CN101247392A - Objective activity estimation device and method - Google Patents
Objective activity estimation device and method Download PDFInfo
- Publication number
- CN101247392A CN101247392A CNA2008100093848A CN200810009384A CN101247392A CN 101247392 A CN101247392 A CN 101247392A CN A2008100093848 A CNA2008100093848 A CN A2008100093848A CN 200810009384 A CN200810009384 A CN 200810009384A CN 101247392 A CN101247392 A CN 101247392A
- Authority
- CN
- China
- Prior art keywords
- action message
- statistical forecast
- data
- module
- statistics
- 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.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides target activity forecast device and method thereof, wherein target activity forecast device includes: monitor module for monitor activity information of target and sending activity information to data preprocessing module; data preprocessing module for executing preprocess to activity information, and sending worked activity information to activity information database; activity information database for storing worked activity information and sending to data digging module; statistical prediction module for providing training statistical prediction model and applying activity information from data preprocessing module to training statistical prediction model to obtain statistical result of target activity rule and forecast result. The invention filter activity data of controlled target from present monitor data, analyzes its disciplinarian, and finds abnormal action.
Description
Technical field
The present invention relates to the monitoring field, relate in particular to objective activity estimation device and method.
Background technology
In snoop procedure, by to (for example from interface, HI2, HI3) data that receive are analyzed, can carry out data mining to a certain degree, from user activity data a large amount of, incomplete, noisy, fuzzy, at random, extract some behavior pattern (as the correlation rule between the behavior) that lies in intercepted user (target) wherein; Behavior pattern according to the user is suitably predicted, can realize accurately establishing control, in time notes abnormalities, and prevents hazardous act.
The basis of statistics is a user behavior, therefore behavioral data need be filtered out from the message that is sent to listening center, is kept in the database, extracts plurality of data when needing to analyze and carry out statistical analysis from database.
For the statistics of mechanics, the function of mainly finishing has the following aspects: the collection of activity data: the collection point is at listening center; Extract the critical field of original record, write in the database; Analyze the correlation rule between the things, i.e. pattern analysis; The rule that visual excavation obtains, and foresight activity place.
Summary of the invention
One or more problems in view of the above the present invention proposes objective activity estimation device and method.Can filter the activity data of controlled object by the present invention from existing monitored data, analyze the rule of summing up wherein, behavior notes abnormalities.
Objective activity estimation device according to an aspect of the present invention comprises: monitor module, be used for the action message of intercept target, and action message is sent to data preprocessing module; Data preprocessing module is used for action message is carried out preliminary treatment, and pretreated action message is sent to the action message database; The action message database is used to store pretreated action message and sends it to data-mining module; The statistical forecast module is used to provide the statistical forecast that trains model, and the statistical forecast model that will be applied to train from the action message of data preprocessing module is with the statistics that obtains the goal activities rule with predict the outcome.
Wherein, the statistical forecast module comprises: learning database (learning database) is used for storing in advance the learning data that is used to train the statistical forecast model; And data-mining module, be used to provide the statistical forecast model, be used to the learning data training statistical forecast model of self study database, and the statistical forecast model that will be applied to train from the action message of data preprocessing module is with the statistics that obtains the goal activities rule with predict the outcome.
Objective activity estimation device also comprises: display module is used to show statistics and predicts the outcome.Display module comprises: the statistics visualization model is used to show statistics; And the visualization model that predicts the outcome, be used for showing predicting the outcome.
Action message comprises following information: the time that object identifier, target occur, the position that reaches the target appearance.Statistics is meant the frequency of target in different time and/or diverse location appearance.Predict the outcome and be meant the probability that target occurs in the scheduled time and/or the precalculated position in future.
Goal activities Forecasting Methodology according to another aspect of the present invention may further comprise the steps: step S202, the multiple action message of receiving target; Step S204 carries out preliminary treatment to action message; Step S206, storage in advance is used to train the learning data of statistical forecast model; And step S208, provide the statistical forecast that trains model, and the statistical forecast model that action message is applied to train is with the statistics that obtains the goal activities rule with predict the outcome.
Wherein, step S208 may further comprise the steps: step S208-2, and storage in advance is used to train the learning data of statistical forecast model; Step S208-4 provides the statistical forecast model, utilizes learning data training statistical forecast model; And step S208-6, the statistical forecast model that action message is applied to train is with the statistics that obtains the goal activities rule and predict the outcome.
The goal activities Forecasting Methodology is further comprising the steps of: show described statistics and described predicting the outcome.Action message comprises following information: the time that object identifier, target occur, the physical location that reaches the target appearance.
By the present invention, from existing monitored data, filter the activity data of controlled object, analyze the rule of summing up wherein, behavior notes abnormalities.
Description of drawings
Accompanying drawing described herein is used to provide further understanding of the present invention, constitutes the application's a part, and illustrative examples of the present invention and explanation thereof are used to explain the present invention, do not constitute improper qualification of the present invention.In the accompanying drawings:
Fig. 1 is the block diagram of objective activity estimation device according to an embodiment of the invention;
Fig. 2 is the flow chart of goal activities Forecasting Methodology according to an embodiment of the invention;
Fig. 3 be according to another embodiment of the invention the activity data collection and the flow chart of rule digging; And
Fig. 4 is the flow chart of predicting according to an embodiment of the invention with modification rule.
Embodiment
Below with reference to accompanying drawing, describe the specific embodiment of the present invention in detail.
Fig. 1 is the block diagram of objective activity estimation device according to an embodiment of the invention.As shown in Figure 1, this device comprises: monitor module (monitoring control module) 102, be used for the action message of intercept target, and action message is sent to data preprocessing module 104; Data preprocessing module 104 is used for action message is carried out preliminary treatment, and pretreated action message is sent to action message database 106; Action message database 106 is used to store pretreated action message and sends it to data-mining module 108-4; Statistical forecast module 108 is used to provide the statistical forecast that trains model, and the statistical forecast model that will be applied to train from the action message of data preprocessing module is with the statistics that obtains the goal activities rule with predict the outcome.
Wherein, statistical forecast module 108 comprises: learning database (learning database) 108-2 is used for storing in advance the learning data that is used to train the statistical forecast model; And data-mining module 108-4, be used to provide the statistical forecast model, be used to the learning data training statistical forecast model of self study database 108-2, and the statistical forecast model that will be applied to train from the action message of data preprocessing module is with the statistics that obtains the goal activities rule with predict the outcome.
Objective activity estimation device also comprises: display module 110 is used to show statistics and predicts the outcome.Display module 110 comprises: statistics visualization model (frequency visualization model) 110-2, be used to show statistics, and for example, target is at the statistical graph of the frequency of different time and/or different location appearance; And the visualization model that predicts the outcome (prediction visualization model) 110-4, be used for showing predicting the outcome, specifically, show that the target that dopes appears at the diagram more intuitively of diverse geographic location, for example, utilize the mode more intuitively of electronic chart etc. to represent to predict the outcome.
Action message comprises following information: the time that object identifier, target occur, the position that reaches the target appearance.Statistics is meant the frequency of target in different time and/or diverse location appearance.Predict the outcome and be meant the probability that target occurs in the scheduled time and/or the precalculated position in future.
Fig. 2 is the flow chart of goal activities Forecasting Methodology according to an embodiment of the invention.As shown in Figure 2, this method may further comprise the steps:
Step S202 gathers the multiple action message of target, and wherein, action message comprises following information: the position that the time that object identifier, target occur, target occur, and under network element etc.
Step S204 carries out preliminary treatment to action message.Specifically, from the action message that step S202 collects, filter out statistics and predict needed information, for example, the time that object identifier, target occur, the position of appearance, and called number etc.
Step S206, storage in advance is used to train the learning data of statistical forecast model.Part in the resulting data of preliminary treatment that this learning data carries out for step S204.
Step S208 provides the statistical forecast that trains model, and the statistical forecast model that action message is applied to train is with the statistics that obtains the goal activities rule with predict the outcome.
Wherein, step S208 may further comprise the steps:
Step S208-2, storage in advance is used to train the learning data of statistical forecast model.Part in the resulting data of preliminary treatment that this learning data carries out for step S204.
Step S208-4 provides the statistical forecast model, utilizes learning data training statistical forecast model.Wherein, the statistical forecast model, for example, about the time of a certain controlled object and the relation curve of position.Specifically, a certain controlled object is at the time tn of n days this month and relational expression or the curve of position pn.Utilize learning data to remove to train this statistical forecast model, can use the Data Mining Tools of specialty here, for example, SQLserver 2000.
Step S208-6, the statistical forecast model that action message is applied to train is with the statistics that obtains the goal activities rule and predict the outcome.Equally, also can use the Data Mining Tools of specialty here, and can select suitable algorithm to predict, for example, decision-making number and the neural network algorithm of SQLserver 2000.
The goal activities Forecasting Methodology is further comprising the steps of: show described statistics and described predicting the outcome.Action message comprises following information: the time that object identifier, target occur, the physical location that reaches the target appearance.
In according to another embodiment of the invention, the goal activities Forecasting Methodology may further comprise the steps:
Step 1 operates in the monitoring control module on the listening center (LIC), after receiving the message that HI2 and HI3 interface report, the life event details is kept at the action message lane database; Message registration under the while traffic measurement server record.
Step 2, data preprocessing module is extraction time, place, called number, the duration of call from historical act incident or traffic record, adds up the frequency of each things, deposits the action message database in.
Step 3 is chosen the algorithm that data-mining module provides and is applied to ready data, draws the correlation model between the activity things; And according to the learning data training pattern of importing, and the rule that will pick out deposits learning database in.
Step 4, graphical statistics shows information of forecasting.
For step 3, use multiple modeling methods such as decision tree that existing data-mining module provides, neural net, neighbour's study, recurrence, association, cluster, Bayes's differentiation to set up model respectively, then these models are carried out odds, thereby pick out the modeling method that the most suitable mechanics is analyzed.Here optimal models can be differentiated for your guidance automatically by system.
Fig. 3 be according to another embodiment of the invention the activity data collection and the flow chart of rule digging, as shown in Figure 3, this flow chart is that data-mining module is applied to the flow process that data are found out model, this is a process that moves in circles.
Step S302 monitors control module the HI2 message of receiving is write the user activity information lane database, and the information of every record comprises user ID, time, physical location.
Step S304, pretreatment module is pressed controlled object ID, and the time, physical location is a parameter, calculated rate.
Step S306 is according to learning database data-mining module training pattern.Here can set different algorithms and draw model with the Data Mining Tools of specialty, use the low volume data verification model again.
Fig. 4 is the flow chart of predicting according to an embodiment of the invention with modification rule.As shown in Figure 4, this flow chart is user's applying portion.The user imports predicted condition, uses a model, and draws the prediction place; Simultaneity factor is upgraded learning database according to real action result correction model, and concrete steps are as follows:
Step S402, the user imports predicted condition, for example, controlled object ID, time, confidence level, and infers the place.
Step S404, according to initial conditions, stress model draws the activity venue of prediction.
Step S406, the prediction place is visual, for example, is presented on the movable map.
Step S408 after step S404, observes the actual place that occurs of controlled object, if mistake, then execution in step S410 changes learning database, correction model.
Step S410, data-mining module is according to the action message correction model.
Step S412, respectively with time, place, and frequency be coordinate, creative activity frequency histogram mode.
By the present invention, from existing monitored data, filter the activity data of controlled object, analyze the rule of summing up wherein, behavior notes abnormalities.
The above is the preferred embodiments of the present invention only, is not limited to the present invention, and for a person skilled in the art, the present invention can have various changes and variation.Within the spirit and principles in the present invention all, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (11)
1. an objective activity estimation device is characterized in that, comprising:
Monitor module, be used to monitor the action message of described target, and described action message is sent to data preprocessing module;
Described data preprocessing module is used for described action message is carried out preliminary treatment, and pretreated action message is sent to the action message database;
Described action message database is used to store described pretreated action message and sends it to data-mining module;
The statistical forecast module is used to provide the statistical forecast that trains model, and will be applied to the described statistical forecast model that trains from the described action message of described data preprocessing module with the statistics that obtains described goal activities rule with predict the outcome.
2. objective activity estimation device according to claim 1 is characterized in that, described statistical forecast module comprises:
Learning database is used for storing in advance the learning data that is used to train described statistical forecast model; And
Described data-mining module, be used to provide described statistical forecast model, be used to train described statistical forecast model, and the statistical forecast model that will be applied to train from the described action message of described data preprocessing module is with the statistics that obtains described goal activities rule with predict the outcome from the described learning data of described learning database.
3. objective activity estimation device according to claim 2 is characterized in that, also comprises:
Display module is used to show described statistics and described predicting the outcome.
4. objective activity estimation device according to claim 3 is characterized in that, described display module comprises:
The statistics visualization model is used to show described statistics; And
The visualization model that predicts the outcome is used to show described predicting the outcome.
5. according to each described objective activity estimation device in the claim 1 to 4, it is characterized in that described action message comprises following information: the time that object identifier, described target occur, and the position that occurs of described target.
6. objective activity estimation device according to claim 5 is characterized in that, described statistics is meant the frequency of described target in different time and/or diverse location appearance.
7. objective activity estimation device according to claim 5 is characterized in that, described predicting the outcome is meant the probability that described target occurs in the scheduled time and/or the precalculated position in future.
8. a goal activities Forecasting Methodology is characterized in that, said method comprising the steps of:
Step S202 receives the multiple action message of described target;
Step S204 carries out preliminary treatment to described action message;
Step S206, storage in advance is used to train the learning data of statistical forecast model; And
Step S208 provides the statistical forecast that trains model, and described action message is applied to the described statistical forecast model that trains with the statistics that obtains described goal activities rule with predict the outcome.
9. goal activities Forecasting Methodology according to claim 8 is characterized in that, described step S208 may further comprise the steps:
Step S208-2, storage in advance is used to train the learning data of described statistical forecast model;
Step S208-4 provides described statistical forecast model, utilizes described learning data to train described statistical forecast model; And
Step S208-6, the statistical forecast model that described action message is applied to train is with the statistics that obtains described goal activities rule and predict the outcome.
10. goal activities Forecasting Methodology according to claim 9 is characterized in that, described method is further comprising the steps of: show described statistics and described predicting the outcome.
11. each described goal activities Forecasting Methodology in 10 according to Claim 8 is characterized in that described action message comprises following information: the time that object identifier, target occur, and the physical location that occurs of target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100093848A CN101247392B (en) | 2008-02-28 | 2008-02-28 | Objective activity estimation device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100093848A CN101247392B (en) | 2008-02-28 | 2008-02-28 | Objective activity estimation device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101247392A true CN101247392A (en) | 2008-08-20 |
| CN101247392B CN101247392B (en) | 2010-12-08 |
Family
ID=39947592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008100093848A Expired - Fee Related CN101247392B (en) | 2008-02-28 | 2008-02-28 | Objective activity estimation device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101247392B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101995823A (en) * | 2010-09-28 | 2011-03-30 | 吴伪亮 | Energy-saving control method based on statistical forecasting technology |
| CN103347064A (en) * | 2013-06-25 | 2013-10-09 | 百度在线网络技术（北京）有限公司 | Method and system for displaying user location |
| CN103942229A (en) * | 2013-01-22 | 2014-07-23 | 日电（中国）有限公司 | Destination prediction device and method |
| WO2017031856A1 (en) * | 2015-08-25 | 2017-03-02 | 百度在线网络技术（北京）有限公司 | Information prediction method and device |
| CN108885718A (en) * | 2016-01-14 | 2018-11-23 | 摄取技术有限公司 | Localize time model prediction |
| CN109726847A (en) * | 2018-11-19 | 2019-05-07 | 北京三快在线科技有限公司 | Position predicting method, device, electronic equipment and readable storage medium storing program for executing |
| CN110738256A (en) * | 2019-10-15 | 2020-01-31 | 四川长虹电器股份有限公司 | Image implicit information mining method and device based on statistical learning model |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7016939B1 (en) * | 2001-07-26 | 2006-03-21 | Mcafee, Inc. | Intelligent SPAM detection system using statistical analysis |
| US6954744B2 (en) * | 2001-08-29 | 2005-10-11 | Honeywell International, Inc. | Combinatorial approach for supervised neural network learning |
| US8280757B2 (en) * | 2005-02-04 | 2012-10-02 | Taiwan Semiconductor Manufacturing Co., Ltd. | Demand forecast system and method |
-
2008
- 2008-02-28 CN CN2008100093848A patent/CN101247392B/en not_active Expired - Fee Related
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101995823A (en) * | 2010-09-28 | 2011-03-30 | 吴伪亮 | Energy-saving control method based on statistical forecasting technology |
| CN101995823B (en) * | 2010-09-28 | 2012-12-12 | 吴伪亮 | Energy-saving control method based on statistical forecasting technology |
| CN103942229A (en) * | 2013-01-22 | 2014-07-23 | 日电（中国）有限公司 | Destination prediction device and method |
| CN103347064A (en) * | 2013-06-25 | 2013-10-09 | 百度在线网络技术（北京）有限公司 | Method and system for displaying user location |
| WO2017031856A1 (en) * | 2015-08-25 | 2017-03-02 | 百度在线网络技术（北京）有限公司 | Information prediction method and device |
| CN108885718A (en) * | 2016-01-14 | 2018-11-23 | 摄取技术有限公司 | Localize time model prediction |
| CN109726847A (en) * | 2018-11-19 | 2019-05-07 | 北京三快在线科技有限公司 | Position predicting method, device, electronic equipment and readable storage medium storing program for executing |
| CN110738256A (en) * | 2019-10-15 | 2020-01-31 | 四川长虹电器股份有限公司 | Image implicit information mining method and device based on statistical learning model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101247392B (en) | 2010-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101247392B (en) | Objective activity estimation device and method | |
| US11247580B2 (en) | Apparatus and method for predicting failure of electric car charger | |
| WO2017076154A1 (en) | Method and apparatus for predicting network event and establishing network event prediction model | |
| CN106254317A (en) | A kind of data security exception monitoring system | |
| CN107402921A (en) | Identify event-order serie data processing method, the apparatus and system of user behavior | |
| CN109978215B (en) | Patrol management method and device | |
| Akpinar et al. | The effect of differential victim crime reporting on predictive policing systems | |
| CN109767227B (en) | System and method for realizing intelligent judgment and control of payment risk through RDS (remote data System) | |
| CN112633395A (en) | Abnormal data detection method and device, computer equipment and storage medium | |
| Wang et al. | Predicting the city foot traffic with pedestrian sensor data | |
| CN115937795B (en) | Method and device for acquiring agronomic activity records based on rural videos | |
| CN117196159A (en) | Intelligent water service partition metering system based on Internet big data analysis | |
| CN108876062B (en) | Big data method and device for intelligent prediction of criminal events | |
| CN116822115A (en) | Environment management method and system for intelligent park based on digital twin technology | |
| CN115049410A (en) | Electricity stealing behavior identification method and device, electronic equipment and computer readable storage medium | |
| CN110166422A (en) | Domain name Activity recognition method, apparatus, readable storage medium storing program for executing and computer equipment | |
| CN117592975A (en) | Operation and maintenance decision processing method and system for electromechanical equipment of expressway based on cloud computing | |
| CN116318907B (en) | Method and system for analyzing computer network situation based on big data and neural network | |
| CN113254733B (en) | Information analysis method, system and storage medium based on big data platform | |
| CN115829073A (en) | Object recognition method, device, equipment, readable storage medium and program product | |
| CN116701551A (en) | Abnormality prediction method, device, equipment and storage medium | |
| CN114358395A (en) | Attendance checking prediction method and device | |
| CA3104317A1 (en) | Systems and methods for identifying an officer at risk of an adverse event | |
| CN117853078B (en) | Unmanned aerial vehicle-based dynamic safety alarm system and method for construction site of building engineering | |
| CN117314370B (en) | Intelligent energy-based data cockpit system and implementation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20101208 Termination date: 20180228 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |