Attention and behavior evaluation system and method based on cloud computing

Abstract

The invention discloses an attention and behavior evaluation system and method based on cloud computing, and relates to the technical field of behavior evaluation data analysis, the system comprises a data monitoring processing module, a behavior data analysis module and a behavior evaluation feedback module; the data monitoring and processing module is used for monitoring an evaluation object in real time by arranging a non-contact acquisition sensor in a current activity environment of the evaluation object, and is also used for acquiring information of a situation where the evaluation object is located; the behavior data analysis module is used for training a situation-behavior reference deep learning model, calculating a reference deviation of each behavior state evaluation parameter of an evaluation object, constructing a behavior state evaluation knowledge graph, and performing data updating iteration on reference deviation historical data of the behavior state evaluation parameters; and the behavior evaluation feedback module updates and feeds back the evaluation result of the evaluation object in real time according to the behavior state evaluation knowledge graph data.

Description

Technical Field

[0001] The present invention relates to the technical field of behavior assessment data analysis, and in particular to an attention and behavior assessment system and method based on cloud computing. Background Art

[0002] In the field of children's behavior status assessment, accurate and comprehensive assessment is crucial for formulating personalized education and training programs; however, the commonly used behavior status assessment methods today have the following technical defects: on the one hand, when collecting data on the assessment object, it is generally through questionnaire interviews, specific situation observations and other methods, which are greatly influenced by the subjective influence of the assessor and the assessment results have large errors; on the other hand, the traditional assessment method that relies on interaction has a more direct contact with the assessment object, which interferes with the subjective behavior status of the assessment object and cannot reflect the most realistic behavior status feedback of the assessment object; in addition, the periodic assessment of the assessment object cannot intuitively show the changes in the behavior status of the assessment object at different times;

[0003] Therefore, a cloud computing-based attention and behavior assessment system and method is needed to solve the above technical problems, realize real-time, contactless collection of the behavioral status of the assessment object, and combine with intelligent analysis technology to provide more objective and accurate assessment results. Summary of the invention

[0004] The object of the present invention is to provide an attention and behavior assessment system and method based on cloud computing to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cloud computing-based attention and behavior assessment method, the method is divided into the following steps:

[0007] Step S100: obtaining the behavior state evaluation parameters and situation parameter information of the evaluation object, marking the reference values ​​of the behavior state evaluation parameters of the evaluation object in different situation parameters, and training the situation-behavior reference deep learning model;

[0008] Step S200: Obtaining the behavior analysis evaluation dimension information of the current evaluation object, marking the weight coefficient of each behavior state parameter in different evaluation dimensions, and constructing a behavior state evaluation knowledge graph for the current evaluation object;

[0009] Step S300: Setting a non-contact acquisition sensor in the current activity environment of the evaluation object, monitoring the evaluation object in real time, obtaining the evaluation parameter data of the real-time behavior state of the evaluation object, and calculating the reference deviation of each behavior state evaluation parameter of the evaluation object;

[0010] Step S400: analyzing the deviation synchronization coefficients between the behavior state evaluation parameters through cloud computing, and then updating the node data of the behavior state evaluation knowledge graph;

[0011] Step S500: Perform real-time behavior evaluation on the evaluation object according to the behavior state evaluation knowledge graph, and draw a radar chart based on the historical data of the evaluation results divided into each time period as feedback on the evaluation results of the current evaluation object in each time period.

[0012] In the above technical solution, step S100 includes the following steps:

[0013] Step S101: obtaining behavior state evaluation parameters and situation parameter information of the evaluation object; the behavior state evaluation parameters refer to parameters that measure the behavior characteristics of the evaluation object and have an impact on the behavior evaluation results of the evaluation object; the situation parameters refer to parameters that reflect the situation characteristics of the evaluation object;

[0014] Step S102: Obtain historical data of the situation in which the evaluation object is located, and mark the reference values ​​of the behavior state evaluation parameters in the situation through manual marking;

[0015] For any combination of situation parameters, the annotation results are stored in a two-dimensional array consisting of a situation parameter vector and a behavior state evaluation parameter reference value vector;

[0016] Step S103: Use the labeled data to train a context-behavior reference deep learning model; the context-behavior reference deep learning model input is a context parameter vector, and the context-behavior reference deep learning model output is a behavior state evaluation parameter reference value vector under the input context parameter vector;

[0017] By manually annotating data sets to train deep learning models, we can build situational behavior relationship chains, reduce reliance on experts in complex situations, improve the standardization of behavioral state assessment, and ensure the generalization ability of the algorithm.

[0018] In the above technical solution, step S200 includes the following steps:

[0019] Step S201: Obtaining the behavior analysis evaluation dimension information of the current evaluation object, and marking the weight coefficient of each behavior state parameter in different evaluation dimensions;

[0020] Step S202: constructing a behavior state evaluation knowledge graph for the current evaluation object; the behavior state evaluation knowledge graph includes behavior state nodes and evaluation dimension nodes, and the edge weights between the behavior state nodes and the evaluation dimension nodes are weight coefficients of each behavior state evaluation parameter in the evaluation dimension corresponding to each evaluation dimension node; wherein each behavior state node corresponds to each behavior state evaluation parameter one-to-one, and each evaluation dimension node corresponds to each evaluation dimension one-to-one;

[0021] Constructing a knowledge graph for behavior state evaluation and analyzing the implicit correlations among different behavior state evaluation parameters avoids the one-sidedness of traditional evaluation methods and effectively enhances the hierarchy and systematicness of system evaluation results.

[0022] In the above technical solution, step S300 includes the following steps:

[0023] Step S301: Setting a non-contact collection sensor in the current activity environment of the evaluation object to monitor the evaluation object and its situation in real time;

[0024] Step S302: performing feature extraction, data dimension reduction and normalization processing on each non-contact collection sensor data, and converting the collected data into one-dimensional data as the actual measured value of the behavior state evaluation parameter of the evaluation object;

[0025] Step S303: Calculate the reference deviation of each behavior state evaluation parameter of the evaluation object; use the context-behavior reference deep learning model, take the context parameters of the context in which the evaluation object is located as input, obtain the reference value of the behavior state evaluation parameter of the evaluation object, calculate the difference between the measured value and the reference value of each behavior state evaluation parameter of the evaluation object, and use it as the reference deviation of each behavior state evaluation parameter of the evaluation object;

[0026] The use of contactless sensor data collection to monitor the evaluation object in real time effectively reduces the interference of data collection on the behavioral state of the evaluation object, making the collected data more authentic and scientific, and further ensuring the accuracy of the system evaluation results.

[0027] In the above technical solution, step S400 includes the following contents:

[0028] Upload the historical data of reference deviations of the evaluation parameters of each behavior state of the evaluation object to the cloud for storage, and simultaneously analyze the deviation synchronization coefficients between the evaluation parameters of each behavior state through cloud computing;

[0029] For any behavior state evaluation parameters x and y, the deviation synchronization coefficient of y to x is calculated as follows:

[0030] k_(y→x)=(1 / Nd)×sum(δx / (δy+ε));

[0031] Wherein, k_(y→x) is the deviation synchronization coefficient of the behavior state evaluation parameter y to x, Nd is the number of historical data of reference deviation of each behavior state evaluation parameter of the evaluation object stored in the cloud, δx is the reference deviation of the behavior state evaluation parameter x, δy is the reference deviation of the behavior state evaluation parameter y, ε is a constant, and sum(δx / δy) is the numerical sum of the reference deviation ratios of the behavior state evaluation parameters x and y in all historical data stored in the cloud;

[0032] The deviation synchronization coefficient between each behavior state transfer parameter is updated to the edge weight between the corresponding behavior state nodes in the behavior state evaluation knowledge graph, and the weight of each behavior state node in the behavior state evaluation knowledge graph is updated and iterated in real time;

[0033] For any behavior state evaluation parameter x, the corresponding behavior state node iteration formula in the behavior state evaluation knowledge graph is as follows:

[0034] x_update=(1-α-β)×x_ori+α×δx+β / (N_p)×sum(k_(p→x)×δp);

[0035] Wherein, x_update is the behavior state node iteration data corresponding to the behavior state evaluation parameter x, x_ori is the behavior state node original data corresponding to the behavior state evaluation parameter x, δx is the reference deviation of the behavior state evaluation parameter x, N_p is the number of other behavior state evaluation parameters except the behavior state evaluation parameter x, sum(k_(p→x)×δp) is the sum of the deviation synchronization coefficient of each behavior state evaluation parameter to x except the behavior state evaluation parameter x and the product of the reference deviation, α is the reference deviation compensation coefficient, β is the deviation synchronization compensation coefficient, α>0, β>0 and α+β<1;

[0036] Through deviation synchronization analysis, the mutual influence between parameters is measured, and the one-sidedness of the way of independently calculating the score of each behavioral parameter in the isolated evaluation mode is broken through, thereby improving the dynamic adaptability of the system; and by analyzing the deviation synchronization coefficient, compensation calculation is performed on each behavioral state evaluation parameter, and then the behavioral state evaluation knowledge graph is updated in real time, which further avoids the defect that the traditional method of using static reporting cannot effectively reflect the changing trend of the behavioral state of the evaluation object.

[0037] In the above technical solution, step S500 includes the following contents:

[0038] Obtain the behavior state evaluation knowledge graph data, extract the latest iteration data of each behavior state node adjacent to each evaluation dimension node, and use the edge weight between the evaluation dimension node and the adjacent behavior state node as a coefficient to weight the node weight of each evaluation dimension node as the evaluation result of each evaluation dimension and upload it to the cloud for storage;

[0039] Set the behavior status evaluation cycle T, divide the time period by T, divide the node weight historical data of each evaluation dimension node, extract the minimum and maximum weights of each evaluation dimension node in the historical data in each time period through cloud computing, and draw a radar chart based on the extracted data of each time period at the end of each time period, as feedback of the behavior status evaluation results of each time period of the current evaluation object;

[0040] The evaluation results in each time period are fed back through radar charts to further improve the user's interactive experience. Through data screening, the evaluation result ranges in each time period are used to replace the single evaluation results in the static report of the traditional method, which more intuitively reflects the fluctuations and changes in the behavioral status of the evaluation object in each time period, ensuring the accuracy of subsequent education and training strategies.

[0041] A cloud computing-based attention and behavior assessment system using a cloud computing-based attention and behavior assessment method in the above technical solution, the system comprising: a data monitoring and processing module, a behavior data analysis module, and a behavior assessment feedback module;

[0042] The data monitoring and processing module monitors the evaluation object in real time by setting up contactless collection sensors in the current activity environment of the evaluation object, and is also used to collect and obtain the situational information of the evaluation object; the behavior data analysis module trains the situation-behavior reference deep learning model, calculates the reference deviation of each behavior state evaluation parameter of the evaluation object, and is also used to construct a behavior state evaluation knowledge graph, and updates and iterates data based on the reference deviation historical data of the behavior state evaluation parameters; the behavior evaluation feedback module updates and feedbacks the evaluation results of the evaluation object in real time based on the behavior state evaluation knowledge graph data.

[0043] In the above technical solution, the data monitoring and processing module includes: a behavior state monitoring unit and a situation monitoring unit;

[0044] The behavior state monitoring unit monitors the behavior state of the evaluation object in real time by setting a contactless collection sensor in the current activity environment of the evaluation object; the situation monitoring unit collects and obtains the situation information of the evaluation object through real-time monitoring.

[0045] In the above technical solution, the behavior data analysis module includes: a reference behavior analysis unit, a behavior deviation analysis unit, and a knowledge graph update unit;

[0046] The reference behavior analysis unit labels the reference values ​​of the behavior state evaluation parameters of the evaluation object in different situational parameters, trains the situation-behavior reference deep learning model, and then analyzes the reference values ​​of the behavior state evaluation parameters of the evaluation object in various situations; the behavior deviation analysis unit calculates the deviation between the monitored value and the reference value of the behavior state evaluation parameter of the evaluation object in real time, and then analyzes the deviation synchronization coefficient between each behavior state evaluation parameter; the knowledge graph updating unit updates and iterates the data in the constructed behavior state evaluation knowledge graph according to the deviation synchronization coefficient between each behavior state evaluation parameter and the monitoring data between the behavior state evaluation parameters.

[0047] In the above technical solution, the behavior assessment feedback module includes: a behavior state assessment unit and an assessment result feedback unit;

[0048] The behavior state evaluation unit performs behavior state evaluation on the evaluation object according to the data in the behavior state evaluation knowledge graph, and updates the evaluation results in real time; the evaluation result feedback unit draws a radar chart after filtering the evaluation results of each evaluation dimension in each time period, and provides feedback as the behavior state evaluation results of the current evaluation object in each time period.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] In the present invention, a non-contact data collection method is used to monitor the evaluation object in real time, avoiding the interference of traditional wearable devices and contact access on the behavior state of the evaluation object, effectively improving the accuracy of the evaluation results, and significantly enhancing the practicality of the system in various types of environments;

[0051] In the present invention, a comprehensive analysis of the behavior state of the evaluation object is conducted by constructing a behavior state evaluation knowledge graph, and cloud computing is used to update and iterate the behavior state node data in the knowledge graph in real time, thereby providing more realistic and effective feedback on the evaluation results of the evaluation object in each evaluation dimension.

[0052] In the present invention, by analyzing the deviation synchronization coefficient between each behavior state evaluation parameter, the data update of each behavior state evaluation parameter is synchronized, thereby reducing the bias of the data update of different behavior state evaluation parameters in the situation where the evaluation object is located, effectively improving the comprehensiveness of the behavior state evaluation of the evaluation object, and further ensuring the accuracy and rationality of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of an attention and behavior assessment method based on cloud computing of the present invention;

[0054] Figure 2 This is an organizational chart of an attention and behavior assessment system based on cloud computing of the present invention. DETAILED DESCRIPTION

[0055] 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 only 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.

[0056] Example: See Figure 1-Figure 2 , the present invention provides the following technical solutions:

[0057] A cloud computing-based attention and behavior assessment method, the method is divided into the following steps:

[0058] Step S100: obtaining the behavior state evaluation parameters and situation parameter information of the evaluation object, marking the reference values ​​of the behavior state evaluation parameters of the evaluation object in different situation parameters, and training the situation-behavior reference deep learning model;

[0059] Step S200: Obtaining the behavior analysis evaluation dimension information of the current evaluation object, marking the weight coefficient of each behavior state parameter in different evaluation dimensions, and constructing a behavior state evaluation knowledge graph for the current evaluation object;

[0060] Step S300: Setting a non-contact acquisition sensor in the current activity environment of the evaluation object, monitoring the evaluation object in real time, obtaining the evaluation parameter data of the real-time behavior state of the evaluation object, and calculating the reference deviation of each behavior state evaluation parameter of the evaluation object;

[0061] Step S400: analyzing the deviation synchronization coefficients between the behavior state evaluation parameters through cloud computing, and then updating the node data of the behavior state evaluation knowledge graph;

[0062] Step S500: Perform real-time behavior evaluation on the evaluation object according to the behavior state evaluation knowledge graph, and draw a radar chart based on the historical data of the evaluation results divided into each time period as feedback on the evaluation results of the current evaluation object in each time period.

[0063] The step S100 includes the following steps:

[0064] Step S101: obtaining behavior state evaluation parameters and situation parameter information of the evaluation object; the behavior state evaluation parameters refer to parameters that measure the behavior characteristics of the evaluation object and have an impact on the behavior evaluation results of the evaluation object; the situation parameters refer to parameters that reflect the situation characteristics of the evaluation object;

[0065] Step S102: Obtain historical data of the situation in which the evaluation object is located, and mark the reference values ​​of the behavior state evaluation parameters in the situation through manual marking;

[0066] For any combination of situation parameters, the annotation results are stored in a two-dimensional array consisting of a situation parameter vector and a behavior state evaluation parameter reference value vector;

[0067] Step S103: Use the labeled data to train a context-behavior reference deep learning model; the context-behavior reference deep learning model input is a context parameter vector, and the context-behavior reference deep learning model output is a behavior state evaluation parameter reference value vector under the input context parameter vector;

[0068] In the specific implementation, taking the autism assessment of children as an example, based on the existing autism assessment standards, behavioral state assessment parameters such as eye contact, facial expressions, language communication, body movements, physiological signs, etc. can be selected; at the same time, environmental temperature and humidity, population density, environmental noise intensity, situation type, communication type, etc. can be selected as situational parameters of the environment in which the assessment object is located;

[0069] When collecting data, cameras, WIFI_Sensing, millimeter-wave radars and audio collectors can be used to collect original signals, and then feature extraction and data dimension reduction are performed on the collected data to convert the original signals into one-dimensional data with the required features in the original signals; for eye contact and facial expressions, images are collected through cameras, and facial feature recognition algorithms are used to analyze the facial features of the evaluation object and identify the evaluation object's gaze direction data; for body movements, the current movement posture of the evaluation object is analyzed through posture estimation based on the collected image information; for physiological signs, WIFI_Sensing is used to monitor the breathing and heart rate data of the evaluation object, and then the multi-dimensional data of physiological signs is converted into one-dimensional data through time-frequency analysis and data dimension reduction;

[0070] The processed data is then used to construct a dataset, and a deep learning model is constructed in a data-driven way to achieve adaptive mapping of many-to-many parameters of context-behavior.

[0071] The step S200 includes the following steps:

[0072] Step S201: Obtaining the behavior analysis evaluation dimension information of the current evaluation object, and marking the weight coefficient of each behavior state parameter in different evaluation dimensions;

[0073] Step S202: constructing a behavior state evaluation knowledge graph for the current evaluation object; the behavior state evaluation knowledge graph includes behavior state nodes and evaluation dimension nodes, and the edge weights between the behavior state nodes and the evaluation dimension nodes are weight coefficients of each behavior state evaluation parameter in the evaluation dimension corresponding to each evaluation dimension node; wherein each behavior state node corresponds to each behavior state evaluation parameter one-to-one, and each evaluation dimension node corresponds to each evaluation dimension one-to-one;

[0074] In the specific implementation, when conducting behavioral status assessment on autistic children, the relevant behavioral status assessment parameter combinations are different in different situations. For example, in a classroom teaching situation, the relevant situational parameters include personnel density, ambient temperature, situation type, communication type, etc., and the eye contact, body movements, physiological signs, etc. of the assessment object need to be considered. In the communication situation of the family environment, there is no need to consider the personnel density of the situation in which the assessment object is located, and the facial expression of the assessment object needs to be additionally considered.

[0075] The step S300 includes the following steps:

[0076] Step S301: Setting a non-contact collection sensor in the current activity environment of the evaluation object to monitor the evaluation object and its situation in real time;

[0077] Step S302: performing feature extraction, data dimension reduction and normalization processing on each non-contact collection sensor data, and converting the collected data into one-dimensional data as the actual measured value of the behavior state evaluation parameter of the evaluation object;

[0078] Step S303: Calculate the reference deviation of each behavioral state evaluation parameter of the evaluation object; use the context-behavior reference deep learning model, take the context parameters of the context in which the evaluation object is located as input, obtain the reference value of the behavioral state evaluation parameter of the evaluation object, and calculate the difference between the actual value and the reference value of each behavioral state evaluation parameter of the evaluation object as the reference deviation of each behavioral state evaluation parameter of the evaluation object.

[0079] The step S400 includes the following contents:

[0080] Upload the historical data of reference deviations of the evaluation parameters of each behavior state of the evaluation object to the cloud for storage, and simultaneously analyze the deviation synchronization coefficients between the evaluation parameters of each behavior state through cloud computing;

[0081] For any behavior state evaluation parameters x and y, the deviation synchronization coefficient of y to x is calculated as follows:

[0082] k_(y→x)=(1 / Nd)×sum(δx / (δy+ε));

[0083] Wherein, k_(y→x) is the deviation synchronization coefficient of the behavior state evaluation parameter y to x, Nd is the number of historical data of reference deviation of each behavior state evaluation parameter of the evaluation object stored in the cloud, δx is the reference deviation of the behavior state evaluation parameter x, δy is the reference deviation of the behavior state evaluation parameter y, ε is a constant, and sum(δx / δy) is the numerical sum of the reference deviation ratios of the behavior state evaluation parameters x and y in all historical data stored in the cloud;

[0084] In the specific implementation, all behavior state evaluation parameters are initialized, assuming ε=0.00001, and at the same time, each behavior state parameter is retained to two decimal places for calculation to avoid the denominator value being 0; assuming that the reference deviations of the behavior state evaluation parameters x and y in the historical data are: Data 1: δx=0.1, δy=0.1; Data 2: δx=0.2, δy=-0.1; Data 3: δx=-0.1, δy=-0.25; then according to the formula, the deviation synchronization coefficient of y to x can be calculated k_(y→x)=-0.2;

[0085] The deviation synchronization coefficient between each behavior state transfer parameter is updated to the edge weight between the corresponding behavior state nodes in the behavior state evaluation knowledge graph, and the weight of each behavior state node in the behavior state evaluation knowledge graph is updated and iterated in real time;

[0086] For any behavior state evaluation parameter x, the corresponding behavior state node iteration formula in the behavior state evaluation knowledge graph is as follows:

[0087] x_update=(1-α-β)×x_ori+α×δx+β / (N_p)×sum(k_(p→x)×δp);

[0088] Wherein, x_update is the behavior state node iteration data corresponding to the behavior state evaluation parameter x, x_ori is the behavior state node original data corresponding to the behavior state evaluation parameter x, δx is the reference deviation of the behavior state evaluation parameter x, N_p is the number of other behavior state evaluation parameters except the behavior state evaluation parameter x, sum(k_(p→x)×δp) is the sum of the deviation synchronization coefficient of each behavior state evaluation parameter to x except the behavior state evaluation parameter x and the product of the reference deviation, α is the reference deviation compensation coefficient, β is the deviation synchronization compensation coefficient, α>0, β>0 and α+β<1;

[0089] In the specific implementation, assuming that α=β=0.05, the current situation involves a total of 4 behavioral state evaluation parameters {a, x, y, z}; among them, the value of a is 0.6, δa=0.1, δx=0.2, δy=-0.2, δz=-0.25; then the deviation synchronization coefficient between each behavioral state evaluation parameter is scaled to the range of [0,1] through a numerical scale, assuming that the deviation synchronization coefficients of x, y, z to a are: k_(x→a)=0.3, k_(y→a)=-0.4, k_(z→a)=0.8; according to the formula calculation, it can be seen that: a_update=0.544.

[0090] The step S500 includes the following contents:

[0091] Obtain the behavior state evaluation knowledge graph data, extract the latest iteration data of each behavior state node adjacent to each evaluation dimension node, and use the edge weight between the evaluation dimension node and the adjacent behavior state node as a coefficient to weight the node weight of each evaluation dimension node as the evaluation result of each evaluation dimension and upload it to the cloud for storage;

[0092] Set the behavior status evaluation cycle T, divide the time period by T, divide the node weight historical data of each evaluation dimension node, extract the minimum and maximum weights of each evaluation dimension node in the historical data in each time period through cloud computing, and draw a radar chart based on the extracted data of each time period at the end of each time period, as feedback of the behavior status evaluation results of each time period of the current evaluation object;

[0093] In specific implementation, each behavior state evaluation parameter is updated at equal time intervals or when the evaluation object context is switched, and the value of each evaluation dimension is updated synchronously, and then the evaluation results of each evaluation dimension node are calculated and updated simultaneously;

[0094] Furthermore, the data divided into each time period are classified and stored, and the maximum value of the evaluation results of each evaluation dimension is screened out in the cloud, and the maximum value of each evaluation dimension is synchronously marked in the radar chart, so as to intuitively reflect the fluctuation of the evaluation results of the evaluation object in each evaluation dimension in each time period. Compared with the timed visit evaluation of the traditional method, the above scheme more intuitively and popularly reflects the changes in the behavioral state of the evaluation object in each time period, thereby more effectively assisting in educational training and treatment.

[0095] A cloud computing-based attention and behavior assessment system, the system comprising: a data monitoring and processing module, a behavior data analysis module, and a behavior assessment feedback module;

[0096] The data monitoring and processing module monitors the evaluation object in real time by setting up contactless collection sensors in the current activity environment of the evaluation object, and is also used to collect and obtain the situational information of the evaluation object; the behavior data analysis module trains the situation-behavior reference deep learning model, calculates the reference deviation of each behavior state evaluation parameter of the evaluation object, and is also used to construct a behavior state evaluation knowledge graph, and updates and iterates data based on the reference deviation historical data of the behavior state evaluation parameters; the behavior evaluation feedback module updates and feedbacks the evaluation results of the evaluation object in real time based on the behavior state evaluation knowledge graph data.

[0097] The data monitoring and processing module includes: a behavior state monitoring unit and a situation monitoring unit;

[0098] The behavior state monitoring unit monitors the behavior state of the evaluation object in real time by setting a contactless collection sensor in the current activity environment of the evaluation object; the situation monitoring unit collects and obtains the situation information of the evaluation object through real-time monitoring.

[0099] The behavior data analysis module includes: a reference behavior analysis unit, a behavior deviation analysis unit, and a knowledge graph update unit;

[0100] The reference behavior analysis unit labels the reference values ​​of the behavior state evaluation parameters of the evaluation object in different situational parameters, trains the situation-behavior reference deep learning model, and then analyzes the reference values ​​of the behavior state evaluation parameters of the evaluation object in various situations; the behavior deviation analysis unit calculates the deviation between the monitored value and the reference value of the behavior state evaluation parameter of the evaluation object in real time, and then analyzes the deviation synchronization coefficient between each behavior state evaluation parameter; the knowledge graph updating unit updates and iterates the data in the constructed behavior state evaluation knowledge graph according to the deviation synchronization coefficient between each behavior state evaluation parameter and the monitoring data between the behavior state evaluation parameters.

[0101] The behavior assessment feedback module includes: a behavior state assessment unit and an assessment result feedback unit;

[0102] The behavior state evaluation unit performs behavior state evaluation on the evaluation object according to the data in the behavior state evaluation knowledge graph, and updates the evaluation results in real time; the evaluation result feedback unit draws a radar chart after filtering the evaluation results of each evaluation dimension in each time period, and provides feedback as the behavior state evaluation results of the current evaluation object in each time period.

[0103] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A cloud computing-based attention and behavior assessment method, characterized in that , the method is divided into the following steps: Step S100: Obtaining behavior state evaluation parameters and situation parameter information of the evaluation object, marking reference values ​​of the behavior state evaluation parameters of the evaluation object in different situation parameters, storing the marking results in a two-dimensional array consisting of situation parameter vectors and behavior state evaluation parameter reference value vectors, and training a situation-behavior reference deep learning model; The context-behavior reference deep learning model input is a context parameter vector, and the context-behavior reference deep learning model output is a behavior state evaluation parameter reference value vector under the input context parameter vector; Step S200: Obtaining the behavior analysis evaluation dimension information of the current evaluation object, marking the weight coefficient of each behavior state parameter in different evaluation dimensions, and constructing a behavior state evaluation knowledge graph for the current evaluation object; Step S300: Setting a non-contact acquisition sensor in the current activity environment of the evaluation object, monitoring the evaluation object in real time, obtaining the evaluation parameter data of the real-time behavior state of the evaluation object, and calculating the reference deviation of each behavior state evaluation parameter of the evaluation object; Step S400: analyzing the deviation synchronization coefficients between the behavior state evaluation parameters through cloud computing, and updating and iterating the weights of the behavior state nodes in the behavior state evaluation knowledge graph in real time, thereby updating the node data of the behavior state evaluation knowledge graph; Step S500: Perform real-time behavior evaluation on the evaluation object according to the behavior state evaluation knowledge graph, and extract the minimum and maximum weights of each evaluation dimension node in the historical data in each time period through cloud computing based on the historical data of the evaluation results divided into each time period, and draw a radar chart as feedback on the evaluation results of the current evaluation object in each time period.

2. The method for assessing attention and behavior based on cloud computing according to claim 1, characterized in that: The step S100 includes the following steps: Step S101: obtaining behavior state evaluation parameters and situation parameter information of the evaluation object; the behavior state evaluation parameters refer to parameters that measure the behavior characteristics of the evaluation object and have an impact on the behavior evaluation results of the evaluation object; the situation parameters refer to parameters that reflect the situation characteristics of the evaluation object; Step S102: Obtain historical data of the situation in which the evaluation object is located, annotate the behavioral state evaluation parameters in the situation with reference values ​​through manual annotation, and use the annotated data to train a situation-behavior reference deep learning model.

3. The cloud computing-based attention and behavior assessment method according to claim 1, characterized in that: The step S200 includes the following steps: Step S201: Obtaining the behavior analysis evaluation dimension information of the current evaluation object, and marking the weight coefficient of each behavior state parameter in different evaluation dimensions; Step S202: construct a behavior state evaluation knowledge graph for the current evaluation object; the behavior state evaluation knowledge graph includes behavior state nodes and evaluation dimension nodes, and the edge weights between the behavior state nodes and the evaluation dimension nodes are the weight coefficients of each behavior state evaluation parameter in the evaluation dimension corresponding to each evaluation dimension node; wherein each behavior state node corresponds one-to-one to each behavior state evaluation parameter, and each evaluation dimension node corresponds one-to-one to each evaluation dimension.

4. The method for assessing attention and behavior based on cloud computing according to claim 1, characterized in that: The step S300 includes the following steps: Step S301: Setting a non-contact collection sensor in the current activity environment of the evaluation object to monitor the evaluation object and its situation in real time; Step S302: performing feature extraction, data dimension reduction and normalization processing on each non-contact collection sensor data, and converting the collected data into one-dimensional data as the actual measured value of the behavior state evaluation parameter of the evaluation object; Step S303: Calculate the reference deviation of each behavioral state evaluation parameter of the evaluation object; use the context-behavior reference deep learning model, take the context parameters of the context in which the evaluation object is located as input, obtain the reference value of the behavioral state evaluation parameter of the evaluation object, and calculate the difference between the actual value and the reference value of each behavioral state evaluation parameter of the evaluation object as the reference deviation of each behavioral state evaluation parameter of the evaluation object.

5. The method for assessing attention and behavior based on cloud computing according to claim 1, characterized in that: The step S400 includes the following contents: Upload the historical data of reference deviations of the evaluation parameters of each behavior state of the evaluation object to the cloud for storage, and simultaneously analyze the deviation synchronization coefficients between the evaluation parameters of each behavior state through cloud computing; For any behavior state evaluation parameters x and y, the deviation synchronization coefficient of y to x is calculated as follows: k_(y→x)=(1 / Nd)×sum(δx / (δy+ε)); Wherein, k_(y→x) is the deviation synchronization coefficient of the behavior state evaluation parameter y to x, Nd is the number of historical data of reference deviation of each behavior state evaluation parameter of the evaluation object stored in the cloud, δx is the reference deviation of the behavior state evaluation parameter x, δy is the reference deviation of the behavior state evaluation parameter y, ε is a constant, and sum(δx / δy) is the numerical sum of the reference deviation ratios of the behavior state evaluation parameters x and y in all historical data stored in the cloud; The deviation synchronization coefficient between each behavior state transfer parameter is updated to the edge weight between the corresponding behavior state nodes in the behavior state evaluation knowledge graph, and the weight of each behavior state node in the behavior state evaluation knowledge graph is updated and iterated in real time; For any behavior state evaluation parameter x, the corresponding behavior state node iteration formula in the behavior state evaluation knowledge graph is as follows: x_update=(1-α-β)×x_ori+α×δx+β / (N_p)×sum(k_(p→x)×δp); Among them, x_update is the iteration data of the behavior state node corresponding to the behavior state evaluation parameter x, x_ori is the original data of the behavior state node corresponding to the behavior state evaluation parameter x, δx is the reference deviation of the behavior state evaluation parameter x, N_p is the number of other behavior state evaluation parameters except the behavior state evaluation parameter x, sum(k_(p→x)×δp) is the numerical sum of the product of the deviation synchronization coefficient of each behavior state evaluation parameter to x except the behavior state evaluation parameter x and the reference deviation, α is the reference deviation compensation coefficient, β is the deviation synchronization compensation coefficient, α>0, β>0 and α+β<1.

6. The method for assessing attention and behavior based on cloud computing according to claim 1, characterized in that: The step S500 includes the following contents: Obtain the behavior state evaluation knowledge graph data, extract the latest iteration data of each behavior state node adjacent to each evaluation dimension node, and use the edge weight between the evaluation dimension node and the adjacent behavior state node as a coefficient to weight the node weight of each evaluation dimension node as the evaluation result of each evaluation dimension and upload it to the cloud for storage; Set the behavior status evaluation cycle T, divide the time period by T, divide the node weight historical data of each evaluation dimension node, extract the minimum and maximum weights of each evaluation dimension node in the historical data in each time period through cloud computing, and draw a radar chart based on the extracted data of each time period at the end of each time period, as feedback on the behavior status evaluation results of each time period of the current evaluation object.

7. A cloud computing-based attention and behavior assessment system using a cloud computing-based attention and behavior assessment method according to any one of claims 1 to 6, characterized in that: The system includes: a data monitoring and processing module, a behavior data analysis module, and a behavior evaluation feedback module; The data monitoring and processing module monitors the evaluation object in real time by setting up contactless collection sensors in the current activity environment of the evaluation object, and is also used to collect and obtain the situational information of the evaluation object; the behavior data analysis module trains the situation-behavior reference deep learning model, calculates the reference deviation of each behavior state evaluation parameter of the evaluation object, and is also used to construct a behavior state evaluation knowledge graph, and updates and iterates data based on the reference deviation historical data of the behavior state evaluation parameters; the behavior evaluation feedback module updates and feedbacks the evaluation results of the evaluation object in real time based on the behavior state evaluation knowledge graph data.

8. The cloud computing-based attention and behavior assessment system according to claim 7, characterized in that: The data monitoring and processing module includes: a behavior state monitoring unit and a situation monitoring unit; The behavior state monitoring unit monitors the behavior state of the evaluation object in real time by setting a contactless collection sensor in the current activity environment of the evaluation object; the situation monitoring unit collects and obtains the situation information of the evaluation object through real-time monitoring.

9. The cloud computing-based attention and behavior assessment system according to claim 7, characterized in that: The behavior data analysis module includes: a reference behavior analysis unit, a behavior deviation analysis unit, and a knowledge graph update unit; The reference behavior analysis unit labels the reference values ​​of the behavior state evaluation parameters of the evaluation object in different situational parameters, trains the situation-behavior reference deep learning model, and then analyzes the reference values ​​of the behavior state evaluation parameters of the evaluation object in various situations; the behavior deviation analysis unit calculates the deviation between the monitored value and the reference value of the behavior state evaluation parameter of the evaluation object in real time, and then analyzes the deviation synchronization coefficient between each behavior state evaluation parameter; the knowledge graph updating unit updates and iterates the data in the constructed behavior state evaluation knowledge graph according to the deviation synchronization coefficient between each behavior state evaluation parameter and the monitoring data between the behavior state evaluation parameters.

10. The cloud computing-based attention and behavior assessment system according to claim 7, characterized in that: The behavior assessment feedback module includes: a behavior state assessment unit and an assessment result feedback unit; The behavior state evaluation unit performs behavior state evaluation on the evaluation object according to the data in the behavior state evaluation knowledge graph, and updates the evaluation results in real time; the evaluation result feedback unit draws a radar chart after filtering the evaluation results of each evaluation dimension in each time period, and provides feedback as the behavior state evaluation results of the current evaluation object in each time period.

Images