CN110083641B - Intelligence analysis method and device based on target behavior - Google Patents
Intelligence analysis method and device based on target behaviorDownload PDFInfo
- Publication number
- CN110083641B CN110083641BCN201910347686.4ACN201910347686ACN110083641BCN 110083641 BCN110083641 BCN 110083641BCN 201910347686 ACN201910347686 ACN 201910347686ACN 110083641 BCN110083641 BCN 110083641B
- Authority
- CN
- China
- Prior art keywords
- behavior data
- data
- recommendation
- historical behavior
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Technical Field
The present application relates to the field of data network technologies, and in particular, to an intelligence analysis method and apparatus based on target behaviors.
Background
With the increasing degree of informatization, people have increasingly strong desire for large data analysis service, and products for performing information analysis by using large data are produced accordingly. However, the existing intelligence analysis products only combine the collected fragmented data, and cannot perform correlation analysis on the fragmented data, so that the accuracy of the final intelligence analysis result is low.
Disclosure of Invention
The embodiment of the application provides an intelligence analysis method and device based on target behaviors, and solves the problem that correlation analysis cannot be performed on fragmented data in the prior art, so that intelligence analysis results are optimized.
In order to solve the above problem, an embodiment of the present application provides a method for intelligence analysis based on target behavior, which is suitable for being executed in a computing device, and at least includes the following steps:
acquiring a plurality of current behavior data of a target; the plurality of current behavior data comprise target subject data, time data, position data and event data;
classifying each historical behavior data stored in a database according to each current behavior data;
acquiring first associated information of the current behavior data and each historical behavior data in the same category based on an Apriori algorithm, and acquiring second associated information of the current behavior data and each historical behavior data in the same category based on typical correlation analysis, and then taking the first associated information and the second associated information of the same category as an information set;
acquiring a plurality of recommendation indexes of the historical behavior data based on a plurality of recommendation algorithms and the information set; the recommendation algorithm corresponds to the recommendation index one by one;
and weighting each corresponding recommendation index based on the preset weight of each recommendation algorithm to obtain an analysis result.
Further, the classifying, according to each of the current behavior data, each of the historical behavior data stored in the database is specifically:
and classifying the historical behavior data stored in the database based on a K-nearest neighbor algorithm according to the current behavior data.
Further, the method also comprises the following steps:
and when the analysis result is larger than a preset threshold value, pushing the historical behavior data corresponding to the analysis result to the user terminal.
Further, the method also comprises the following steps:
and when negative feedback information sent by the user terminal according to the historical behavior data is received, adjusting the preset weight of each recommendation algorithm according to the negative feedback information.
Further, the plurality of recommendation algorithms at least comprises:
collaborative filtering based recommendation algorithms, association rule based recommendation algorithms, and content based recommendation algorithms.
Further, an intelligence analysis device based on target behaviors is provided, which includes:
the data acquisition module is used for acquiring a plurality of current behavior data of the target; the plurality of current behavior data comprise target subject data, time data, position data and event data;
the data classification module is used for classifying the historical behavior data stored in the database according to the current behavior data;
the data association module is used for acquiring first association information of the current behavior data and each historical behavior data in the same category based on an Apriori algorithm, acquiring second association information of the current behavior data and each historical behavior data in the same category based on typical correlation analysis, and then taking the first association information and the second association information in the same category as an information set;
the data recommendation module is used for acquiring a plurality of recommendation indexes of the historical behavior data based on a plurality of recommendation algorithms and the information set; the recommendation algorithm corresponds to the recommendation index one by one;
and the result analysis module is used for weighting each corresponding recommendation index based on the preset weight of each recommendation algorithm to obtain an analysis result.
Further, the data classification module is specifically configured to:
and classifying the historical behavior data stored in the database based on a K-nearest neighbor algorithm according to the current behavior data.
Further, the method also comprises the following steps:
and the data alarm module is used for pushing the historical behavior data corresponding to the analysis result to the user terminal when the analysis result is greater than a preset threshold value.
Further, the method also comprises the following steps:
and the data adjusting module is used for adjusting the preset weight of each recommendation algorithm according to the negative feedback information when the negative feedback information sent by the user terminal according to the historical behavior data is received.
The embodiment of the application has the following beneficial effects:
according to the information analysis method and device based on the target behavior, after the historical behavior data are classified according to the current behavior data, strong correlation information and weak correlation information between the historical behavior data and the current behavior data are obtained through an Apriori algorithm and typical correlation analysis, so that the intrinsic correlation is established between fragmented data, the subsequently recommended information data are not simple data combination any more, the information analysis result is optimized, and the accuracy, the integrity and the effectiveness of the information analysis are improved.
Drawings
FIG. 1 is a flow diagram of a method for intelligence analysis based on target behavior according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for intelligence analysis based on target behavior according to yet another embodiment of the present application;
FIG. 3 is a flow chart of a method for intelligence analysis based on target behavior according to another embodiment of the present application;
FIG. 4 is a schematic structural diagram of an intelligence analysis apparatus based on target behavior according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a target behavior-based intelligence analysis apparatus according to another embodiment of the present application;
fig. 6 is a schematic structural diagram of an intelligence analysis apparatus based on target behaviors according to still another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Please refer to fig. 1.
Referring to fig. 1, it is a schematic flow chart of an intelligence analysis method based on target behaviors provided in an embodiment of the present application, and as shown in fig. 1, each step is specifically as follows:
in step S11, a plurality of current behavior data of the target are acquired.
The plurality of current behavior data comprise target subject data, time data, position data and event data.
In this embodiment, the target is determined by the user, and may be an individual or an organization, or may be an event. According to the 6W principle, namely: what happens, Where, When, What happens, What participates, Why, How, collecting, extracting, sorting and removing duplication of the whole network resource, obtaining a plurality of current behavior data of the target, and storing the plurality of current behavior data into a relation database, thereby determining the target center.
In step S12, the historical behavior data stored in the database are classified according to the current behavior data.
Specifically, the historical behavior data stored in the database are classified based on a K-nearest neighbor algorithm according to the current behavior data.
In this embodiment, after classifying the current behavior data according to 4 indexes, namely, a target subject index, a time index, a location index and an event index, based on a K-nearest neighbor algorithm, each historical behavior data is classified, and in each category, after selecting a plurality of pieces of historical behavior data whose distance from the current behavior data is within a preset range, the selected plurality of pieces of historical behavior data are sorted into one relational database, thereby reducing the classification workload and improving the efficiency.
In this embodiment, the target subject index is a person, thing, or organization; the time index is the time when the event occurs; the place indexes are places where the events occur, including longitude and latitude, countries, streets and the like; the event index is an event that occurs.
Step S13, based on Apriori algorithm, obtaining first association information between the current behavior data and each historical behavior data in the same category, and based on typical correlation analysis, obtaining second association information between the current behavior data and each historical behavior data in the same category, and then using the first association information and the second association information in the same category as an information set.
In this embodiment, Apriori algorithm is adopted to perform association analysis on each historical behavior data of the same category and the current behavior data of the same category, so as to find out first association information indicating that there is an obvious internal association between the data, which is helpful for early warning of events occurring in the future, and by adopting a typical correlation analysis method, the historical behavior data of each high-dimensional space in the same category and the current behavior data in the same category are mapped to a low-dimensional space, so as to find out second association information indicating that the data are weakly associated, which is helpful for more accurately predicting and sensing future events. For example, each historical behavior data belonging to the target subject index is subjected to correlation analysis with the current behavior data belonging to the target subject index, so that each historical behavior data of the target subject index, and the first correlation information and the second correlation information of the current behavior data of the target subject index are obtained.
On the basis of obtaining the information set, behavior data is searched around a target determined by a user through a fuzzy matching algorithm and an accurate matching algorithm based on a knowledge graph, so that associated historical behavior data is obtained, and the obtained historical behavior data is associated and displayed in combination with data input by the user on a visual interface.
And step S14, acquiring a plurality of recommendation indexes of historical behavior data based on a plurality of recommendation algorithms and information sets.
And the recommendation algorithm corresponds to the recommendation index one by one.
In this embodiment, the information set is used as parameters of a collaborative filtering-based recommendation algorithm, an association rule-based recommendation algorithm, and a content-based recommendation algorithm, so as to obtain a plurality of recommendation indexes of historical behavior data.
And step S15, weighting each corresponding recommendation index based on the preset weight of each recommendation algorithm to obtain an analysis result.
In this embodiment, the existing recommendation algorithm based on collaborative filtering, the recommendation algorithm based on association rules, and the recommendation algorithm based on content are combined, and a plurality of recommendation algorithms are weighted, so as to obtain an analysis result, wherein a specific formula is as follows:
wherein S is an analysis result, n is a recommended algorithm number, and alphaiIs the ith recommendation index, kiIs the ith recommended algorithm weight.
After the historical behavior data are classified according to the current behavior data, strong correlation information and weak correlation information between the historical behavior data and the current behavior data are obtained through an Apriori algorithm and typical correlation analysis, and correlation analysis can be performed on data of all dimensions, so that internal correlation is established between fragmented data, subsequently recommended intelligence data are not simple data combination any more, and intelligence analysis results are optimized.
Please refer to fig. 2.
Further, referring to fig. 2, a flowchart of a method for analyzing intelligence based on target behavior according to still another embodiment of the present application is shown. Besides the flow shown in fig. 1, the method further comprises the following steps:
and step S16, when the analysis result is larger than the preset threshold value, pushing historical behavior data corresponding to the analysis result to the user terminal.
In this embodiment, the historical behavior data is arranged in a descending order according to the size of the analysis result and displayed on the terminal interface, and if the analysis result is greater than 80%, the corresponding historical behavior data is pushed to the user terminal in an alarm state.
According to the embodiment, the corresponding historical behavior data are displayed on the terminal interface in a descending order according to the size of the analysis result, so that a user can browse the data conveniently, and when the analysis result is larger than the preset threshold value, the corresponding historical behavior data are pushed to the user terminal, so that the user can obtain the prediction information with higher accuracy, and the user can take corresponding measures in time according to the information.
Please refer to fig. 3.
Fig. 3 is a schematic flow chart of a method for intelligence analysis based on target behavior according to another embodiment of the present application. In addition to the flow shown in fig. 2, the method further includes:
and step S17, when negative feedback information sent by the user terminal according to the historical behavior data is received, adjusting the preset weight of each recommendation algorithm according to the negative feedback information.
In this embodiment, the preset weight is adjusted by positive and negative feedback adjustment. If positive feedback information sent by a user according to the pushed historical behavior data is received, the pushed data is in accordance with actual expectation; if negative feedback information sent by the user according to the pushed historical behavior data is received, the fact that the difference between the pushed data and an actual result is large is indicated, at the moment, the preset weight of each recommendation algorithm is adjusted according to the negative feedback of the user, for example, the weight of the recommendation algorithm based on collaborative filtering is reduced, the weight of the recommendation algorithm based on the content is increased, and the accuracy of the pushed data is further improved.
The embodiment adjusts the preset weight of the recommendation algorithm in real time according to the information fed back by the user, and solves the problem that the intelligence analysis accuracy is low due to the fact that the fixed preset weight is used, so that the predicted data are more accurate, and the accuracy is higher along with the increase of the user feedback information.
Please refer to fig. 4.
Further, refer to fig. 4, which is a schematic structural diagram of an intelligence analysis apparatus based on target behavior according to an embodiment of the present application. The method comprises the following steps:
thedata obtaining module 101 is configured to obtain a plurality of current behavior data of the target.
The plurality of current behavior data comprise target subject data, time data, position data and event data.
And thedata classification module 102 is configured to classify each historical behavior data stored in the database according to each current behavior data.
Specifically, thedata classification module 102 is configured to classify, according to each current behavior data, each historical behavior data stored in the database based on a K-nearest neighbor algorithm.
Thedata association module 103 is configured to obtain first association information between the current behavior data and each historical behavior data in the same category based on an Apriori algorithm, obtain second association information between the current behavior data and each historical behavior data in the same category based on a typical correlation analysis, and use the first association information and the second association information in the same category as an information set.
And thedata recommendation module 104 is configured to obtain a plurality of recommendation indexes of the historical behavior data based on a plurality of recommendation algorithms and information sets. And the recommendation algorithm corresponds to the recommendation index one by one.
And theresult analysis module 105 is configured to weight each corresponding recommendation index based on the preset weight of each recommendation algorithm to obtain an analysis result.
After the historical behavior data are classified according to the current behavior data, strong correlation information and weak correlation information between the historical behavior data and the current behavior data are obtained through an Apriori algorithm and typical correlation analysis, and correlation analysis can be performed on data of all dimensions, so that internal correlation is established between fragmented data, subsequently recommended intelligence data are not simple data combination any more, and intelligence analysis results are optimized.
Please refer to fig. 5.
Fig. 5 is a schematic structural diagram of an intelligence analysis apparatus based on target behavior according to still another embodiment of the present application. In addition to the structure shown in fig. 4, the method further includes:
and thedata alarm module 106 is configured to, when the analysis result is greater than a preset threshold, push historical behavior data corresponding to the analysis result to the user terminal.
According to the embodiment, the corresponding historical behavior data are displayed on the terminal interface in a descending order according to the size of the analysis result, so that a user can browse the data conveniently, and when the analysis result is larger than the preset threshold value, the corresponding historical behavior data are pushed to the user terminal, so that the user can obtain the prediction information with higher accuracy, and the user can take corresponding measures in time according to the information.
Please refer to fig. 6.
Fig. 6 is a schematic structural diagram of an intelligence analysis apparatus based on target behavior according to still another embodiment of the present application. In addition to the structure shown in fig. 5, the structure further includes:
and thedata adjusting module 107 is configured to, when receiving negative feedback information sent by the user terminal according to the historical behavior data, adjust the preset weight of each recommendation algorithm according to the negative feedback information.
The embodiment adjusts the preset weight of the recommendation algorithm in real time according to the information fed back by the user, and solves the problem that the intelligence analysis accuracy is low due to the fact that the fixed preset weight is used, so that the predicted data are more accurate, and the accuracy is higher along with the increase of the user feedback information.
Yet another embodiment of the present application further provides a targeted behavior based intelligence analysis terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the targeted behavior based intelligence analysis method according to the above embodiment when executing the computer program.
The foregoing is a preferred embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations are also regarded as the protection scope of the present application.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Claims (7)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347686.4ACN110083641B (en) | 2019-04-26 | 2019-04-26 | Intelligence analysis method and device based on target behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347686.4ACN110083641B (en) | 2019-04-26 | 2019-04-26 | Intelligence analysis method and device based on target behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110083641A CN110083641A (en) | 2019-08-02 |
| CN110083641Btrue CN110083641B (en) | 2021-07-09 |
Family
ID=67417189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910347686.4AActiveCN110083641B (en) | 2019-04-26 | 2019-04-26 | Intelligence analysis method and device based on target behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110083641B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10133791B1 (en)* | 2014-09-07 | 2018-11-20 | DataNovo, Inc. | Data mining and analysis system and method for legal documents |
| US20170277793A1 (en)* | 2016-03-24 | 2017-09-28 | NewsRx, LLC | Narrated search results |
| CN109272155B (en)* | 2018-09-11 | 2021-07-06 | 郑州向心力通信技术股份有限公司 | Enterprise behavior analysis system based on big data |
| CN109543963B (en)* | 2018-11-06 | 2022-01-11 | 深圳信息职业技术学院 | Big data analysis method and system based on student learning habits |
- 2019
- 2019-04-26CNCN201910347686.4Apatent/CN110083641B/enactiveActive
Also Published As
| Publication number | Publication date |
|---|---|
| CN110083641A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112258093B (en) | Data processing method and device for risk level, storage medium and electronic equipment | |
| CN110163647B (en) | Data processing method and device | |
| CN107341268B (en) | Hot searching ranking method and system | |
| CN111914090A (en) | Method and device for enterprise industry classification identification and characteristic pollutant identification | |
| CN111553127A (en) | A method and device for feature selection of multi-label text data | |
| CN105354198B (en) | A data processing method and device | |
| CN112039903B (en) | Network security situation assessment method based on deep self-coding neural network model | |
| CN113722478B (en) | Multi-dimensional feature fusion similar event calculation method and system and electronic equipment | |
| CN111767404B (en) | Event mining method and device | |
| CN114358207B (en) | Improved k-means abnormal load detection method and system | |
| CN116756688A (en) | Public opinion risk discovery method based on multi-mode fusion algorithm | |
| CN107545075B (en) | Restaurant recommendation method based on online comments and context awareness | |
| CN118734247B (en) | Smart city central data fusion computing model training method, early warning method and equipment based on MOE architecture | |
| CN106202530B (en) | Data processing method and device | |
| CN113407808B (en) | Method, device and computer equipment for determining the applicability of graph neural network models | |
| CN119444232B (en) | Digital economic risk management evaluation method and system based on cloud computing | |
| CN114943424B (en) | A method and system for generating enterprise management index relationship | |
| CN116628628A (en) | User information literacy analysis method, system and storage medium based on retrieved information | |
| CN112417152A (en) | Topic detection method and device for case-related public sentiment | |
| CN113988149B (en) | A service clustering method based on particle swarm fuzzy clustering | |
| CN110083641B (en) | Intelligence analysis method and device based on target behavior | |
| CN116823069B (en) | Intelligent customer service quality inspection method based on text analysis and related equipment | |
| Iyer et al. | Machine learning and dataming algorithms for predicting accidental small forest fires | |
| Radovanović et al. | Making hospital readmission classifier fair–What is the cost? | |
| JP6705763B2 (en) | Generation device, generation method, and generation program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right | Effective date of registration:20220112 Address after:523000 B502, No. 17, headquarters Second Road, Songshanhu high tech Industrial Development Zone, Dongguan City, Guangdong Province Patentee after:Dongguan Zhidun Information Security Technology Co.,Ltd. Address before:No. 230, Waihuan West Road, Guangzhou University Town, Panyu, Guangzhou City, Guangdong Province, 510006 Patentee before:Guangzhou University |