CN109831478A - Rule-based and model distributed processing intelligent decision system and method in real time - Google Patents
Rule-based and model distributed processing intelligent decision system and method in real time Download PDFInfo
- Publication number
- CN109831478A CN109831478A CN201811556554.4A CN201811556554A CN109831478A CN 109831478 A CN109831478 A CN 109831478A CN 201811556554 A CN201811556554 A CN 201811556554A CN 109831478 A CN109831478 A CN 109831478A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- business
- target service
- rule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention provides rule-based and model distributed processing intelligent decision system and method in real time.The described method includes: reading target service data to be processed and being pre-processed to it;It is loaded as the business rule and machine learning model of the target service data deployment;The target service data are analyzed according to the logical order between the business rule and the machine learning model, and export analysis result.Technical solution of the present invention has preferable complicated event processing capability in real time, and handling capacity is high, is not necessarily to secondary development in face of different business scenarios.
Description
Technical field
The present invention relates to the real-time calculating fields of big data, more particularly to suitable for the anti-fraud of finance, IOT internet of things equipment
Rule-based and model distributed processing intelligent decision system and the method in real time of more scenes such as monitoring alarm.
Background technique
Big data era, data contain a large amount of value as the carrier of information, are the most important means of production.With
The development of internet industry, data are also momently generating and are presenting explosive growth, how timely and effectively to handle
Data simultaneously excavate valuable information to service for production, just become particularly important.
In the method to data processing, event handling is that a kind of monitoring, analysis and therefrom obtain the one of decision at information flow
Kind method.And Complex event processing exactly analyzes multi-information flow and it is existing between specific mode or event to identify
Certain complex relationship, for example, a possibility that getting a profit, potential threat etc., and this is responded as far as possible.It is deposited in reality
In a variety of similar scenes, such as:
1. financial field: transaction analysis, fraud detection, risk management etc.;
2. medical field: complaint handling, patient condition real-time detection etc.;
3. transportation industry: real-time road etc.;
4. Internet of Things automation: equipment state abnormality detection, flow monitoring etc..
In traditional solution, big data batch calculates the tupe first deposited and calculated afterwards can be effectively for certain specific
Business scenario carries out Data Analysis Services, state-detection, but is not particularly suited for the scene high to requirement of real-time;On the other hand,
Although the quasi real time scheme based on regulation engines such as traditional Spring project combination Drools can prolong in detecting event, processing in time
It is lower late, but handling capacity is not high, it is also limited to the generating date ability of magnanimity, and different business scenarios is needed
Want secondary development, scalability poor.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide rule-based and model distributions
Processing intelligent decision system and method in real time, for solving, handling capacity poor to complicated event processing capability in real time in the prior art
The technical problems such as secondary development are needed under low, more scenes.
In order to achieve the above objects and other related objects, the present invention provides a kind of rule-based and model distributed real-time
Handle intelligent decision system, comprising: data acquisition module for obtaining business datum to be processed, and sends it to first
Message-oriented middleware module;First message middleware module, for by received business datum partitioned storage, and to core decision model
Block gives out information, to provide the target service data of analysis needed for it to the core decision-making module;Service arrangement module, is used for
Business rule needed for target service data described in deployment analysis, machine learning model, and the logical order between both;Core
Heart decision-making module, for from reading the target service data in the first message middleware module and being carried out in advance to it
Reason;Load the business rule and machine learning model that the service arrangement module is target service data deployment;According to institute
The logical order stated between business rule and the machine learning model analyzes the target service data, and will analysis
As a result it is sent to second message middleware module;Second message middleware module, for storing the analysis as a result, and to business
Side sends message, with the analysis result needed for providing it to the business side.
In one embodiment of the invention, the first message middleware module uses Kafka message-oriented middleware cluster;It is described
Kafka message-oriented middleware cluster creates specific topic, the partition that each topic includes according to different types of service
Number relies on concrete scene.
In one embodiment of the invention, the service arrangement module, comprising: Business Rule Engine, for defeated according to user
Enter to dispose business rule;Machine learning model engine, for inputting deployment machine learning model according to user;Monitoring management mould
Block, for monitoring the resource service condition of the first message middleware module and the operating status of the core decision-making module;
Authority management module, the data area that can be accessed for controlling business.
In one embodiment of the invention, the core decision-making module, comprising: stream process module, for reading incremental mesh
Mark business datum simultaneously pre-processes it in real time;It is suitable according to the logic between the business rule and the machine learning model
Incremental target service data described in ordered pair are analyzed in real time, and analysis result is sent to second message middleware module;
Batch processing module, for reading full dose type target service data in batches and being pre-processed to it;According to the business rule and
Logical order between the machine learning model carries out batch quantity analysis to the full dose type target service data, and analysis is tied
Fruit is sent to second message middleware module;Infrastructure service module is the target industry for loading the service arrangement module
The business rule and machine learning model of data of being engaged in deployment, use for the stream process module or the batch processing module, and
For providing the service of system monitoring service and the load of external third-parties interface.
In one embodiment of the invention, the second message middleware module is used: Hbase storage, Redis storage or
Kafka message-oriented middleware cluster.
In one embodiment of the invention, the business datum includes: transaction data, operation data, server log data,
And/or bury point data.
In one embodiment of the invention, point data and the server log data, the data acquisition are buried for described
Module can be collected by flume component, be sent to the first message middleware module later.
In one embodiment of the invention, received business datum is first converted into preset data lattice by the data acquisition module
Formula, then send it to the first message middleware module.
In order to achieve the above objects and other related objects, the present invention provides a kind of rule-based and model distributed real-time
Handle Intelligent Decision-making Method, comprising: read target service data to be processed and pre-process to it;It is loaded as the target
The business rule and machine learning model of business datum deployment;According between the business rule and the machine learning model
Logical order analyzes the target service data, and exports analysis result.
In order to achieve the above objects and other related objects, the present invention provides a kind of electronic equipment, comprising: processor and storage
Device;Wherein, the memory is for storing computer program;The processor is used for computer program described in load and execution, with
The electronic equipment is set to execute rule-based and model the distributed processing Intelligent Decision-making Method in real time.
As described above, rule-based and model distributed processing intelligent decision system and method in real time of the invention, tool
Have following
The utility model has the advantages that
1. being directed to plurality of application scenes, the autonomous dynamic configuration for realizing business rule and machine learning model, without excessive
It relies on technical staff and secondary development, service upgrade is carried out to original system, greatly shorten the development cycle;
2. complicated calculating, distributed computing can be carried out in second grade, numerous areas is successfully met to big data processing
The demand of high concurrent low delay;
3. the accuracy that the combination of rule and model improves state-detection.
Detailed description of the invention
Fig. 1 is shown as rule-based and model the distributed processing intelligent decision system in real time in one embodiment of the invention
Configuration diagram.
Fig. 2 is shown as rule-based and model the distributed processing intelligent decision system in real time in one embodiment of the invention
Workflow schematic diagram.
Fig. 3 is shown as the flow chart of method performed by the core decision-making module in one embodiment of the invention.
Fig. 4 is shown as the structural schematic diagram of the electronic equipment in one embodiment of the invention.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
Referring to Fig. 1, the present embodiment propose based on Spark Streaming distributed stream Computational frame combine can dynamic
The business rule of configuration and the intelligent decision system of machine learning model, are not necessarily to the problem of several scenes event can be effectively treated
It depends on technical staff unduly and secondary development, service upgrade is carried out to original system, greatly shorten the development cycle, and there is handling capacity
The high, many advantages such as calculating speed is fast.
As shown in Figure 1, being shown as rule-based and model the distributed processing intelligent decision system in real time of the present embodiment
Framework, with good flexibility, adaptability and scalability, main includes successively communicating to connect: data acquisition module,
First message middleware module, service arrangement module, core decision-making module, second message middleware module, wherein red line represents
Service class data, green line represent infrastructure service data, and blue line indicates deployment management operation class data.
It will describe in detail below to the function of modules:
1) data acquisition module
In this present embodiment, data acquisition module is mainly obtained from business department's transaction, action type data
(Business Data) and server log (LOG) and bury point data (SDK) etc..It, then generally can root for service class data
According to the needs of processing, according to fixed format Json or Avro etc. is directly issued to first message middleware module;For burying points
According to and server log data, then can be collected by flume component, then be issued to first message middleware module.
2) first message middleware module
In this present embodiment, first message middleware module is using Kafka message-oriented middleware cluster, a kind of distribution
Publish/subscribe message system has high-throughput, data persistence, and support level extension, distributed consumer, each subregion disappear
Cease the features such as orderly.Kafka message-oriented middleware cluster includes according to different service creation specific topic, each topic
Partition number relies on depending on concrete scene.For the scene of needs sequence consumption, partition number is set as 1, no
Then settable multiple subregions are consumed parallel.
3) service configuration module
In this present embodiment, service configuration module uses Web service form, draws including configurable Drools business rule
It holds up and machine learning model engine (Rule and Model engine), monitoring management module (Monitoring), rights management
Module (ACL).Business personnel can on web page in a manner of dynamically dragging formula business needed for deployment process target service data
Rule and machine learning model, and generate, management rule stream and model stream.In addition, monitoring management module, for monitoring cluster
Resource service condition and the operating status of project etc.;Authority management module, for controlling the data area etc. that business can access.
4) core decision-making module
In this present embodiment, core decision-making module mainly includes three parts: stream process module (Spark Streaming
Compute), batch processing module (Spark Batch compute), infrastructure service module (Base Service).
Stream process module mainly handles online real-time incremental data, specifically, it is used to read in Kafka in real time
The data of topic carry out these data the pretreatment such as to clean, Drools regular flow and machine based on infrastructure service module loading
Device learning model algorithm, analyzes pretreated data, and analysis result is sent to second message middleware module.
Wherein, third party (3rd service) data relied on are provided by infrastructure service module.Such as: if intelligent decision system needle
Pair be the detection of air control antifraud, third party's service then provides blacklist data etc..
The full dose data of the main processing business history of batch processing module, specifically, it is based on using Spark Sql engine
The calculating that full dose data periodically carry out index generates corresponding service label, such as: user's portrait label, and update engineering
Practise model etc..
Infrastructure service module is for providing load service (the Rule and of Drools business rule and machine learning model
Model Loader), system monitoring service (Monitor Agent) and external third-parties interface load service (Access
Control)。
5) second message middleware module
In this present embodiment, second message middleware module is used to store the analysis of core decision-making module as a result, and providing
The service of message output, mainly uses the external storages such as HBase, Redis or Kafka message-oriented middleware cluster.
As shown in Fig. 2, the workflow of the intelligent decision system of the present embodiment is as follows:
S21: the requirement of data producer or data sender according to business side to data format is by data source, such as: burying
Point data, daily record data etc. are sent in business side specified Kafka message queue and corresponding topic;
S22:Kafka message queue stores the data received, is backed up;
S23: the relevant information of business department disposition data source and data output component on web, and configure the industry of needs
Business rule, machine learning model and the logic of data processing, such as: machine learning model depends on the execution knot of business rule
Fruit, then the logic for needing to configure data processing is business rule -> machine learning model;Core decision-making module consumes Kafka message
Data in queue will analyze result and be sent to the specified downstream Kafka message queue in business side;
S24: business side obtains the processing result of output.
In addition, business department can monitor in real time by health status of the monitoring system to application, make intelligent decision
System being capable of stable operation.
Refering to Fig. 3, it is shown as method and step performed by core decision-making module in above-mentioned intelligent decision system, comprising:
S31: target service data to be processed are read and it is pre-processed;
S32: disposing and is loaded as handling business rule and machine learning model set by the target service data;
S33: according to the logical order between the business rule and the machine learning model to the target service number
According to being analyzed, and export analysis result.
Since the technical principle of embodiment illustrated in fig. 3 and the core decision-making module of embodiment illustrated in fig. 1 are corresponding, so
This no longer does repeatability to same technical detail and repeats.
Realize that all or part of the steps of above-mentioned each method embodiment can be by the relevant hardware of computer program come complete
At.Based on this understanding, the present invention also provides a kind of computer program products, including one or more computer instructions.Institute
Stating computer instruction may be stored in a computer readable storage medium.The computer readable storage medium can be computer
Any usable medium that can be stored either includes the data such as one or more usable mediums integrated server, data center
Store equipment.The usable medium can be magnetic medium (such as: floppy disk, hard disk, tape), optical medium (such as: DVD) or half
Conductive medium (such as: solid state hard disk Solid State Disk (SSD)).
Refering to Fig. 4, the present embodiment provides a kind of electronic equipment, electronic equipment can be server, desktop computer, portable electric
The equipment such as brain, smart phone.Detailed, electronic equipment, which includes at least, passes through what bus 41 connected: memory 42, processor 43,
Wherein, memory 42 is for storing computer program, and processor 43 is used to execute the computer program of the storage of memory 42, to hold
All or part of the steps in row preceding method embodiment.
System bus mentioned above can be Peripheral Component Interconnect standard (Peripheral Pomponent
Interconnect, abbreviation PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, abbreviation EISA) bus etc..The system bus can be divided into address bus, data/address bus, control bus etc..
Only to be indicated with a thick line in figure, it is not intended that an only bus or a type of bus convenient for indicating.Communication connects
Mouth is for realizing the communication between database access device and other equipment (such as client, read-write library and read-only library).Storage
Device may include random access memory (Random Access Memory, abbreviation RAM), it is also possible to further include non-volatile deposit
Reservoir (non-volatile memory), for example, at least a magnetic disk storage.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
Abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.;It can also be digital signal processor
(Digital Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific
Integrated Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array,
Abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.
In conclusion rule-based and model distributed processing intelligent decision system and method in real time of the invention, tool
There is preferable complicated event processing capability in real time, handling capacity is high, is not necessarily to secondary development in face of different business scenarios.So this
Invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (10)
1. a kind of rule-based and model distributed processing intelligent decision system in real time characterized by comprising
Data acquisition module for obtaining business datum to be processed, and sends it to first message middleware module;
First message middleware module, for giving out information by received business datum partitioned storage, and to core decision-making module,
To provide the target service data of analysis needed for it to the core decision-making module;
Service arrangement module, for business rule needed for target service data described in deployment analysis, machine learning model, and
Logical order between both;
Core decision-making module, for reading the target service data from the first message middleware module and being carried out to it
Pretreatment;Load the business rule and machine learning model that the service arrangement module is target service data deployment;Root
The target service data are analyzed according to the logical order between the business rule and the machine learning model, and will
Analysis result is sent to second message middleware module;
Second message middleware module, for store the analysis as a result, and send message to business side, with to the business side
Analysis result needed for it is provided.
2. system according to claim 1, which is characterized in that the first message middleware module uses Kafka message
Middleware cluster;The Kafka message-oriented middleware cluster creates specific topic, each topic according to different types of service
The partition number for including relies on concrete scene.
3. system according to claim 1, which is characterized in that the service arrangement module, comprising:
Business Rule Engine, for inputting deployment business rule according to user;
Machine learning model engine, for inputting deployment machine learning model according to user;
Monitoring management module, for monitor the first message middleware module resource service condition and the core decision model
The operating status of block;
Authority management module, the data area that can be accessed for controlling business.
4. system according to claim 1, which is characterized in that the core decision-making module, comprising:
Stream process module, for reading incremental target service data and being pre-processed in real time to it;It is advised according to the business
Then and the logical order between the machine learning model analyzes the incremental target service data in real time, and will divide
Analysis result is sent to second message middleware module;
Batch processing module, for reading full dose type target service data in batches and being pre-processed to it;It is advised according to the business
Then and the logical order between the machine learning model carries out batch quantity analysis to the full dose type target service data, and will divide
Analysis result is sent to second message middleware module;
Infrastructure service module, for loading the business rule and machine that the service arrangement module is target service data deployment
Device learning model is used for the stream process module or the batch processing module, and for providing system monitoring service and outer
The service of portion's third party's interface load.
5. system according to claim 1, which is characterized in that the second message middleware module uses: Hbase is deposited
Storage, Redis storage or Kafka message-oriented middleware cluster.
6. system according to claim 1, which is characterized in that the business datum includes: transaction data, operation data,
Server log data, and/or bury point data.
7. system according to claim 6, which is characterized in that bury point data and the server log number for described
According to the data acquisition module can be collected by flume component, be sent to the first message middleware module later.
8. system according to claim 1, which is characterized in that the data acquisition module first turns received business datum
It changes preset data form into, then sends it to the first message middleware module.
9. a kind of rule-based and model distributed processing Intelligent Decision-making Method in real time characterized by comprising
It reads target service data to be processed and it is pre-processed;
It is loaded as the business rule and machine learning model of the target service data deployment;
The target service data are divided according to the logical order between the business rule and the machine learning model
Analysis, and export analysis result.
10. a kind of electronic equipment characterized by comprising processor and memory;Wherein,
The memory is for storing computer program;
The processor is for computer program described in load and execution, so that the electronic equipment executes as claimed in claim 9
Rule-based and model distributed processing Intelligent Decision-making Method in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811556554.4A CN109831478A (en) | 2018-12-19 | 2018-12-19 | Rule-based and model distributed processing intelligent decision system and method in real time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811556554.4A CN109831478A (en) | 2018-12-19 | 2018-12-19 | Rule-based and model distributed processing intelligent decision system and method in real time |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109831478A true CN109831478A (en) | 2019-05-31 |
Family
ID=66858819
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811556554.4A Pending CN109831478A (en) | 2018-12-19 | 2018-12-19 | Rule-based and model distributed processing intelligent decision system and method in real time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109831478A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111555957A (en) * | 2020-03-26 | 2020-08-18 | 孩子王儿童用品股份有限公司 | Kafka-based synchronous message service system and implementation method |
CN111695064A (en) * | 2020-04-29 | 2020-09-22 | 北京城市网邻信息技术有限公司 | Embedded point loading method and device |
CN112036577A (en) * | 2020-08-20 | 2020-12-04 | 第四范式(北京)技术有限公司 | Method and device for application machine learning based on data form and electronic equipment |
CN112104706A (en) * | 2020-08-24 | 2020-12-18 | 中国银联股份有限公司 | Method, device, equipment and storage medium for releasing model in distributed system |
CN112540893A (en) * | 2020-12-16 | 2021-03-23 | 北京同有飞骥科技股份有限公司 | Performance test method for distributed storage |
CN112583931A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Message processing method, message middleware, electronic device and storage medium |
CN112685400A (en) * | 2021-01-22 | 2021-04-20 | 浪潮云信息技术股份公司 | Method and system for detecting quality of health medical data based on SDK rule engine |
CN112698971A (en) * | 2020-12-30 | 2021-04-23 | 平安科技(深圳)有限公司 | Rule engine based parameter conversion method, device, equipment and medium |
CN112783920A (en) * | 2021-02-05 | 2021-05-11 | 树根互联股份有限公司 | Industrial Internet of things data real-time computing method and system based on data arrangement |
WO2021088400A1 (en) * | 2019-11-07 | 2021-05-14 | 达而观信息科技(上海)有限公司 | Document review method, apparatus and system, device, and storage medium |
WO2021223215A1 (en) * | 2020-05-08 | 2021-11-11 | Paypal, Inc. | Automated decision platform |
CN113762688A (en) * | 2021-01-06 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Business analysis system, method and storage medium |
CN115035705A (en) * | 2021-03-03 | 2022-09-09 | 上海博泰悦臻网络技术服务有限公司 | Vehicle real-time condition monitoring method and device, electronic equipment and medium |
CN115269208A (en) * | 2022-09-29 | 2022-11-01 | 北京中科江南信息技术股份有限公司 | Resource processing method and system based on formula configuration |
CN116185782A (en) * | 2023-04-23 | 2023-05-30 | 智者四海(北京)技术有限公司 | Service monitoring method and device for social software |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103795791A (en) * | 2014-01-22 | 2014-05-14 | 北京交通大学 | Railway disaster prevention safety monitoring system based on wireless sensor network |
CN105224445A (en) * | 2015-10-28 | 2016-01-06 | 北京汇商融通信息技术有限公司 | Distributed tracking system |
CN106815338A (en) * | 2016-12-25 | 2017-06-09 | 北京中海投资管理有限公司 | A kind of real-time storage of big data, treatment and inquiry system |
-
2018
- 2018-12-19 CN CN201811556554.4A patent/CN109831478A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103795791A (en) * | 2014-01-22 | 2014-05-14 | 北京交通大学 | Railway disaster prevention safety monitoring system based on wireless sensor network |
CN105224445A (en) * | 2015-10-28 | 2016-01-06 | 北京汇商融通信息技术有限公司 | Distributed tracking system |
CN106815338A (en) * | 2016-12-25 | 2017-06-09 | 北京中海投资管理有限公司 | A kind of real-time storage of big data, treatment and inquiry system |
Non-Patent Citations (2)
Title |
---|
徐东泽: "基于STORM的网络流量实时分析系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑(月刊)》 * |
王志泳: "分布式消息系统Kafka的性能建模与优化技术研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑(月刊)》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021088400A1 (en) * | 2019-11-07 | 2021-05-14 | 达而观信息科技(上海)有限公司 | Document review method, apparatus and system, device, and storage medium |
CN111555957A (en) * | 2020-03-26 | 2020-08-18 | 孩子王儿童用品股份有限公司 | Kafka-based synchronous message service system and implementation method |
CN111695064B (en) * | 2020-04-29 | 2023-08-18 | 北京城市网邻信息技术有限公司 | Buried point loading method and device |
CN111695064A (en) * | 2020-04-29 | 2020-09-22 | 北京城市网邻信息技术有限公司 | Embedded point loading method and device |
US20210350262A1 (en) * | 2020-05-08 | 2021-11-11 | Paypal, Inc. | Automated decision platform |
WO2021223215A1 (en) * | 2020-05-08 | 2021-11-11 | Paypal, Inc. | Automated decision platform |
CN112036577B (en) * | 2020-08-20 | 2024-02-20 | 第四范式(北京)技术有限公司 | Method and device for applying machine learning based on data form and electronic equipment |
CN112036577A (en) * | 2020-08-20 | 2020-12-04 | 第四范式(北京)技术有限公司 | Method and device for application machine learning based on data form and electronic equipment |
CN112104706B (en) * | 2020-08-24 | 2022-12-20 | 中国银联股份有限公司 | Method, device, equipment and storage medium for releasing model in distributed system |
CN112104706A (en) * | 2020-08-24 | 2020-12-18 | 中国银联股份有限公司 | Method, device, equipment and storage medium for releasing model in distributed system |
CN112540893A (en) * | 2020-12-16 | 2021-03-23 | 北京同有飞骥科技股份有限公司 | Performance test method for distributed storage |
CN112583931A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Message processing method, message middleware, electronic device and storage medium |
CN112698971A (en) * | 2020-12-30 | 2021-04-23 | 平安科技(深圳)有限公司 | Rule engine based parameter conversion method, device, equipment and medium |
CN113762688A (en) * | 2021-01-06 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Business analysis system, method and storage medium |
CN112685400A (en) * | 2021-01-22 | 2021-04-20 | 浪潮云信息技术股份公司 | Method and system for detecting quality of health medical data based on SDK rule engine |
CN112783920A (en) * | 2021-02-05 | 2021-05-11 | 树根互联股份有限公司 | Industrial Internet of things data real-time computing method and system based on data arrangement |
CN115035705A (en) * | 2021-03-03 | 2022-09-09 | 上海博泰悦臻网络技术服务有限公司 | Vehicle real-time condition monitoring method and device, electronic equipment and medium |
CN115269208A (en) * | 2022-09-29 | 2022-11-01 | 北京中科江南信息技术股份有限公司 | Resource processing method and system based on formula configuration |
CN116185782A (en) * | 2023-04-23 | 2023-05-30 | 智者四海(北京)技术有限公司 | Service monitoring method and device for social software |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109831478A (en) | Rule-based and model distributed processing intelligent decision system and method in real time | |
US11627053B2 (en) | Continuous data sensing of functional states of networked computing devices to determine efficiency metrics for servicing electronic messages asynchronously | |
US11288142B2 (en) | Recovery strategy for a stream processing system | |
CN105005570B (en) | Magnanimity intelligent power data digging method and device based on cloud computing | |
CN109086325A (en) | Data processing method and device based on block chain | |
CN109032914A (en) | Resource occupation data predication method, electronic equipment, storage medium | |
CN107103064B (en) | Data statistical method and device | |
CN107566498A (en) | A kind of method for monitoring numerical control machine and system based on Internet of Things | |
Zhu et al. | A framework-based approach to utility big data analytics | |
CN109254901B (en) | A kind of Monitoring Indexes method and system | |
CN110532152A (en) | A kind of monitoring alarm processing method and system based on Kapacitor computing engines | |
CN110019087A (en) | Data processing method and its system | |
Zainab et al. | Big data management in smart grids: Technologies and challenges | |
CN107220360A (en) | A kind of Unified Modeling storage cut-in method based on magnanimity electric power monitoring data | |
CN110262951A (en) | A kind of business second grade monitoring method and system, storage medium and client | |
CN115640935A (en) | Method and device for calculating carbon emission of power system and computer equipment | |
Zhang et al. | Research and development of off-line services for the 3D automatic printing machine based on cloud manufacturing | |
CN114356692A (en) | Visual processing method and device for application monitoring link and storage medium | |
Reddy et al. | A comprehensive literature review on data analytics in IIoT (Industrial Internet of Things) | |
CN104050193A (en) | Message generating method and data processing system for realizing method | |
Marin et al. | Reaching for the clouds: contextually enhancing smartphones for energy efficiency | |
CN114756301B (en) | Log processing method, device and system | |
CN114757448B (en) | Manufacturing inter-link optimal value chain construction method based on data space model | |
CN116431324A (en) | Edge system based on Kafka high concurrency data acquisition and distribution | |
Chen | Visual design of landscape architecture based on high-density three-dimensional internet of things |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190531 |