voice to obtain a corresponding second voice characteristic; calculating a first ratio of the first speech feature to the second speech feature; it will be appreciated that the first speech feature and the second speech feature are extracted text features, which are extracted only for text contained in the speech during the extraction process, and other noise features (e.g. bird sounds, wind sounds, etc.) are not extracted.
Then inputting the first voice characteristic into an initial noise reduction model for prediction, and obtaining a corresponding second ratio by prediction; and calculating the approximation degree of the first ratio and the second ratio based on a loss function in the initial noise reduction model, and iteratively training the initial noise reduction model until the approximation degree is not changed, so as to obtain a trained noise reduction model.
In another embodiment, a solution for health monitoring of old users is also provided, specifically as follows:
after the step of judging whether the user to be monitored is a new user, the method further comprises the following steps:
if the user to be monitored is not a new user, matching a unique identification code corresponding to the user to be monitored in a database; wherein the unique identification code comprises a plurality of characters; in this embodiment, the unique identifier may include a plurality of target character combinations, and each target character combination may correspond to a health monitoring model. The unique identification code not only has uniqueness, but also has the function of matching with a health monitoring model
Identifying the identifier of the unique identification code, and detecting the identifier included in the unique identification code; the identifier is a specific character such as #, & lt, +/-.
Judging whether the identifier is positioned at a designated position of the unique identification code; if the identifier is located, the identifier is used as a target identifier; in this embodiment, the identifier is only located at the designated position, and if not located at the designated position, it indicates that the unique identifier code is wrong and does not conform to the set rule.
Matching a target identification code segmentation mode corresponding to the target identifier in a database; wherein, the database is pre-stored with the corresponding relation between the identifier and the dividing mode of the identifier code; in this embodiment, the identifier is used to express an identifier code division manner in the unique identifier code; different identifiers correspond to different identification code splitting modes; the identification code dividing mode comprises that every two characters are used as a character combination from the head part of the unique identification code; alternatively, it is also possible to start from the unique identification code header, with every three characters as a character combination; the above-mentioned identification code dividing method is not described in detail herein.
Removing the target identifier in the unique identification code to obtain a removed identification code;
dividing the eliminating identification codes based on the target identification code dividing mode to obtain a plurality of target character combinations;
Matching health monitoring models corresponding to the target character combinations in a database; wherein, different target character combinations correspond to different health monitoring models; in this embodiment, a correspondence relationship between the health monitoring model and the identifier combinations is preset, and different identifier combinations correspond to different health monitoring models. The health monitoring model is used for monitoring the health of the user.
And acquiring physiological information of the user to be monitored, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and acquiring a corresponding monitoring result as a human health monitoring result of the user to be monitored. This step is similar to the step S7 described above, and will not be described in detail here.
In an embodiment, the step of inputting the physiological information of the user to be monitored into the health monitoring model to monitor, and obtaining the corresponding monitoring result as the human health monitoring result of the user to be monitored includes:
generating a plurality of character combinations, and binding the character combinations with the health monitoring model and storing the character combinations in a database; in this embodiment, it may be understood that when the health monitoring model is plural, the character combinations may also be plural, where each character combination may be stored in a binding manner corresponding to one health monitoring model. The character combination may be generated by a specific encoding method according to the name of the user.
Acquiring a random target identifier from a database, and acquiring a splicing mode corresponding to the target identifier; the database is pre-stored with the corresponding relation between the target identifier and the splicing mode;
splicing the character combinations according to the splicing mode to obtain spliced character combinations; adding the target identifier at the appointed position of the spliced character combination to obtain an identification code;
judging whether the identification code exists in the database, and if not, taking the identification code as the unique identification code of the user to be monitored. It can be understood that the unique identification code not only has uniqueness, but also can express the association with the health monitoring model from the unique identification code, so that the health monitoring model matched with the user can be directly obtained from the unique identification code.
In one embodiment, a scheme for generating a plurality of character combinations is provided. The user information of the user to be monitored comprises Chinese names, wherein the names comprise surnames and names, and the number of the character combinations is three; the step of generating a plurality of character combinations includes:
acquiring pinyin characteristics, stroke characteristics and radical characteristics of the surnames and the names; for example, if the user name is Zhang three, the pinyin characteristics of the name and the name are zhang and san respectively, the corresponding stroke characteristics are 8 and 3 respectively, and the component characteristics are bow. Wherein, the upper, lower, left and right parts of Chinese characters are called as components. In general, the term "header" is referred to above as "" + "in the word of flowers, and the term" grass header "; hereinafter referred to as the "bottom"; the character components express the structural characteristics of the Chinese characters. It can be understood that if the Chinese characters are polyphones, common pronunciation can be selected or any pronunciation can be selected.
Based on the pinyin characteristics of the surnames and the people names, matching corresponding first generation rules in a database, and generating corresponding first characters by adopting the first generation rules;
based on the stroke characteristics of the surnames and the person names, matching corresponding second generation rules in a database, and generating corresponding second characters by adopting the second generation rules;
based on the radical characteristics of the surnames and the person names, matching corresponding third generation rules in a database, and generating corresponding third characters by adopting the third generation rules; in this embodiment, the database stores the first generation rule, the second generation rule, and the third generation rule, which correspond to the pinyin feature, the stroke feature, and the radical feature of the surname and the name, respectively. And aiming at the pinyin characteristics, the stroke characteristics and the radical characteristics, adopting corresponding generation rules to generate corresponding characters so that the unique identification codes generated subsequently are combined with the multidimensional characteristics of the user name.
Acquiring a first rule symbol, a second rule symbol and a third rule symbol which respectively correspond to the first generation rule, the second generation rule and the third generation rule in a database; in this embodiment, the database further stores correspondence relationships between the first generation rule, the second generation rule, and the third generation rule and the first rule symbol, the second rule symbol, and the third rule symbol, which are mapped respectively.
Combining the first character with the first rule symbol to obtain a first character combination; combining the second character with the second rule symbol to obtain a second character combination; combining the third character with the third rule symbol to obtain a third character combination; the first character combination, the second character combination and the third character combination are three generated character combinations. In this embodiment, in order to facilitate the subsequent derivation of the first, second, and third generation rules from the character combination, a first rule symbol, a second rule symbol, and a third rule symbol corresponding to the first, second, and third generation rules, respectively, may be added in the process of generating the character combination. Based on the above, when the character combination is analyzed later, only the corresponding first rule symbol, second rule symbol and third rule symbol are needed to be identified, so that the corresponding first generation rule, second generation rule and third generation rule can be obtained; and the specific mode of storing the first generation rule, the second generation rule and the third generation rule is not needed to be recorded, so that the data storage capacity is reduced.
In a specific embodiment, the step of matching corresponding first generation rules in the database based on pinyin features of the surnames and the first names and generating corresponding first characters by adopting the first generation rules includes:
based on the pinyin characteristics of the surnames, matching corresponding first generation rules in a database; wherein, the database stores the corresponding relation between the pinyin characteristics and the generation rules; the pinyin characteristics of the surname comprise pinyin; the pinyin characteristics of the name comprise initial consonant characteristics, final characteristics and tone characteristics; the first generation rule is a mapping relation table of initial consonant characteristics, final sound characteristics and tone characteristics and mapping characters respectively;
mapping the initial consonant feature into a first mapping character, mapping the final feature into a second mapping character and mapping the tone feature into a third mapping character based on the first generation rule;
splicing the first mapping character, the second mapping character and the third mapping character once to obtain spliced characters;
based on the pinyin characteristics of the surnames, matching corresponding coding tables in a database; wherein, the database stores the mapping relation between the phonetic feature and the coding table;
And encoding the spliced character based on the encoding table to obtain the first character.
Referring to fig. 2, in an embodiment of the present invention, there is also provided a human health monitoring apparatus, including:
the judging unit is used for judging whether the user to be monitored is a new user or not, and if so, the physiological information of the user to be monitored is acquired; wherein the physiological information is collected by a plurality of sensors;
the acquisition unit is used for acquiring the face image of the user to be monitored, carrying out face recognition on the face image by adopting a preset image detection model, and acquiring user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality;
the acquisition unit is used for acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored;
the searching unit is used for searching a health monitoring initial model matched with the health type to be monitored in the database; wherein the health monitoring initial model is an initial model for detecting the health type;
the matching unit is used for matching the model parameter set of the health monitoring initial model according to the user information of the user to be monitored; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model;
The updating unit is used for updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model;
and the monitoring unit is used for inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result which is used as the human health monitoring result of the user to be monitored.
In an embodiment, the determining unit is further configured to:
if the user to be monitored is not a new user, matching a unique identification code corresponding to the user to be monitored in a database; wherein the unique identification code comprises a plurality of characters;
identifying the identifier of the unique identification code, and detecting the identifier included in the unique identification code;
judging whether the identifier is positioned at a designated position of the unique identification code; if the identifier is located, the identifier is used as a target identifier;
matching a target identification code segmentation mode corresponding to the target identifier in a database; wherein, the database is pre-stored with the corresponding relation between the identifier and the dividing mode of the identifier code;
removing the target identifier in the unique identification code to obtain a removed identification code;
Dividing the eliminating identification codes based on the target identification code dividing mode to obtain a plurality of target character combinations;
matching health monitoring models corresponding to the target character combinations in a database; wherein, different target character combinations correspond to different health monitoring models;
and acquiring physiological information of the user to be monitored, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and acquiring a corresponding monitoring result as a human health monitoring result of the user to be monitored.
In this embodiment, for specific implementation of each unit in the above embodiment of the apparatus, please refer to the description in the above embodiment of the method, and no further description is given here.
Referring to fig. 3, in an embodiment of the present invention, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the corresponding data in this embodiment. 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 implement a method of human health monitoring.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a human health monitoring method. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
In summary, the method, the device and the computer device for monitoring human health provided in the embodiments of the present invention include: judging whether the user to be monitored is a new user, if so, collecting physiological information of the user to be monitored; wherein the physiological information is collected by a plurality of sensors; acquiring a face image of the user to be monitored, and carrying out face recognition on the face image by adopting a preset image detection model to acquire user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality; acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored; searching a health monitoring initial model matched with the health type to be monitored in a database; wherein the health monitoring initial model is an initial model for detecting the health type; according to the user information of the user to be monitored, matching the model parameter set of the health monitoring initial model; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model; updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model; and inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored. According to the invention, corresponding model parameter sets are matched according to different users to be monitored, so that corresponding health monitoring models are updated for health monitoring, and differentiated health monitoring can be performed according to different users.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile 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), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. A method for monitoring human health, comprising the steps of:
judging whether the user to be monitored is a new user, if so, collecting physiological information of the user to be monitored; wherein the physiological information is collected by a plurality of sensors;
Acquiring a face image of the user to be monitored, and carrying out face recognition on the face image by adopting a preset image detection model to acquire user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality;
acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored;
searching a health monitoring initial model matched with the health type to be monitored in a database; wherein the health monitoring initial model is an initial model for detecting the health type;
according to the user information of the user to be monitored, matching the model parameter set of the health monitoring initial model; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model;
updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model;
and inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result as a human health monitoring result of the user to be monitored.
2. The human health monitoring method according to claim 1, wherein the step of judging whether the user to be monitored is a new user comprises:
sending out a voice prompt to inquire whether the user to be monitored is a new user;
receiving voice information fed back by a user to be monitored, carrying out voice recognition on the voice information by adopting a preset recognition model, acquiring a feedback text of the user to be monitored, and judging whether the user to be monitored is a new user or not based on the feedback text; the recognition model is a deep learning model which is obtained through pre-training.
3. The method of claim 2, wherein the recognition model comprises a noise reduction model and a speech recognition model;
the training process of the noise reduction model comprises the following steps:
collecting pure user voices of a plurality of users;
mixing the pure user voice with a preset background sound to obtain a mixed voice;
extracting the characteristics of the mixed voice to obtain corresponding first voice characteristics; extracting the characteristics of the pure user voice to obtain a corresponding second voice characteristic;
calculating a first ratio of the first speech feature to the second speech feature;
Inputting the first voice characteristic into an initial noise reduction model for prediction, and obtaining a corresponding second ratio by prediction;
and calculating the approximation degree of the first ratio and the second ratio based on a loss function in the initial noise reduction model, and iteratively training the initial noise reduction model until the approximation degree is not changed, so as to obtain a trained noise reduction model.
4. The method for monitoring human health according to claim 1, wherein after the step of determining whether the user to be monitored is a new user, further comprising:
if the user to be monitored is not a new user, matching a unique identification code corresponding to the user to be monitored in a database; wherein the unique identification code comprises a plurality of characters;
identifying the identifier of the unique identification code, and detecting the identifier included in the unique identification code;
judging whether the identifier is positioned at a designated position of the unique identification code; if the identifier is located, the identifier is used as a target identifier;
matching a target identification code segmentation mode corresponding to the target identifier in a database; wherein, the database is pre-stored with the corresponding relation between the identifier and the dividing mode of the identifier code;
Removing the target identifier in the unique identification code to obtain a removed identification code;
dividing the eliminating identification codes based on the target identification code dividing mode to obtain a plurality of target character combinations;
matching health monitoring models corresponding to the target character combinations in a database; wherein, different target character combinations correspond to different health monitoring models;
and acquiring physiological information of the user to be monitored, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and acquiring a corresponding monitoring result as a human health monitoring result of the user to be monitored.
5. The method for monitoring the human health according to claim 1, wherein the step of inputting the physiological information of the user to be monitored into the health monitoring model to monitor and obtain the corresponding monitoring result, as the human health monitoring result of the user to be monitored, comprises:
generating a plurality of character combinations, and binding the character combinations with the health monitoring model and storing the character combinations in a database;
acquiring a random target identifier from a database, and acquiring a splicing mode corresponding to the target identifier; the database is pre-stored with the corresponding relation between the target identifier and the splicing mode;
Splicing the character combinations according to the splicing mode to obtain spliced character combinations; adding the target identifier at the appointed position of the spliced character combination to obtain an identification code;
judging whether the identification code exists in the database, and if not, taking the identification code as the unique identification code of the user to be monitored.
6. The method according to claim 5, wherein the user information of the user to be monitored includes a chinese name, the name including a surname and a person name, and the number of character combinations is three; the step of generating a plurality of character combinations includes:
acquiring pinyin characteristics, stroke characteristics and radical characteristics of the surnames and the names;
based on the pinyin characteristics of the surnames and the people names, matching corresponding first generation rules in a database, and generating corresponding first characters by adopting the first generation rules;
based on the stroke characteristics of the surnames and the person names, matching corresponding second generation rules in a database, and generating corresponding second characters by adopting the second generation rules;
based on the radical characteristics of the surnames and the person names, matching corresponding third generation rules in a database, and generating corresponding third characters by adopting the third generation rules;
Acquiring a first rule symbol, a second rule symbol and a third rule symbol which respectively correspond to the first generation rule, the second generation rule and the third generation rule in a database;
combining the first character with the first rule symbol to obtain a first character combination; combining the second character with the second rule symbol to obtain a second character combination; combining the third character with the third rule symbol to obtain a third character combination; the first character combination, the second character combination and the third character combination are three generated character combinations.
7. The method for monitoring human health according to claim 6, wherein the step of matching corresponding first generation rules in the database based on pinyin characteristics of the surnames and the names, and generating corresponding first characters using the first generation rules comprises:
based on the pinyin characteristics of the surnames, matching corresponding first generation rules in a database; wherein, the database stores the corresponding relation between the pinyin characteristics and the generation rules; the pinyin characteristics of the surname comprise pinyin; the pinyin characteristics of the name comprise initial consonant characteristics, final characteristics and tone characteristics; the first generation rule is a mapping relation table of initial consonant characteristics, final sound characteristics and tone characteristics and mapping characters respectively;
Mapping the initial consonant feature into a first mapping character, mapping the final feature into a second mapping character and mapping the tone feature into a third mapping character based on the first generation rule;
splicing the first mapping character, the second mapping character and the third mapping character once to obtain spliced characters;
based on the pinyin characteristics of the surnames, matching corresponding coding tables in a database; wherein, the database stores the mapping relation between the phonetic feature and the coding table;
and encoding the spliced character based on the encoding table to obtain the first character.
8. A human health monitoring device, comprising:
the judging unit is used for judging whether the user to be monitored is a new user or not, and if so, the physiological information of the user to be monitored is acquired; wherein the physiological information is collected by a plurality of sensors;
the acquisition unit is used for acquiring the face image of the user to be monitored, carrying out face recognition on the face image by adopting a preset image detection model, and acquiring user information of the user to be monitored, wherein the user information comprises age groups, gender and nationality;
the acquisition unit is used for acquiring the health type to be monitored of the user to be monitored; wherein the health type is selected for input by the user to be monitored;
The searching unit is used for searching a health monitoring initial model matched with the health type to be monitored in the database; wherein the health monitoring initial model is an initial model for detecting the health type;
the matching unit is used for matching the model parameter set of the health monitoring initial model according to the user information of the user to be monitored; wherein the model parameter set comprises a set of optimal parameters of each health monitoring initial model;
the updating unit is used for updating the model parameters of the health monitoring initial model into the optimal parameters in the model parameter set to obtain a corresponding health monitoring model;
and the monitoring unit is used for inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and obtaining a corresponding monitoring result which is used as the human health monitoring result of the user to be monitored.
9. The human health monitoring device according to claim 8, wherein the judging unit is further configured to:
if the user to be monitored is not a new user, matching a unique identification code corresponding to the user to be monitored in a database; wherein the unique identification code comprises a plurality of characters;
Identifying the identifier of the unique identification code, and detecting the identifier included in the unique identification code;
judging whether the identifier is positioned at a designated position of the unique identification code; if the identifier is located, the identifier is used as a target identifier;
matching a target identification code segmentation mode corresponding to the target identifier in a database; wherein, the database is pre-stored with the corresponding relation between the identifier and the dividing mode of the identifier code;
removing the target identifier in the unique identification code to obtain a removed identification code;
dividing the eliminating identification codes based on the target identification code dividing mode to obtain a plurality of target character combinations;
matching health monitoring models corresponding to the target character combinations in a database; wherein, different target character combinations correspond to different health monitoring models;
and acquiring physiological information of the user to be monitored, inputting the physiological information of the user to be monitored into the health monitoring model for monitoring, and acquiring a corresponding monitoring result as a human health monitoring result of the user to be monitored.
10. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310738119.8A CN116487050B (en) | 2023-06-21 | 2023-06-21 | Human health monitoring method, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310738119.8A CN116487050B (en) | 2023-06-21 | 2023-06-21 | Human health monitoring method, device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116487050A true CN116487050A (en) | 2023-07-25 |
| CN116487050B CN116487050B (en) | 2023-12-22 |
Family
ID=87219927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310738119.8A Active CN116487050B (en) | 2023-06-21 | 2023-06-21 | Human health monitoring method, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116487050B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448852A (en) * | 2018-11-29 | 2019-03-08 | 平安科技（深圳）有限公司 | Health control method, device and computer equipment based on prediction model |
| CN110731766A (en) * | 2018-07-19 | 2020-01-31 | 杭州星迈科技有限公司 | Health monitoring method and system |
| CN111227789A (en) * | 2018-11-29 | 2020-06-05 | 百度在线网络技术（北京）有限公司 | Human health monitoring method and device |
| CN111354463A (en) * | 2018-12-24 | 2020-06-30 | 缤刻普达（北京）科技有限责任公司 | Human health measuring method, device, computer equipment and storage medium |
| CN111681758A (en) * | 2020-05-15 | 2020-09-18 | 浙江科技学院 | Family health monitoring method, monitoring system and monitoring device |
| CN112233816A (en) * | 2020-10-27 | 2021-01-15 | 贵州精准医疗电子有限公司 | Health monitoring method, device and computer readable medium |
| CN112380842A (en) * | 2020-11-25 | 2021-02-19 | 北京明略软件系统有限公司 | Name error correction method and device, computer equipment and readable storage medium |
| CN113160987A (en) * | 2021-04-28 | 2021-07-23 | 平安科技（深圳）有限公司 | Health state prediction method and device, computer equipment and storage medium |
| CN115880826A (en) * | 2023-02-22 | 2023-03-31 | 肯特智能技术（深圳）股份有限公司 | Park access method and system based on access data |
| CN116110112A (en) * | 2023-04-12 | 2023-05-12 | 广东浩博特科技股份有限公司 | Self-adaptive adjustment method and device of intelligent switch based on face recognition |
-
2023
- 2023-06-21 CN CN202310738119.8A patent/CN116487050B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110731766A (en) * | 2018-07-19 | 2020-01-31 | 杭州星迈科技有限公司 | Health monitoring method and system |
| CN109448852A (en) * | 2018-11-29 | 2019-03-08 | 平安科技（深圳）有限公司 | Health control method, device and computer equipment based on prediction model |
| CN111227789A (en) * | 2018-11-29 | 2020-06-05 | 百度在线网络技术（北京）有限公司 | Human health monitoring method and device |
| CN111354463A (en) * | 2018-12-24 | 2020-06-30 | 缤刻普达（北京）科技有限责任公司 | Human health measuring method, device, computer equipment and storage medium |
| CN111681758A (en) * | 2020-05-15 | 2020-09-18 | 浙江科技学院 | Family health monitoring method, monitoring system and monitoring device |
| CN112233816A (en) * | 2020-10-27 | 2021-01-15 | 贵州精准医疗电子有限公司 | Health monitoring method, device and computer readable medium |
| CN112380842A (en) * | 2020-11-25 | 2021-02-19 | 北京明略软件系统有限公司 | Name error correction method and device, computer equipment and readable storage medium |
| CN113160987A (en) * | 2021-04-28 | 2021-07-23 | 平安科技（深圳）有限公司 | Health state prediction method and device, computer equipment and storage medium |
| CN115880826A (en) * | 2023-02-22 | 2023-03-31 | 肯特智能技术（深圳）股份有限公司 | Park access method and system based on access data |
| CN116110112A (en) * | 2023-04-12 | 2023-05-12 | 广东浩博特科技股份有限公司 | Self-adaptive adjustment method and device of intelligent switch based on face recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116487050B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170345424A1 (en) | Voice dialog device and voice dialog method | |
| CN104598644B (en) | Favorite label mining method and device | |
| CN109493850B (en) | Growing type dialogue device | |
| CN111883140B (en) | Authentication method, device, equipment and medium based on knowledge graph and voiceprint recognition | |
| US20170270922A1 (en) | Smart home control method based on emotion recognition and the system thereof | |
| CN110634472B (en) | Speech recognition method, server and computer readable storage medium | |
| CN109408821B (en) | Corpus generation method and device, computing equipment and storage medium | |
| CN109545184B (en) | Recitation detection method based on voice calibration and electronic equipment | |
| CN109331470B (en) | Method, device, equipment and medium for processing answering game based on voice recognition | |
| CN111986675A (en) | Voice conversation method, device and computer readable storage medium | |
| CN113724695A (en) | Electronic medical record generation method, device, equipment and medium based on artificial intelligence | |
| CN111223476B (en) | Method and device for extracting voice feature vector, computer equipment and storage medium | |
| CN111261162A (en) | Speech recognition method, speech recognition apparatus, and storage medium | |
| CN110544470B (en) | Voice recognition method and device, readable storage medium and electronic equipment | |
| CN110246485B (en) | Sample data acquisition method, terminal equipment and medium based on voice recognition model | |
| CN110797044A (en) | Audio data processing method and device, computer equipment and storage medium | |
| CN109785834B (en) | Voice data sample acquisition system and method based on verification code | |
| CN109086455B (en) | Method for constructing voice recognition library and learning equipment | |
| US20190213998A1 (en) | Method and device for processing data visualization information | |
| CN113094478A (en) | Expression reply method, device, equipment and storage medium | |
| CN113468891A (en) | Text processing method and device | |
| KR20210071713A (en) | Speech Skill Feedback System | |
| CN109408175B (en) | Real-time interaction method and system in general high-performance deep learning calculation engine | |
| CN110931018A (en) | Intelligent voice interaction method and device and computer readable storage medium | |
| CN114639175A (en) | Method, device, equipment and storage medium for predicting examination cheating behaviors |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |