CN109359126B - Method and system for constructing intelligent learning query model based on business user habits - Google Patents
Method and system for constructing intelligent learning query model based on business user habits Download PDFInfo
- Publication number
- CN109359126B CN109359126B CN201811009136.3A CN201811009136A CN109359126B CN 109359126 B CN109359126 B CN 109359126B CN 201811009136 A CN201811009136 A CN 201811009136A CN 109359126 B CN109359126 B CN 109359126B
- Authority
- CN
- China
- Prior art keywords
- data
- log
- query
- user
- habits
- 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
Abstract
The invention belongs to the technical field of data query, and particularly relates to a construction method of an intelligent learning query model based on business user habits, which comprises the following steps: s1, acquiring data query records of the service user from the data source; s2, analyzing data query habits according to the data query records obtained in the step S1; s3, constructing a query model according to the data query habit analysis result obtained in the step S2. The invention also provides an intelligent learning and inquiring system based on the habits of the service users. According to the invention, the data query habit of the service user is analyzed, a data query scheme is formulated according to the analysis result, and a query model is constructed, so that the data concerned by the service user can be pushed to the service user in advance, and the method has the characteristics of short query time and good user experience effect.
Description
The present application claims application number 201810332569.6 filed 2018, 04, 13, entitled priority of an inventive patent application for an intelligent learning query model based on business user habits, which is incorporated herein by reference.
Technical Field
The invention belongs to the technical field of data query, and particularly relates to a construction method and a system of an intelligent learning query model based on business user habits.
Background
In the existing data query system, especially the comprehensive prevention management system, the main function is to perform operations such as query, statistics, analysis and the like on the call ticket data accessed by the front end, however, the data volume accessed by the system per day exceeds ten million orders, the accumulated data volume in one month is hundred million, for such data query, a user usually selects various query conditions and then manually queries, the query time is relatively long, the user operation is complex, and the experience effect is poor. Aiming at the ever-increasing service data in the system, modeling research needs to be carried out on daily service query operation of a service user, a service model for the service user to carry out query is mainly constructed according to the operation specification of the service user, and relevant query data is preprocessed, so that the response speed is improved.
From the above analysis, the data query system of the prior art has the following disadvantages:
the data query system in the prior art has complex user operation, thereby causing long query time and poor user experience effect.
Disclosure of Invention
The invention provides a construction method of an intelligent learning query model based on business user habits, which can effectively solve the technical problem of long query time of the existing data query system.
In order to solve the above problems, the invention provides a method for constructing an intelligent learning query model based on business user habits, which comprises the following steps:
the method for constructing the intelligent learning query model based on the habits of the service users comprises the following steps:
s1: acquiring a data query record of a service user from a data source; the data query record is a user operation log file; the data source is a log storage system;
s2: performing data query habit analysis according to the data query record obtained in the step S1;
s3: and constructing a query model according to the data query habit analysis result obtained in the step S2.
Preferably, in step S2, the data query habit analysis specifically includes the following steps:
s21: periodically analyzing the data query records obtained in the step S1; the data analysis comprises data cleaning, data filtering, data comparison and data classification;
s22: extracting frequent item features of the browsing interest patterns of the service users from the data analysis results obtained in the step S21, and calculating the operation weight values of the habits of the service users;
s23: filing the same business operation according to the operation weight value obtained in the step S22 to form a behavior model;
s24: extracting input and output parameters of the service user from the data analysis result obtained in the step S21; the input and output parameters comprise source information, called information, topic classification information, local point information and local direction information;
s25: and acquiring the data query habit of the service user according to the behavior model formed in the step S23 and the input and output parameters of the service user extracted in the step S24.
Preferably, step S22 specifically includes the following steps:
s221, in the data analysis result obtained in the step S21, in a Wed log node n of the data query record, defining the distribution state of the feature information of the browsing interest mode of the service user as l (n), and defining the set of the QoS requirement between two service users and the feature information of the interest mode as L (n); evaluating the Wed log node n according to the trust of the service user to the data source, and constructing a behavior learning model by adopting a multi-mode characteristic state recombination mode;
s222, defining the state feature set of one Wed log node n as Dn(ii) a Defining the child node set of l (n) as Dl(n)In the semantic ontology model of the child nodes of l (n), the average child node of the feature set of the user browsing interest mode is obtained
S223, the total average sub-node number from the source node to the target node topology tree is defined as M, and the total number of the interest feature points browsed by the user in the resource layer node meets the following relation:
Preferably, in step S3, constructing the query model includes the following steps:
s31: rebuilding a log system;
s32: log data persistence;
s33: in the log system reconstructed in step S31, a data query model is created from the data query habit analysis result obtained in step S2.
Preferably, in step S31, the rebuilding log system specifically includes the following steps:
s311, reorganizing the data structure of log analysis: adding new log data according to the data parameters required by the data query analysis result obtained in the step S2; the log data comprises a user name, a user operation module type, user operation time, and user input and output parameters;
s312, adding a log storage queue: writing the log data added in the step S311 into a log persistence queue, and processing the log by a consumer of the log persistence queue;
s313, log data storage: and when the consumers of the log persistent queue monitor that the log data enter the queue, circularly popping according to the enqueue sequence of the queue, and writing the obtained log data into a database for storage.
Preferably, in step S32, the log data persistence includes the steps of:
s321, configuring a persistence range of log data: performing persistent control on one or more operations of the service user;
s322, filtering and cleaning the user log data: collecting the log data subjected to the persistent control in the step S321, and screening the collected log data according to an effective log rule to obtain effective log data;
s323, storage of the cleaned log data: writing the cleaned effective log data into a log persistence queue, and processing the log data by the consumers of the log persistence queue;
s324, log data storage: and when the consumers of the log persistent queue monitor that the log data enter the queue, circularly popping according to the enqueue sequence of the queue, and writing the obtained log data into a database for storage.
Preferably, the method for constructing an intelligent learning query model based on business user habits further includes step S4, and step S4 includes: and extracting query data from the constructed query model and pushing the query data to a service user.
Preferably, in step S4, the query model extracts the query data by setting a filtering condition.
Further preferably, the filtering condition is call ticket data; the call bill data comprises one or more of local points, local directions, telephone calling time, source places, called places, topic classifications, call duration, template numbers and states.
The invention also provides an intelligent learning and inquiring system based on business user habits, which can realize the construction method of the intelligent learning and inquiring model based on business user habits, and comprises the following steps:
the data source storage system is used for receiving and storing an external data source;
the data filtering system is connected with the data source storage system and is used for filtering and screening the data source at regular time;
the data index storage system is connected with the data filtering system and is used for storing the filtered and screened data source;
and the data display system is connected with the data index storage system and is used for providing an operation space for a service user and displaying the push data received by the service user.
Analysis shows that compared with the prior art, the invention has the advantages and beneficial effects that:
the data query method and the data query system provided by the invention can be used for making a data query scheme aiming at the analysis result by analyzing the data query habit of the service user and improving the existing data query system, can be used for pushing the data concerned by the service user to the service user in advance, and have the characteristics of short query time and good user experience effect.
Drawings
Fig. 1 is a flow diagram illustrating a method for constructing an intelligent learning query model based on business user habits according to the present invention.
Fig. 2 is a schematic analysis flow diagram of the intelligent learning query system based on business user habits according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
As shown in fig. 1 and fig. 2, the present invention provides a method for constructing an intelligent learning query model based on business user habits, comprising the following steps:
s1: acquiring a data query record of a service user from a data source; the data query record is a user operation log file; the data source is a log storage system;
s2: performing data query habit analysis according to the data query record obtained in the step S1;
s3: and constructing a query model according to the data query habit analysis result obtained in the step S2.
As a specific implementation manner of this embodiment, in step S2, the data query habit analysis, that is, log analysis, the log analysis content mainly analyzes information such as a user daily operation process, a data type focused by the user, an input condition and an output parameter of the user daily query, and specifically includes the following steps:
s21: periodically analyzing the data query records obtained in the step S1; the data analysis comprises data cleaning, data filtering, data comparison and data classification;
s22: from the data analysis result obtained in step S21, the frequent item features of the browsing interest pattern of the service user are extracted, and the operation weight value used by the service user is calculated.
As a specific implementation manner of this embodiment, it includes the following steps:
s221, in the data analysis result obtained in step S21, in a Wed log node n of the data query record, defining the distribution state of the feature information of the browsing interest pattern of the service user as l (n), defining the set of the QoS requirement and the feature information of the interest pattern between two service users as l (n), and in this embodiment, defining the set of the QoS requirement and the feature point of interest between users A, B as l (n); evaluating the Wed log node n according to the trust of the service user to the data source, and constructing a behavior learning model by adopting a multi-mode characteristic state recombination mode; a user builds a behavior learning model for a resource trust evaluation node n in a multi-mode characteristic state recombination mode;
s222, in the master node set of the feature space, defining the state feature set of Wed log node n as Dn(ii) a Defining the child node set of l (n) as Dl(n)In the semantic ontology model of the child nodes of l (n), the average child node of the feature set of the user browsing interest mode is obtained
S223, the total average sub-node number from the source node to the target node topology tree is defined as M, and the total number of the interest feature points browsed by the user in the resource layer node meets the following relation:
S23: and (4) filing the same business operation according to the operation weight value obtained in the step (S22) to form a behavior model. As an alternative implementation manner of this embodiment, archiving processing of similar business operations may also be performed, and a behavior model is formed;
s24: extracting input and output parameters of the service user from the data analysis result obtained in the step S21; the input and output parameters comprise source information, called information, topic classification information, local point information and local direction information;
s25: and acquiring the data query habit of the service user according to the behavior model formed in the step S23 and the input and output parameters of the service user extracted in the step S24.
As a specific implementation manner of this embodiment, in step S3, a query model is constructed according to the data query habit analysis result obtained in step S2, and the log system of the existing query system can be re-modified and log data can be persisted. In step S3, building the query model includes the following steps:
s31: rebuilding a log system; as a specific implementation manner of this embodiment, in step S31, the rebuilding log system specifically includes the following steps:
s311, reorganizing the data structure of log analysis: adding new log data according to the data parameters required by the data query analysis result obtained in the step S2; the log data comprises a user name, a user operation module type, user operation time, and user input and output parameters;
s312, adding a log storage queue: and writing the log data added in the step S311 into a log persistence queue, and processing the log by a consumer of the log persistence queue. The log storage queue is added, the main function is to write data into a log persistence queue, a large amount of operation logs can be generated due to continuous operation of a user during work, and in order to keep stable operation of a system and not occupy processing time of the system, the logs are processed by queue consumers.
S313, log data storage: and when the consumers of the log persistent queue monitor that the log data enter the queue, circularly popping according to the enqueue sequence of the queue, and writing the obtained log data into a database for storage.
S32: log data persistence; the log data persistence mainly stores input and output parameters of business personnel and operation processes of the business personnel, and performs statistical analysis on the data so as to obtain data query habits of business users and create a data query model. Due to continuous operation of a user during work, a large amount of operation logs can be generated; in order to keep the system running stably and not occupy the processing time of the system; the log persistence mode stores the user data in a data queue mode.
As a specific implementation manner of this embodiment, in step S32, the log data persistence includes the following steps:
s321, configuring a persistence range of log data: performing persistent control on one or more operations of the service user; because the business personnel in the system operate a lot in work and the business types are inconsistent, the system can carry out persistent control aiming at one or more operations. In this embodiment, the setup A, B function enables log storage and the log persistence system persists A, B.
S322, filtering and cleaning the user log data: collecting the log data subjected to the persistent control in the step S321, and screening the collected log data according to an effective log rule to obtain effective log data; the valid log data refers to data meeting log validity rules.
S323, storage of the cleaned log data: writing the cleaned effective log data into a log persistence queue, and processing the log data by the consumers of the log persistence queue;
s324, log data storage: and when the consumers of the log persistent queue monitor that the log data enter the queue, circularly popping according to the enqueue sequence of the queue, and writing the obtained log data into a database for storage.
S33: in the log system reconstructed in step S31, a data query model is created from the data query habit analysis result obtained in step S2.
As a preferred implementation manner of this embodiment, the method for constructing an intelligent learning query model based on business user habits further includes step S4, where step S4 includes: and extracting query data from the constructed query model and pushing the query data to a service user. The query model extracts the query data by setting a filter condition. The filtering condition is call ticket data; the call bill data comprises one or more of local points, local directions, telephone calling time, source places, called places, topic classifications, call duration, template numbers and states.
The method for constructing the intelligent learning query model based on the business user habits can enable the log storage service to automatically store various log data operated by a user, the analysis service analyzes information such as a normal operation process of the user, a data type concerned by the user, input conditions and output parameters of daily query of the user through effective log rules, a data query model is automatically generated, data is regularly screened through a data preprocessing system according to the model, the operations mainly comprise filtering, cleaning, classifying and the like of single data, different types of data are obtained, different types of key business data are stored in a specific database for data management, various types of data are associated through Rowkey (namely row key), and basic data are provided for quick query operation of the business system.
The invention also provides an intelligent learning and inquiring system based on business user habits, which comprises a data source storage system, a data source storage system and a data processing system, wherein the data source storage system is used for receiving and storing external data sources;
the data filtering system is connected with the data source storage system and is used for filtering and screening the data source at regular time;
the data index storage system is connected with the data filtering system and is used for storing the filtered and screened data source;
and the data display system is connected with the data index storage system and is used for providing an operation space for a service user and displaying the push data received by the service user.
The model driving service obtains a user behavior model according to user behavior analysis, extracts effective data of the existing call ticket data of the system, extracts key fields (calling time, calling number, called number, source place, called place, local point, local direction, topic classification and the like) in the call ticket, creates a unique index, and stores the data into a Hadoop distributed file storage system for user query. The log analysis service can update user behavior habits at regular time, wherein the user behavior habits comprise user attention data types, input parameters (calling time, calling numbers, called numbers, source places, called places, local points, local directions, topic classifications and the like), and the model driving service optimizes the model according to the updated user behavior habits to realize the function of dynamically adjusting the model.
Analysis shows that compared with the prior art, the invention has the advantages and beneficial effects that:
the data query method and the data query system provided by the invention can be used for making a data query scheme aiming at the analysis result by analyzing the data query habit of the service user and improving the existing data query system, can be used for pushing the data concerned by the service user to the service user in advance, and have the characteristics of short query time and good user experience effect.
It will be appreciated by those skilled in the art that the invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The embodiments disclosed above are therefore to be considered in all respects as illustrative and not restrictive. All changes which come within the scope of or equivalence to the invention are intended to be embraced therein.
Claims (9)
1. A construction method of an intelligent learning query model based on business user habits is characterized by comprising the following steps:
s1: acquiring a data query record of a service user from a data source; the data query record is a user operation log file; the data source is a log storage system;
s2: performing data query habit analysis according to the data query record obtained in the step S1;
s3: constructing a query model according to the data query habit analysis result obtained in the step S2;
in step S2, the data query habit analysis specifically includes the following steps:
s21: periodically analyzing the data query records obtained in the step S1; the data analysis comprises data cleaning, data filtering, data comparison and data classification;
s22: extracting frequent item features of the browsing interest patterns of the service users from the data analysis results obtained in the step S21, and calculating the operation weight values of the habits of the service users;
s23: filing the same business operation according to the operation weight value obtained in the step S22 to form a behavior model;
s24: extracting input and output parameters of the service user from the data analysis result obtained in the step S21; the input and output parameters comprise source information, called information, topic classification information, local point information and local direction information;
s25: and acquiring the data query habit of the service user according to the behavior model formed in the step S23 and the input and output parameters of the service user extracted in the step S24.
2. The method for constructing the intelligent learning and query model based on business user habits according to claim 1, wherein the step S22 specifically includes the following steps:
s221, in the data analysis result obtained in the step S21, in a Web log node n recorded by the data query, defining the distribution state of the characteristic information of the browsing interest mode of the service user as l (n), and defining the set of the QoS requirement between the two service users and the characteristic information of the interest mode as L (n);
s222, defining the state feature set of a Web log node n as Dn(ii) a Defining the child node set of l (n) as Dl(n)In the semantic ontology model of the child nodes of l (n), the average child node of the feature set of the user browsing interest mode is obtained
S223, the total average sub-node number from the source node to the target node topology tree is defined as M, and the total number of the interest feature points browsed by the user in the resource layer node meets the following relation:
3. The method for constructing the intelligent learning query model based on business user habits according to claim 2, wherein in step S3, constructing the query model comprises the following steps:
s31: rebuilding a log system;
s32: log data persistence;
s33: in the log system reconstructed in step S31, a data query model is created from the data query habit analysis result obtained in step S2.
4. The method for constructing an intelligent learning and query model based on business user habits according to claim 3, wherein in step S31, the log rebuilding system specifically includes the following steps:
s311, reorganizing the data structure of log analysis: adding new log data according to the data parameters required by the data query analysis result obtained in the step S2; the log data comprises a user name, a user operation module type, user operation time, and user input and output parameters;
s312, adding a log storage queue: writing the log data added in the step S311 into a log persistence queue, and processing the log by a consumer of the log persistence queue;
s313, log data storage: and when the consumers of the log persistent queue monitor that the log data enter the queue, circularly popping according to the enqueue sequence of the queue, and writing the obtained log data into a database for storage.
5. The method for constructing an intelligent learning query model based on business user habits according to claim 4, wherein in step S32, the log data persistence comprises the following steps:
s321, configuring a persistence range of log data: performing persistent control on one or more operations of the service user;
s322, filtering and cleaning the user log data: collecting the log data subjected to the persistent control in the step S321, and screening the collected log data according to an effective log rule to obtain effective log data;
s323, storage of the cleaned log data: writing the cleaned effective log data into a log persistence queue, and processing the log data by the consumers of the log persistence queue;
s324, log data storage: and when the consumers of the log persistent queue monitor that the log data enter the queue, circularly popping according to the enqueue sequence of the queue, and writing the obtained log data into a database for storage.
6. The method for constructing the intelligent learning and querying model based on the habits of the business users according to claim 1, wherein:
includes a step S4, the step S4 includes: and extracting query data from the constructed query model and pushing the query data to a service user.
7. The method for constructing the intelligent learning and query model based on the habits of the business users according to claim 6, wherein:
in step S4, the query model extracts the query data by setting filtering conditions.
8. The method for constructing the intelligent learning and query model based on the habits of the business users according to claim 7, wherein:
the filtering condition is call ticket data; the call bill data comprises one or more of local points, local directions, telephone calling time, source places, called places, topic classifications, call duration, template numbers and states.
9. An intelligent learning and querying system based on business user habits is characterized in that the method for constructing the intelligent learning and querying model based on business user habits, which is disclosed by any one of claims 1 to 8, is realized, and comprises the following steps:
the data source storage system is used for receiving and storing an external data source;
the data filtering system is connected with the data source storage system and is used for filtering and screening the data source at regular time;
the data index storage system is connected with the data filtering system and is used for storing the filtered and screened data source;
and the data display system is connected with the data index storage system and is used for providing an operation space for a service user and displaying the push data received by the service user.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810332569.6A CN108536841A (en) | 2018-04-13 | 2018-04-13 | Intelligence learning interrogation model based on service-user custom |
| CN2018103325696 | 2018-04-13 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109359126A CN109359126A (en) | 2019-02-19 |
| CN109359126B true CN109359126B (en) | 2021-06-04 |
Family
ID=63480536
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810332569.6A Pending CN108536841A (en) | 2018-04-13 | 2018-04-13 | Intelligence learning interrogation model based on service-user custom |
| CN201811009136.3A Active CN109359126B (en) | 2018-04-13 | 2018-08-30 | Method and system for constructing intelligent learning query model based on business user habits |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810332569.6A Pending CN108536841A (en) | 2018-04-13 | 2018-04-13 | Intelligence learning interrogation model based on service-user custom |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108536841A (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110765427B (en) * | 2019-09-23 | 2022-08-19 | 秦滢珺 | Accounting document processing method |
| CN111666308B (en) * | 2020-06-03 | 2022-09-30 | 国家计算机网络与信息安全管理中心 | Behavior analysis-based intelligent big data recommendation query method and system |
| CN114780620B (en) * | 2022-06-21 | 2022-08-26 | 联通(江苏)产业互联网有限公司 | Cloud computing service analysis method, device and system based on big data mining performance |
| CN117520597B (en) * | 2023-09-11 | 2024-04-26 | 北京国卫星通科技有限公司 | Data record implementation method of inertial navigation data acquisition and analysis system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324720A (en) * | 2013-06-25 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Personalized recommendation method and system according to user state |
| CN103970891A (en) * | 2014-05-23 | 2014-08-06 | 三星电子（中国）研发中心 | Method for inquiring user interest information based on context |
| CN104462267A (en) * | 2014-11-23 | 2015-03-25 | 国云科技股份有限公司 | Fast data query method |
| CN106294688A (en) * | 2016-08-05 | 2017-01-04 | 浪潮软件集团有限公司 | Query expansion method, device and system based on user characteristic analysis |
| CN106294390A (en) * | 2015-05-20 | 2017-01-04 | 上海纳鑫信息科技有限公司 | A kind of data mining analysis method and system |
| CN107577805A (en) * | 2017-09-26 | 2018-01-12 | 华南理工大学 | A kind of business service system towards the analysis of daily record big data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096667B (en) * | 2009-12-09 | 2015-06-03 | 高文龙 | Information retrieval method and system |
| AU2015225870B2 (en) * | 2014-01-27 | 2020-02-27 | Camelot Uk Bidco Limited | System and methods for cleansing automated robotic traffic from sets of usage logs |
| CN103995828B (en) * | 2014-04-11 | 2017-06-13 | 西安电子科技大学宁波信息技术研究院 | A kind of cloud storage daily record data analysis method |
| US10346393B2 (en) * | 2014-10-20 | 2019-07-09 | International Business Machines Corporation | Automatic enumeration of data analysis options and rapid analysis of statistical models |
| US10592482B2 (en) * | 2015-12-29 | 2020-03-17 | Cognizant Technology Solutions India Pvt. Ltd. | Method and system for identifying and analyzing hidden data relationships in databases |
-
2018
- 2018-04-13 CN CN201810332569.6A patent/CN108536841A/en active Pending
- 2018-08-30 CN CN201811009136.3A patent/CN109359126B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324720A (en) * | 2013-06-25 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Personalized recommendation method and system according to user state |
| CN103970891A (en) * | 2014-05-23 | 2014-08-06 | 三星电子（中国）研发中心 | Method for inquiring user interest information based on context |
| CN104462267A (en) * | 2014-11-23 | 2015-03-25 | 国云科技股份有限公司 | Fast data query method |
| CN106294390A (en) * | 2015-05-20 | 2017-01-04 | 上海纳鑫信息科技有限公司 | A kind of data mining analysis method and system |
| CN106294688A (en) * | 2016-08-05 | 2017-01-04 | 浪潮软件集团有限公司 | Query expansion method, device and system based on user characteristic analysis |
| CN107577805A (en) * | 2017-09-26 | 2018-01-12 | 华南理工大学 | A kind of business service system towards the analysis of daily record big data |
Non-Patent Citations (1)
| Title |
|---|
| "大规模查询日志分析模型构建机制";王逸兮 等;《数字通信世界》;20171130;第（2017）卷(第11期);第109页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109359126A (en) | 2019-02-19 |
| CN108536841A (en) | 2018-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359126B (en) | Method and system for constructing intelligent learning query model based on business user habits | |
| CN108595461B (en) | Interest exploration method, storage medium, electronic device and system | |
| CN111475509A (en) | Big data-based user portrait and multidimensional analysis system | |
| CN104714984A (en) | Database optimization method and device | |
| CN102542474A (en) | Method for sorting inquiry results and device | |
| Hill et al. | Building an effective representation for dynamic networks | |
| CN110147360A (en) | A kind of data integration method, device, storage medium and server | |
| CN112817834B (en) | Data table evaluation method and device | |
| CN107832333A (en) | Method and system based on distributed treatment and DPI data structure user network data fingerprint | |
| US20140337274A1 (en) | System and method for analyzing big data in a network environment | |
| CN110009416A (en) | A kind of system based on big data cleaning and AI precision marketing | |
| CN113722383A (en) | Investigation device and method based on time sequence information | |
| CN106528804A (en) | User grouping method based on fuzzy clustering | |
| CN107704289A (en) | Using method for cleaning, device, storage medium and electronic equipment | |
| CN111666308B (en) | Behavior analysis-based intelligent big data recommendation query method and system | |
| CN114238360A (en) | User behavior analysis system | |
| CN114116872A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| CN106446289A (en) | Information inquiry method and device based on Pinpoint | |
| US11776078B2 (en) | Systems and methods for generating strategic competitive intelligence data relevant for an entity | |
| CN106933993B (en) | Information processing method and device | |
| CN110175151A (en) | A kind of processing method, device, equipment and the storage medium of agricultural big data | |
| JP4892896B2 (en) | Communication analysis apparatus and method | |
| CN113298310A (en) | BI data analysis system and method based on custom configuration | |
| CN114911769A (en) | Data management method and system supporting custom dynamic tag construction | |
| CN114265887A (en) | Dimension data processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |