Anxiety level monitoring method and device, computer equipment and storage medium

Abstract

The invention provides an anxiety grade monitoring method and device, computer equipment and a storage medium, and belongs to the field of artificial intelligence. The anxiety level monitoring method comprises the following steps: acquiring voice features and voice feature change information of a user in a first time period according to voice data of the user in the first time period; the voice features and the voice feature change information of the user can reflect the anxiety degree of the user, so that the anxiety level of the user in the first time period can be obtained by processing the voice features and the voice feature change information through the anxiety monitoring model, and then the suggestion information corresponding to the anxiety level is output. In the process, the anxiety level of the user is automatically determined through the anxiety monitoring model, so that the anxiety level of the user can be monitored at high frequency, real-time monitoring is realized, and the timeliness of anxiety level monitoring is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an anxiety level monitoring method, device, computer equipment and storage medium. Background Art

[0002] As the pace of life quickens, people are under increasing pressure, and anxiety has gradually become a common mental disorder.

[0003] At present, one method for monitoring anxiety levels is for professionals to analyze the anxiety assessment questionnaires filled out by users to obtain the user's anxiety level, or for professionals to interview users and analyze the user's expressions, movements, and answers during the interview to obtain the user's anxiety level. Professionals provide users with corresponding suggestions based on their anxiety levels.

[0004] The above method requires the user to fill out an anxiety assessment questionnaire or conduct an interview with a professional, which results in a low frequency of anxiety level monitoring, making it difficult to monitor the user's anxiety level in real time, and the timeliness of anxiety level monitoring is low. Summary of the invention

[0005] The embodiment of the present application provides an anxiety level monitoring method, device, computer equipment and storage medium, which are used to improve the timeliness of anxiety level monitoring. The technical solution is as follows:

[0006] In a first aspect, a method for monitoring an anxiety level is provided, the method comprising: collecting voice data of a user within a first time period; based on the voice data of the user within the first time period, obtaining voice features of the user within the first time period and voice feature change information of the user within the first time period, the voice feature change information indicating the magnitude of change of the voice features; processing the voice features and the voice feature change information of the user within the first time period through an anxiety monitoring model, and outputting the anxiety level of the user within the first time period, the anxiety level indicating the degree of anxiety of the user; based on the anxiety level of the user within the first time period, outputting suggestion information corresponding to the anxiety level of the user within the first time period.

[0007] The anxiety level monitoring method provided in the embodiment of the present application obtains the user's voice features and voice feature change information in the first time period based on the user's voice data in the first time period. The user's voice features and voice feature change information can reflect the user's anxiety level. Therefore, by processing the voice features and voice feature change information through the anxiety monitoring model, the user's anxiety level in the first time period can be obtained, and then the suggestion information corresponding to the anxiety level can be output. This process automatically determines the user's anxiety level through the anxiety monitoring model, so that the user's anxiety level can be monitored at a high frequency, achieving real-time monitoring and improving the timeliness of anxiety level monitoring.

[0008] In some embodiments, the above-mentioned collecting the user's voice data in the first time period includes: collecting original voice data in the first time period; and extracting the user's voice data in the first time period from the original voice data in the first time period based on the user's voiceprint.

[0009] In some embodiments, the above-mentioned obtaining the user's voice features in the first time period and the user's voice feature change information in the first time period based on the user's voice data in the first time period includes: based on invalid voice data in the voice data in the first time period, splitting the user's voice data in the first time period to obtain multiple sub-voice data; for each sub-voice data, obtaining the voice features of the sub-voice data based on the sub-voice data; based on the voice features of multiple sub-voice data, obtaining the user's voice feature change information in the first time period.

[0010] In some embodiments, the above method also includes: based on the voice features of the user in the first time period, querying the voice features in the voice feature library to obtain the target voice features, the target voice features are the features in the voice feature library that are most similar to the voice features of the user in the first time period; based on the anxiety level corresponding to the target voice features, adjusting the anxiety level of the user in the first time period.

[0011] In some embodiments, the above-mentioned adjustment of the user's anxiety level in the first time period based on the anxiety level corresponding to the target voice feature includes: if the anxiety level corresponding to the target voice feature is higher than the user's anxiety level in the first time period, the user's anxiety level in the first time period is increased by one level; if the anxiety level corresponding to the target voice feature is the same as the user's anxiety level in the first time period, the user's anxiety level in the first time period is not adjusted; if the anxiety level corresponding to the target voice feature is lower than the user's anxiety level in the first time period, the user's anxiety level in the first time period is reduced by one level.

[0012] In some embodiments, the above method also includes: obtaining the user's anxiety level change information based on the user's anxiety level in a first time period and the user's anxiety level in a second time period, the second time period being the time period before the first time period, and the anxiety level change information indicates the change in the user's anxiety level; based on the user's anxiety level change information, outputting suggestion information corresponding to the user's anxiety level change information.

[0013] In some embodiments, the above-mentioned obtaining the user's anxiety level change information based on the user's anxiety level in the first time period and the user's anxiety level in the second time period includes at least one of the following: calculating the difference between the user's anxiety level in the first time period and the user's anxiety level in the second time period to obtain the user's anxiety level change amplitude information, the change amplitude information indicating the change amplitude of the anxiety level; fitting the user's anxiety level in the first time period and the user's anxiety level in the second time period to obtain the user's anxiety level change function, and based on the change function, obtaining the user's anxiety level change trend information based on the change function, the change trend information indicating the change trend of the anxiety level.

[0014] In a second aspect, an anxiety level monitoring device is provided, which includes: an acquisition module for collecting voice data of a user within a first time period; a feature acquisition module for acquiring the voice features of the user within the first time period and voice feature change information of the user within the first time period based on the voice data of the user within the first time period, wherein the voice feature change information indicates the change amplitude of the voice features; a level acquisition module for processing the voice features and voice feature change information of the user within the first time period through an anxiety monitoring model, and outputting the anxiety level of the user within the first time period, wherein the anxiety level indicates the degree of anxiety of the user; a first suggestion module for outputting suggestion information corresponding to the anxiety level of the user within the first time period based on the anxiety level of the user within the first time period.

[0015] In a third aspect, a computer device is provided, comprising a processor and a memory, wherein the memory is used to store at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the anxiety level monitoring method provided in the first aspect or various optional implementations of the first aspect.

[0016] In a fourth aspect, a computer-readable storage medium is provided, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor to implement the operations performed by the anxiety level monitoring method provided in the above-mentioned first aspect or various optional implementations of the first aspect.

[0017] In a fifth aspect, a computer program product or a computer program is provided, which includes at least one program segment, and the at least one program segment is stored in a computer-readable storage medium. A processor of a computer device reads the at least one program segment from the computer-readable storage medium, and the processor executes the at least one program segment, so that the computer device performs the operations performed by the anxiety level monitoring method provided in the above-mentioned first aspect or various optional implementations of the first aspect.

[0018] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a schematic diagram of an implementation environment of an anxiety level monitoring method provided in an embodiment of the present application;

[0021] Figure 2 is a flow chart of an anxiety level monitoring method provided in an embodiment of the present application;

[0022] Figure 3 is a flow chart of another anxiety level monitoring method provided in an embodiment of the present application;

[0023] Figure 4 is a structural block diagram of an anxiety level monitoring device provided in an embodiment of the present application;

[0024] Figure 5 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0026] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with basically the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on quantity and execution order.

[0027] In the present application, the term "at least one" means one or more, and the term "plurality" means two or more.

[0028] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the voice data involved in this application are all obtained with full authorization.

[0029] Figure 1 is a schematic diagram of an implementation environment of an anxiety level monitoring method provided in an embodiment of the present application, such as Figure 1 As shown, the implementation environment includes a terminal 101 and a server 102. The terminal 101 communicates with the server 102 via a network. The terminal 101 and the server 102 are collectively referred to as computer devices. Figure 1 In the embodiment, the number of terminals and servers is only an example. For example, the number of terminals and servers can be multiple, and this is not limited in the embodiments of the present application.

[0030] The terminal 101 is a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc., but is not limited thereto. The server 102 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), big data and artificial intelligence platforms.

[0031] In some embodiments, the terminal 101 is installed with an application that supports anxiety level monitoring, which application may be a health application, a social application, or a virtual assistant application, etc., which is not limited in the embodiments of the present application. The terminal 101 may be an independent terminal, or a terminal deployed in a system such as a smart home system or a smart medical system, which is not limited in the embodiments of the present application. The terminal 101 monitors the user's anxiety level through interaction between the above-mentioned application and the server 102. During the interaction, the terminal 101 collects the user's voice data through the above-mentioned application and sends the voice data to the server 102. The server 102 processes the received voice data, obtains suggestion information corresponding to the user's anxiety level, and returns the suggestion information to the terminal 101.

[0032] In other embodiments, the terminal 101 can also independently process the user's voice data to monitor the user's anxiety level.

[0033] The anxiety level monitoring method provided in the embodiment of the present application can be achieved through the above Figure 1 The implementation environment shown is implemented. Figure 2 is a flow chart of an anxiety level monitoring method provided in an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0034] 201. A computer device collects voice data of a user within a first time period.

[0035] Among them, the first time period is the time period before any monitoring time point, and the monitoring time point is a pre-set time point. For example, it is pre-set from 6 o'clock to 22 o'clock every day, and the user's anxiety level is monitored every 4 hours, then the monitoring time points are 10 o'clock, 14 o'clock, 18 o'clock and 22 o'clock every day. The start time and end time of the first time period are pre-set. For example, the start time of the first time period is pre-set to be the previous monitoring time point, and the end time is the current monitoring time point. For another example, the first time period is set to 2 hours before the current monitoring time point, then when the monitoring time point is 10 o'clock, the corresponding first time period is from 8 o'clock to 10 o'clock. Voice data includes conversation data between users and others and conversation data between users and virtual voice assistants, etc., which is not limited to this in the embodiments of the present application.

[0036] In an embodiment of the present application, before collecting the user's voice data for the first time, the computer device displays an authorization page to the user, and displays a collection setting request and an authorization request for the voice data through the authorization page. The collection setting request is used to obtain the monitoring time point, the start time of the first time period, and the end time of the first time period, and the authorization request is used to obtain the authority to collect voice data. The computer device responds to the collection setting instruction and the authorization instruction, and collects the user's voice data in the first time period every time the start time of a first time period is reached according to the monitoring time point, the start time of the first time period indicated by the collection setting instruction.

[0037] 202. The computer device obtains the voice features of the user in the first time period and the voice feature change information of the user in the first time period based on the voice data of the user in the first time period, where the voice feature change information indicates the change range of the voice features.

[0038] The voice features indicate the user's speaking style, including the user's tone, volume, speaking speed, number of pauses, etc. The voice feature change information can reflect the user's anxiety level. For example, if the voice feature change information shows that the user's tone changes greatly in the first time period, the user's anxiety level is high.

[0039] In the embodiment of the present application, the computer device uses a preset algorithm to process the language data of the user in the first time period to obtain the voice features of the user in the first time period. The preset algorithm can be MFCC (Mel Frequency Cepstrum Coefficient), LPC (Linear Predictive Coding), LPCC (Linear Predictive Cepstral Coefficient) or PLP (Perceptual Linear Predictive), etc., which is not limited in the embodiment of the present application. There are many methods for obtaining voice feature change information, and the detailed process is shown in the following step 305.

[0040] 203. The computer device processes the voice features and voice feature change information of the user in the first time period through the anxiety monitoring model, and outputs the anxiety level of the user in the first time period, where the anxiety level indicates the anxiety degree of the user.

[0041] Among them, the anxiety monitoring model is a pre-trained model, which can be any machine learning model, such as SVM (Support Vector Machine) or DNN (Deep Neural Network). The anxiety monitoring model can output the user's anxiety level based on the user's voice features and voice feature change information. The computer device for training the anxiety monitoring model can be the above-mentioned computer device, or it can be other computer devices except the above-mentioned computer device. Before training the anxiety monitoring model, the computer device collects a large number of user's voice data in multiple time periods, and for each user's voice data in each time period, manually identifies the anxiety level corresponding to the voice data, obtains the anxiety level label of the voice data, and uses the preset algorithm in the above step 202 to process the voice data to obtain the voice features and voice feature change information of the voice data. During the training process, the computer device adjusts the anxiety monitoring model through multiple rounds of training. During each round of training, the computer device calls the anxiety monitoring model to process the voice features and voice feature change information corresponding to the pre-collected voice data to obtain the predicted anxiety level. The computer device obtains a loss value corresponding to the predicted anxiety level based on the predicted anxiety level and the preset correct anxiety level, and the loss value indicates the difference between the predicted anxiety level and the preset correct anxiety level. The computer device adjusts the parameters in the anxiety monitoring model through back propagation according to the loss value until the loss value is less than the loss value threshold or the number of training rounds of the anxiety monitoring model reaches the preset number of rounds.

[0042] The anxiety level corresponds to the anxiety degree. For example, if the anxiety level is level 0, the anxiety degree is calm, if the anxiety level is level 1, the anxiety degree is mild anxiety, if the anxiety level is level 2, the anxiety degree is moderate anxiety, and if the anxiety level is level 3, the anxiety degree is severe anxiety. The correspondence between the anxiety level and the anxiety degree is only an example, and the embodiments of the present application are not limited to this.

[0043] 204. The computer device outputs suggestion information corresponding to the anxiety level of the user in the first time period based on the anxiety level of the user in the first time period.

[0044] Among them, the suggested information includes breathing exercises, distracting attention by listening to music, appropriate exercise, and contacting professionals, etc. Different suggested information indicates different intervention intensities. Different anxiety levels correspond to different suggested information. The higher the anxiety level indicated by the anxiety level, the greater the intervention intensity indicated by the corresponding suggested information. For example, if the anxiety level is level 1, indicating that the anxiety level is mild anxiety, then the corresponding suggested information is to do breathing exercises. If the anxiety level is level 3, indicating that the anxiety level is severe anxiety, then the corresponding suggested information is to contact a professional.

[0045] In the embodiment of the present application, the computer device searches a suggestion information library based on the user's anxiety level in the first time period and outputs suggestion information corresponding to the anxiety level. The suggestion information library includes multiple suggestion information and the anxiety level corresponding to each suggestion information.

[0046] The anxiety level monitoring method provided in the embodiment of the present application obtains the user's voice features and voice feature change information in the first time period based on the user's voice data in the first time period. The user's voice features and voice feature change information can reflect the user's anxiety level. Therefore, by processing the voice features and voice feature change information through the anxiety monitoring model, the user's anxiety level in the first time period can be obtained, and then the suggestion information corresponding to the anxiety level can be output. This process automatically determines the user's anxiety level through the anxiety monitoring model, so that the user's anxiety level can be monitored at a high frequency, achieving real-time monitoring and improving the timeliness of anxiety level monitoring.

[0047] Above Figure 2 The anxiety level monitoring method provided in the embodiment of the present application is briefly described. Figure 3 This is a flowchart of another anxiety level monitoring method provided in an embodiment of the present application. Figure 3 This method is described in detail. Figure 3 As shown, the method includes the following steps.

[0048] 301. A computer device collects original voice data within a first time period.

[0049] Among them, the original voice data is the data corresponding to all voices recorded by the computer device within the first time period. The voices recorded by the computer device include not only the voices emitted by the user, but may also include voices emitted by other people other than the user, ambient sounds and noises, etc., which are not limited in this embodiment of the present application.

[0050] The process of collecting the original voice data is the same as step 201 above, and will not be described in detail in this embodiment of the present application.

[0051] In some embodiments, the computer device uses encryption and anonymization technology to process the original voice data so that the operations performed by the anxiety level monitoring method provided in the embodiments of the present application comply with preset privacy protection regulations, ensure the privacy security of the user, and improve the user's trust.

[0052] 302. The computer device extracts the voice data of the user in the first time period from the original voice data in the first time period based on the voiceprint of the user.

[0053] The user's voiceprint is acquired in advance, and the acquisition process includes: before the first anxiety level detection, the computer device collects the user's initial voice data, extracts the user's voiceprint features from the initial voice data, and obtains the user's voiceprint.

[0054] In the embodiment of the present application, the computer device splits the original voice data in the first time period according to the preset time length to obtain a plurality of sub-original voice data. For each sub-original voice data, the computer device performs human voice separation processing on the sub-original voice data to obtain the human voice data in the sub-original voice data. The computer device extracts the voiceprint feature from the human voice data to obtain at least one voiceprint of the sub-original voice data. The computer device calculates the distance between the at least one voiceprint and the user's voiceprint. If there is a voiceprint with a distance less than the distance threshold in the at least one voiceprint, then according to the voiceprint with a distance less than the distance threshold, the voice data corresponding to the voiceprint with a distance less than the distance threshold is extracted from the sub-original voice data. If there is no voiceprint with a distance less than the distance threshold in the at least one voiceprint, the sub-original voice data is regarded as invalid data. The computer device splices the extracted voice data and the invalid data according to the original time sequence to obtain the voice data of the user in the first time period. The above distance can be Euclidean distance, Mahalanobis distance or cosine distance, etc., which is not limited in the embodiment of the present application.

[0055] In some embodiments, after the computer device performs voice separation processing on the sub-original voice data, if the human voice data of the sub-original voice data is not obtained, the sub-original voice data is regarded as invalid data.

[0056] In some embodiments, the method for performing human voice separation processing by the above-mentioned computer device may be a method based on the time-frequency domain or a method based on deep learning, which is not limited in the embodiments of the present application.

[0057] The above steps 301 to 302 are a possible implementation method for the computer device to collect the voice data of the user in the first time period. In this possible implementation method, the computer device processes the original voice data to remove the ambient sound, noise and the voices of other people except the user in the original voice data, so as to avoid the influence of other sounds on the anxiety level monitoring, so as to make the subsequent monitoring of the user's anxiety level more accurate.

[0058] It should be noted that the above steps 301 to 302 are optional steps. The computer device can use the data extracted from the original voice data as the voice data of the user in the first time period, or can directly use the collected voice data as the voice data of the user in the first time period. The embodiment of the present application is not limited to this.

[0059] 303. The computer device splits the voice data of the user in the first time period based on the invalid voice data in the voice data in the first time period to obtain a plurality of sub-voice data.

[0060] Invalid voice data refers to voice data without human voice, such as voice data corresponding to a time period when no one speaks.

[0061] In the embodiment of the present application, the computer device identifies the invalid voice data in the voice data. If the duration corresponding to the continuous invalid voice data is greater than or equal to the duration threshold, the time point at which the continuous invalid voice data starts and the time point at which the continuous invalid voice data ends are used as split points, and the voice data located between two adjacent split points and not invalid voice data is used as sub-voice data to obtain multiple sub-voice data. For example, in the voice data with a duration of one hour, the voice data corresponding to the 20th minute to the 30th minute is invalid voice data, then the 20th minute and the 30th minute are split points, and the voice data corresponding to the 0th minute to the 20th minute and the voice data corresponding to the 30th minute to the 60th minute are sub-voice data. By splitting the user's voice data in the first time period through invalid voice data, it is possible to split the user's voice data into voice data corresponding to multiple continuous dialogue segments according to the pauses in the human voice, and it is possible to avoid the interference of invalid voice data, thereby improving the accuracy and efficiency of anxiety level monitoring.

[0062] 304. For each sub-voice data, the computer device obtains a voice feature of the sub-voice data based on the sub-voice data.

[0063] The process of obtaining the voice features of the sub-voice data is similar to the process of obtaining the voice features of the user in the first time period in step 202, and will not be described in detail in this embodiment of the present application.

[0064] 305. The computer device obtains voice feature change information of the user within a first time period based on the voice features of the plurality of sub-voice data, where the voice feature change information indicates a change range of the voice features.

[0065] There are multiple ways to obtain voice feature change information. Different ways to obtain voice feature change information are introduced below.

[0066] In some embodiments, for any adjacent sub-speech data, the computer device calculates the distance between the speech features of the adjacent sub-speech data, and obtains speech feature change information according to the mean of the distances between multiple speech features. For example, the speech feature change information includes a speech feature with a small change amplitude, a speech feature with a moderate change amplitude, and a speech feature with a large change amplitude. If the mean of the distances between multiple speech features is less than a first threshold, the speech feature change information is that the speech feature has a small change amplitude, if the mean of the distances between multiple speech features is greater than or equal to the first threshold and less than a second threshold, the speech feature change information is that the speech feature has a moderate change amplitude, and if the mean of the distances between multiple speech features is greater than or equal to the second threshold, the speech feature change information is that the speech feature has a large change amplitude. This method obtains speech feature change information according to the mean of the distances, the calculation process is relatively simple, and the efficiency of obtaining speech feature change information is high.

[0067] In some embodiments, the computer device fits the voice features of multiple sub-voice data to obtain a function corresponding to the user's voice data in the first time period, obtains the maximum and minimum values ​​of the function in the first time period, and obtains voice feature change information based on the difference between the maximum and minimum values. The process of obtaining voice feature change information based on the difference is the same as the process of obtaining voice feature change information based on the mean of the distance, and the embodiments of the present application are not repeated here. This method obtains voice feature change information based on the function obtained by fitting, which can improve the accuracy of voice feature change information.

[0068] In some embodiments, the computer device processes the voice features of the user in the first time period through a change information acquisition model, and outputs the voice feature change information of the user in the first time period. The change information acquisition model is a pre-trained model that can output voice feature change information of the voice feature according to the input voice feature. The method acquires voice feature change information according to the pre-trained change information acquisition model, and can simultaneously ensure the efficiency of acquiring language feature change information and the accuracy of language feature change information.

[0069] The above steps 303 to 305 are a possible implementation method for the computer device to obtain the voice features of the user in the first time period and the voice feature change information of the user in the first time period based on the voice data of the user in the first time period. This possible implementation method first splits the voice data of the user in the first time period into multiple sub-voice data, then obtains the voice features of each sub-voice data, and obtains the voice feature change information according to the voice features of each sub-voice data, so as to obtain the voice features of the user in different continuous dialogue segments and the change range of the voice features of the user in different continuous dialogue segments, and monitor the anxiety level according to the obtained information, so as to improve the accuracy of monitoring.

[0070] It should be noted that the above steps 303 to 305 of first splitting the voice data into sub-voice data and then obtaining voice features and voice feature change information are optional. The computer device can also directly obtain voice features and voice feature change information based on the unsplit voice data. The embodiment of the present application does not limit this.

[0071] 306. The computer device processes the voice features and voice feature change information of the user in the first time period through the anxiety monitoring model, and outputs the anxiety level of the user in the first time period, where the anxiety level indicates the anxiety degree of the user.

[0072] In the embodiment of the present application, the computer device inputs the voice features and voice feature change information of the user in the first time period into the anxiety monitoring model, and the anxiety monitoring model calculates the voice features and voice feature change information according to the parameters of each layer of the model, and outputs the anxiety level of the user in the first time period. This process obtains the anxiety level through the anxiety monitoring model, and can monitor the user's anxiety level at a high frequency, thereby realizing real-time and continuous monitoring of the user's anxiety state, and improving the effectiveness of anxiety level monitoring. In addition, through the anxiety monitoring model, the user's voice features and voice feature change information are analyzed to obtain the user's anxiety level, which can reduce the error caused by subjective factors and improve the objectivity and accuracy of anxiety level monitoring. In addition, the anxiety monitoring model automatically monitors the user's anxiety level according to the voice data corresponding to the user's daily conversation, so that the user does not need to perform any additional operations, and can achieve non-sensing monitoring (non-invasive monitoring), improving the convenience of monitoring and the user's experience.

[0073] 307. The computer device queries the voice features in the voice feature library based on the voice features of the user in the first time period to obtain a target voice feature, where the target voice feature is a feature in the voice feature library that is most similar to the voice features of the user in the first time period.

[0074] Among them, the voice feature library includes multiple voice features and the anxiety level corresponding to each voice feature, the anxiety level corresponding to each voice feature in the voice feature library is the correct anxiety level of the voice feature, and the target voice feature is the feature most similar to the voice feature of the user in the first time period, which means that the target voice feature is the feature with the shortest distance to the voice feature of the user in the first time period.

[0075] In an embodiment of the present application, for each voice feature in the voice feature library, the computer device calculates the distance between the voice feature and the voice feature of the user in the first time period, and determines the voice feature with the shortest distance in the voice feature library as the target voice feature.

[0076] It should be noted that after the computer device obtains the voice features of the user in the first time period, it can execute step 307. The embodiment of the present application does not limit the execution order of step 307. For example, the computer device can execute step 307 after step 304 and before step 305.

[0077] 308. The computer device adjusts the anxiety level of the user in the first time period based on the anxiety level corresponding to the target voice feature.

[0078] In an embodiment of the present application, if the anxiety level corresponding to the target voice feature is higher than the anxiety level of the user in the first time period, it indicates that the anxiety level output by the anxiety monitoring model is lower than the correct anxiety level, and the computer device increases the anxiety level of the user in the first time period by one level. If the anxiety level corresponding to the target voice feature is the same as the anxiety level of the user in the first time period, it indicates that the anxiety level output by the anxiety monitoring model is not much different from the correct anxiety level, and the computer device does not adjust the anxiety level of the user in the first time period. If the anxiety level corresponding to the target voice feature is lower than the anxiety level of the user in the first time period, it indicates that the anxiety level output by the anxiety monitoring model is higher than the correct anxiety level, and the computer device reduces the anxiety level of the user in the first time period by one level.

[0079] In some embodiments, the computer device adjusts the anxiety monitoring model according to the adjusted anxiety level to improve the accuracy of the anxiety level output by the anxiety monitoring model. Accordingly, the computer device calculates the distance between the adjusted anxiety level and the anxiety level before the adjustment, and performs back-propagation adjustment on the parameters of each layer of the anxiety monitoring model according to the distance.

[0080] The above steps 307 to 308 adjust the anxiety level output by the anxiety monitoring model according to the correct anxiety level of the speech features in the speech feature library, which can improve the accuracy of the anxiety monitoring level.

[0081] It should be noted that the above steps 307 to 308 are optional steps. The computer device can execute steps 307 to 308 to improve the accuracy of monitoring, or can not execute steps 307 to 308 to improve the efficiency of monitoring. The embodiment of the present application does not limit this.

[0082] 309. The computer device outputs suggestion information corresponding to the anxiety level of the user in the first time period based on the anxiety level of the user in the first time period.

[0083] This process is the same as the above step 204 and will not be described in detail in this embodiment of the present application.

[0084] In some embodiments, after the computer device outputs suggestion information corresponding to the user's anxiety level, the user can provide feedback to the computer device based on personal circumstances or the advice of professionals, and the computer device adjusts the user's suggestion information in response to the feedback instructions and outputs the adjusted suggestion information, or adjusts the user's anxiety level and outputs suggestion information corresponding to the adjusted anxiety level.

[0085] The anxiety level monitoring method provided in the embodiment of the present application obtains the user's voice features and voice feature change information in the first time period based on the user's voice data in the first time period. The user's voice features and voice feature change information can reflect the user's anxiety level. Therefore, by processing the voice features and voice feature change information through the anxiety monitoring model, the user's anxiety level in the first time period can be obtained, and then the suggestion information corresponding to the anxiety level can be output. This process automatically determines the user's anxiety level through the anxiety monitoring model, so that the user's anxiety level can be monitored at a high frequency, achieving real-time monitoring and improving the timeliness of anxiety level monitoring.

[0086] Above Figure 3 The anxiety level monitoring process is described in detail. In the application process of the anxiety level monitoring method provided in the embodiment of the present application, the computer device periodically performs the anxiety level monitoring process. That is, each time a monitoring time point is reached, the computer device performs the following steps according to the voice data of the first time period corresponding to the monitoring time point: Figure 3 The anxiety level monitoring method shown is used to achieve real-time monitoring of the user's anxiety state.

[0087] The above processes all provide corresponding advice information to the user based on the result of one monitoring. In some embodiments, the computer device obtains the user's anxiety level change information based on the user's anxiety level in the first time period and the user's anxiety level in the second time period, and outputs the advice information corresponding to the user's anxiety level change information based on the user's anxiety level change information. Among them, the second time period is the time period before the first time period, and the anxiety level change information indicates the change of the user's anxiety level. Correspondingly, every time the preset number of monitoring is performed, the computer device obtains the user's anxiety level change information based on the anxiety level monitored for the preset number of times, and outputs the advice information corresponding to the anxiety level change information. For example, it is preset that from 6 o'clock to 22 o'clock every day, the user's anxiety level is monitored every 4 hours, and the monitoring time points are 10 o'clock, 14 o'clock, 18 o'clock and 22 o'clock every day, and the anxiety level at 22 o'clock is the anxiety level of the first time period, and the anxiety level at 10 o'clock, 14 o'clock and 18 o'clock is the anxiety level of the second time period. The computer device obtains the user's anxiety level change information within a day based on the anxiety levels at 10 o'clock, 14 o'clock, 18 o'clock and 22 o'clock, and outputs the advice information corresponding to the anxiety level change information.

[0088] There are multiple ways to obtain the anxiety level change information. In some embodiments, the computer device calculates the difference between the anxiety level of the user in the first time period and the anxiety level of the user in the second time period to obtain the change amplitude information of the user's anxiety level, and the change amplitude information indicates the change amplitude of the anxiety level. Correspondingly, the computer device calculates the difference between the anxiety levels in adjacent time periods, and obtains the anxiety level change information based on the difference between the anxiety levels in multiple adjacent time periods. The acquisition process is the same as the process of obtaining the voice feature change information in step 305 above, and the embodiments of the present application will not be repeated here. In other embodiments, the computer device fits the anxiety level of the user in the first time period and the anxiety level of the user in the second time period to obtain the change function of the user's anxiety level. Based on the change function, the change trend information of the user's anxiety level is obtained, and the change trend information indicates the change trend of the anxiety level.

[0089] The above process monitors the dynamic changes of the user's anxiety state based on the current monitoring results and historical monitoring results, and provides the user with corresponding suggestion information based on the monitoring results of the dynamic changes, which can improve the continuity and effectiveness of anxiety level monitoring.

[0090] Figure 4 is a structural block diagram of an anxiety level monitoring device provided in an embodiment of the present application. The device is used to execute the steps of the anxiety level monitoring method described above, see Figure 4 , the anxiety level monitoring device comprises:

[0091] The collection module 401 is used to collect the voice data of the user in the first time period;

[0092] A feature acquisition module 402, configured to acquire, based on the voice data of the user in the first time period, the voice features of the user in the first time period and the voice feature change information of the user in the first time period, wherein the voice feature change information indicates the change range of the voice features;

[0093] The level acquisition module 403 is used to process the voice features and voice feature change information of the user in the first time period through the anxiety monitoring model, and output the anxiety level of the user in the first time period, where the anxiety level indicates the anxiety degree of the user;

[0094] The first suggestion module 404 is configured to output suggestion information corresponding to the anxiety level of the user in the first time period based on the anxiety level of the user in the first time period.

[0095] In some embodiments, the acquisition module 401 is used to:

[0096] Collecting original voice data within a first time period;

[0097] Based on the voiceprint of the user, voice data of the user in the first time period is extracted from the original voice data in the first time period.

[0098] In some embodiments, the feature acquisition module 402 is used to:

[0099] Based on invalid voice data in the voice data in the first time period, the voice data of the user in the first time period is split to obtain a plurality of sub-voice data;

[0100] For each sub-speech data, based on the sub-speech data, obtaining speech features of the sub-speech data;

[0101] Based on the voice features of the plurality of sub-voice data, voice feature change information of the user within a first time period is obtained.

[0102] In some embodiments, the anxiety level monitoring device further comprises:

[0103] A query module, configured to query the voice features in the voice feature library based on the voice features of the user in the first time period to obtain a target voice feature, where the target voice feature is a feature in the voice feature library that is most similar to the voice features of the user in the first time period;

[0104] The adjustment module is used to adjust the anxiety level of the user in the first time period based on the anxiety level corresponding to the target voice feature.

[0105] In some embodiments, the adjustment module is used to:

[0106] If the anxiety level corresponding to the target voice feature is higher than the anxiety level of the user in the first time period, the anxiety level of the user in the first time period is increased by one level;

[0107] If the anxiety level corresponding to the target voice feature is the same as the anxiety level of the user in the first time period, then the anxiety level of the user in the first time period is not adjusted;

[0108] If the anxiety level corresponding to the target voice feature is lower than the anxiety level of the user in the first time period, the anxiety level of the user in the first time period is reduced by one level.

[0109] In some embodiments, the anxiety level monitoring device further comprises:

[0110] a change information acquisition module, configured to acquire anxiety level change information of the user based on the anxiety level of the user in a first time period and the anxiety level of the user in a second time period, wherein the second time period is a time period before the first time period, and the anxiety level change information indicates a change in the anxiety level of the user;

[0111] The second suggestion module is used to output suggestion information corresponding to the user's anxiety level change information based on the user's anxiety level change information.

[0112] In some embodiments, the change information acquisition module is used to:

[0113] Calculating a difference between the anxiety level of the user in the first time period and the anxiety level of the user in the second time period to obtain information on a change in the anxiety level of the user, where the change information indicates a change in the anxiety level;

[0114] The anxiety level of the user in the first time period and the anxiety level of the user in the second time period are fitted to obtain a change function of the user's anxiety level, and based on the change function, change trend information of the user's anxiety level is obtained, the change trend information indicating the change trend of the anxiety level.

[0115] It should be noted that: the device provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when monitoring the anxiety level. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0116] Figure 5It is a structural diagram of a computer device provided in an embodiment of the present application. The computer device 500 may have relatively large differences due to different configurations or performances, and may include one or more CPUs (Central Processing Units, processors) 501 and one or more memories 502, wherein the memory 502 stores at least one computer program, and the at least one computer program is loaded and executed by the processor 501 to implement the anxiety level monitoring method provided in the above-mentioned various method embodiments. Of course, the computer device may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The computer device may also include other components for implementing device functions, which will not be repeated here.

[0117] The embodiment of the present application also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is loaded and executed by the processor of the computer device to implement the operation performed by the computer device in the anxiety level monitoring method of the above embodiment. For example, the computer-readable storage medium can be ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk and optical data storage device, etc.

[0118] In some embodiments, the computer program involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

[0119] The embodiment of the present application also provides a computer program product or a computer program, which includes at least one program segment, and the at least one program segment is stored in a computer-readable storage medium. The processor of the computer device reads the at least one program segment from the computer-readable storage medium, and the processor executes the at least one program segment, so that the computer device executes the anxiety level monitoring method provided in the above various optional implementations.

[0120] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0121] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring anxiety level, characterized in that: The method comprises: Collecting voice data of the user in a first time period; Based on the voice data of the user in the first time period, acquiring the voice feature of the user in the first time period and the voice feature change information of the user in the first time period, wherein the voice feature change information indicates the change range of the voice feature; Processing the voice features and the voice feature change information of the user in the first time period by an anxiety monitoring model, and outputting the anxiety level of the user in the first time period, wherein the anxiety level indicates the anxiety degree of the user; Based on the anxiety level of the user in the first time period, advice information corresponding to the anxiety level of the user in the first time period is output.

2. The method according to claim 1, characterized in that The collecting of the user's voice data in the first time period includes: Collecting original voice data within the first time period; Based on the voiceprint of the user, the voice data of the user in the first time period is extracted from the original voice data in the first time period.

3. The method according to claim 1, characterized in that The acquiring, based on the voice data of the user in the first time period, the voice features of the user in the first time period and the voice feature change information of the user in the first time period comprises: Based on invalid voice data in the voice data in the first time period, split the voice data of the user in the first time period to obtain a plurality of sub-voice data; For each sub-speech data, based on the sub-speech data, acquiring the speech feature of the sub-speech data; Based on the voice features of the plurality of sub-voice data, voice feature change information of the user in the first time period is obtained.

4. The method according to claim 1, characterized in that: The method further comprises: Based on the voice features of the user in the first time period, query the voice features in the voice feature library to obtain a target voice feature, where the target voice feature is a feature in the voice feature library that is most similar to the voice features of the user in the first time period; Based on the anxiety level corresponding to the target voice feature, the anxiety level of the user in the first time period is adjusted.

5. The method according to claim 4, characterized in that The adjusting the anxiety level of the user in the first time period based on the anxiety level corresponding to the target voice feature includes: If the anxiety level corresponding to the target voice feature is higher than the anxiety level of the user in the first time period, increasing the anxiety level of the user in the first time period by one level; If the anxiety level corresponding to the target voice feature is the same as the anxiety level of the user in the first time period, then the anxiety level of the user in the first time period is not adjusted; If the anxiety level corresponding to the target voice feature is lower than the anxiety level of the user in the first time period, the anxiety level of the user in the first time period is reduced by one level.

6. The method according to claim 1, characterized in that The method further comprises: acquiring anxiety level change information of the user based on the anxiety level of the user in the first time period and the anxiety level of the user in a second time period, wherein the second time period is a time period before the first time period, and the anxiety level change information indicates a change in the anxiety level of the user; Based on the anxiety level change information of the user, suggestion information corresponding to the anxiety level change information of the user is output.

7. The method according to claim 6, characterized in that The acquiring the anxiety level change information of the user based on the anxiety level of the user in the first time period and the anxiety level of the user in the second time period includes at least one of the following: Calculating a difference between the anxiety level of the user in the first time period and the anxiety level of the user in the second time period to obtain information on a change in the anxiety level of the user, wherein the information on the change in the anxiety level indicates a change in the anxiety level; The anxiety level of the user in the first time period and the anxiety level of the user in the second time period are fitted to obtain a change function of the user's anxiety level, and based on the change function, change trend information of the user's anxiety level is obtained, wherein the change trend information indicates a change trend of the anxiety level.

8. An anxiety level monitoring device, characterized in that: The device comprises: A collection module, used to collect voice data of the user within a first time period; a feature acquisition module, configured to acquire, based on the voice data of the user in the first time period, the voice features of the user in the first time period and the voice feature change information of the user in the first time period, wherein the voice feature change information indicates the change range of the voice features; a level acquisition module, configured to process the voice features and the voice feature change information of the user in the first time period by using an anxiety monitoring model, and output the anxiety level of the user in the first time period, wherein the anxiety level indicates the anxiety degree of the user; The first suggestion module is used to output suggestion information corresponding to the anxiety level of the user in the first time period based on the anxiety level of the user in the first time period.

9. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the memory is used to store at least one computer program, and the at least one computer program is loaded by the processor to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store at least one computer program, and the at least one computer program is used to execute the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images