CN118430111A - Intelligent doorbell user behavior analysis system - Google Patents
Intelligent doorbell user behavior analysis system Download PDFInfo
- Publication number
- CN118430111A CN118430111A CN202410799278.3A CN202410799278A CN118430111A CN 118430111 A CN118430111 A CN 118430111A CN 202410799278 A CN202410799278 A CN 202410799278A CN 118430111 A CN118430111 A CN 118430111A
- Authority
- CN
- China
- Prior art keywords
- behavior
- result
- data
- formula
- analysis
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 106
- 230000006399 behavior Effects 0.000 claims abstract description 220
- 238000012545 processing Methods 0.000 claims abstract description 77
- 238000012544 monitoring process Methods 0.000 claims abstract description 55
- 230000004044 response Effects 0.000 claims abstract description 38
- 230000003993 interaction Effects 0.000 claims abstract description 15
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000003860 storage Methods 0.000 claims abstract description 10
- 238000003909 pattern recognition Methods 0.000 claims abstract description 7
- 230000035945 sensitivity Effects 0.000 claims description 33
- 230000000694 effects Effects 0.000 claims description 28
- 238000013468 resource allocation Methods 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 21
- 230000003542 behavioural effect Effects 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 12
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 9
- 238000013139 quantization Methods 0.000 claims description 7
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 230000003321 amplification Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 230000007774 longterm Effects 0.000 claims description 4
- 230000009022 nonlinear effect Effects 0.000 claims description 4
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 4
- 238000012805 post-processing Methods 0.000 claims description 4
- 238000007670 refining Methods 0.000 claims description 4
- 230000004043 responsiveness Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 238000005728 strengthening Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000009795 derivation Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012803 optimization experiment Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/26—Discovering frequent patterns
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/186—Video door telephones
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of user behavior analysis, in particular to an intelligent doorbell user behavior analysis system, which comprises an event-driven behavior analysis module, an asynchronous visitor data processing module, a behavior pattern recognition module and a customized security policy module. In the present invention. By introducing event-driven processing logic and asynchronous data technology, the system efficiently manages and accurately analyzes user behavior data, real-time adjusts doorbell CPU and storage resources through user interaction trigger events, optimizes system performance, dynamically allocates computing resources, utilizes time sequence analysis to deeply identify user behavior patterns, predicts future behaviors, enhances system prediction capacity and safety, customizes security policies to adjust monitoring policies according to behavior trends, deals with high-access time periods, pertinently enhances security measures, provides personalized experience, improves living and working environment safety and convenience, ensures efficient utilization of resources and optimizes system response speed.
Description
Technical Field
The invention relates to the technical field of user behavior analysis, in particular to an intelligent doorbell user behavior analysis system.
Background
The technical field of user behavior analysis, which aims to identify, record and interpret individual behaviors in a specific environment or system through various data processing and analysis technologies, utilizes algorithms and machine learning technologies to extract meaningful patterns from a large amount of user interaction data, aims to understand behavior habits of users, predict future behaviors or make personalized service adjustments, can help enterprises or service providers optimize product designs, improve user experience, and improve safety, for example, prevent fraud by identifying abnormal behaviors, and is a key tool for improving service quality and efficiency.
The intelligent doorbell user behavior analysis system is a system combining intelligent doorbell equipment and user behavior analysis technology, and the system is mainly used for enhancing safety and convenience of living or working environments by analyzing behavior patterns of individuals in front of doors. The video or image data is collected through the camera installed in the doorbell, and the system can identify and classify different behaviors of the visitor, such as residence time, access frequency and the like, so that early warning of suspicious behaviors or automatic access control management of the resident are realized, and the system is also used for improving the dynamic perception capability of the resident to the visitor, so that more intelligent and personalized visitor reception service is provided.
The existing intelligent doorbell user behavior analysis system is dependent on a traditional data processing method when processing a large amount of user interaction data, and has obvious defects in real-time performance and resource optimization. Particularly in the aspects of user behavior prediction and abnormal behavior recognition, the existing system cannot effectively utilize a time sequence analysis technology, so that understanding of a user behavior mode is not deep enough, and potential safety risks cannot be predicted. The prior art does not support dynamic resource allocation, so that the system is poor in performance, response delay and influence on user experience and overall safety of the system in a high-load period, and the deficiency causes poor effects in safety monitoring and personalized service adjustment, so that market competitiveness and user satisfaction of products are influenced.
Disclosure of Invention
The application provides the intelligent doorbell user behavior analysis system, and the existing intelligent doorbell user behavior analysis system has obvious defects in real-time performance and resource optimization due to the fact that the existing intelligent doorbell user behavior analysis system depends on a traditional data processing method when processing a large amount of user interaction data. Particularly in the aspects of user behavior prediction and abnormal behavior recognition, the existing system cannot effectively utilize a time sequence analysis technology, so that understanding of a user behavior mode is not deep enough, and potential safety risks cannot be predicted. The prior art does not support dynamic resource allocation, so that the system is poor in performance, response delay and influence on user experience and overall safety of the system in a high-load period, and the deficiency causes poor effects in safety monitoring and personalized service adjustment, so that the market competitiveness of products and the user satisfaction are influenced.
In view of the above, the present application provides an intelligent doorbell user behavior analysis system.
The application provides an intelligent doorbell user behavior analysis system, wherein the system comprises:
the event-driven behavior analysis module receives intelligent doorbell user interaction, triggers event processing, records details, classifies the details into a priority queue to obtain an event classification result, adjusts doorbell CPU and storage resources according to the event classification result, optimizes performance and obtains a resource allocation result;
The asynchronous visitor data processing module processes the differentiated event through an asynchronous processing technology based on the resource allocation result, triggers video recording and behavior analysis, distributes tasks to a differentiated processing unit for execution to obtain a parallel processing result, and carries out callback on data processed by the parallel processing result to obtain a callback determination result;
the behavior pattern recognition module performs pattern recognition on the user behavior data by adopting time sequence analysis based on the callback determination result, recognizes abnormal behaviors, obtains a behavior trend analysis result, performs behavior prediction by using the behavior trend analysis result, predicts a user activity pattern in a future time period, and obtains a behavior prediction result;
And the customized security policy module adjusts the response policy of the doorbell and matches the differentiated user behavior mode in the period of the predicted access amount by strengthening monitoring according to the behavior prediction result to obtain a dedicated security policy, and dynamically optimizes according to the user feedback and the monitoring data of the dedicated security policy to obtain an upgrade protection scheme.
Preferably, the step of obtaining the resource allocation result specifically includes:
receiving intelligent doorbell user interaction, collecting user interaction data of the intelligent doorbell, classifying the data according to event types, and respectively calculating occurrence frequency and priority for each event type by using the formula:
An event weight array is generated, wherein, Is the weight of the event and,Represent the firstThe frequency of occurrence of the class event,Represent the firstThe priority of the class event(s),Is a trade-off between frequency and priority,AndAdjusting the sensitivity of the frequency input;
and carrying out resource demand evaluation on the event weight array, and calculating a formula:
Generating an array of resource requirements, wherein, Is a need for resources such as a pool of resources,The weight of the event is represented as,Representing the coefficients of demand of the CPU,Representing the coefficient of the storage demand and,Is a resource demand adjustment coefficient;
based on the resource demand array, dynamically adjusting the resource allocation of the intelligent doorbell according to the resource demand by using an optimization algorithm, wherein a calculation formula is as follows:
generating a resource allocation result, wherein, Is the result of resource allocation and the method is that,Is a need for resources such as a pool of resources,Is a parameter of the sensitivity of the resource adjustment,Is the threshold value of the threshold,Is a global adjustment coefficient.
Preferably, the step of obtaining the parallel processing result specifically includes:
based on the asynchronous visitor data of the resource allocation result, the parts are classified according to the type and the characteristics of the data, and the formula is adopted:
Generating a differential event classification result, wherein, Representing the differential event classification result,Is an event typeIs used to determine the sensitivity coefficient of the (c),Is a parameter of the time of day,AndThe sensitivity and the offset of the classification are adjusted,AndIs an additional regulatory factor;
Based on the differential event classification result, triggering a video recording task by adopting the formula:
generating an array of video recording tasks, wherein, Represent the firstThe quantization result of the video-like recording task,Is the result of the classification of the event by differentiation,Is a parameter of the demand of the basic video,Is an adjustment coefficient;
according to the video recording task array, assigning tasks to the differentiated processing units, and applying the formula:
generating an allocation result of the behavior analysis task, wherein, Is allocated to unitsIs used for analyzing the task amount of the behavior,Is the result of the quantization of the video recording task,Is a unitIs used for the processing power of the (c) in the (c),Is the total number of processing units;
and carrying out parallel processing according to the distribution result of the behavior analysis task, and adopting the formula:
generating a parallel processing result, wherein, Representing the results of the parallel processing,Is allocated to unitsIs used for analyzing the task amount of the behavior,AndIs the tuning parameter for parallel processing.
Preferably, the step of obtaining the callback determination result specifically includes:
initializing a data callback process according to the parallel processing result, and adopting the formula:
adjusting sensitivity and threshold of data callback, generating preliminary callback response array, wherein, Representing a preliminary callback response,Is the result of the parallel processing of the data,AndIs a parameter that adjusts the sensitivity and threshold,Is an amplification factor that enhances responsiveness;
verifying the callback response, and applying the formula:
generating an array of validated callback results, wherein, Is a callback result that is verified and is,Is a preliminary callback response that is sent to the user,Is an index of the integrity of the data,Is a threshold of the desired integrity value and,Is a weight adjustment index;
Executing a determining process according to the verified callback result array, and adopting a formula:
generating a callback determination result, wherein, Representing the callback determination result,Is the callback result after the verification,AndIs the tuning parameter for parallel processing.
Preferably, the step of obtaining the behavioral trend analysis result specifically includes:
based on the callback determination result, processing and standardizing the user behavior data, and applying the formula:
the processed behavior data is generated, wherein, Representing the post-processing behavior data,Is a callback determination result,Is the weight coefficient of the data point;
performing time sequence analysis on the processed behavior data, identifying a mode and abnormal behaviors, and adopting a formula:
generating a behavior pattern analysis result, wherein, Is the result of the analysis of the behavior pattern,AndThe processed behavior data of the previous time point and the current time point respectively,Is a coefficient for smoothing;
Based on the analysis result of the behavior pattern, analyzing and identifying the long-term behavior trend, and adopting the formula:
Generating a behavioral trend analysis result, wherein, Representing the results of the behavioral trend analysis,Is the result of the analysis of the behavior pattern,Is a coefficient of standardization that is set to be a standard,Is a small amount of the total of all the components,Is a coefficient that adjusts the sensitivity of the behavioral trend response.
Preferably, the step of obtaining the behavior prediction result specifically includes:
Based on the behavioral trend analysis results, key time series data points are extracted, and the formula is applied:
The extracted behavior trend data is generated, wherein, The extracted behavior trend data is represented,Is the point in timeIs a function of the behavior trend data of the (c),Is a time-decay factor that is a function of the time,Representing a time offset parameter;
And simulating a user activity mode in a future time period by using the extracted behavior trend data, wherein the method adopts the following formula:
A simulated future activity pattern is generated, wherein, Is a simulated future activity pattern of the device,Is the extracted behavior trend data,Is the adjustment coefficient of the light source,AndA characteristic of the periodic variation is defined,
Based on the simulated future activity pattern, a predicted behavior is calculated, applying the formula:
generating a behavior prediction result, wherein, Representing the result of the prediction of the behaviour,Is a simulated future activity pattern of the device,Is the length of the predicted time period,Is a weighting factor.
Preferably, the step of obtaining the dedicated security policy specifically includes:
calculating monitoring intensity by using the behavior prediction result, and adopting the formula:
Strengthen nonlinear effect, generate monitoring intensity adjusting standard, wherein, Representing the reference for the adjustment of the monitoring intensity,Is the result of the prediction of the behaviour,Is the adjustment coefficient of the light source,Is a behavioral impact index;
And according to the monitoring intensity adjustment standard, a strategy facing the high access amount time period is formulated, and the following formula is applied:
refining the response policy, generating a refined monitoring policy, wherein, Is a monitoring strategy after the refinement of the method,Is a reference for monitoring the adjustment of the intensity,AndIs a factor of the regulation and is used for regulating the quantity of the liquid,
According to the refined monitoring strategy, combining with differentiated user behavior modes, formulating an exclusive security strategyThe formula is as follows:
generating a proprietary security policy, wherein, In order to be a proprietary security policy,Is a parameter for the individual adjustment of the parameters,Is a refined monitoring strategy.
Preferably, the step of obtaining the upgrade protection scheme specifically includes:
Capturing user feedback data based on the exclusive security policy, summarizing the associated data for processing, monitoring the data in real time, summarizing the data, analyzing the processed and processed data, and generating a user feedback and monitoring data set;
Analyzing the user feedback and monitoring data set, identifying a key behavior pattern, using the formula:
generating a behavior pattern analysis result, wherein, Representing the weighted behavior pattern analysis results,Is the weight of the sample, and the weight of the sample,Is a data point that is to be read,Is the total number of data points,Is a small positive number;
According to the behavior pattern analysis result, combining dynamic adjustment parameters, and applying the formula:
an upgrade protection scheme is generated, wherein, Representing an upgrade protection scheme,Is the result of the analysis of the behavior pattern,、Is a parameter for adjusting the protection scheme,The sensitivity of the threshold value is controlled,The reaction rate of the time span is adjusted,A time threshold is defined for starting the adjustment.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
By introducing event-driven processing logic and asynchronous data processing technology, efficient management and accurate analysis of user behavior data are realized, doorbell CPU and storage resources are adjusted in real time by receiving events triggered by user interaction, system performance is effectively optimized, computing resources are dynamically allocated for different events, a time sequence analysis is utilized to deeply identify user behavior patterns and predict future behavior patterns, the prediction capacity of the system is enhanced, safety is also improved, a customized safety strategy is used for responding to a high access amount period by analyzing behavior trends, a monitoring strategy is adjusted, safety measures are pertinently enhanced, personalized user experience is provided, safety and convenience of living and working environments are improved, and more efficient resource utilization and better system response speed are ensured.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a flow chart showing an overall system for analyzing user behavior of an intelligent doorbell according to the present invention;
FIG. 2 is a flow chart showing the result of resource allocation of an intelligent doorbell user behavior analysis system according to the present invention;
FIG. 3 is a flow chart showing the parallel processing results of an intelligent doorbell user behavior analysis system according to the present invention;
FIG. 4 is a flow chart showing the callback determination result of an intelligent doorbell user behavior analysis system according to the present invention;
FIG. 5 is a flow chart showing the results of behavior trend analysis of an intelligent doorbell user behavior analysis system according to the present invention;
FIG. 6 is a flow chart showing the behavior prediction results of an intelligent doorbell user behavior analysis system according to the present invention;
FIG. 7 is a flow chart of a proprietary security policy of an intelligent doorbell user behavior analysis system according to the present invention;
fig. 8 is a flowchart of an upgrade protection scheme of an intelligent doorbell user behavior analysis system according to the present invention.
Detailed Description
The application provides an intelligent doorbell user behavior analysis system.
Summary of the application
The intelligent doorbell user behavior analysis system in the prior art is dependent on the traditional data processing method when processing a large amount of user interaction data, and has obvious defects in real-time performance and resource optimization. Particularly in the aspects of user behavior prediction and abnormal behavior recognition, the existing system cannot effectively utilize a time sequence analysis technology, so that understanding of a user behavior mode is not deep enough, and potential safety risks cannot be predicted. The prior art does not support dynamic resource allocation, so that the system is poor in performance, response delay and influence on user experience and overall safety of the system in a high-load period, and the deficiency causes poor effects in safety monitoring and personalized service adjustment, so that market competitiveness and user satisfaction of products are influenced.
Aiming at the technical problems, the technical scheme provided by the application has the following general thought.
Examples
As shown in fig. 1, the present application provides an intelligent doorbell user behavior analysis system, wherein the system comprises:
The event-driven behavior analysis module receives intelligent doorbell user interaction, triggers event processing, records details, classifies the details into a priority queue to obtain event classification results, adjusts doorbell CPU and storage resources according to the event classification results, optimizes performance and obtains resource allocation results.
The asynchronous visitor data processing module processes the differentiated event through an asynchronous processing technology based on the resource allocation result, triggers video recording and behavior analysis, distributes tasks to the differentiated processing unit for execution, obtains a parallel processing result, and carries out callback aiming at data processed by the parallel processing result to obtain a callback determination result.
And the behavior pattern recognition module performs pattern recognition on the user behavior data by adopting time sequence analysis based on the callback determination result, recognizes abnormal behaviors to obtain a behavior trend analysis result, performs behavior prediction by using the behavior trend analysis result, predicts the user activity pattern in a future time period, and obtains a behavior prediction result.
And the customized security policy module adjusts the response policy of the doorbell and matches the differentiated user behavior mode in the period of the predicted access amount by strengthening monitoring according to the behavior prediction result to obtain an exclusive security policy, and dynamically optimizes according to the user feedback and the monitoring data of the exclusive security policy to obtain an upgrade protection scheme.
The event classification result comprises event level, resource demand type and performance adjustment demand, the resource allocation result comprises CPU core allocation, storage capacity configuration and performance optimization level, the parallel processing result comprises processing task type, task completion state and efficiency index, the callback determination result comprises data integrity level, matching accuracy and abnormal activity identification, the behavior trend analysis result comprises behavior pattern change, abnormal activity frequency and user activity trend, the behavior prediction result comprises prediction activity type, potential risk level and prediction reliability, the exclusive security policy comprises monitoring intensity adjustment, response speed setting and user behavior adaptability, and the upgrading protection scheme comprises monitoring upgrading details, feedback optimization policy and optimization measure implementation effect.
Specifically, as shown in fig.2, the steps for obtaining the resource allocation result specifically include:
receiving intelligent doorbell user interaction, collecting user interaction data of the intelligent doorbell, classifying the data according to event types, and respectively calculating occurrence frequency and priority for each event type by using the formula:
An event weight array is generated, wherein, Is the weight of the event and,Represent the firstThe frequency of occurrence of the class event,Represent the firstThe priority of the class event(s),Is a trade-off between frequency and priority,AndAdjusting the sensitivity of the frequency input;
carrying out resource demand evaluation on the event weight array, and calculating a formula:
Generating an array of resource requirements, wherein, Is a need for resources such as a pool of resources,The weight of the event is represented as,Representing the coefficients of demand of the CPU,Representing the coefficient of the storage demand and,Is a resource demand adjustment coefficient;
based on the resource demand array, dynamically adjusting the resource allocation of the intelligent doorbell according to the resource demand by using an optimization algorithm, wherein a calculation formula is as follows:
generating a resource allocation result, wherein, Is the result of resource allocation and the method is that,Is a need for resources such as a pool of resources,Is a parameter of the sensitivity of the resource adjustment,Is the threshold value of the threshold,Is a global adjustment coefficient.
Weight formula derivation of events:
； : the frequency of occurrence of event i, assuming the value: ；
: priority of event i, assume the value: (priority ranges from 1 to 10);
: frequency versus priority trade-off coefficient, assume the value: ；
: the sensitivity of the function is adjusted, assuming the value: ；
: baseline frequency offset, assumed value: ；
calculating an index part: ；
calculating the inverse of the exponential function: ；
Calculating final weight: ；
Representing the weight of the event i, taking into account the frequency and priority of occurrence of the event, and the adjustment calculation of the frequency offset Indicating a score of importance for the event.
Equation derivation of resource demand:；
: the weight of the event, assumed to be 81.89;
: CPU demand coefficient, assumed value: ；
: storing a demand coefficient, assuming values: ；
: resource requirement adjustment coefficients. Assume values: Calculating a flow;
Computing resource demand radix: ；
calculating the product of the total requirements: ；
The square root of the total demand is calculated: ；
And (3) adjusting resource requirements: ；
is the resource demand value obtained by calculation, comprehensively considers the weight of the event and the demand on CPU and storage, and adjusts the coefficient And obtaining a final resource demand score.
Formula derivation of resource allocation results:
；
: resource demand, assumption value: (assuming the same for all events);
: resource adjustment sensitivity parameter, assumed value: ；
: threshold, assumed value: ；
: global adjustment coefficients, assumed values: ；
assume that there are 3 events, i.e ；
Calculating an adjustment section for each event:；
calculating the inverse of the exponential function: ；
calculating the adjusted resource requirement for each event: ；
Is the resource allocation result, which represents the total resource allocated by the system to all events after dynamic adjustment, and is calculated Indicating the system's response resource configuration to the event.
Specifically, as shown in fig. 3, the parallel processing result obtaining step specifically includes:
asynchronous visitor data based on resource allocation results are classified according to types and characteristics of the data, and the formula is adopted:
Generating a differential event classification result, wherein, Representing the differential event classification result,Is an event typeIs used to determine the sensitivity coefficient of the (c),Is a time parameter, c and d adjust the sensitivity and offset of the classification,AndIs an additional regulatory factor;
based on the differential event classification result, triggering a video recording task by adopting the formula:
generating an array of video recording tasks, wherein, Represent the firstThe quantization result of the video-like recording task,Is the result of the classification of the event by differentiation,Is a parameter of the demand of the basic video,Is an adjustment coefficient;
according to the video recording task array, the tasks are distributed to a differentiated processing unit, and the formula is applied:
generating an allocation result of the behavior analysis task, wherein, Is allocated to unitsIs used for analyzing the task amount of the behavior,Is the result of the quantization of the video recording task,Is a unitIs used for the processing power of the (c) in the (c),Is the total number of processing units;
Parallel processing is carried out according to the distribution result of the behavior analysis task, and the formula is adopted:
generating a parallel processing result, wherein, Representing the results of the parallel processing,Is allocated to unitsIs used for analyzing the task amount of the behavior,AndIs the tuning parameter for parallel processing.
Generating a differential event classification result by the following formula:
；
: the sensitivity coefficient of the event type, assumed to be 0.5, means that the sensitivity of the occurrence of the event to time is moderate;
: time parameters, assuming this is the number of hours in a day, e.g. 12 (noon);
c, performing operation; parameters for adjusting the classification threshold, assuming 2, represent an adjustment with moderate amplitude;
: the adjustment factor, which enhances model flexibility, is assumed to be 1.5;
: an offset parameter, assumed to be 0.8, for fine tuning the threshold;
: another adjustment factor, for enhancing the nonlinear effect of the threshold, is assumed to be 0.7.
For eventsCalculation using the above parameters：
Final resultA specific point in time will be indicated, the probability of response to such an event.
First, theThe quantization result formula of the video-like recording task:
；
: differentiating event classification results;
: a base video demand parameter, assumed to be 3, which represents a high video demand;
: adjusting the coefficient, which is assumed to be 0.5, for adjusting the final result;
Assume that ，
The value of (2) indicates a weighted value for the video recording requirement for the event.
Assigned to unitsA behavior analysis task amount formula of (2):
； : video recording task amount; : unit cell Is assumed to be 4, indicating a higher processing capacity; : the total number of processing units, assuming 10 units;
Continue to use Is a value 1.5635 of:
The value of (2) indicates the quantized value of the behavior analysis task assigned to that cell.
Generating a parallel processing result by the following formula:
； : behavior analysis task amount; g. h: adjusting parameters, provided AndFor fine tuning the nonlinear response;
Using Is 0.394:
Calculating this formula will result in a composite value that represents the efficiency of the parallel processing.
Specifically, as shown in fig. 4, the step of obtaining the callback determination result specifically includes:
Initializing a data callback process according to the parallel processing result, and adopting the formula:
adjusting sensitivity and threshold of data callback, generating preliminary callback response array, wherein, Representing a preliminary callback response,Is the result of the parallel processing of the data,AndIs a parameter that adjusts the sensitivity and threshold,Is an amplification factor that enhances responsiveness;
verifying the callback response, and applying the formula:
generating an array of validated callback results, wherein, Is a callback result that is verified and is,Is a preliminary callback response that is sent to the user,Is an index of the integrity of the data,Is a threshold of the desired integrity value and,Is a weight adjustment index;
executing a determining process according to the verified callback result array, and adopting a formula:
generating a callback determination result, wherein, Representing the callback determination result,Is the callback result after the verification,AndIs the tuning parameter for parallel processing.
The calculation process formula of the preliminary callback response comprises the following steps:
； : parallel processing of the first A result; : an amplification factor for enhancing responsiveness; : sensitivity adjustment parameters; : a threshold parameter;
And (3) data acquisition: Directly from parallel processing systems, assuming ；
Parameter setting: setting upThe parameters are determined through a system optimization experiment or expert experience, and conform to the actual operation range.
The formula is substituted:
；
Calculation results:
Results Representing preliminary evaluation values of callback responses for given parameters and processing results.
The verified callback result formula:
； : preliminary callback response; : a data integrity indicator; : a desired integrity threshold; : weight adjustment index;
and (3) data acquisition: is provided with ，，; The formula is substituted:
；
Calculation results:
; results The validated callback results are represented, taking into account data integrity.
Generating a callback determination result formula:
； : a verified callback result; 、 : adjusting parameters of parallel processing efficiency; parameter setting: is provided with 、；
Formula substitution (assuming there are three results that are similar）：
; Calculation results:
Results And the total callback determination result is represented, and the comprehensive processing effect is represented.
Specifically, as shown in fig. 5, the steps for obtaining the behavioral trend analysis result specifically include:
based on the callback determination result, processing and standardizing the user behavior data, and applying the formula:
the processed behavior data is generated, wherein, Representing the post-processing behavior data,Is a callback determination result,Is the weight coefficient of the data point;
performing time sequence analysis on the processed behavior data, identifying a mode and abnormal behaviors, and adopting a formula:
generating a behavior pattern analysis result, wherein, Is the result of the analysis of the behavior pattern,AndThe processed behavior data of the previous time point and the current time point respectively,Is a coefficient for smoothing;
Based on the analysis result of the behavior pattern, analyzing and identifying the long-term behavior trend, and adopting the formula:
Generating a behavioral trend analysis result, wherein, Representing the results of the behavioral trend analysis,Is the result of the analysis of the behavior pattern,Is a coefficient of standardization that is set to be a standard,Is a small amount of the total of all the components,Is a coefficient that adjusts the sensitivity of the behavioral trend response.
The post-processing behavior data formula:
； : first, the The callback determination result can be obtained through the previous step; : data points Is set by a user based on the importance or reliability of the data points; : the processed behavior data is a weighted average value, and the influence of key data points is emphasized;
Assume that there are three callback determination junctions ，，And corresponding weights，，。
Calculating a weight square sum:，，；
calculating a weighted result:
；
；
Calculation of ：
；Representing the pre-processing result of behavior data after weighted averaging emphasizes the effect of higher weighted data points on the overall result.
Behavior pattern analysis result formula:
；
: smoothing coefficients for balancing weights of data points before and after in time series analysis, set by an analyst according to fluctuation of the data;
: the processed behavior data of the previous time point;
: the processed behavior data of the current time point;
: and analyzing results of the behavior patterns.
Assume that，，(From the previous calculation);
Calculation of ：
；Representing the behavior pattern analysis result after time sequence analysis, reflecting the comprehensive influence of the current data point and the previous data point;
The generation formula of the behavior trend analysis result is as follows:
；
: the normalization coefficient is used for adjusting the scale of the analysis result;
: a small amount of the method avoids logarithmic operation errors and is set as a very small positive number;
: the adjusting coefficient is used for controlling the sensitivity of logarithmic operation;
: and analyzing results of the behavior trend.
Assume that，，，(From the previous calculation);
Calculation of ：
And (3) representing a behavior trend analysis result, quantifying the long-term trend of the behavior pattern, and reflecting the stability or variability of the pattern.
Specifically, as shown in fig. 6, the step of obtaining the behavior prediction result specifically includes:
Based on the behavioral trend analysis results, key time series data points are extracted, and the formula is applied:
The extracted behavior trend data is generated, wherein, The extracted behavior trend data is represented,Is the point in timeIs a function of the behavior trend data of the (c),Is a time-decay factor that is a function of the time,Representing a time offset parameter;
and simulating a user activity mode in a future time period by using the extracted behavior trend data, and adopting the formula:
A simulated future activity pattern is generated, wherein, Is a simulated future activity pattern of the device,Is the extracted behavior trend data,、、Is the adjustment coefficient of the light source,AndA characteristic of the periodic variation is defined,
Based on the simulated future activity pattern, a predicted behavior is calculated, applying the formula:
generating a behavior prediction result, wherein, Representing the result of the prediction of the behaviour,Is a simulated future activity pattern of the device,Is the length of the predicted time period,Is a weighting factor.
The extracted behavior trend data formula:
: time point Assuming results derived from previous analyses;
: a time attenuation factor for controlling the attenuation of the influence of the time distance on the data;
: a time offset parameter for adjusting a focus of the data extraction;
Assume that: (considering the data at 5 time points), (The behavior trend values obtained by analysis),，；
The calculation process comprises the following steps: for each t (from 1 to 5), calculate：
；
Sum up: 4.52+5.42+7.41+5.91+2.02=25.28; results: this represents the integration of weighted behavioral trend data for 5 time points given decay and offset conditions.
Simulated future activity pattern formula:
；
Assume that: ，，， (assuming period is ，，(Calculating an analog value for a point in time);
The calculation process comprises the following steps:
；
Results: is shown in Predicted active mode value for time of day.
Behavior prediction result formula:
Since this is a theoretical calculation, the intent is described herein, and the specific integration and summation needs to be dependent on A complete expression of (c) and a numerical solution of the integral. Assume that:，；
Calculation hypothesis examples: simplification of Is 12.9871 atIs kept constant for a period of time;
; the integral result is ; The summation result is；
; Results: Representing the total amount of behavioural activity over the predicted period of time, indicates the aggressiveness or intensity of the model prediction.
Specifically, as shown in fig. 7, the specific security policy is obtained by the steps of:
Calculating the monitoring intensity by using the behavior prediction result, and adopting the formula:
Strengthen nonlinear effect, generate monitoring intensity adjusting standard, wherein, Representing the reference for the adjustment of the monitoring intensity,Is the result of the prediction of the behaviour,、Is the adjustment coefficient of the light source,Is a behavioral impact index;
and (3) according to the monitoring intensity adjustment standard, formulating a strategy facing the high access amount time period, and applying the formula:
refining the response policy, generating a refined monitoring policy, wherein, Is a monitoring strategy after the refinement of the method,Is a reference for monitoring the adjustment of the intensity,、、、AndIs a factor of the regulation and is used for regulating the quantity of the liquid,
According to the refined monitoring strategy, combining with differentiated user behavior mode, formulating an exclusive security strategyThe formula is as follows:
generating a proprietary security policy, wherein, In order to be a proprietary security policy,、、、Is a parameter for the individual adjustment of the parameters,Is a refined monitoring strategy.
Monitoring an intensity adjustment reference formula:
；
: the influence coefficient of the behavior prediction result can be obtained according to the past data analysis, and the coefficient is assumed to be 0.5;
: behavior influence index, which indicates the nonlinear influence degree of the prediction result, and is assumed to be 2;
: the basic monitoring intensity adjustment coefficient is determined through analysis of historical monitoring data and environmental factors, and is assumed to be 0.3;
: the behavior prediction result is output by the data analysis model, assuming 4 (meaning a medium behavior risk level).
Calculation of：；
Calculation of：；
Calculation of binding parameters：；
Final resultRepresenting an adjusted monitor intensity reference based on the current behavior prediction result.
And (3) refining a monitoring strategy formula:
；
: the high access response adjustment factor is adjusted according to the operation characteristics of the facility and the historical access data, and is assumed to be 0.8;
: the steepness of the curve, which represents the sensitivity of the response strategy, is assumed to be 1.5;
: the current access level is obtained by real-time data monitoring, and is assumed to be 10;
: an access amount reference threshold value, which is set according to historical data and is assumed to be 8;
: the base adjustment factor ensures a basic response also at low access, say 0.1.
The calculation flow is as follows: a calculation response adjustment section:
；
Adding basic adjustment factors to and with Combining:
；
Final result Representing the intensity of the monitoring policy refined for the high access period.
The formula of the exclusive security policy:
；
: a user behavior pattern adjustment factor, which is set according to the user behavior difference and is assumed to be 0.5;
: the steepness of the curve is adjusted to represent the sensitivity of the strategy to behavior change, and the assumption is 1;
: the user specific behavior index is output by the user behavior analysis model, and is assumed to be 5;
: a behavior reference threshold, which is set according to historical behaviors of the user group and is assumed to be 3;
Calculating a user behavior mode adjustment ratio:
；
Calculating final policy intensity: ；
Final result The specific security policy intensity customized according to the user behavior mode is represented, and the user behavior characteristics are matched more accurately.
Specifically, as shown in fig. 8, the step of obtaining the upgrade protection scheme specifically includes:
Based on the exclusive security policy, capturing user feedback data, summarizing the associated data for processing, monitoring the data in real time, summarizing the data, analyzing the processed and processed data, and generating a user feedback and monitoring data set;
Analyzing the user feedback and monitoring the data set, identifying a key behavior pattern, using the formula:
generating a behavior pattern analysis result, wherein, Representing the weighted behavior pattern analysis results,Is the weight of the sample, and the weight of the sample,Is a data point that is to be read,Is the total number of data points,Is a small positive number;
according to the analysis result of the behavior mode, combining the dynamic adjustment parameters, and applying the formula:
an upgrade protection scheme is generated, wherein, Representing an upgrade protection scheme,Is the result of the analysis of the behavior pattern,、Is a parameter for adjusting the protection scheme,The sensitivity of the threshold value is controlled,The reaction rate of the time span is adjusted,A time threshold is defined for starting the adjustment.
Formula derivation of weighted behavior pattern analysis results:
Parameter setting:
: there are 5 data points shown.
: The weight of each data point is assumed to be [0.2,0.2,0.2,0.2,0.2].
: Data point values, assumed to be [1,2,3,4,5];
: a small positive number for evading division by zero;
For each of Calculation of：
；
Calculating a weighted sum:
；
Calculation of ：；
Obtained byThe value is 0.581, which represents the weighted behavior pattern analysis result according to the given weight and data point.
Formula derivation of upgrade protection scheme:
；
Assume that ；
: Adjusting the sensitivity of the threshold;
: a current time;
: a time threshold;
: an adjustment coefficient of the time response;
: a threshold for time adjustment;
Calculating a threshold function:
；
calculating a time response function:
；
Calculating U:
；
Final end The value is 1.674, which represents the strength of the upgrade protection scheme calculated from the current time and the adjusted parameters.
Although the application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, it is intended that the present application cover the modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.
Claims (8)
1. An intelligent doorbell user behavior analysis system, the system comprising:
the event-driven behavior analysis module receives intelligent doorbell user interaction, triggers event processing, records details, classifies the details into a priority queue to obtain an event classification result, adjusts doorbell CPU and storage resources according to the event classification result, optimizes performance and obtains a resource allocation result;
The asynchronous visitor data processing module processes the differentiated event through an asynchronous processing technology based on the resource allocation result, triggers video recording and behavior analysis, distributes tasks to a differentiated processing unit for execution to obtain a parallel processing result, and carries out callback on data processed by the parallel processing result to obtain a callback determination result;
the behavior pattern recognition module performs pattern recognition on the user behavior data by adopting time sequence analysis based on the callback determination result, recognizes abnormal behaviors, obtains a behavior trend analysis result, performs behavior prediction by using the behavior trend analysis result, predicts a user activity pattern in a future time period, and obtains a behavior prediction result;
And the customized security policy module adjusts the response policy of the doorbell and matches the differentiated user behavior mode in the period of the predicted access amount by strengthening monitoring according to the behavior prediction result to obtain a dedicated security policy, and dynamically optimizes according to the user feedback and the monitoring data of the dedicated security policy to obtain an upgrade protection scheme.
2. The intelligent doorbell user behavior analysis system according to claim 1, wherein the step of obtaining the resource allocation result specifically comprises:
receiving intelligent doorbell user interaction, collecting user interaction data of the intelligent doorbell, classifying the data according to event types, and respectively calculating occurrence frequency and priority for each event type by using the formula:
An event weight array is generated, wherein, Is the weight of the event and,Represent the firstThe frequency of occurrence of the class event,Representation ofThe priority of the class event(s),Is a trade-off between frequency and priority,AndAdjusting the sensitivity of the frequency input;
and carrying out resource demand evaluation on the event weight array, and calculating a formula:
Generating an array of resource requirements, wherein, Is a need for resources such as a pool of resources,The weight of the event is represented as,Representing the coefficients of demand of the CPU,Representing the coefficient of the storage demand and,Is a resource demand adjustment coefficient;
based on the resource demand array, dynamically adjusting the resource allocation of the intelligent doorbell according to the resource demand by using an optimization algorithm, wherein a calculation formula is as follows:
generating a resource allocation result, wherein, Is the result of resource allocation and the method is that,Is a need for resources such as a pool of resources,Is a parameter of the sensitivity of the resource adjustment,Is the threshold value of the threshold,Is a global adjustment coefficient.
3. The intelligent doorbell user behavior analysis system according to claim 2, wherein the step of obtaining the parallel processing result specifically comprises:
based on the asynchronous visitor data of the resource allocation result, the parts are classified according to the type and the characteristics of the data, and the formula is adopted:
Generating a differential event classification result, wherein, Representing the differential event classification result,Is an event typeIs used to determine the sensitivity coefficient of the (c),Is a parameter of the time of day,AndThe sensitivity and the offset of the classification are adjusted,AndIs an additional regulatory factor;
Based on the differential event classification result, triggering a video recording task by adopting the formula:
generating an array of video recording tasks, wherein, Represent the firstThe quantization result of the video-like recording task,Is the result of the classification of the event by differentiation,Is a parameter of the demand of the basic video,Is an adjustment coefficient;
according to the video recording task array, assigning tasks to the differentiated processing units, and applying the formula:
generating an allocation result of the behavior analysis task, wherein, Is allocated to unitsIs used for analyzing the task amount of the behavior,Is the result of the quantization of the video recording task,Is a unitIs used for the processing power of the (c) in the (c),Is the total number of processing units;
and carrying out parallel processing according to the distribution result of the behavior analysis task, and adopting the formula:
generating a parallel processing result, wherein, Representing the results of the parallel processing,Is allocated to unitsIs used for analyzing the task amount of the behavior,AndIs the tuning parameter for parallel processing.
4. The intelligent doorbell user behavior analysis system according to claim 3, wherein the step of obtaining the callback determination result specifically comprises:
initializing a data callback process according to the parallel processing result, and adopting the formula:
adjusting sensitivity and threshold of data callback, generating preliminary callback response array, wherein, Representing a preliminary callback response,Is the result of the parallel processing of the data,AndIs a parameter that adjusts the sensitivity and threshold,Is an amplification factor that enhances responsiveness;
verifying the callback response, and applying the formula:
generating an array of validated callback results, wherein, Is a callback result that is verified and is,Is a preliminary callback response that is sent to the user,Is an index of the integrity of the data,Is a threshold of the desired integrity value and,Is a weight adjustment index;
Executing a determining process according to the verified callback result array, and adopting a formula:
generating a callback determination result, wherein, Representing the callback determination result,Is the callback result after the verification,AndIs the tuning parameter for parallel processing.
5. The intelligent doorbell user behavior analysis system according to claim 4, wherein the behavior trend analysis result obtaining step specifically comprises:
based on the callback determination result, processing and standardizing the user behavior data, and applying the formula:
the processed behavior data is generated, wherein, Representing the post-processing behavior data,Is a callback determination result,Is the weight coefficient of the data point;
performing time sequence analysis on the processed behavior data, identifying a mode and abnormal behaviors, and adopting a formula:
generating a behavior pattern analysis result, wherein, Is the result of the analysis of the behavior pattern,AndThe processed behavior data of the previous time point and the current time point respectively,Is a coefficient for smoothing;
Based on the analysis result of the behavior pattern, analyzing and identifying the long-term behavior trend, and adopting the formula:
Generating a behavioral trend analysis result, wherein, Representing the results of the behavioral trend analysis,Is the result of the analysis of the behavior pattern,Is a coefficient of standardization that is set to be a standard,Is a small amount of the total of all the components,Is a coefficient that adjusts the sensitivity of the behavioral trend response.
6. The intelligent doorbell user behavior analysis system according to claim 5, wherein the behavior prediction result obtaining step specifically comprises:
Based on the behavioral trend analysis results, key time series data points are extracted, and the formula is applied:
The extracted behavior trend data is generated, wherein, The extracted behavior trend data is represented,Is the point in timeIs a function of the behavior trend data of the (c),Is a time-decay factor that is a function of the time,Representing a time offset parameter;
And simulating a user activity mode in a future time period by using the extracted behavior trend data, wherein the method adopts the following formula:
A simulated future activity pattern is generated, wherein, Is a simulated future activity pattern of the device,Is the extracted behavior trend data,、、Is the adjustment coefficient of the light source,AndA characteristic of the periodic variation is defined,
Based on the simulated future activity pattern, a predicted behavior is calculated, applying the formula:
generating a behavior prediction result, wherein, Representing the result of the prediction of the behaviour,Is a simulated future activity pattern of the device,Is the length of the predicted time period,Is a weighting factor.
7. The intelligent doorbell user behavior analysis system according to claim 6, wherein the step of obtaining the proprietary security policy specifically comprises:
calculating monitoring intensity by using the behavior prediction result, and adopting the formula:
Strengthen nonlinear effect, generate monitoring intensity adjusting standard, wherein, Representing the reference for the adjustment of the monitoring intensity,Is the result of the prediction of the behaviour,、Is the adjustment coefficient of the light source,Is a behavioral impact index;
And according to the monitoring intensity adjustment standard, a strategy facing the high access amount time period is formulated, and the following formula is applied:
refining the response policy, generating a refined monitoring policy, wherein, Is a monitoring strategy after the refinement of the method,Is a reference for monitoring the adjustment of the intensity,、、、AndIs a factor of the regulation and is used for regulating the quantity of the liquid,
According to the refined monitoring strategy, combining with differentiated user behavior modes, formulating an exclusive security strategyThe formula is as follows:
generating a proprietary security policy, wherein, In order to be a proprietary security policy,、、、Is a parameter for the individual adjustment of the parameters,Is a refined monitoring strategy.
8. The intelligent doorbell user behavior analysis system according to claim 7, wherein the step of obtaining the upgrade protection scheme comprises:
Capturing user feedback data based on the exclusive security policy, summarizing the associated data for processing, monitoring the data in real time, summarizing the data, analyzing the processed and processed data, and generating a user feedback and monitoring data set;
Analyzing the user feedback and monitoring data set, identifying a key behavior pattern, using the formula:
generating a behavior pattern analysis result, wherein, Representing the weighted behavior pattern analysis results,Is the weight of the sample, and the weight of the sample,Is a data point that is to be read,Is the total number of data points,Is a small positive number;
According to the behavior pattern analysis result, combining dynamic adjustment parameters, and applying the formula:
an upgrade protection scheme is generated, wherein, Representing an upgrade protection scheme,Is the result of the analysis of the behavior pattern,、Is a parameter for adjusting the protection scheme,The sensitivity of the threshold value is controlled,The reaction rate of the time span is adjusted,A time threshold is defined for starting the adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410799278.3A CN118430111A (en) | 2024-06-20 | 2024-06-20 | Intelligent doorbell user behavior analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410799278.3A CN118430111A (en) | 2024-06-20 | 2024-06-20 | Intelligent doorbell user behavior analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118430111A true CN118430111A (en) | 2024-08-02 |
Family
ID=92335436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410799278.3A Pending CN118430111A (en) | 2024-06-20 | 2024-06-20 | Intelligent doorbell user behavior analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118430111A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007052474A (en) * | 2005-08-15 | 2007-03-01 | Advanced Telecommunication Research Institute International | Behavior identification system |
| WO2016109839A1 (en) * | 2014-12-31 | 2016-07-07 | Google Inc. | Handling visitor interaction at a smart-home in a do not disturb mode |
| CN109657580A (en) * | 2018-12-07 | 2019-04-19 | 南京高美吉交通科技有限公司 | A kind of urban track traffic gate passing control method |
| CN110213539A (en) * | 2019-06-03 | 2019-09-06 | 移康智能科技（上海）股份有限公司 | A kind of electronic peephole viewer with message-leaving function |
| CN110291489A (en) * | 2017-02-14 | 2019-09-27 | 微软技术许可有限责任公司 | The efficient mankind identify intelligent assistant's computer in calculating |
| US20200265240A1 (en) * | 2019-02-20 | 2020-08-20 | Vigilands Inc | System and method for image analysis based security system |
| CN114765609A (en) * | 2020-12-30 | 2022-07-19 | 深圳绿米联创科技有限公司 | Monitoring method and device, door lock, cloud server, terminal, system and medium |
| CN116862740A (en) * | 2023-07-13 | 2023-10-10 | 辽宁警察学院 | Intelligent prison management and control system based on Internet |
| US20240029490A1 (en) * | 2022-07-25 | 2024-01-25 | Bank Of America Corporation | User Authentication Using Behavior Patterns |
| CN117633511A (en) * | 2023-12-03 | 2024-03-01 | 中电万维信息技术有限责任公司 | Time sequence feature extraction method for operator customer churn prediction |
| CN117749995A (en) * | 2023-12-22 | 2024-03-22 | 深圳市智安天下科技有限公司 | Video monitoring method and system based on multi-scene recognition and voice interaction |
-
2024
- 2024-06-20 CN CN202410799278.3A patent/CN118430111A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007052474A (en) * | 2005-08-15 | 2007-03-01 | Advanced Telecommunication Research Institute International | Behavior identification system |
| WO2016109839A1 (en) * | 2014-12-31 | 2016-07-07 | Google Inc. | Handling visitor interaction at a smart-home in a do not disturb mode |
| CN110291489A (en) * | 2017-02-14 | 2019-09-27 | 微软技术许可有限责任公司 | The efficient mankind identify intelligent assistant's computer in calculating |
| CN109657580A (en) * | 2018-12-07 | 2019-04-19 | 南京高美吉交通科技有限公司 | A kind of urban track traffic gate passing control method |
| US20200265240A1 (en) * | 2019-02-20 | 2020-08-20 | Vigilands Inc | System and method for image analysis based security system |
| CN110213539A (en) * | 2019-06-03 | 2019-09-06 | 移康智能科技（上海）股份有限公司 | A kind of electronic peephole viewer with message-leaving function |
| CN114765609A (en) * | 2020-12-30 | 2022-07-19 | 深圳绿米联创科技有限公司 | Monitoring method and device, door lock, cloud server, terminal, system and medium |
| US20240029490A1 (en) * | 2022-07-25 | 2024-01-25 | Bank Of America Corporation | User Authentication Using Behavior Patterns |
| CN116862740A (en) * | 2023-07-13 | 2023-10-10 | 辽宁警察学院 | Intelligent prison management and control system based on Internet |
| CN117633511A (en) * | 2023-12-03 | 2024-03-01 | 中电万维信息技术有限责任公司 | Time sequence feature extraction method for operator customer churn prediction |
| CN117749995A (en) * | 2023-12-22 | 2024-03-22 | 深圳市智安天下科技有限公司 | Video monitoring method and system based on multi-scene recognition and voice interaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Slaq: quality-driven scheduling for distributed machine learning | |
| US20210056647A1 (en) | Method for multi-dimensional identification of flexible load demand response effect | |
| US20190180379A1 (en) | Life insurance system with fully automated underwriting process for real-time underwriting and risk adjustment, and corresponding method thereof | |
| CN112398700B (en) | Service degradation method and device, storage medium and computer equipment | |
| CN111199469A (en) | User payment model generation method and device and electronic equipment | |
| CN114912720A (en) | Memory network-based power load prediction method, device, terminal and storage medium | |
| CN116258318B (en) | Emergency event response and material overall allocation method and system | |
| CN116819352A (en) | Self-adaptive setting method, device and equipment for battery threshold value and storage medium | |
| CN113033938B (en) | Method, device, terminal equipment and storage medium for determining resource allocation strategy | |
| CN118430111A (en) | Intelligent doorbell user behavior analysis system | |
| CN111967919A (en) | System and method for analyzing electricity consumption behavior of residents based on autoregressive and adaptive boosting algorithm | |
| CN115221555B (en) | Health medical big data privacy protection method based on risk adaptive access control | |
| CN116010228B (en) | Time estimation method and device for network security scanning | |
| CN115797047B (en) | Intelligent customer management risk assessment method and system | |
| CN117435025A (en) | Intelligent wearable device data processing method and system based on multi-source data | |
| CN115935212A (en) | Adjustable load clustering method and system based on longitudinal trend prediction | |
| CN115758336A (en) | Asset identification method and device | |
| CN118644050B (en) | Resource configuration method and system based on environment coupling | |
| CN118426318B (en) | Internet of things service self-adaptive system based on process mining | |
| CN117788188B (en) | Automatic accounting method and system based on cloud computing | |
| CN116628465B (en) | Feature selection method based on screening machine learning user | |
| CN104200383A (en) | Application of multivariate regression analysis to tax decision | |
| CN117234871A (en) | Evaluation method for importance of application programming interface and related equipment | |
| KR102704617B1 (en) | Artificial intelligence wind power generation forecasting device | |
| CN118473837B (en) | Method for constructing multi-level network safety protection system |
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 |