CN117421084B - Cloud platform-based intelligent software data analysis system and method - Google Patents
Cloud platform-based intelligent software data analysis system and method Download PDFInfo
- Publication number
- CN117421084B CN117421084B CN202311468819.6A CN202311468819A CN117421084B CN 117421084 B CN117421084 B CN 117421084B CN 202311468819 A CN202311468819 A CN 202311468819A CN 117421084 B CN117421084 B CN 117421084B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- software
- software interface
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 82
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 230000004044 response Effects 0.000 claims description 37
- 238000007405 data analysis Methods 0.000 claims description 34
- 239000013598 vector Substances 0.000 claims description 33
- 239000011159 matrix material Substances 0.000 claims description 28
- 230000006399 behavior Effects 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 24
- 230000008859 change Effects 0.000 claims description 21
- 238000007726 management method Methods 0.000 claims description 21
- 230000000007 visual effect Effects 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000013145 classification model Methods 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 6
- 238000013523 data management Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 230000006378 damage Effects 0.000 abstract description 5
- 230000004438 eyesight Effects 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 4
- 208000027418 Wounds and injury Diseases 0.000 abstract description 2
- 208000014674 injury Diseases 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000010415 Low Vision Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a cloud platform-based intelligent analysis system and method for software data, which relate to the technical field of intelligent analysis for software data and comprise the following steps: s1: monitoring the use condition of a user on a software interface to acquire related data of the user on the use of the software; s2: judging whether the software interface elements of the user need to be automatically adjusted, and when the software interface elements of the user need to be automatically adjusted, combining the related information of the user equipment to adjust the software interface elements; s3: when the software interface element is automatically adjusted, collecting feedback data of the user on the automatic adjustment of the software interface element, and modeling the user according to the feedback data of the user; s4: managing the software account of the user according to user modeling, and carrying out configuration updating on the related attribute of the software account of the user; the user experience is improved, and the eyesight and health injury caused by unreasonable parameter setting of the user when the software is used is avoided.
Description
Technical Field
The invention relates to the technical field of intelligent analysis of software data, in particular to an intelligent analysis system and an intelligent analysis method of software data based on a cloud platform.
Background
The cloud computing technology provides powerful computing and storage capacity for the cloud platform, can realize efficient data processing and analysis, and can flexibly adjust the scale of computing resources so as to adapt to the data analysis requirements of different scales and complexity. The intelligent analysis of data based on the cloud platform needs to process massive data, and in order to perform effective data analysis, the data needs to be collected from various data sources, cleaned and preprocessed. The core of intelligent analysis is the data analysis and mining technology part, including methods of statistical analysis, machine learning, deep learning and the like. These techniques can help discover patterns, trends, and rules from the data, make predictions and classifications, and provide insight and decision support.
At present, a software interface used by a user is usually provided with an interface layout style by the user, and the user can freely adjust the position and the size of interface elements so as to meet the preference and the use habit of the user and select a satisfactory layout mode. However, with the development of information technology, the vision of a user is gradually damaged by using an electronic device for a long time, and the use requirement of the user is sometimes affected by a fixed software interface layout, for example, the increasingly reduced vision of the user and the unbalance of interface content can lead to the user being more close to a screen when the user uses the electronic device carelessly or using a reading gesture harmful to the body, so that the body health of the user is damaged for a long time, and meanwhile, the vicious circle of the vision damage of the user is caused.
Therefore, in order to solve the above problems or part of the problems, the invention provides a cloud platform-based intelligent software data analysis system and method.
Disclosure of Invention
The invention aims to provide a cloud platform-based intelligent software data analysis system and method, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a cloud platform-based intelligent analysis method for software data comprises the following steps:
s1: monitoring the use condition of a user on a software interface to acquire related data of the use of the software by the user;
s2: analyzing the related data obtained by monitoring, judging whether the software interface elements of the user need to be automatically adjusted, and according to the analysis result, combining the related information of the user equipment to adjust the software interface elements when the software interface elements of the user need to be automatically adjusted;
s3: when the software interface element is automatically adjusted, collecting feedback data of the user on the automatic adjustment of the software interface element, and modeling the user according to the feedback data of the user;
s4: and (3) carrying out corresponding management on the software account of the user according to the user modeling in the S3, and carrying out configuration updating on the related attribute of the software account of the user.
Further, in the step S1, operation related data of the user on the software interface is obtained by recording operations, such as clicking, sliding, inputting, etc., of the user, and the operation related data of the user on the software interface is preprocessed to generate a user operation related data set C, c= { T, M }; wherein T represents a waiting time length set for waiting for a user response time, t= { T1, T2, & gt, tn }, where T1, T2, & gt, tn represent waiting time lengths for waiting for the user response by the software for the 1 st, 2 nd, n times, respectively, and n represents the total number of times for waiting for the user response operation by the acquired software; m represents the set of invalid operations within the waiting user response time, m= { M1, M2, -, mn, wherein, M1, M2, & mn represent the number of invalidation operations within the response time of the stand-by user, respectively, 1, 2, & n times; the invalid operation represents operations such as clicking, sliding and the like of an operation response required by feedback software in a current interface of the software;
according to the user-defined setting of the user to the software, the setting parameters of the user to the software interface elements including layout, color, font size and the like are obtained, and the use frequency and the use time of the user to the software interface are obtained through log inquiry or plug-in unit, so that the actual use condition of the user to the software is conveniently known; when the access right of the user equipment is acquired, acquiring the related information of the user equipment and the software use environment data of the user at the current equipment; preprocessing acquired user software by using environment data to generate a user environment data set H, H= { L, D }; wherein L represents an ambient light data set in waiting user response time, l= { L1, L2, & gt, ln }, L1, L2, & gt, ln respectively represent ambient light indexes in waiting user response time of software 1 st, 2 nd, n times, and the ambient light indexes are obtained by reading the ambient data collected by the user equipment; d represents the distance change value of the user from the software interface within the waiting user response time, d= { D1, D2,..and Dn }, D1, D2,..and Dn represent the distance change value of the user from the software interface within the waiting user response time of the 1 st, 2 nd..and n times of software respectively, so as to better understand the use environment and the requirement of the user;
Further, the step S2 includes:
step S2-1: extracting a preprocessed user operation related data set C and a preprocessed user environment data set H according to the monitoring data obtained in the step S1, and converting the original data in the extracted two data sets, wherein the original data meets the assumption requirement of a model; carrying out standardization or normalization treatment on the converted original data so as to eliminate dimension differences among different data; splitting the processed data into a training set and a testing set in a random extraction mode to obtain feature data of a constructed model;
step S2-2: constructing a judgment model through the training set in the step S2-1, marking one type of the training set which represents that the training set needs to be adjusted as positive, marking the class label as y=1, marking the other type of the training set which represents that the training set does not need to be adjusted as negative, marking the class label as y=0, and modeling according to the following formula:
P(y＝1|x)＝1/(1+e zx+b )；
wherein x represents a given input feature, and P (y= 1|x) represents a probability of discriminating a result into 1 under the condition of the given input feature x, namely a probability that a discrimination model predicts that a sample belongs to a positive example; e represents the bottom of the natural logarithm, z is the transpose of a weight matrix W, the weight matrix W represents a matrix matched with the x dimension, and b is a bias parameter;
The weight matrix W and the bias parameter b are determined according to the following steps:
a1: the loss function S is defined according to the following formula:
S(W,b)＝-[y*log(p(y＝1|x))+(1-y)*log(1-p(y＝1|x))]；
a2: obtaining gradient information of a weight matrix W and a bias parameter b by deriving a loss function, wherein the gradient of the loss function to the weight matrix W is as follows: dS/dw=x (p (y= 1|x) -y);
the gradient of the loss function to the bias parameter b is: dS/db=p (y= 1|x) -y;
a3: updating the weight matrix W and the bias parameter b according to the gradient information and the learning rate a:
W＝W-a*dS/dW；
b＝b-a*dS/db；
the learning rate a represents the super-parameter for controlling the magnitude of the parameter updating amplitude at each time and is preset by related personnel; or automatically adjusting the learning rate a by a self-adaptive learning rate algorithm so as to improve the model training effect;
a4: repeating the steps A2 and A3 until convergence of the loss function value reaches a preset termination condition, and updating to obtain a weight matrix W and a bias parameter b;
step S2-3: when the prediction performance of the judgment model meets the actual requirement after the judgment model is evaluated, predicting the newly acquired related data of the user using software by using the trained judgment model; when the probability value P (y= 1|x) calculated by the judgment model is larger than or equal to a preset threshold value q, the class label of the related data of the newly acquired user using software is y=1, and the prediction result is a positive example, and automatic adjustment is needed for the current software interface element of the user; when the probability value P (y= 1|x) calculated by the judgment model is smaller than a preset threshold value q, the predicted result is a negative example, and automatic adjustment of the current software interface element of the user is not needed;
Step S2-4: according to the prediction result of the discrimination model, when the software interface element of the user needs to be automatically adjusted, according to the related information of the user equipment obtained in the step S1, if the distance change value of the user from the software interface continuously increases within the current waiting user response time and exceeds the preset distance change value d, the fonts and icons in the current software interface are increased according to the pixel density and the size of the user equipment screen, so that the fonts and the icons are displayed clearly and readable on different equipment;
preferably, according to the type of the operating system and the browser of the user equipment, corresponding interaction adjustment modes are provided for different equipment, and the size and the interval of the adjustment buttons can be optimized so that a user can click on a screen more easily.
Further, the step S3 includes:
step S3-1: when the software interface element is automatically adjusted, collecting feedback data of the user on the automatic adjustment of the software interface element, wherein the feedback data comprise response time t 'of the user after the automatic adjustment of the software interface element and a distance change value d' of the user from the software interface within the waiting time of the user; the feedback data are arranged into a matrix F, wherein each row represents one sample, and each column represents one feature; mapping the corresponding visual recognition obstacle label into a vector, wherein each element in the vector represents a label of one sample; the tag vector is represented using a form of one-hot encoding;
One-hot encoding is a method of representing discrete features as binary vectors, where each class is represented by a unique binary vector. Specifically, if there are r different categories, the length of the label vector is r, the corresponding position of the label for each sample is set to be 1, the other positions are set to be 0, and the label of each sample can be represented by a vector with the length of r.
Step S3-2: the minimum value and the maximum value of the feature are used for carrying out linear change on the feature matrix, and the feature value is scaled to be within the range of [0,1] so as to realize normalization of the feature; converting the characteristics of the feedback data into a vector form, and generating a two-dimensional characteristic vector, wherein each dimension corresponds to one characteristic; the feature mapping is performed by the following formula:
K(v i ,v j )＝tanh(θ×v i T v j +ε)；
wherein v is i And v j Respectively represent the input eigenvectors, v i T Representing v i Is a transpose of (2); θ and ε are adjustable super parameters preset by related personnel; the tanh function is a commonly used nonlinear activation function;
step S3-3: establishing a user classification model according to the following formula, and obtaining a prediction result Y by inputting a feature vector v' of user feedback data to be distinguished:
where u represents the number of samples in the feedback data; sign () represents a sign function, returning 1 when the value in brackets is greater than 0, returning-1 when it is less than 0, and returning 0 when it is equal to 0; alpha i A Lagrangian multiplier representing a feature vector corresponding to the ith input, the Lagrangian multiplier in a support vector machine algorithm for determining a support vector and calculating a decision boundary; beta i A class label representing an ith feedback data sample in a training set of the input model; b is a bias term, which is calculated by a support vector;
y is the output result of the user classification model and is used for judging the type of the user feedback data; when Y >0, the user feedback data is judged to be positive, which means that the visual recognition obstacle label is required to be added in the user modeling; when Y is less than or equal to 0, the user feedback data is judged to be negative, and the user modeling is represented that the visual recognition obstacle label is not added;
further, in the step S4, the software account of the user is managed according to the user modeling in the step S3; when the user modeling indicates that the current user has visual recognition obstacle, storing corresponding software interface recommendation attribute configuration of the user modeling into a software database according to user permission, setting software interface elements according to relevant data of user equipment, and updating relevant data of a user account.
Specifically, when a visual recognition obstacle exists in the corresponding user modeling in the user software account, if the parameters of the software interface elements are beyond the standard threshold set by the visual recognition obstacle label in the process of using the software by the user, automatically adjusting the software interface elements according to the screen data of the user equipment, or updating the size settings of elements such as fonts and icons in the current software interface, so that the body damage caused by the fact that the user changes the browsing gesture due to difficulty in identifying the software interface elements is avoided.
A cloud platform based intelligent analysis system for software data, the system comprising: the system comprises a software data monitoring module, a monitoring data analysis module, a user feedback detection module and a software interface management module;
the software data monitoring module is used for monitoring operation data and behavior data when a user uses software, and transmitting relevant data obtained by monitoring to the monitoring data analysis module;
the monitoring data analysis module is used for analyzing the related data obtained by monitoring and judging whether the current software interface needs to be adjusted according to the operation data and the behavior data when the user uses the software;
the user feedback detection module is used for detecting the user related data after the software interface is adjusted, and generating user modeling through mining the user related data;
the software interface management module is used for correspondingly managing the software interface of the user according to the analysis result of the monitoring data analysis module, and correspondingly configuring and updating the software setting according to user modeling;
the output end of the software data monitoring module is connected with the input ends of the monitoring data analysis module and the user feedback detection module, and the output ends of the monitoring data analysis module and the user feedback detection module are connected with the input end of the software interface management module.
Further, the software data monitoring module comprises a user operation acquisition unit, a user behavior acquisition unit and a monitoring data management unit;
the user operation acquisition unit is used for acquiring software operation data of a user in the software use process;
the user behavior acquisition unit is used for acquiring human behavior data of a user in the software use process;
the monitoring data management unit is used for preprocessing and storing the related data obtained by monitoring and transmitting the preprocessed monitoring data to the monitoring data analysis module.
Further, the monitoring data analysis module comprises a monitoring data extraction unit and a data analysis unit;
the monitoring data extraction unit is used for extracting the received monitoring data, acquiring partial data required by data analysis and generating a corresponding data set;
the data analysis unit is used for analyzing the user state according to the monitoring data set and judging whether the current software interface needs to be adjusted.
Further, the user feedback detection module comprises a feedback data acquisition unit and a user modeling generation unit;
the feedback data acquisition unit is used for acquiring user behavior data after the software interface is adjusted to obtain feedback data of the user for automatically adjusting the software interface elements; the data can comprise clicking, browsing, operating and other actions of the user on the interface and interaction conditions with the interface elements, and feedback information of automatic adjustment of the software interface elements by the user can be obtained by collecting the data.
The user modeling generating unit is used for mining the user behavior according to the collected feedback data and modeling the user. The user behavior is mined based on the collected feedback data, so that the requirements of the user can be better understood, personalized services and recommendations are provided for the user, and the satisfaction degree and the use effect of the user are improved.
Further, the software interface management module comprises a software data adjustment unit and a user account management unit;
the software data adjusting unit is used for adjusting corresponding parameters of the software interface elements according to the judging result of the data analyzing unit and in combination with the monitoring data of the software data monitoring module;
the user account management unit is used for managing accounts of users in the software database according to the modeling result of the user modeling generation unit, storing and updating user labels obtained by user modeling, and recording corresponding parameters of the software interface elements according to the user labels. By adjusting the related parameters of the software interface elements in real time, the flexibility and individuation of the software interface are improved, the software interface presents the best effect under different environments or user requirements, and better user experience is provided.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the use condition of the user on the software interface is monitored and analyzed, so that the requirements and the behavior mode of the user can be known in real time, and further, the software interface elements are adjusted according to the analysis result, so that the software interface elements are more in line with the expectations and habits of the user, the user experience is improved, and the operation difficulty of the user is reduced.
Through user modeling, the requirements of the user can be deeply known, so that personalized services and recommendations are provided for the user. According to feedback data of users, software interface elements are automatically adjusted according to relevant information of user equipment, requirements and equipment characteristics of different users are met, and more customized user experience is provided. The vision and health injury caused by unreasonable data setting when the user uses the software is avoided.
The satisfaction degree and effect of the user on the adjustment can be known by collecting feedback data of the user on the automatic adjustment of the software interface element. By combining user modeling and account management, the relevant attribute of the user's software account can be configured and updated, and the user experience is further optimized. Meanwhile, according to the feedback data and the behavior mode of the user, the design and the function of the software interface can be continuously improved and optimized, so that the software interface meets the requirements and the expectations of the user.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a module structure of a cloud platform-based intelligent software data analysis system;
fig. 2 is a flow chart of a software data intelligent analysis method based on a cloud platform.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is further described with reference to fig. 1, 2 and embodiments.
Example 1: as shown in fig. 1, the present embodiment provides a cloud platform-based intelligent software data analysis system, which includes: the system comprises a software data monitoring module, a monitoring data analysis module, a user feedback detection module and a software interface management module;
The software data monitoring module is used for monitoring operation data and behavior data when a user uses software and transmitting related data obtained by monitoring to the monitoring data analysis module; the software data monitoring module comprises a user operation acquisition unit, a user behavior acquisition unit and a monitoring data management unit;
the user operation acquisition unit is used for acquiring software operation data of a user in the software use process;
the user behavior acquisition unit is used for acquiring human behavior data of a user in the use process of the software;
the monitoring data management unit is used for preprocessing and storing the related data obtained by monitoring and transmitting the preprocessed monitoring data to the monitoring data analysis module.
The monitoring data analysis module is used for analyzing the related data obtained by monitoring and judging whether the current software interface needs to be adjusted according to the operation data and the behavior data when the user uses the software; the monitoring data analysis module comprises a monitoring data extraction unit and a data analysis unit;
the monitoring data extraction unit is used for extracting the received monitoring data, acquiring partial data required by data analysis and generating a corresponding data set;
The data analysis unit is used for analyzing the user state according to the monitoring data set and judging whether the current software interface needs to be adjusted.
The user feedback detection module is used for detecting the user related data after the software interface is adjusted, and generating user modeling through mining the user related data; the user feedback detection module comprises a feedback data acquisition unit and a user modeling generation unit;
the feedback data acquisition unit is used for acquiring the user behavior data after the software interface is adjusted to obtain feedback data of the user for automatically adjusting the software interface elements; the data can comprise clicking, browsing, operating and other actions of the user on the interface and interaction conditions with the interface elements, and feedback information of automatic adjustment of the software interface elements by the user can be obtained by collecting the data.
The user modeling generating unit is used for mining the user behavior according to the collected feedback data and modeling the user. The user behavior is mined based on the collected feedback data, so that the requirements of the user can be better understood, personalized services and recommendations are provided for the user, and the satisfaction degree and the use effect of the user are improved.
The software interface management module is used for carrying out corresponding management on a software interface of a user according to an analysis result of the monitoring data analysis module, and carrying out corresponding configuration and update on software setting according to user modeling; the software interface management module comprises a software data adjustment unit and a user account management unit;
the software data adjusting unit is used for adjusting corresponding parameters of the software interface elements according to the judging result of the data analyzing unit and combining the monitoring data of the software data monitoring module;
the user account management unit is used for managing accounts of users in the software database according to the modeling result of the user modeling generation unit, storing and updating user labels obtained by user modeling, and recording corresponding parameters of the software interface elements according to the user labels. By adjusting the related parameters of the software interface elements in real time, the flexibility and individuation of the software interface are improved, the software interface presents the best effect under different environments or user requirements, and better user experience is provided.
Example 2: as shown in fig. 2, the present embodiment provides a cloud platform-based software data intelligent analysis method, which is implemented based on a cloud platform-based software data intelligent analysis system in the embodiment, and specifically includes the following steps:
S1: monitoring the use condition of a user on a software interface to acquire related data of the use of the software by the user;
in S1, operation related data of a user on a software interface is obtained by recording operations, such as clicking, sliding, inputting and the like, of the user, and the operation related data of the user on the software interface is preprocessed to generate a user operation related data set C, c= { T, M }; wherein T represents a waiting time length set for waiting for a user response time, t= { T1, T2, & gt, tn }, where T1, T2, & gt, tn represent waiting time lengths for waiting for the user response by the software for the 1 st, 2 nd, n times, respectively, and n represents the total number of times for waiting for the user response operation by the acquired software; m represents the set of invalid operations within the waiting user response time, m= { M1, M2, -, mn, wherein, M1, M2, & mn represent the number of invalidation operations within the response time of the stand-by user, respectively, 1, 2, & n times; the invalid operation represents operations such as clicking, sliding and the like of an operation response required by feedback software in a current interface of the software;
according to the user-defined setting of the user to the software, the setting parameters of the user to the software interface elements including layout, color, font size and the like are obtained, and the use frequency and the use time of the user to the software interface are obtained through log inquiry or plug-in unit, so that the actual use condition of the user to the software is conveniently known; when the access right of the user equipment is obtained, the related information of the user equipment and the software using environment data of the user at the current equipment are obtained, wherein the related information of the user equipment comprises the screen resolution, the screen size, an operating system and the like of the user equipment, and the related information of the user equipment is obtained through a front-end technology, such as JavaScript, or a back-end server. Preprocessing acquired user software by using environment data to generate a user environment data set H, H= { L, D }; wherein L represents an ambient light data set in waiting user response time, l= { L1, L2, & gt, ln }, L1, L2, & gt, ln respectively represent ambient light indexes in waiting user response time of software 1 st, 2 nd, n times, and the ambient light indexes are obtained by reading the ambient data collected by the user equipment; d represents a distance change value of the user from the software interface within waiting user response time, d= { D1, D2, & gt, dn }, D1, D2, & gt, dn represent distance change values of the user from the software interface within waiting user response time of 1 st, 2 nd, and n times of software respectively, wherein the distance change value is judged by the size of a user face collected by a camera in the user equipment, when a face identification collected by the equipment is larger, the user distance interface is represented as being closer, namely, the change value is a positive number, and when the face identification collected by the equipment is smaller, the user distance interface is represented as being farther, namely, the change value is a negative number; so as to facilitate better understanding of the use environment and requirements of the user;
S2: analyzing the related data obtained by monitoring, judging whether the software interface elements of the user need to be automatically adjusted, and according to the analysis result, combining the related information of the user equipment to adjust the software interface elements when the software interface elements of the user need to be automatically adjusted;
step S2-1: according to the monitoring data obtained in the step S1, extracting a preprocessed user operation related data set C and a preprocessed user environment data set H, and converting the original data in the two extracted data sets to enable the original data to meet the assumption requirement of a model, for example, discretizing continuous characteristic data, converting the continuous characteristic data into ordered discrete variables, so that the continuous characteristic data is easier to learn by the model; carrying out standardization or normalization treatment on the converted original data so as to eliminate dimension differences among different data; splitting the processed data into a training set and a testing set by a random extraction mode, wherein 80% of the data is used as the training set and the rest data is used as the testing set in the embodiment; obtaining characteristic data of the constructed model;
step S2-2: constructing a judgment model through the training set in the step S2-1, marking one type of the training set which represents that the training set needs to be adjusted as positive, marking the class label as y=1, marking the other type of the training set which represents that the training set does not need to be adjusted as negative, marking the class label as y=0, and modeling according to the following formula:
P(y＝1|x)＝1/(1+e zx+b )；
Wherein x represents a given input feature, and P (y= 1|x) represents a probability of discriminating a result into 1 under the condition of the given input feature x, namely a probability that a discrimination model predicts that a sample belongs to a positive example; e represents the bottom of the natural logarithm, z is the transpose of a weight matrix W, the weight matrix W represents a matrix matched with the x dimension, and b is a bias parameter;
the weight matrix W and the bias parameter b are determined according to the following steps:
a1: the loss function S is defined according to the following formula:
S(W,b)＝-[y*log(p(y＝1|x))+(1-y)*log(1-p(y＝1|x))]；
a2: obtaining gradient information of a weight matrix W and a bias parameter b by deriving a loss function, wherein the gradient of the loss function to the weight matrix W is as follows: dS/dw=x (p (y= 1|x) -y);
the gradient of the loss function to the bias parameter b is: dS/db=p (y= 1|x) -y;
a3: updating the weight matrix W and the bias parameter b according to the gradient information and the learning rate a:
W＝W-a*dS/dW；
b＝b-a*dS/db；
the learning rate a represents the super-parameter for controlling the magnitude of the parameter updating amplitude at each time and is preset by related personnel; or automatically adjusting the learning rate a by a self-adaptive learning rate algorithm so as to improve the model training effect;
a4: repeating the steps A2 and A3 until convergence of the loss function value reaches a preset termination condition, and updating to obtain a weight matrix W and a bias parameter b;
Step S2-3: when the prediction performance of the judgment model meets the actual requirement after the judgment model is evaluated by the test set, predicting the newly acquired related data of the user using the software by using the trained judgment model; when the probability value P (y= 1|x) calculated by the judgment model is greater than or equal to a preset threshold value q, q=0.5 is taken in the embodiment, the class label of the related data representing the newly acquired user use software is y=1, and the prediction result is positive, so that automatic adjustment is required for the current software interface element of the user; when the probability value P (y= 1|x) calculated by the judgment model is smaller than 0.5, the predicted result is a negative example, and automatic adjustment of the current software interface element of the user is not needed;
step S2-4: according to the prediction result of the discrimination model, when the software interface element of the user needs to be automatically adjusted, according to the related information of the user equipment obtained in the step S1, if the distance change value of the user from the software interface continuously increases within the current waiting user response time and exceeds the preset distance change value d, the fonts and icons in the current software interface are increased according to the pixel density and the size of the user equipment screen, so that the fonts and the icons are displayed clearly and readable on different equipment;
According to the operating system type and browser type of the user equipment, corresponding interaction adjustment modes are provided for different equipment, for example, for touch screen equipment, the size and the interval of the adjustment buttons can be optimized, so that the user can click on a screen more easily.
S3: when the software interface element is automatically adjusted, collecting feedback data of the user on the automatic adjustment of the software interface element, and modeling the user according to the feedback data of the user;
step S3-1: when the software interface element is automatically adjusted, collecting feedback data of the user on the automatic adjustment of the software interface element, wherein the feedback data comprise response time t 'of the user after the automatic adjustment of the software interface element and a distance change value d' of the user from the software interface within the waiting time of the user; the feedback data are arranged into a matrix F, wherein each row represents one sample, and each column represents one characteristic, and the characteristic is the response time of a user after the automatic adjustment of the software interface element and the distance change value of the user from the software interface in the waiting time of the user response; mapping the corresponding visual recognition obstacle tag into a vector, for example, [1,0]; each element in the vector represents a label of one sample; the tag vector is represented using a form of one-hot encoding;
One-hot encoding is a method of representing discrete features as binary vectors, where each class is represented by a unique binary vector. Specifically, if there are 2 different categories, the length of the label vector is 2, the corresponding position is set to 1 for the label of each sample, the other positions are set to 0, and the label of each sample can be represented by a vector with the length of 2.
In some embodiments, user feedback mechanisms, such as feedback buttons, satisfaction surveys, and the like, may be incorporated into the software interface. Ensuring that the user can conveniently provide feedback; when a user initiates feedback or participates in satisfaction survey, collecting feedback data of the user; the feedback data comprise information such as evaluation of interface adjustment by a user, use experience and the like; preprocessing and feature extraction are carried out on the collected user feedback data, and natural language processing technology is used for extracting emotion tendencies, keywords and the like of the user for interface adjustment so as to facilitate subsequent user modeling analysis.
Step S3-2: linear variation of feature matrix using minimum and maximum values of feature, scaling feature values to [0,1 ]]In the range of (2) to achieve normalization of the features; converting the features of the feedback data into a vector form, generating a two-dimensional feature vector, each dimension corresponding to a feature, e.g., the feature vector of the feedback data may be expressed as (v) 1 ,v 2 ) Wherein v is 1 And v 2 Representing the values of the first and second features, respectively; the feature mapping is performed by the following formula:
K(v i ,v j )＝tanh(θ×v i T v j +ε)；
wherein v is i And v j Respectively represent the input eigenvectors, v i T Representing v i Is a transpose of (2); θ and ε are adjustable super parameters preset by related personnel; the tanh function is a commonly used nonlinear activation function;
step S3-3: establishing a user classification model according to the following formula, and obtaining a prediction result Y by inputting a feature vector v' of user feedback data to be distinguished:
where u represents the number of samples in the feedback data; sign () represents a sign function, returning 1 when the value in brackets is greater than 0, returning-1 when it is less than 0, and returning 0 when it is equal to 0; alpha i A Lagrangian multiplier representing a feature vector corresponding to the ith input, the Lagrangian multiplier in a support vector machine algorithm for determining a support vector and calculating a decision boundary; beta i A class label representing an ith feedback data sample in a training set of the input model; b is a bias term, which is calculated by a support vector;
y is the output result of the user classification model and is used for judging the type of the user feedback data; when Y >0, the user feedback data is judged to be positive, which means that the visual recognition obstacle label is required to be added in the user modeling; when Y is less than or equal to 0, the user feedback data is judged to be negative, and the user modeling is represented that the visual recognition obstacle label is not added;
In some embodiments, the user is modeled based on user feedback data, and the established user model is evaluated to verify its accuracy and effectiveness. Model adjustments and iterations can be performed to improve predictive power and user modeling accuracy if improvements are needed.
In some embodiments, step S3-4 is included: and applying the established user model to an automatic adjustment process, predicting the response of the user to interface adjustment according to the modeling result of the user, and carrying out corresponding automatic adjustment according to the prediction result.
S4: managing the software account of the user according to the user modeling in the S3; when the user modeling indicates that the current user has visual recognition obstacle, storing corresponding software interface recommendation attribute configuration of the user modeling into a software database according to user permission, setting software interface elements according to relevant data of user equipment, and updating relevant data of a user account.
When visual recognition barriers exist in corresponding user modeling in a user software account, if the condition that element parameters of a software interface exceed a standard threshold set by a visual recognition barrier label exists in a software interface which is set by user definition when a user uses software, reminding the user that the current interface setting possibly affects visual health through a popup window;
If the parameter of the software interface element exceeds the standard threshold value set by the visual recognition obstacle label due to interface jump in the process of using the software by the user, automatically adjusting the software interface element according to the screen data of the user equipment, or updating the size settings of elements such as fonts and icons in the current software interface, thereby avoiding the visual damage caused by the too close distance between the face of the user and the equipment due to difficult recognition of the software interface element by the user.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A cloud platform-based intelligent analysis method for software data is characterized in that: the method comprises the following steps:
s1: monitoring the use condition of a user on a software interface to acquire related data of the use of the software by the user;
s2: analyzing the related data obtained by monitoring, judging whether the software interface elements of the user need to be automatically adjusted, and according to the analysis result, combining the related information of the user equipment to adjust the software interface elements when the software interface elements of the user need to be automatically adjusted;
s3: when the software interface element is automatically adjusted, collecting feedback data of the user on the automatic adjustment of the software interface element, and modeling the user according to the feedback data of the user;
s4: corresponding management is carried out on the software account of the user according to the user modeling in the S3, and configuration updating is carried out on the relevant attribute of the software account of the user;
step S3-1: when the software interface element is automatically adjusted, feedback data of the user for automatically adjusting the software interface element is collected, wherein the feedback data comprise waiting time t 'for waiting for a user to respond by the software after the software interface element is automatically adjusted and distance change value d' of the user from the software interface within the waiting time; the feedback data are arranged into a matrix F, wherein each row represents one sample, and each column represents one feature; mapping the corresponding visual recognition obstacle label into a vector, wherein each element in the vector represents a label of one sample;
Step S3-2: the minimum value and the maximum value of the feature are used for carrying out linear change on the feature matrix, and the feature value is scaled to be in the range of [0,1 ]; converting the characteristics of the feedback data into a vector form to generate a two-dimensional characteristic vector; the feature mapping is performed by the following formula:
K(v i ,v j )＝tanh(θ×v i T v j +ε)；
wherein v is i And v j Respectively represent the input eigenvectors, v i T Representing v i Is a transpose of (2); θ and ε are adjustable super parameters preset by related personnel; the tanh function is a nonlinear activation function;
step S3-3: establishing a user classification model according to the following formula, and obtaining a prediction result Y by inputting a feature vector v' of user feedback data to be distinguished:
where u represents the number of samples in the feedback data; sign () represents a sign function; alpha i A Lagrangian multiplier representing a feature vector corresponding to the ith input; beta i A class label representing an ith feedback data sample in a training set of the input model; b is a bias term;
y is the output result of the user classification model and is used for judging the type of the user feedback data; when Y >0, the user feedback data is judged to be positive, which means that the visual recognition obstacle label is required to be added in the user modeling; when Y is less than or equal to 0, the user feedback data is judged to be negative, which means that the visual recognition obstacle label is not added in the user modeling.
2. The intelligent analysis method for software data based on the cloud platform as claimed in claim 1, wherein the intelligent analysis method is characterized by comprising the following steps: in the step S1, operation related data of a user on a software interface is obtained by recording the operation of the user on the software interface, and the operation related data of the user on the software interface is preprocessed to generate a user operation related data set C, c= { T, M }; wherein T represents a waiting time length set for waiting for a user response time, t= { T1, T2, & gt, tn }, where T1, T2, & gt, tn represent waiting time lengths for waiting for the user response by the software for the 1 st, 2 nd, n times, respectively, and n represents the total number of times for waiting for the user response operation by the acquired software; m represents the set of invalid operations within the waiting user response time, m= { M1, M2, -, mn, wherein, M1, M2, & mn represent the number of invalidation operations within the response time of the stand-by user, respectively, 1, 2, & n times;
acquiring setting parameters of a user on software interface elements according to user-defined settings of the user on the software, and acquiring the use frequency and the use time length of the user on the software interface through log inquiry or plug-in; when the access right of the user equipment is acquired, acquiring the related information of the user equipment and the software use environment data of the user at the current equipment; preprocessing acquired user software by using environment data to generate a user environment data set H, H= { L, D }; wherein L represents an ambient light data set in waiting user response time, l= { L1, L2,..once, ln }, L1, L2,..once, ln represents ambient light index in waiting user response time of 1 st, 2 nd..once, n times of software respectively, D represents a distance change value of the user from the software interface in waiting user response time of d= { D1, D2,..once, dn }, D1, D2,..once, dn represents a distance change value of the user from the software interface in waiting user response time of 1 st, 2 nd..once, n times of software respectively.
3. The intelligent analysis method for software data based on the cloud platform as claimed in claim 2, wherein the intelligent analysis method is characterized by comprising the following steps: the step S2 comprises the following steps:
step S2-1: extracting a preprocessed user operation related data set C and a preprocessed user environment data set H according to the monitoring data obtained in the step S1, and converting original data in the extracted two data sets; carrying out standardization or normalization treatment on the converted original data, and splitting the treated data into a training set and a testing set;
step S2-2: constructing a judgment model through the training set in the step S2-1, marking one type of the training set which represents that the training set needs to be adjusted as positive, marking the class label as y=1, marking the other type of the training set which represents that the training set does not need to be adjusted as negative, marking the class label as y=0, and modeling according to the following formula:
P(y＝1|x)＝1/(1+e zx+b )；
where x represents an input feature, and P (y= 1|x) represents a probability that the result is discriminated as 1 given the input feature x; e represents the bottom of natural logarithm, z is the transpose of the weight matrix W, and b is the bias parameter;
the weight matrix W and the bias parameter b are determined according to the following steps:
a1: the loss function S is defined according to the following formula:
S(W,b)＝-[y*log(P(y＝1|x))+(1-y)*log(1-P(y＝1|x))]；
a2: obtaining gradient information of a weight matrix W and a bias parameter b by deriving a loss function, wherein the gradient of the loss function to the weight matrix W is as follows: dS/dw=x (P (y= 1|x) -y);
The gradient of the loss function to the bias parameter b is: dS/db=P (y= 1|x) -y;
a3: updating the weight matrix W and the bias parameter b according to the gradient information and the learning rate a:
W＝W-a*dS/dW；
b＝b-a*dS/db；
the learning rate a represents the super-parameter for controlling the magnitude of the parameter updating amplitude at each time and is preset by related personnel;
a4: repeating the steps A2 and A3 until convergence of the loss function value reaches a preset termination condition, and updating to obtain a weight matrix W and a bias parameter b;
step S2-3: when the prediction performance of the judgment model meets the actual requirement after the judgment model is evaluated, predicting the newly acquired related data of the user using software by using the trained judgment model; when the probability value P (y= 1|x) calculated by the judgment model is larger than or equal to a preset threshold value q, the class label of the related data of the newly acquired user using software is y=1, and the prediction result is a positive example, and automatic adjustment is needed for the current software interface element of the user; when the probability value P (y= 1|x) calculated by the judgment model is smaller than a preset threshold value q, the predicted result is a negative example, and automatic adjustment of the current software interface element of the user is not needed;
step S2-4: and (3) when the software interface elements of the user are required to be automatically adjusted according to the prediction result of the discrimination model, increasing the fonts and icons in the current software interface according to the pixel density and the size of the screen of the user equipment if the distance change value of the user from the software interface continuously increases and exceeds the preset distance change value d within the current waiting user response time according to the related information of the user equipment acquired in the step (S1).
4. The intelligent analysis method for software data based on the cloud platform as claimed in claim 1, wherein the intelligent analysis method is characterized by comprising the following steps: in the step S4, managing the software account of the user according to the user modeling in the step S3; when the user modeling indicates that the current user has visual recognition obstacle, storing corresponding software interface recommendation attribute configuration of the user modeling into a software database according to user permission, setting software interface elements according to relevant data of user equipment, and updating relevant data of a user account.
5. A cloud platform-based intelligent analysis system for executing the cloud platform-based intelligent analysis method for software data according to claim 1, wherein: the system comprises: the system comprises a software data monitoring module, a monitoring data analysis module, a user feedback detection module and a software interface management module;
the software data monitoring module is used for monitoring operation data and behavior data when a user uses software, and transmitting relevant data obtained by monitoring to the monitoring data analysis module;
the monitoring data analysis module is used for analyzing the related data obtained by monitoring and judging whether the current software interface needs to be adjusted according to the operation data and the behavior data when the user uses the software;
The user feedback detection module is used for detecting the user related data after the software interface is adjusted, and generating user modeling through mining the user related data;
the software interface management module is used for correspondingly managing the software interface of the user according to the analysis result of the monitoring data analysis module, and correspondingly configuring and updating the software setting according to user modeling;
the output end of the software data monitoring module is connected with the input ends of the monitoring data analysis module and the user feedback detection module, and the output ends of the monitoring data analysis module and the user feedback detection module are connected with the input end of the software interface management module.
6. The intelligent analysis system for software data based on a cloud platform as claimed in claim 5, wherein: the software data monitoring module comprises a user operation acquisition unit, a user behavior acquisition unit and a monitoring data management unit;
the user operation acquisition unit is used for acquiring software operation data of a user in the software use process;
the user behavior acquisition unit is used for acquiring human behavior data of a user in the software use process;
The monitoring data management unit is used for preprocessing and storing the related data obtained by monitoring and transmitting the preprocessed monitoring data to the monitoring data analysis module.
7. The intelligent analysis system for software data based on a cloud platform as claimed in claim 5, wherein: the monitoring data analysis module comprises a monitoring data extraction unit and a data analysis unit;
the monitoring data extraction unit is used for extracting the received monitoring data, acquiring partial data required by data analysis and generating a corresponding data set;
the data analysis unit is used for analyzing the user state according to the monitoring data set and judging whether the current software interface needs to be adjusted.
8. The intelligent analysis system for software data based on a cloud platform as claimed in claim 5, wherein: the user feedback detection module comprises a feedback data acquisition unit and a user modeling generation unit;
the feedback data acquisition unit is used for acquiring user behavior data after the software interface is adjusted to obtain feedback data of the user for automatically adjusting the software interface elements;
the user modeling generating unit is used for mining the user behavior according to the collected feedback data and modeling the user.
9. The intelligent analysis system for software data based on a cloud platform as claimed in claim 5, wherein: the software interface management module comprises a software data adjustment unit and a user account management unit;
the software data adjusting unit is used for adjusting corresponding parameters of the software interface elements according to the judging result of the data analyzing unit and in combination with the monitoring data of the software data monitoring module;
the user account management unit is used for managing accounts of users in the software database according to the modeling result of the user modeling generation unit, storing and updating user labels obtained by user modeling, and recording corresponding parameters of the software interface elements according to the user labels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311468819.6A CN117421084B (en) | 2023-11-07 | 2023-11-07 | Cloud platform-based intelligent software data analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311468819.6A CN117421084B (en) | 2023-11-07 | 2023-11-07 | Cloud platform-based intelligent software data analysis system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117421084A CN117421084A (en) | 2024-01-19 |
| CN117421084B true CN117421084B (en) | 2024-03-22 |
Family
ID=89526268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311468819.6A Active CN117421084B (en) | 2023-11-07 | 2023-11-07 | Cloud platform-based intelligent software data analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117421084B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9930102B1 (en) * | 2015-03-27 | 2018-03-27 | Intuit Inc. | Method and system for using emotional state data to tailor the user experience of an interactive software system |
| CN110929196A (en) * | 2019-11-26 | 2020-03-27 | 泰康保险集团股份有限公司 | Display method and device of mobile terminal Web page |
| CN113467673A (en) * | 2021-05-24 | 2021-10-01 | 康键信息技术（深圳）有限公司 | Mobile terminal interface arrangement method, device, equipment and storage medium |
| WO2021216175A1 (en) * | 2020-04-24 | 2021-10-28 | Microsoft Technology Licensing, Llc | Utilization of predictive gesture analysis for preloading and executing application components |
| CN113885979A (en) * | 2021-09-18 | 2022-01-04 | 航天信息股份有限公司 | Method and device for intelligently adjusting user interface |
| CN114296857A (en) * | 2021-12-29 | 2022-04-08 | 北京五八信息技术有限公司 | Interface adjusting method and device, electronic equipment and readable medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11868595B2 (en) * | 2021-06-11 | 2024-01-09 | Roku, Inc. | Intelligent user interface customization for one-handed use |
-
2023
- 2023-11-07 CN CN202311468819.6A patent/CN117421084B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9930102B1 (en) * | 2015-03-27 | 2018-03-27 | Intuit Inc. | Method and system for using emotional state data to tailor the user experience of an interactive software system |
| CN110929196A (en) * | 2019-11-26 | 2020-03-27 | 泰康保险集团股份有限公司 | Display method and device of mobile terminal Web page |
| WO2021216175A1 (en) * | 2020-04-24 | 2021-10-28 | Microsoft Technology Licensing, Llc | Utilization of predictive gesture analysis for preloading and executing application components |
| CN113467673A (en) * | 2021-05-24 | 2021-10-01 | 康键信息技术（深圳）有限公司 | Mobile terminal interface arrangement method, device, equipment and storage medium |
| CN113885979A (en) * | 2021-09-18 | 2022-01-04 | 航天信息股份有限公司 | Method and device for intelligently adjusting user interface |
| CN114296857A (en) * | 2021-12-29 | 2022-04-08 | 北京五八信息技术有限公司 | Interface adjusting method and device, electronic equipment and readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117421084A (en) | 2024-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zliobaite et al. | Adaptive preprocessing for streaming data | |
| CN112163165A (en) | Information recommendation method, device, equipment and computer readable storage medium | |
| CN110516210B (en) | Text similarity calculation method and device | |
| Sangeetha et al. | A hybrid optimization algorithm using BiLSTM structure for sentiment analysis | |
| CN111523421A (en) | Multi-user behavior detection method and system based on deep learning and fusion of various interaction information | |
| JP6971514B1 (en) | Information processing equipment, information processing methods and programs | |
| CN116994709A (en) | Personalized diet and exercise recommendation method and system and electronic equipment | |
| CN112819024B (en) | Model processing method, user data processing method and device and computer equipment | |
| CN117390499A (en) | Be applied to multiple sample detecting system that food pesticide remained and detected | |
| CN111078546A (en) | Method for expressing page features and electronic equipment | |
| CN117061322A (en) | Internet of things flow pool management method and system | |
| CN113326384A (en) | Construction method of interpretable recommendation model based on knowledge graph | |
| CN112016769A (en) | Method and device for managing relative person risk prediction and information recommendation | |
| CN117992743A (en) | Intelligent analysis and treatment method and system for power grid faults based on knowledge graph | |
| CN117475806B (en) | Display screen self-adaptive response method and device based on multidimensional sensing data feedback | |
| KR102190304B1 (en) | preferred content recommending apparatus based on GPU computing Using deep learning and method therefor | |
| CN114330482A (en) | Data processing method and device and computer readable storage medium | |
| CN117421084B (en) | Cloud platform-based intelligent software data analysis system and method | |
| CN115794898B (en) | Financial information recommendation method and device, electronic equipment and storage medium | |
| CN111767404A (en) | Event mining method and device | |
| Corpuz | An application method of long short-term memory neural network in classifying english and tagalog-based customer complaints, feedbacks, and commendations | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| CN115238645A (en) | Asset data identification method and device, electronic equipment and computer storage medium | |
| Malhotra et al. | A neuro-fuzzy classifier for website quality prediction | |
| CN113407808A (en) | Method and device for judging applicability of graph neural network model and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |