User risk early warning implementation method and device based on intelligent wearing

Abstract

The invention discloses a user risk early warning implementation method and device based on intelligent wearing. The method comprises the following steps: receiving a student user sign data set collected by current target intelligent wearing equipment; acquiring an associated user information set and an associated user feedback data set corresponding to the to-be-evaluated student user information; obtaining a first classification result corresponding to the student user sign data set based on a first classification model, and obtaining a second classification result corresponding to the associated user feedback data set based on a second classification model; and carrying out weighted summation on the two classification results to determine a comprehensive classification result. Through the method, the student user sign data set and the associated user feedback data set can be obtained for the to-be-evaluated object, the classification results are correspondingly obtained from at least two dimensions in combination with the classification model, weighted summation is carried out, the final comprehensive classification result is obtained, and the corresponding current user risk early warning information is intelligently obtained. And the information is timely sent to a receiving terminal used by a teacher user of a mental health major for checking and analysis.

Description

Technical Field

[0001] The present invention relates to the field of intelligent decision-making technology of artificial intelligence, and in particular to a method and device for implementing user risk warning based on smart wearables. Background Art

[0002] At present, when teachers evaluate students' mental health, the more common way is to conduct psychological tests on them, such as using a mental health scale to evaluate students' mental state. However, when using a mental health scale to test students, the test content is often fixed, and student users may not answer questions as truthfully as possible based on objective conditions, which makes the psychological test results obtained distorted, resulting in a low reference value for the test results. Moreover, the amount of student user data obtained by a single test is limited, and the effectiveness of the test results cannot be guaranteed. In order to solve the above problems, it is necessary to provide a more effective method for implementing student user risk warning. Summary of the invention

[0003] The embodiment of the present invention provides a method and device for implementing user risk warning based on smart wear, aiming to solve the problem that when a mental health scale is used in the prior art to test and evaluate the mental state of students, student users may not try to answer questions truthfully based on objective circumstances, which makes the psychological test results obtained have data distortion and limited data volume, resulting in low reference value of the test results and the problem that the validity of the data cannot be guaranteed.

[0004] In a first aspect, an embodiment of the present invention provides a method for implementing user risk warning based on smart wear, which includes: In response to a user evaluation instruction, obtaining the to-be-evaluated student user information corresponding to the user evaluation instruction and the current smart wearable device acquisition strategy corresponding to the to-be-evaluated student user information, and sending the current smart wearable device acquisition strategy to the corresponding current target smart wearable device; Receive a student user vital sign data set collected by the current target smart wearable device according to the current smart wearable device collection strategy; Acquire an associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy; wherein the associated user information set includes associated student user information and / or associated teacher user information; Acquire associated user feedback data corresponding to each associated user information in the associated user information set, and form an associated user feedback data set; Acquire a first classification result corresponding to the student user vital sign dataset based on a pre-trained first classification model, and acquire a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model; Based on a preset weighted sum model, a comprehensive classification result corresponding to the first classification result and the second classification result is obtained, and the current user risk warning information is determined based on the comprehensive classification result and the warning information mapping relationship, and sent to the corresponding receiving terminal.

[0005] In a second aspect, an embodiment of the present invention provides a user risk warning implementation device based on smart wear, which includes: A collection strategy acquisition unit, configured to, in response to a user evaluation instruction, acquire the to-be-evaluated student user information corresponding to the user evaluation instruction and the current smart wearable device collection strategy corresponding to the to-be-evaluated student user information, and send the current smart wearable device collection strategy to the corresponding current target smart wearable device; A vital sign data set receiving unit, configured to receive a student user vital sign data set correspondingly collected by the current target smart wearable device according to the current smart wearable device collection strategy; An associated user information set acquisition unit, configured to acquire an associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy; wherein the associated user information set includes associated student user information and / or associated teacher user information; An associated user feedback data set acquisition unit, used to acquire associated user feedback data corresponding to each associated user information in the associated user information set, and form an associated user feedback data set; A classification unit, configured to obtain a first classification result corresponding to the student user physical sign dataset based on a pre-trained first classification model, and to obtain a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model; A user risk warning information generation unit is used to obtain a comprehensive classification result corresponding to the first classification result and the second classification result based on a preset weighted sum model, determine the current user risk warning information based on the comprehensive classification result and the warning information mapping relationship, and send it to the corresponding receiving terminal.

[0006] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer device executes the computer program, the method for implementing user risk warning based on smart wearables as described in the first aspect above is implemented.

[0007] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for implementing user risk warning based on smart wearables as described in the first aspect above is implemented.

[0008] The embodiment of the present invention provides a method and device for implementing user risk warning based on smart wear, the method comprising: in response to a user evaluation instruction, obtaining student user information to be evaluated corresponding to the user evaluation instruction, and a current smart wear device collection strategy corresponding to the student user information to be evaluated, and sending the current smart wear device collection strategy to the corresponding current target smart wear device; receiving a student user vital sign data set corresponding to the current target smart wear device collected according to the current smart wear device collection strategy; obtaining an associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy; wherein the associated user information set includes associated student user information and / or associated teacher user information; obtaining associated user feedback data corresponding to each associated user information in the associated user information set, and forming an associated user feedback data set; obtaining a first classification result corresponding to the student user vital sign data set based on a pre-trained first classification model, and obtaining a second classification result corresponding to the associated user feedback data set based on a pre-trained second classification model; obtaining a comprehensive classification result corresponding to the first classification result and the second classification result based on a preset weighted sum model, determining the current user risk warning information based on the comprehensive classification result and the warning information mapping relationship, and sending it to the current target smart wear device. Through the above method, for the object to be evaluated corresponding to the student user information to be evaluated, not only the student user vital sign data set uploaded by the smart wearable device can be obtained, but also the associated user feedback data set of several associated users can be obtained. The classification results are obtained from at least two dimensions in combination with the classification model and then weighted summed to obtain the final comprehensive classification result and intelligently obtain the corresponding current user risk warning information, and send it to the receiving terminal used by the teacher user of the mental health major in time for viewing and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of an application scenario of a method for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 2A flowchart of a method for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of a method for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process of a method for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 5 A schematic diagram of a sub-process of a method for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 6 A schematic block diagram of a device for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 7 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0013] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0014] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] See also Figure 1 and Figure 2 , Figure 1 The embodiment of the present invention provides Figure 1 A schematic diagram of an application scenario of a method for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention; Figure 2 The flowchart of the method for implementing the user risk warning based on smart wearables provided by the embodiment of the present invention is as follows; the method for implementing the user risk warning based on smart wearables is applied to a server 10, and the server 10 is connected to the smart wearable device 20 used by the student user and the user terminal 30 used by the teacher user. Figure 2 As shown, the method includes steps S110 to S160.

[0016] S110. In response to a user evaluation instruction, obtain the to-be-evaluated student user information corresponding to the user evaluation instruction and the current smart wearable device acquisition strategy corresponding to the to-be-evaluated student user information, and send the current smart wearable device acquisition strategy to the corresponding current target smart wearable device.

[0017] In this embodiment, when the teacher user needs to evaluate the psychological state of a student or multiple students in the future, data can be collected from at least two dimensions, where the first dimension is the user's physical sign data related to the student himself, and the other dimension is the associated user feedback data obtained by talking to other users who are highly associated with the student. The teacher user can use the name of a student selected from the student user list displayed on the corresponding user interaction interface of the user terminal as the object to be evaluated, and then generate the current smart wearable device collection strategy for the object to be evaluated, and send it to the current target smart wearable device corresponding to the object to be evaluated. Among them, the current target smart wearable device is a smart wearable device used by the object to be evaluated, such as a smart watch, a smart bracelet, etc.

[0018] In one embodiment, if Figure 3 As shown, step S110 includes: S111, obtaining a unique number of the student user to be evaluated corresponding to the user evaluation instruction, and obtaining the student user information to be evaluated corresponding to the unique number of the student user to be evaluated from a local student information database; wherein the student user information to be evaluated includes at least the student user name, the student user gender, the class to which the student user belongs, and the student user tag; S112, based on the instruction generation time of the user evaluation instruction and the preset analysis data acquisition time, determine the current target time interval; wherein the start date of the current target time interval is the date corresponding to the instruction generation time, and the end date of the current target time interval is the date corresponding to the instruction generation time + the analysis data acquisition time; S113. Obtain risk keyword information corresponding to the student user information to be evaluated, and generate the current smart wearable device collection strategy based on the risk keyword information and the current target time interval; wherein the current smart wearable device collection strategy includes at least a vital sign indicator collection type and an indicator collection cycle.

[0019] In this embodiment, when determining the student user corresponding to the object to be evaluated (i.e., the student user corresponding to the student user information to be evaluated) in the server, the unique number of the student user to be evaluated (such as the student ID number of the student user in the school) can be determined first, and then the corresponding student user information to be evaluated can be obtained from the local student information database using the unique number of the student user to be evaluated as a search condition, and at least the student user name, student user gender, student user class and student user label can be obtained from the student user information to be evaluated.

[0020] The difference from obtaining the historical data of the user in the prior art is that the user data of the student user in the future is obtained in this application. Specifically, the start date of the current target time interval is determined by the date corresponding to the instruction generation time, and the end date of the current target time interval is determined by the date corresponding to the instruction generation time + the analysis data acquisition time. After determining the current target time interval, the risk keyword information corresponding to the student user information to be evaluated is then obtained (such as including a significant decline in academic performance in the recent period, high learning pressure, etc.), and the current smart wearable device collection strategy is generated with the risk keyword information and the current target time interval as key reference information. For example, a mapping relationship between risk keywords and physical sign index collection types is preset in the server (such as the keyword of high learning pressure corresponds to the heart rate index, and the corresponding index collection cycle is 1 minute for every 1 hour), and the current smart wearable device collection strategy can be generated after the physical sign index collection type and the index collection cycle are determined from the above mapping relationship based on the risk keyword information set. It can be seen that through the above method, different current smart wearable device collection strategies are flexibly generated for different student users.

[0021] S120: Receive a student user vital sign data set collected by the current target smart wearable device according to the current smart wearable device collection strategy.

[0022] In this embodiment, after the server sends the current smart wearable device collection strategy to the current target smart wearable device corresponding to the object to be evaluated, the current smart wearable device collection strategy will be executed in the corresponding time period. The collected data corresponds to the student user's vital sign data set, and can also be used as reference data for analyzing one dimension of the student user's recent psychological state.

[0023] In one embodiment, step S120 includes: A subset of student user vital sign data arranged in ascending order of date is received and collected by the current target smart wearable device based on the current smart wearable device collection strategy and the current target time interval, and the subset of student user vital sign data is formed into the student user vital sign data set.

[0024] In this embodiment, for example, when the current target time interval corresponds to a week, the current smart wearable device collection strategy can collect a subset of student user vital sign data every day, and then arrange these student user vital sign data subsets in ascending order by date to form the student user vital sign data set. Among them, the specific collection time point corresponding to each student user vital sign data included in the student user vital sign data set is also known. For example, each student user vital sign data in the obtained student user vital sign data set is a heart rate value, and data analysis of the student user vital sign data set can indirectly obtain reference data for intuitive feedback on the student user's recent mental health status.

[0025] S130: Acquire a set of associated user information corresponding to the student user information to be evaluated based on a preset associated user screening strategy.

[0026] The associated user information set includes associated student user information and / or associated teacher user information.

[0027] In this embodiment, in order to obtain more information associated with the student user, it is also possible to obtain associated user information corresponding to the student user information to be evaluated (such as student user information or associated teacher user information) based on the associated user screening strategy, and then conduct a questionnaire survey or voice interview-style communication with these associated users on the object to be evaluated, so as to obtain data or information corresponding to the student user information to be evaluated from other dimensions.

[0028] In one embodiment, if Figure 4 As shown, step S130 includes: S131, obtaining an information network corresponding to a local student user information database; S132, obtaining a community mining strategy corresponding to the associated user screening strategy, and obtaining a current target community network corresponding to the student user information to be evaluated from the information network based on the community mining strategy; S133: Acquire user information corresponding to each node in the current target community network to form the associated user information set.

[0029] In this embodiment, in determining the associated user information set corresponding to the student user information to be evaluated, the community mining technology can be specifically applied, that is, first obtain the information network corresponding to the local student user information database, which includes multiple nodes (each node corresponds to a student user or a teacher user, and each node has specific attribute data, such as user name, user gender, user unique number, etc.), and the nodes with mutual association are also connected by edges. After the graph structure of the information network is known, the current target community network corresponding to the student user information to be evaluated can be obtained from the information network through the community mining strategy. For example, the community mining strategy specifically adopts a graph partitioning-based method to determine the current target community network composed of multiple management users of the student user information to be evaluated. Finally, the user information corresponding to each node in the current target community network is obtained (it may be a student user or a teacher user), thereby forming an associated user information set. It can be seen that the associated user information set corresponding to the student user information to be evaluated can be quickly obtained through the above-mentioned community mining method.

[0030] S140: Acquire associated user feedback data corresponding to each associated user information in the associated user information set, and form an associated user feedback data set.

[0031] In this embodiment, after obtaining each associated user information in the associated user information set, a questionnaire or direct voice interview can be distributed to the associated users corresponding to each associated user information to quickly obtain the associated user feedback data corresponding to each associated user information and form an associated user feedback data set.

[0032] In one embodiment, step S140 includes: For each piece of associated user information in the associated user information set, associated user feedback data of a text type or an interactive interview voice type is obtained from the associated user terminal to form the associated user feedback data set.

[0033] In this embodiment, taking the associated user corresponding to the associated user information in the associated user information set as an example, the server may use an intelligent artificial customer service robot to conduct interactive interview voice communication with the associated user, or may generate a questionnaire corresponding to the student user information to be evaluated (including multiple interview questions). The above methods all correspond to obtaining associated user feedback data of text type or interactive interview voice type from the associated user terminal, and constitute the associated user feedback data set.

[0034] S150. Obtain a first classification result corresponding to the student user vital sign dataset based on a pre-trained first classification model, and obtain a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model.

[0035] In one embodiment, if Figure 5 As shown, step S150 includes: S151, obtaining a student user vital sign data sequence corresponding to the student user vital sign data set, and inputting the sequence into the first classification model to obtain the first classification result; S152: Obtain a keyword extraction result set corresponding to the associated user feedback data set, and input the result set into the second classification model to obtain the second classification result.

[0036] In this embodiment, for example, when the acquired student user's physical sign data set is a heart rate data set, it can be converted into heart rate variability data (i.e., HRV data) in combination with the intervals between consecutive heartbeats in the heart rate data set, and then a sequence consisting of heart rate variability data is obtained as input data for the first classification model (such as the first classification model using a convolutional neural network), thereby obtaining a first classification result. The first classification result obtained is a probability value ranging from 0 to 1, and when it belongs to a more specific value interval between 0 and 1, a classification result label such as high pressure, moderate pressure, no pressure, etc. can be determined according to the more specific value interval.

[0037] In specific implementation, the second classification model can use a random forest model, and multiple keywords corresponding to the associated user feedback data set are input into the second classification model to obtain the second classification result. Among them, the obtained second classification result is a probability value with a value range between 0-1, and when it belongs to a more specific value interval between 0-1, a classification result label such as high pressure, moderate pressure, no pressure, etc. can be determined according to the more specific value interval. It can be seen that through the above method, multiple classification models can be combined to determine the classification results corresponding to data of different dimensions.

[0038] S160. Based on a preset weighted sum model, obtain a comprehensive classification result corresponding to the first classification result and the second classification result, determine the current user risk warning information based on the comprehensive classification result and the warning information mapping relationship, and send it to the corresponding receiving terminal.

[0039] In one embodiment, step S160 includes: The target warning information having the comprehensive classification result in the warning information mapping relationship is obtained, and the target warning information is used as the current user risk warning information.

[0040] In this embodiment, a weighted sum model is pre-set in the server, and in the weighted sum model, a first weight value is set corresponding to the first classification result, and a second weight value is set corresponding to the second classification result. The calculation result corresponding to the first classification result*first weight value+second classification result*second weight value is used as the comprehensive classification result.

[0041] A warning information mapping relationship is also set up in the server, and includes multiple classification result-warning information correspondences, and each correspondence includes a classification result and corresponding warning information. After the comprehensive classification result is determined based on the weighted sum, it is used as a search condition to obtain the target warning information with the comprehensive classification result in the warning information mapping relationship, and the target warning information is used as the current user risk warning information, such as the current user risk warning information is "this student user has a large academic pressure, and needs timely communication to relieve psychological pressure." Through the above method, the current user risk warning information corresponding to the student user information to be evaluated can be quickly determined, and then sent from the server to the corresponding receiving terminal such as the user terminal used by the teacher user, so that the current user risk warning information can be viewed in time.

[0042] During specific implementation, a suggestion plan knowledge base can also be built in the server, which can provide recommended reading book data or recommended exercise training data corresponding to various risk warning information, so as to recommend book reading or physical exercise to corresponding student users.

[0043] It can be seen that the embodiment of the method can obtain not only the student user vital sign data set uploaded by the smart wearable device, but also the associated user feedback data set of several associated users for the object to be evaluated corresponding to the student user information to be evaluated, and obtain the classification results corresponding to the classification model from at least two dimensions and then perform weighted summation to obtain the final comprehensive classification result and intelligently obtain the corresponding current user risk warning information, and send it to the receiving terminal used by the teacher user of the mental health major in time for viewing and analysis.

[0044] The embodiment of the present invention also provides a user risk warning implementation device based on smart wear, which can be configured in a server, and is used to execute any embodiment of the user risk warning implementation method based on smart wear. Figure 6 , Figure 6 A schematic block diagram of a device for implementing user risk warning based on smart wearable devices provided in an embodiment of the present invention. Figure 6As shown, the user risk warning implementation device 100 based on smart wear includes a collection strategy acquisition unit 110, a vital sign data set receiving unit 120, an associated user information set acquisition unit 130, an associated user feedback data set acquisition unit 140, a classification unit 150 and a user risk warning information generation unit 160.

[0045] The collection strategy acquisition unit 110 is used to respond to the user evaluation instruction, obtain the student user information to be evaluated corresponding to the user evaluation instruction, and the current smart wearable device collection strategy corresponding to the student user information to be evaluated, and send the current smart wearable device collection strategy to the corresponding current target smart wearable device.

[0046] In this embodiment, when the teacher user needs to evaluate the psychological state of a student or multiple students in the future, data can be collected from at least two dimensions, where the first dimension is the user's physical sign data related to the student himself, and the other dimension is the associated user feedback data obtained by talking to other users who are highly associated with the student. The teacher user can use the name of a student selected from the student user list displayed on the corresponding user interaction interface of the user terminal as the object to be evaluated, and then generate the current smart wearable device collection strategy for the object to be evaluated, and send it to the current target smart wearable device corresponding to the object to be evaluated. Among them, the current target smart wearable device is a smart wearable device used by the object to be evaluated, such as a smart watch, a smart bracelet, etc.

[0047] In one embodiment, the collection strategy acquisition unit 110 is specifically used to: Obtaining a unique number of the student user to be evaluated corresponding to the user evaluation instruction, and obtaining the student user information to be evaluated corresponding to the unique number of the student user to be evaluated from a local student information database; wherein the student user information to be evaluated includes at least the student user name, the student user gender, the class to which the student user belongs, and the student user tag; Based on the instruction generation time of the user evaluation instruction and the preset analysis data acquisition time, determine the current target time interval; wherein the start date of the current target time interval is the date corresponding to the instruction generation time, and the end date of the current target time interval is the date corresponding to the instruction generation time + the analysis data acquisition time; Obtain risk keyword information corresponding to the student user information to be evaluated, and generate the current smart wearable device collection strategy based on the risk keyword information and the current target time interval; wherein the current smart wearable device collection strategy includes at least a vital sign indicator collection type and an indicator collection cycle.

[0048] In this embodiment, when determining the student user corresponding to the object to be evaluated (i.e., the student user corresponding to the student user information to be evaluated) in the server, the unique number of the student user to be evaluated (such as the student ID number of the student user in the school) can be determined first, and then the corresponding student user information to be evaluated can be obtained from the local student information database using the unique number of the student user to be evaluated as a search condition, and at least the student user name, student user gender, student user class and student user label can be obtained from the student user information to be evaluated.

[0049] The difference from obtaining the historical data of the user in the prior art is that the user data of the student user in the future is obtained in this application. Specifically, the start date of the current target time interval is determined by the date corresponding to the instruction generation time, and the end date of the current target time interval is determined by the date corresponding to the instruction generation time + the analysis data acquisition time. After determining the current target time interval, the risk keyword information corresponding to the student user information to be evaluated is then obtained (such as including a significant decline in academic performance in the recent period, high learning pressure, etc.), and the current smart wearable device collection strategy is generated with the risk keyword information and the current target time interval as key reference information. For example, a mapping relationship between risk keywords and physical sign index collection types is preset in the server (such as the keyword of high learning pressure corresponds to the heart rate index, and the corresponding index collection cycle is 1 minute for every 1 hour), and the current smart wearable device collection strategy can be generated after the physical sign index collection type and the index collection cycle are determined from the above mapping relationship based on the risk keyword information set. It can be seen that through the above method, different current smart wearable device collection strategies are flexibly generated for different student users.

[0050] The vital sign data set receiving unit 120 is used to receive the student user vital sign data set collected by the current target smart wearable device according to the current smart wearable device collection strategy.

[0051] In this embodiment, after the server sends the current smart wearable device collection strategy to the current target smart wearable device corresponding to the object to be evaluated, the current smart wearable device collection strategy will be executed in the corresponding time period. The collected data corresponds to the student user's vital sign data set, and can also be used as reference data for analyzing one dimension of the student user's recent psychological state.

[0052] In one embodiment, the vital sign data set receiving unit 120 is specifically used for: A subset of student user vital sign data arranged in ascending order of date is received and collected by the current target smart wearable device based on the current smart wearable device collection strategy and the current target time interval, and the subset of student user vital sign data is formed into the student user vital sign data set.

[0053] In this embodiment, for example, when the current target time interval corresponds to a week, the current smart wearable device collection strategy can collect a subset of student user vital sign data every day, and then arrange these student user vital sign data subsets in ascending order by date to form the student user vital sign data set. Among them, the specific collection time point corresponding to each student user vital sign data included in the student user vital sign data set is also known. For example, each student user vital sign data in the obtained student user vital sign data set is a heart rate value, and data analysis of the student user vital sign data set can indirectly obtain reference data for intuitive feedback on the student user's recent mental health status.

[0054] The associated user information set acquisition unit 130 is used to acquire the associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy.

[0055] The associated user information set includes associated student user information and / or associated teacher user information.

[0056] In this embodiment, in order to obtain more information associated with the student user, it is also possible to obtain associated user information corresponding to the student user information to be evaluated (such as student user information or associated teacher user information) based on the associated user screening strategy, and then conduct a questionnaire survey or voice interview-style communication with these associated users on the object to be evaluated, so as to obtain data or information corresponding to the student user information to be evaluated from other dimensions.

[0057] In one embodiment, the associated user information set acquiring unit 130 is specifically used to: Obtaining the information network corresponding to the local student user information database; Acquire a community mining strategy corresponding to the associated user screening strategy, and acquire a current target community network corresponding to the student user information to be evaluated from the information network based on the community mining strategy; The user information corresponding to each node in the current target community network is obtained to form the associated user information set.

[0058] In this embodiment, in determining the associated user information set corresponding to the student user information to be evaluated, the community mining technology can be specifically applied, that is, first obtain the information network corresponding to the local student user information database, which includes multiple nodes (each node corresponds to a student user or a teacher user, and each node has specific attribute data, such as user name, user gender, user unique number, etc.), and the nodes with mutual association are also connected by edges. After the graph structure of the information network is known, the current target community network corresponding to the student user information to be evaluated can be obtained from the information network through the community mining strategy. For example, the community mining strategy specifically adopts a graph partitioning-based method to determine the current target community network composed of multiple management users of the student user information to be evaluated. Finally, the user information corresponding to each node in the current target community network is obtained (it may be a student user or a teacher user), thereby forming an associated user information set. It can be seen that the associated user information set corresponding to the student user information to be evaluated can be quickly obtained through the above-mentioned community mining method.

[0059] The associated user feedback data set acquisition unit 140 is used to acquire associated user feedback data corresponding to each associated user information in the associated user information set and form an associated user feedback data set.

[0060] In this embodiment, after obtaining each associated user information in the associated user information set, a questionnaire or direct voice interview can be distributed to the associated users corresponding to each associated user information to quickly obtain the associated user feedback data corresponding to each associated user information and form an associated user feedback data set.

[0061] In one embodiment, the associated user feedback data set acquisition unit 140 is specifically used to: For each piece of associated user information in the associated user information set, associated user feedback data of a text type or an interactive interview voice type is obtained from the associated user terminal to form the associated user feedback data set.

[0062] In this embodiment, taking the associated user corresponding to the associated user information in the associated user information set as an example, the server may use an intelligent artificial customer service robot to conduct interactive interview voice communication with the associated user, or may generate a questionnaire corresponding to the student user information to be evaluated (including multiple interview questions). The above methods all correspond to obtaining associated user feedback data of text type or interactive interview voice type from the associated user terminal, and constitute the associated user feedback data set.

[0063] The classification unit 150 is used to obtain a first classification result corresponding to the student user vital sign dataset based on a pre-trained first classification model, and to obtain a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model.

[0064] In one embodiment, the classification unit 150 is specifically used for: Acquire a student user vital sign data sequence corresponding to the student user vital sign data set, and input the sequence into the first classification model to obtain the first classification result; A keyword extraction result set corresponding to the associated user feedback data set is obtained, and the keyword extraction result set is input into the second classification model to obtain the second classification result.

[0065] In this embodiment, for example, when the acquired student user's physical sign data set is a heart rate data set, it can be converted into heart rate variability data (i.e., HRV data) in combination with the intervals between consecutive heartbeats in the heart rate data set, and then a sequence consisting of heart rate variability data is obtained as input data for the first classification model (such as the first classification model using a convolutional neural network), thereby obtaining a first classification result. The first classification result obtained is a probability value ranging from 0 to 1, and when it belongs to a more specific value interval between 0 and 1, a classification result label such as high pressure, moderate pressure, no pressure, etc. can be determined according to the more specific value interval.

[0066] In specific implementation, the second classification model can use a random forest model, and multiple keywords corresponding to the associated user feedback data set are input into the second classification model to obtain the second classification result. Among them, the obtained second classification result is a probability value with a value range between 0-1, and when it belongs to a more specific value interval between 0-1, a classification result label such as high pressure, moderate pressure, no pressure, etc. can be determined according to the more specific value interval. It can be seen that through the above method, multiple classification models can be combined to determine the classification results corresponding to data of different dimensions.

[0067] The user risk warning information generation unit 160 is used to obtain a comprehensive classification result corresponding to the first classification result and the second classification result based on a preset weighted sum model, determine the current user risk warning information based on the comprehensive classification result and the warning information mapping relationship, and send it to the corresponding receiving terminal.

[0068] In one embodiment, the user risk warning information generating unit 160 is specifically used to: The target warning information having the comprehensive classification result in the warning information mapping relationship is obtained, and the target warning information is used as the current user risk warning information.

[0069] In this embodiment, a weighted sum model is pre-set in the server, and in the weighted sum model, a first weight value is set corresponding to the first classification result, and a second weight value is set corresponding to the second classification result. The calculation result corresponding to the first classification result*first weight value+second classification result*second weight value is used as the comprehensive classification result.

[0070] A warning information mapping relationship is also set up in the server, and includes multiple classification result-warning information correspondences, and each correspondence includes a classification result and corresponding warning information. After the comprehensive classification result is determined based on the weighted sum, it is used as a search condition to obtain the target warning information with the comprehensive classification result in the warning information mapping relationship, and the target warning information is used as the current user risk warning information, such as the current user risk warning information is "this student user has a large academic pressure, and needs timely communication to relieve psychological pressure." Through the above method, the current user risk warning information corresponding to the student user information to be evaluated can be quickly determined, and then sent from the server to the corresponding receiving terminal such as the user terminal used by the teacher user, so that the current user risk warning information can be viewed in time.

[0071] During specific implementation, a suggestion plan knowledge base can also be built in the server, which can provide recommended reading book data or recommended exercise training data corresponding to various risk warning information, so as to recommend book reading or physical exercise to corresponding student users.

[0072] It can be seen that the implementation example of the device can obtain not only the student user vital sign data set uploaded by the smart wearable device, but also the associated user feedback data set of several associated users for the object to be evaluated corresponding to the student user information to be evaluated, and obtain the classification results corresponding to the classification model from at least two dimensions and then perform weighted summation to obtain the final comprehensive classification result and intelligently obtain the corresponding current user risk warning information, and send it to the receiving terminal used by the teacher user of the mental health major in time for viewing and analysis.

[0073] The above-mentioned user risk warning implementation device based on smart wear can be implemented in the form of a computer program, which can be used in Figure 7 Runs on the computer device shown.

[0074] See also Figure 7 , Figure 7 1 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device integrates any user risk early warning implementation device based on smart wearable provided by an embodiment of the present invention.

[0075] See also Figure 7The computer device 400 includes a processor 402 , a memory and a network interface 405 connected via a system bus 401 , wherein the memory may include a storage medium 403 and an internal memory 404 .

[0076] The storage medium 403 can store an operating system 4031 and a computer program 4032. The computer program 4032 includes program instructions, and when the program instructions are executed, the processor 402 can execute the above-mentioned user risk warning implementation method based on smart wear.

[0077] The processor 402 is used to provide computing and control capabilities to support the operation of the entire computer device.

[0078] The internal memory 404 provides an environment for the operation of the computer program 4032 in the storage medium 403. When the computer program 4032 is executed by the processor 402, the processor 402 can execute the above-mentioned user risk warning implementation method based on smart wear.

[0079] The network interface 405 is used to communicate with other devices over the network. Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0080] The processor 402 is used to run a computer program 4032 stored in a memory to implement the user risk warning method based on smart wear as described above.

[0081] It should be understood that in the embodiment of the present invention, the processor 402 may be a central processing unit (CPU), and the processor 402 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0082] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer device to implement the process steps of the embodiment of the above method.

[0083] Therefore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the user risk warning implementation method based on smart wear as described above.

[0084] The computer-readable storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0085] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0086] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0087] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0089] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for implementing user risk warning based on smart wear, characterized in that: include: In response to a user evaluation instruction, obtaining the to-be-evaluated student user information corresponding to the user evaluation instruction and the current smart wearable device acquisition strategy corresponding to the to-be-evaluated student user information, and sending the current smart wearable device acquisition strategy to the corresponding current target smart wearable device; Receive a student user vital sign data set collected by the current target smart wearable device according to the current smart wearable device collection strategy; Acquire an associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy; wherein the associated user information set includes associated student user information and / or associated teacher user information; Acquire associated user feedback data corresponding to each associated user information in the associated user information set, and form an associated user feedback data set; Acquire a first classification result corresponding to the student user vital sign dataset based on a pre-trained first classification model, and acquire a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model; Based on a preset weighted sum model, a comprehensive classification result corresponding to the first classification result and the second classification result is obtained, and the current user risk warning information is determined based on the comprehensive classification result and the warning information mapping relationship, and sent to the corresponding receiving terminal.

2. The method for implementing user risk warning based on smart wearable devices according to claim 1, characterized in that: The obtaining of the to-be-evaluated student user information corresponding to the user evaluation instruction and the current smart wearable device acquisition strategy corresponding to the to-be-evaluated student user information includes: Obtaining a unique number of the student user to be evaluated corresponding to the user evaluation instruction, and obtaining the student user information to be evaluated corresponding to the unique number of the student user to be evaluated from a local student information database; wherein the student user information to be evaluated includes at least the student user name, the student user gender, the class to which the student user belongs, and the student user tag; Based on the instruction generation time of the user evaluation instruction and the preset analysis data acquisition time, determine the current target time interval; wherein the start date of the current target time interval is the date corresponding to the instruction generation time, and the end date of the current target time interval is the date corresponding to the instruction generation time + the analysis data acquisition time; Obtain risk keyword information corresponding to the student user information to be evaluated, and generate the current smart wearable device collection strategy based on the risk keyword information and the current target time interval; wherein the current smart wearable device collection strategy includes at least a vital sign indicator collection type and an indicator collection cycle.

3. The method for implementing user risk warning based on smart wearable according to claim 2 is characterized in that: The receiving of the student user vital sign data set collected by the current target smart wearable device according to the current smart wearable device collection strategy includes: Receive the student user vital sign data subset arranged in ascending order of date, which is collected by the current target smart wearable device based on the current smart wearable device collection strategy and the current target time interval, and form the student user vital sign data set.

4. The method for implementing user risk warning based on smart wearable according to claim 1, characterized in that: The step of obtaining the associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy includes: Obtaining the information network corresponding to the local student user information database; Acquire a community mining strategy corresponding to the associated user screening strategy, and acquire a current target community network corresponding to the student user information to be evaluated from the information network based on the community mining strategy; The user information corresponding to each node in the current target community network is obtained to form the associated user information set.

5. The method for implementing user risk warning based on smart wearable according to claim 1, characterized in that: The acquiring of associated user feedback data corresponding to each associated user information in the associated user information set and forming an associated user feedback data set includes: For each piece of associated user information in the associated user information set, associated user feedback data of a text type or an interactive interview voice type is obtained from the associated user terminal to form the associated user feedback data set.

6. The method for implementing user risk warning based on smart wearable according to claim 1, characterized in that: The method of obtaining a first classification result corresponding to the student user's physical sign dataset based on a pre-trained first classification model, and obtaining a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model, includes: Acquire a student user vital sign data sequence corresponding to the student user vital sign data set, and input the sequence into the first classification model to obtain the first classification result; A keyword extraction result set corresponding to the associated user feedback data set is obtained, and the keyword extraction result set is input into the second classification model to obtain the second classification result.

7. The method for implementing user risk warning based on smart wearable according to claim 1, characterized in that: The determining of the current user risk warning information based on the comprehensive classification result and the warning information mapping relationship includes: The target warning information having the comprehensive classification result in the warning information mapping relationship is obtained, and the target warning information is used as the current user risk warning information.

8. A user risk warning implementation device based on smart wearables, characterized in that: include: A collection strategy acquisition unit, configured to, in response to a user evaluation instruction, acquire the to-be-evaluated student user information corresponding to the user evaluation instruction and the current smart wearable device collection strategy corresponding to the to-be-evaluated student user information, and send the current smart wearable device collection strategy to the corresponding current target smart wearable device; A vital sign data set receiving unit, configured to receive a student user vital sign data set correspondingly collected by the current target smart wearable device according to the current smart wearable device collection strategy; An associated user information set acquisition unit, configured to acquire an associated user information set corresponding to the student user information to be evaluated based on a preset associated user screening strategy; wherein the associated user information set includes associated student user information and / or associated teacher user information; An associated user feedback data set acquisition unit, used to acquire associated user feedback data corresponding to each associated user information in the associated user information set, and form an associated user feedback data set; A classification unit, configured to obtain a first classification result corresponding to the student user physical sign dataset based on a pre-trained first classification model, and to obtain a second classification result corresponding to the associated user feedback dataset based on a pre-trained second classification model; A user risk warning information generation unit is used to obtain a comprehensive classification result corresponding to the first classification result and the second classification result based on a preset weighted sum model, determine the current user risk warning information based on the comprehensive classification result and the warning information mapping relationship, and send it to the corresponding receiving terminal.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer device executes the computer program, the method for implementing user risk warning based on smart wearable devices is implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for implementing user risk warning based on smart wearable devices as described in any one of claims 1 to 7 is implemented.

Images