CN107016028B - Data processing method and apparatus thereof - Google Patents
Data processing method and apparatus thereof Download PDFInfo
- Publication number
- CN107016028B CN107016028B CN201611140090.XA CN201611140090A CN107016028B CN 107016028 B CN107016028 B CN 107016028B CN 201611140090 A CN201611140090 A CN 201611140090A CN 107016028 B CN107016028 B CN 107016028B
- Authority
- CN
- China
- Prior art keywords
- data set
- algorithm
- data
- verification
- source
- 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; CALCULATING OR 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
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Disclosed are a data processing method and an apparatus thereof, the method including: extracting a training data set corresponding to the algorithm from a source data set; processing the training data set through the algorithm to generate a result data set; labeling the result data set according to the feedback information to generate a labeling data set; and storing the marking data set as a verification data set according to the storage mode of the source data set. According to the method, the result data set is labeled by utilizing the feedback information, and the marking data set is used as the verification data set to carry out iterative training on the algorithm, so that the algorithm can be optimized, and the performance of the algorithm is improved.
Description
Technical Field
The present application relates to the field of computer software technologies, and in particular, to a data processing method and device.
Background
At present, with the rapid development of the internet, various forms of online transactions are emerging. For various purposes such as safety, prediction and the like, the transaction data can be processed through historical transaction data and a preset training model, and a corresponding algorithm is verified based on the processing result. For example, the transaction data can be monitored in real time through an abnormal alarm algorithm of the transaction data, alarm data is generated based on a monitoring result, then, according to feedback or data tracking of a merchant, the corresponding alarm data is labeled (marking for short), if the alarm is correct, the marking is plus, if the alarm is wrong, the marking is minus, and then the transaction data is marked.
It can be seen that the data after marking is not utilized and managed in the prior art.
Disclosure of Invention
The main object of the present invention is to provide a solution to the above mentioned problems.
An embodiment of the present application provides a data processing method, including: extracting a training data set corresponding to the algorithm from a source data set; processing the training data set through the algorithm to generate a result data set; labeling the result data set according to the feedback information to generate a labeling data set; and storing the marking data set as a verification data set according to the storage mode of the source data set.
Another embodiment of the present application provides a data processing apparatus, including: the extraction module extracts a training data set corresponding to the algorithm from the source data set; the first generation module is used for processing the training data set through the algorithm to generate a result data set; the second generation module is used for labeling the result data set according to the feedback information to generate a labeling data set; and the storage module is used for storing the marking data set into a verification data set according to the storage mode of the source data set.
According to the technical scheme, the result data set is labeled by using the feedback information, and the marking data set is used as the verification data set to carry out iterative training on the algorithm, so that the algorithm can be optimized, and the performance of the algorithm is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 illustrates a flow chart of a data processing method according to an exemplary embodiment of the present invention;
FIG. 2 shows a flow diagram of a data processing method according to another exemplary embodiment of the invention;
FIG. 3 shows a block diagram of a monitoring system utilizing the data processing method according to the invention under a monitoring platform;
fig. 4 shows a block diagram of a data processing device according to an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some 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.
The algorithm evaluation method according to the present invention will be described in detail with reference to fig. 1.
After the Data sets are obtained from the various databases, the Data sets are stored according to a predetermined storage format, the predetermined storage format includes storing the Data sets corresponding to the names of the warehouses where the Data sets are located (i.e., names of the warehouses created according to the algorithm requirements) and names of the Data tables (corresponding to the Data sets), and the Data tables can be directly obtained through a UR L which forms the Data sets by the names of the warehouses of the Data sets and the names of the Data tables, and can be rapidly queried by the UR L. the various databases described above may include Mysql databases, hbase databases and offline databases, wherein the source Data source is an Open source Data source, the Data sets are extracted by a Mysql database, the Data sets are stored in a non-relational database (Open database) which is suitable for Processing on the basis of a real-time Query database (cloud computing platform) (cloud computing platform — Open database) and database (cloud computing platform — Open database — database).
The source data set is stored in a data table form corresponding to each column and the characteristics, and the data format is convenient for extracting the corresponding characteristic data according to the columns according to the requirements. A data table (table) is a data storage unit which is logically a two-dimensional structure consisting of rows and columns, each row representing a record, each column representing an attribute, and a field having the same data type and name; a record may contain one or more columns, the name and type of each column constituting the table schema (schema) of such a table. A data store may contain a plurality of tables. Specifically, the data in the source data set can generate various types of data tables according to the characteristics of each column, and when the data of a specific characteristic is required according to the algorithm, only the data corresponding to each characteristic can be extracted.
For example, the data set can be extracted from the database by writing SQ L, and then the data set is subjected to data cleaning, and the data set after data cleaning is saved.
In an alternative embodiment, the algorithm corresponding to the application scenario may be determined before performing step S110. The application scenarios include monitoring abnormal data, transaction prediction, data mining and other scenarios, the application scenarios can be preset as required, and the application scenarios can be associated with corresponding algorithms, for example, the application scenarios and the corresponding algorithms can be correspondingly stored in a relation table, so that the corresponding algorithms can be started under the condition that the application scenarios are determined, and the corresponding scenarios and the corresponding algorithms can be added as required, for example, data analysis scenarios and analysis algorithms corresponding to the data analysis scenarios can be added as required. Because different algorithms correspond to different training sets, in the case of determining an algorithm, a training data set corresponding to the algorithm is determined according to the algorithm, for example, in an algorithm for performing anomaly monitoring or transaction prediction on a transaction platform, the training data set refers to transaction data.
Then, in step S120, the training data set is processed by the algorithm to generate a result data set. Then, in step S130, the result data set is labeled according to feedback information, which is information for feeding back the calculation result, to generate a labeled data set. For example, in the case of a data anomaly monitoring algorithm, the feedback information includes information fed back by the merchant (e.g., transaction anomalies) or information obtained from data tracking based on anomaly cues. For example, if the algorithm result is determined to be correct according to the feedback information, the result data set is labeled with a "+" label, and if the algorithm result is determined to be incorrect according to the feedback information, the result data is labeled with a "-" label, so that the labeled data set can be obtained, or the transaction data with the correct algorithm result can be labeled with a "tune" as required, and the transaction data with the incorrect algorithm result is labeled with a "false". It should be noted that tagging the result data set is only used to differentially identify the various cases in the result data set.
In step S140, the marking dataset is stored as the verification dataset according to the storage manner of the source dataset. The validation dataset is a dataset used to validate an algorithm. Specifically, the marking dataset may be converted into a data table having the same form as the data table of the source dataset; and storing the converted data table as a verification data set into a data warehouse in which the source data set is located. The name of the data table corresponding to the validation data set may be different from the name of the data table corresponding to the training data set, whereby the method according to the invention may invoke a different data set depending on the name of the data table. Since the validation dataset is a dataset that has been validated, the algorithm can be optimized by iteratively training the validation dataset according to the algorithm.
For example, in the case of evaluating an algorithm by accuracy, the data marked with a "+" in the validation data set can be compared with all transaction data to achieve accuracy.
According to the data processing method, the result data set can be labeled by utilizing the feedback information, and the labeling data set is used as the verification data set to carry out iterative training on the algorithm, so that the algorithm can be optimized, and the performance of the algorithm is improved. Further, the data processing method of the present invention can evaluate the algorithm by using the verification data set, thereby enabling intuitive and quantitative evaluation of the performance of the algorithm. In addition, the data processing method can also evaluate different algorithms under different scenes, and has strong compatibility.
Fig. 2 illustrates a flowchart of a data processing method according to another exemplary embodiment of the present invention. As shown in fig. 2, the application scenario is store portal monitoring. And determining the algorithm as an abnormal data monitoring algorithm according to the application scene.
The result data set is then tagged with feedback information, specifically, the result data can be processed with merchant feedback, when an anomaly exists in the merchant feedback, the corresponding data set is tagged with a "+". for example, a transaction corresponding to the time is determined based on the time fed back by the merchant and the transaction data related to the transaction is tagged with a "-" based on the time fed back by the merchant, or after the result data set is obtained, the transaction related to the result data set is tracked and the transaction data corresponding to the normal transaction is tagged with a "+" based on the tracked result, the transaction data corresponding to the transaction anomaly is tagged with a "-" based on the transaction data, then the tagging data set is converted into a verification data set in the form of a source data set, for example, the source data set is stored in the form of a data table in the ODPS warehouse and the data set corresponding to the tagging data set is stored in the form of a source data set warehouse, the data set is stored in the form of a tagging data set, and the data set can be modified in the form of a query data set, such as a name of a training data set, and a training data set, can be modified by a training data set, and a training data set, can be modified by a training data set.
For example, in the case of evaluating the algorithm by a false positive rate, the data tagged with a "-" in the validation data set is false positive, and the number of transactions marked with a "-" is compared with the total number of transactions, thereby obtaining a false positive rate.
Furthermore, the same application scenario may correspond to a different algorithm, depending on the association table of application scenarios and algorithms. Under the condition that the same application scene corresponds to different algorithms, under the condition that the application scene is selected, the needed algorithm is required to be determined.
In order to more clearly understand the inventive concept of the present invention, a framework diagram of a monitoring system using the data processing method according to the present invention under a monitoring platform will be described below with reference to fig. 3.
As shown in FIG. 3, regular monitoring and intelligent monitoring can be performed on the transaction situation on the monitoring platform. The rule monitoring means that a combination of monitoring rules is used to monitor the transaction situation, for example, the transaction amount of a single-day merchant is greater than 0 and the transaction amount is less than the transaction baseline 2, and the business data (also referred to as "transaction data") includes merchant transaction data, portal transaction data, and the like.
In addition, intelligent monitoring of transaction data can be selected. As shown in fig. 3, in the case of marking transaction data, the system may include an application module, a management module, and an optimization module in the case of intelligent monitoring, wherein the application module may include an algorithm providing adaptation to a scene according to an input scene; judging an algorithm output result; provide an alarm response, etc. The management module may include management of data involved in application scenarios, algorithms, and their training models. The optimization module may include training, iteration, and evaluation of the selected algorithm.
Fig. 4 shows a block diagram of a data processing device according to an exemplary embodiment of the present invention. The data processing device includes an extraction module 410, a generation module 420, a marking module 430, and a storage module 440. Those of ordinary skill in the art will understand that: the data processing apparatus in fig. 4 shows only components related to the present exemplary embodiment, and may include general components other than those shown in fig. 4.
The extracting module 410 extracts a training data set corresponding to an algorithm from a source data set, where the source data is a data set obtained by data cleaning of a data set extracted from multiple databases, stores the data set according to a predetermined storage format after obtaining the data set from the multiple databases, where the predetermined storage format includes storing the data set in correspondence with a name of a warehouse where the source data set is located (i.e., a name of a data warehouse created according to the algorithm requirement) and a name of a data table (corresponding to the data set), and can directly obtain the data table through the UR L that forms the data set by the name of the data warehouse and the name of the data table and quickly query the data set by using the UR L.
Alternatively, before the extraction module 410 performs the extraction operation, the data processing apparatus may determine an algorithm corresponding to the selected application scenario by using a determination module (not shown), so that the extraction module 410 may extract a training data set corresponding to the algorithm from the source data set, and further, the data processing apparatus further includes a storage module (not shown), which may store the application scenario and the algorithm corresponding to the application scenario in association in advance.
The first generation module 420 processes the training data set through the algorithm to generate a result data set. The second generation module 430 then tags the resulting data set according to the feedback information to generate a tagged data set. The feedback information refers to information for feeding back a calculation result. For example, in the case of a data anomaly monitoring algorithm, the feedback information includes information fed back by the merchant (e.g., transaction anomalies) or information obtained from data tracking based on anomaly cues. For example, if the algorithm result is determined to be correct according to the feedback information, the result data set is labeled with a "+" label, and if the algorithm result is determined to be incorrect according to the feedback information, the result data is labeled with a "-" label, so that the labeled data set can be obtained, or the transaction data with the correct algorithm result can be labeled with a "tune" as required, and the transaction data with the incorrect algorithm result is labeled with a "false". It should be noted that tagging the result data set is only used to differentially identify the various cases in the result data set.
The storage module 440 stores the marking dataset as the verification dataset according to the storage manner of the source dataset. Specifically, the storage module 440 converts the marking dataset into a data table in the same form as the data table of the source dataset; and storing the converted data table as a verification data set into a data warehouse in which the source data set is located. The name of the data table corresponding to the validation data set may be different from the name of the data table corresponding to the training data set, whereby the method according to the invention may invoke a different data set depending on the name of the data table. Since the validation dataset is a dataset that has been validated, the algorithm can be optimized by iteratively training the validation dataset according to the algorithm.
For example, in the case of evaluating an algorithm by accuracy, the data marked with a "+" tag in the validation data set can be compared with all transaction data to achieve accuracy.
According to the data processing equipment, the result data set can be labeled by utilizing the feedback information, and the labeling data set is used as the verification data set to carry out iterative training on the algorithm, so that the algorithm can be optimized, and the performance of the algorithm is improved. Further, the data processing apparatus of the present invention can evaluate the algorithm by using the verification data set, thereby enabling intuitive and quantitative evaluation of the performance of the algorithm. In addition, the data processing equipment can also evaluate different algorithms under different scenes, and has strong compatibility.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application. The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A data processing method, comprising:
extracting a training data set corresponding to an algorithm from a source data set, wherein the source data set is stored in a data table form corresponding to each column and characteristic;
processing the training data set through the algorithm to generate a result data set;
labeling the result data set according to feedback information to generate a labeling data set, wherein the feedback information refers to information for feeding back the algorithm result;
storing the marking data set into a verification data set according to a storage mode of the source data set, wherein the verification data set is used for verifying the algorithm, and the verification data set is used for performing iterative training on the verification data set according to the algorithm to optimize the algorithm;
the step of storing the marking data set as the verification data set according to the storage mode of the source data set comprises the following steps:
converting the marking data set into a data table with the same form as that of the data table of the source data set;
and storing the converted data table as a verification data set into a data warehouse in which the source data set is located.
2. The method of claim 1, prior to extracting the training data set corresponding to the algorithm from the source data set, further comprising: an algorithm corresponding to the selected application scenario is determined.
3. The method of claim 2, prior to determining the algorithm corresponding to the selected application scenario, further comprising: and associating and storing the application scene and the algorithm corresponding to the application scene in advance.
4. A method as claimed in any one of claims 1 to 3 wherein the source data set is a data set after data cleansing of data sets extracted from a plurality of databases.
5. The method of claim 1, after generating the marking dataset, further comprising: and calling data in the verification data set to evaluate the performance of the algorithm.
6. A data processing apparatus, characterized by comprising:
the extraction module is used for extracting a training data set corresponding to the algorithm from a source data set, wherein the source data set is stored in a data table form corresponding to each column and characteristic;
the first generation module is used for processing the training data set through the algorithm to generate a result data set;
the second generation module is used for labeling the result data set according to the feedback information to generate a labeling data set;
the storage module is used for storing the marking data set into a verification data set according to a storage mode of the source data set, the verification data set is used for verifying the algorithm, and the verification data set is used for carrying out iterative training on the verification data set according to the algorithm to optimize the algorithm;
the storage module converts the marking data set into a data table in the same form as the data table of the source data set; and storing the converted data table as a verification data set into a data warehouse in which the source data set is located.
7. The apparatus of claim 6, further comprising: and the determining module is used for determining the algorithm corresponding to the selected application scene, so that the extracting module extracts the training data set corresponding to the algorithm from the source data set.
8. The apparatus of claim 7, further comprising: and the storage module is used for associating and storing the application scene and the algorithm corresponding to the application scene in advance.
9. An apparatus, according to any one of claims 6 to 8, wherein said source data set is a data set after data cleansing of data sets extracted from a plurality of databases.
10. The apparatus of claim 6, further comprising: and the evaluation module is used for calling the data in the verification data set to evaluate the performance of the algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611140090.XA CN107016028B (en) | 2016-12-12 | 2016-12-12 | Data processing method and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611140090.XA CN107016028B (en) | 2016-12-12 | 2016-12-12 | Data processing method and apparatus thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107016028A CN107016028A (en) | 2017-08-04 |
| CN107016028B true CN107016028B (en) | 2020-07-14 |
Family
ID=59439591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611140090.XA Active CN107016028B (en) | 2016-12-12 | 2016-12-12 | Data processing method and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016028B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108198268B (en) * | 2017-12-19 | 2020-10-16 | 江苏极熵物联科技有限公司 | Production equipment data calibration method |
| CN109213656A (en) * | 2018-07-23 | 2019-01-15 | 武汉智领云科技有限公司 | A kind of interactive mode big data dysgnosis detection system and method |
| CN110954110B (en) * | 2019-12-10 | 2023-04-07 | 西安电子科技大学 | X-ray pulsar navigation processing system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120217A (en) * | 2015-08-21 | 2015-12-02 | 上海小蚁科技有限公司 | Intelligent camera motion detection alarm system and method based on big data analysis and user feedback |
| CN105279382A (en) * | 2015-11-10 | 2016-01-27 | 成都数联易康科技有限公司 | Medical insurance abnormal data on-line intelligent detection method |
| CN106097346A (en) * | 2016-06-13 | 2016-11-09 | 中国科学技术大学 | A kind of video fire hazard detection method of self study |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102207940B (en) * | 2010-03-31 | 2014-11-05 | 国际商业机器公司 | Method and system for checking data |
-
2016
- 2016-12-12 CN CN201611140090.XA patent/CN107016028B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120217A (en) * | 2015-08-21 | 2015-12-02 | 上海小蚁科技有限公司 | Intelligent camera motion detection alarm system and method based on big data analysis and user feedback |
| CN105279382A (en) * | 2015-11-10 | 2016-01-27 | 成都数联易康科技有限公司 | Medical insurance abnormal data on-line intelligent detection method |
| CN106097346A (en) * | 2016-06-13 | 2016-11-09 | 中国科学技术大学 | A kind of video fire hazard detection method of self study |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107016028A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI673666B (en) | Method and device for data risk control | |
| CN106202235B (en) | Data processing method and device | |
| CN106557486A (en) | A kind of storage method and device of data | |
| CN108734304B (en) | Training method and device of data model and computer equipment | |
| CN106897342B (en) | Data verification method and equipment | |
| JP6586184B2 (en) | Data analysis support device and data analysis support method | |
| CN107016028B (en) | Data processing method and apparatus thereof | |
| US20170140301A1 (en) | Identifying social business characteristic user | |
| CN110704418A (en) | Block chain information query method, device and equipment | |
| CN113836128A (en) | Abnormal data identification method, system, equipment and storage medium | |
| CN111324883B (en) | Internet-based E-commerce platform intrusion detection method and computer equipment | |
| CN107038193B (en) | Text information processing method and device | |
| US10296527B2 (en) | Determining an object referenced within informal online communications | |
| JP2018133044A (en) | Webapi execution flow generation device and webapi execution flow generation method | |
| CN107562533B (en) | Data loading processing method and device | |
| US11308115B2 (en) | Method and system for persisting data | |
| CN112507725B (en) | Static publishing method, device, equipment and storage medium of financial information | |
| CN114398562A (en) | Shop data management method, device, equipment and storage medium | |
| CN106557564A (en) | A kind of object data analysis method and device | |
| CN106909570B (en) | Data conversion method and device | |
| CN110414186B (en) | Data asset segmentation verification method and device | |
| CN116483735B (en) | Method, device, storage medium and equipment for analyzing influence of code change | |
| US20220261666A1 (en) | Leveraging big data, statistical computation and artificial intelligence to determine a likelihood of object renunciation prior to a resource event | |
| US20220100631A1 (en) | Microservices graph generation | |
| CN114693321A (en) | Image label prediction method, device, equipment and storage medium |
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: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Patentee after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Patentee before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Patentee after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Patentee before: Alibaba Group Holding Ltd. |