WO2024099462A1 - 一种工业大脑处理系统、方法、电子设备及存储介质 - Google Patents

一种工业大脑处理系统、方法、电子设备及存储介质 Download PDF

Info

Publication number
WO2024099462A1
WO2024099462A1 PCT/CN2023/134955 CN2023134955W WO2024099462A1 WO 2024099462 A1 WO2024099462 A1 WO 2024099462A1 CN 2023134955 W CN2023134955 W CN 2023134955W WO 2024099462 A1 WO2024099462 A1 WO 2024099462A1
Authority
WO
WIPO (PCT)
Prior art keywords
management
enterprise
subsystem
data
brain
Prior art date
Application number
PCT/CN2023/134955
Other languages
English (en)
French (fr)
Inventor
方能炜
黄长波
刘艳敏
张莉
汪明
路雪宾
Original Assignee
北京航天数据股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京航天数据股份有限公司 filed Critical 北京航天数据股份有限公司
Publication of WO2024099462A1 publication Critical patent/WO2024099462A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0637Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283Price estimation or determination

Definitions

  • the present application relates to the field of information technology, and in particular to an industrial brain processing system, method, electronic device and storage medium.
  • the development of artificial intelligence has provided methods and means for business management.
  • the enterprise brain composed of information systems and artificial intelligence technologies can not only support enterprise data collection, collection, aggregation and deep mining, but also show the multi-dimensional and multi-faceted characteristics of information, while monitoring enterprise operations, management coordination and decision support.
  • the purpose of this application is to provide an industrial brain processing system, method, electronic device and storage medium, which solves the core issues of concern to the enterprise decision-making level through the coordination between the data support subsystem, the brain work analysis subsystem, the brain application subsystem, the database engine subsystem and the data pool resource management subsystem, and realizes the ability to assist the target enterprise in decision-making and the ability of self-learning and self-solving.
  • the embodiment of the present application provides an industrial brain processing system, which includes a data support subsystem, a brain work analysis subsystem, a brain application subsystem, a database engine subsystem, and a data pool resource management subsystem;
  • the data support subsystem is used to receive external enterprise data from different data sources, and send the external enterprise data to the database engine subsystem and/or the data pool resource management subsystem according to the data source of the external enterprise data;
  • the database engine subsystem is used to provide a core function library for the brain work analysis subsystem so that the brain work analysis subsystem can complete the editing and reasoning of the enterprise decision;
  • the data pool resource management subsystem is used to provide enterprise data knowledge and enterprise data support for the brain work analysis subsystem. support;
  • the brain work analysis subsystem is used to receive the pending business of the target enterprise sent by the brain application subsystem, perform data analysis on the pending business, obtain the enterprise business data corresponding to the pending business from the data support subsystem, and obtain the preset model algorithm corresponding to the pending business from the database engine subsystem; determine the target algorithm model of the pending business according to the enterprise business data and the preset model algorithm; and generate the target enterprise decision of the target enterprise according to the target algorithm model, and send the target enterprise decision to the brain application subsystem;
  • the brain application subsystem is used to perform corresponding decision management and decision application on the target enterprise according to the decision of the target enterprise.
  • the data support subsystem includes a distributed file management module, a file management module and different types of databases;
  • the file management module is used to receive external enterprise data from different data sources
  • the databases of different types are used to classify the external enterprise data according to corresponding structural types and determine the external enterprise data of each type;
  • the distributed file management module is used to send each type of the external enterprise data to the database engine subsystem and/or the data pool resource management subsystem.
  • the database engine subsystem includes an algorithm library management module, a corpus management module, a knowledge base management module and a model library management module;
  • the algorithm library management module is used for basic algorithm management, clustering algorithm management, classification algorithm management, deep learning algorithm management, decision tree learning management and integrated algorithm management;
  • the corpus management module is used for speech de-noising management, identification classification management, multi-dimensional analysis management and algorithm model management;
  • the knowledge base management module is used for index graph management, file upload management, knowledge creation management, class index management, mobile access management and collection subscription management;
  • the model library management module is used for system simulation management, fault prediction management, production prediction management and process flow management.
  • the data pool resource management subsystem includes a patent pool management module, an expert pool management module and a standard pool management module;
  • the patent pool management module is used for mechanism model management, process flow management, working condition safety management, quality management, predictive maintenance management and gain management;
  • the expert pool management module is used for popular expert management, service expert management, technical expert management and industry expert management;
  • the standard pool management module is used for international standard management, national standard management, industry standard management and enterprise standard management.
  • the data pool resource management subsystem includes a patent pool management module, an expert pool management module and a standard pool management module;
  • the patent pool management module is used for mechanism model management, process flow management, working condition safety management, quality management, predictive maintenance management and gain management;
  • the expert pool management module is used for popular expert management, service expert management, technical expert management and industry expert management;
  • the standard pool management module is used for international standard management, national standard management, industry standard management and enterprise standard management.
  • the brain work analysis subsystem also includes a rights management module, an enterprise application market management module, an enterprise application editing module, an enterprise application project management module and a background help module;
  • the permission management module is used to manage the enterprise permissions of external enterprise applications
  • the enterprise application market management module is used to manage the application market of external enterprise applications
  • the enterprise application editing module is used to determine the corresponding external enterprise application according to the target enterprise decision
  • the enterprise application project management module is used to manage the target enterprise decisions sent to the brain application subsystem;
  • the background help module is used to handle problems that occur during the operation of the brain work analysis subsystem.
  • the target algorithm model is an index calculation model, and the formula of the index calculation model is:
  • IPM is used to represent the profit margin of enterprise income
  • ROE refers to the return on net assets
  • ALR is used to represent the debt-to-asset ratio
  • TGOR is used to represent the proportion of two funds in current assets
  • IRTP is used to represent the proportion of technological progress investment
  • APLP is used to represent the labor productivity of all employees
  • WOR is used to represent the asset-to-asset ratio
  • PCNA is used to represent the net assets per capita
  • a, ⁇ , ⁇ , ⁇ , ⁇ , ⁇ , ⁇ and ⁇ are used to characterize the parameters of the exponential calculation model.
  • the present application also provides an industrial brain processing method, which includes:
  • a target enterprise decision of the target enterprise is generated so that the target enterprise can perform corresponding decision management and decision application.
  • An embodiment of the present application also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the industrial brain processing method as described above are performed.
  • An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored.
  • a computer program is stored.
  • the steps of the industrial brain processing method as described above are executed.
  • the industrial brain processing system, method electronic device and storage medium provided in the embodiments of the present application are compared with the prior art.
  • the purpose of this application is to provide an industrial brain processing system, method, electronic device and storage medium.
  • FIG1 shows one of the structural diagrams of an industrial brain processing system provided by an embodiment of the present application
  • FIG. 2 shows a second structural diagram of an industrial brain processing system provided by an embodiment of the present application
  • FIG3 shows a flow chart of an industrial brain processing method provided by an embodiment of the present application
  • FIG4 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
  • 100-industrial brain processing system 110-data support subsystem; 111-distributed file management module; 112-file management module; 113- different types of databases; 120- database engine subsystem; 130- data pool resource management subsystem; 140- brain work analysis subsystem; 150- brain application subsystem; 400- electronic device; 410- processor; 420- memory; 430- bus.
  • This application can be applied in the field of information technology.
  • the existing technology has a small coverage of industrial industries (aluminum manufacturing, automobiles, shipbuilding, food, electronics, construction, etc. are industrial enterprises), and currently only covers some similar types of industrial enterprises.
  • industrial industries aluminum manufacturing, automobiles, shipbuilding, food, electronics, construction, etc. are industrial enterprises
  • the existing technology can only solve local problems of industrial enterprises, and has not yet provided a complete set of solutions from manufacturing, business, management and decision-making.
  • Internet industry companies need to improve their own learning ability and data analysis and computing capabilities, and the Internet industry does not have sufficient accumulation of industrial field knowledge.
  • the embodiment of the present application provides an industrial brain processing system, method, electronic device and storage medium, which solves the core issues of concern to the enterprise decision-making level through the coordination between the data support subsystem, the brain work analysis subsystem, the brain application subsystem, the database engine subsystem and the data pool resource management subsystem, and realizes the ability to assist the target enterprise in making decisions and the self- The ability to learn and self-solve fills the current market gap in enterprise decision-making analysis based on industrial brain.
  • an industrial brain processing system 100 provided in an embodiment of the present application includes a data support subsystem 110, a brain work analysis subsystem 140, a brain application subsystem 150, a database engine subsystem 120, and a data pool resource management subsystem 130.
  • the data support subsystem 110 is used to receive different external enterprise data sources, and send the external enterprise data to the database engine subsystem 120 and/or the data pool resource management subsystem 130 according to the data source of the external enterprise data.
  • the data support subsystem 110 supports real-time or batch transmission of heterogeneous data across platforms, and is compatible with mainstream databases such as mainstream RDBMS and NoSQL databases.
  • the external enterprise data collected by the data support subsystem 110 all come from the industrial Internet platform, two rooms (cloud application studio and cloud business studio), two stations (enterprise cloud service station and SME service station) and information resources (enterprise internal basic information, enterprise external information). These external enterprise data need to be deposited on the industrial Internet platform, and in the above, the external enterprise data in the two rooms (cloud application studio and cloud business studio) are sent to the database engine subsystem 120; the external enterprise data in the two stations (enterprise cloud service station and SME service station) are sent to the data pool resource management subsystem 130.
  • the data support subsystem 110 may crawl and receive external enterprise data from different data sources according to the data transmission (API) interface provided by other cooperating manufacturers.
  • API data transmission
  • the database engine subsystem 120 is used to provide a core function library for the brain work analysis subsystem 140 so that the brain work analysis subsystem 140 can complete the editing and reasoning of the enterprise decision.
  • the policy-makers of the target enterprise can intuitively understand the basic platform and basic model specifically constructed based on the database engine subsystem 120 , which facilitates the decision-makers to understand the theoretical basis of the deduction of the database engine subsystem 120 .
  • the database engine subsystem 120 includes an algorithm library management module, a corpus management module, a knowledge base management module and a model library management module.
  • the algorithm library management module includes basic algorithm management, clustering algorithm management, classification algorithm management, deep learning algorithm management, decision tree learning management and integrated algorithm management.
  • the corpus management module includes speech denoising management, identification classification management, multi-dimensional analysis management and algorithm model management.
  • the knowledge base management module includes index graph management, file upload management, knowledge creation management, class index management, mobile access management and collection subscription management.
  • the model library management module includes system simulation management, fault prediction management, production prediction management and process flow management.
  • the data pool resource management subsystem 130 is used to provide enterprise data knowledge and enterprise data support for the brain work analysis subsystem 140.
  • the data pool resource management subsystem 130 and the database engine subsystem 120 provided in the embodiment of the present application can realize deep learning through the centralized management of the brain work analysis subsystem 140, and then can realize the ability to assist in generating target enterprise decisions and the ability of self-learning and self-solving.
  • the data pool resource management subsystem 130 includes a patent pool management module, an expert pool management module and a standard pool management module.
  • the patent pool management module is used for mechanism model management, process flow management, operating condition safety management, quality management, predictive maintenance management and gain management.
  • the expert pool management module is used for popular expert management, service expert management, technical expert management and industry expert management.
  • the standard pool management module is used for international standard management, national standard management, industry standard management and enterprise standard management.
  • the brain work analysis subsystem 140 is used to receive the pending business of the target enterprise sent by the brain application subsystem 150, perform data analysis on the pending business, obtain the enterprise business data corresponding to the pending business from the data support subsystem 110, and obtain the preset model algorithm corresponding to the pending business from the database engine subsystem 120; determine the target algorithm model of the pending business according to the enterprise business data and the preset model algorithm; and generate the target enterprise decision of the target enterprise according to the target algorithm model, and send the target enterprise decision to the brain application subsystem 150.
  • the brain work analysis subsystem 140 collects external enterprise data through user data reporting, and later collects external enterprise data from the industrial Internet platform.
  • the industrial Internet platform should store the external enterprise data required by the brain work analysis subsystem 140, and the brain work analysis subsystem 140 should deposit the mechanism model into the industrial Internet platform for other subsystems to call, and the target enterprise decision sent to the brain application subsystem 150 corresponds to the business application scenario of the decision application.
  • the brain work analysis subsystem 140 includes an application interface management module, a database engine management module, a mechanism modeling module, a data pool resource management module and a data analysis management module.
  • the application interface management module is used to receive the pending business of the target enterprise sent by the brain application subsystem 150.
  • the data analysis management module is used to perform data analysis on the business to be processed and determine the data analysis results.
  • the database engine management module is used to obtain a preset model algorithm corresponding to the business to be processed from the database engine subsystem 120 according to the data analysis result.
  • the data pool resource management module is used to obtain the enterprise business data corresponding to the to-be-processed business from the data pool resource management subsystem 130 according to the data analysis result.
  • the mechanism modeling module is used to determine the target algorithm model of the business to be processed based on the enterprise business data and a preset model algorithm; and generate a target enterprise decision for the target enterprise based on the target algorithm model.
  • the brain work analysis subsystem 140 is mainly responsible for the management of various other subsystems in the industrial brain processing system 100.
  • the brain work analysis subsystem 140 is also used for the authority management module, the enterprise application market management module, the enterprise application editing module, the enterprise application project management module and the background help module.
  • the authority management module is used to manage the enterprise authority of external enterprise applications.
  • the enterprise application market management module is used to manage the application market of external enterprise applications.
  • the enterprise application editing module is used to determine the corresponding external enterprise application according to the target enterprise decision.
  • the enterprise application project management module is used to manage the target enterprise decisions sent to the brain application subsystem 150.
  • the background help module is used to handle problems that occur during the operation of the brain work analysis subsystem 140.
  • the brain application subsystem 150 is used to perform corresponding decision management and decision application on the target enterprise according to the decision of the target enterprise.
  • the brain application subsystem 150 includes but is not limited to a large visualization screen, and the large visualization screen is mainly used for multi-dimensional horizontal qualitative and vertical quantitative display of the enterprise.
  • the pending business of the target enterprise includes but is not limited to determining the enterprise development index of the target enterprise.
  • the enterprise development index (EDI) of the target enterprise reflects the overall development trend and comprehensive capabilities of the enterprise, and reflects the overall economic contribution index of the enterprise to the society.
  • the following parameters can be obtained, such as sales profit, total operating income, net profit of parent company owners, average equity attributable to parent company owners, total assets, total liabilities, accounts receivable, inventory, working capital, total operating income, total scientific and technological expenditure for the year, industrial added value, average number of all employees, total wage expenditure and total number of employees in the company.
  • the target enterprise's pending business is the target enterprise's business development index.
  • the target algorithm model is an index calculation model, and the formula of the index calculation model is:
  • IPM is used to represent the profit margin of enterprise income
  • ROE refers to the return on net assets
  • ALR is used to represent the debt-to-asset ratio
  • TGOR is used to represent the proportion of two funds in current assets
  • IRTP is used to represent the proportion of technological progress investment
  • APLP is used to represent the labor productivity of all employees
  • WOR is used to represent the asset-to-asset ratio
  • PCNA is used to represent the net assets per capita
  • a, ⁇ , ⁇ , ⁇ , ⁇ , ⁇ , ⁇ and ⁇ are used to characterize the parameters of the exponential calculation model.
  • the settings of various parameters in the index calculation model of the enterprise business development index are obtained through training with practical experience data of enterprises in the same industry.
  • Sales (operating) profit total operating income - operating costs - business taxes and surcharges
  • Table 1 is the enterprise evaluation standard values at different levels. It stipulates that the range of EDI values at each level is: excellent (90-100), good (80-90), average (70-80), low (60-70), poor (0-60).
  • Table 1 Evaluation standard values of enterprises at different levels in the plastic products industry
  • xi (IPM, ROE, TGOR, ALR, IRTP, APLP, WOR, PCNG) represents the development status data of the target enterprise
  • yi represents the target enterprise level
  • g1, g2, g3, g4, g5 represent the evaluation standard values of the target enterprise at five levels, and the corresponding EDI values are recorded as EDI (gi).
  • the EDI (xi) value should be as close as possible to the EDI (gyi) value under the standard value of that level, so we expect to minimize their distance 1/2 (EDI (xi) - EDI (gyi)) 2, and the enterprise development index value at the same level should be within a given range.
  • the following optimization objective problem is obtained:
  • xi (IPM,ROE,TGOR,ALR,IRTP,APLP,WOR,PCNG).
  • IPM ⁇ 5 the company's revenue profit margin is low. It is recommended to increase operating income and reduce operating costs.
  • ROE ⁇ 2 return on net assets is poor, and there is an operating risk warning. It is recommended to actively adjust the investment strategy, reduce costs and increase profits.
  • ALR ⁇ 40 the debt-to-asset ratio is too small, and the debt ratio can be appropriately increased to improve the scale of operations.
  • ALR> 60, the debt-to-asset ratio is too high, which may lead to the risk of insolvency. It is recommended to take timely measures to reduce the debt-to-asset ratio.
  • APLP ⁇ 1.65 (10,000 yuan/person), the total labor productivity is lower than the standard value, it is recommended to increase industrial added value, adjust the personnel structure, and cut redundant personnel.
  • the index calculation model determined according to the enterprise business development index provided in the embodiment of the present application can calculate the results according to the calculation model and make target enterprise decisions based on the results.
  • the various parameter settings in the enterprise business development index are obtained by data training implemented by enterprises in the same industry.
  • the industrial brain processing system 100 provided in the embodiment of the present application solves the core issues of concern to the enterprise decision-making level by coordinating the data support subsystem 110, the brain work analysis subsystem 140, the brain application subsystem 150, the database engine subsystem 120 and the data pool resource management subsystem 130, realizes the ability to assist the target enterprise in making decisions and the ability of self-learning and self-solving, and fills the current market gap in enterprise decision-making analysis based on the industrial brain.
  • FIG. 2 is a flow chart of an industrial brain processing system 100 provided by another embodiment of the present application.
  • an industrial brain processing system 100 provided by an embodiment of the present application includes:
  • the industrial brain processing system 100 includes a data support subsystem 110, a brain work analysis subsystem 140, a brain application subsystem 150, a database engine subsystem 120 and a data pool resource management subsystem 130.
  • the data support subsystem 110 is used to receive external enterprise data from different data sources, and send the external enterprise data to the database engine subsystem 120 and/or the data pool resource management subsystem 130 according to the data source of the external enterprise data.
  • the database engine subsystem 120 is used to provide a core function library for the brain work analysis subsystem 140 so that the brain work analysis subsystem 140 can complete the editing and reasoning of the enterprise decision.
  • the data pool resource management subsystem 130 is used to provide enterprise data knowledge and enterprise data support for the brain work analysis subsystem 140.
  • the brain work analysis subsystem 140 is used to receive the pending business of the target enterprise sent by the brain application subsystem 150, perform data analysis on the pending business, obtain the enterprise business data corresponding to the pending business from the data support subsystem 110, and obtain the preset model algorithm corresponding to the pending business from the database engine subsystem 120; determine the target algorithm model of the pending business according to the enterprise business data and the preset model algorithm; and generate the target enterprise decision of the target enterprise according to the target algorithm model, and send the target enterprise decision to the brain application subsystem 150.
  • the brain application subsystem 150 is used to perform corresponding decision management and decision application on the target enterprise according to the decision of the target enterprise.
  • the data support subsystem 110 includes a distributed file management module 111 , a file management module 112 and different types of databases 113 .
  • the file management module 112 is used to receive external enterprise data from different data sources.
  • the databases of different types are used to classify the external enterprise data according to corresponding structural types and determine the external enterprise data of each type.
  • the file management module 112 is used to send various types of external enterprise data to the database engine subsystem 120 and/or the data pool resource management subsystem 130 .
  • the industrial brain processing system provided in the embodiment of the present application solves the core issues of concern to the enterprise decision-making level by coordinating the data support subsystem, the brain work analysis subsystem, the brain application subsystem, the database engine subsystem and the data pool resource management subsystem, realizes the ability to assist the target enterprise in making decisions and the ability of self-learning and self-solving, and fills the current market gap in enterprise decision-making analysis based on the industrial brain.
  • Figure 3 is a flow chart of an industrial brain processing method provided by an embodiment of the present application. As shown in Figure 3, the flow chart of the industrial brain processing method includes the following steps:
  • Data analysis is performed on the business to be processed to determine the enterprise business data corresponding to the business to be processed and the preset model algorithm corresponding to the business to be processed.
  • a target algorithm model for the business to be processed is determined.
  • a target enterprise decision of the target enterprise is generated so that the target enterprise can perform corresponding decision management and decision application.
  • the industrial brain processing method provided in the embodiment of the present application solves the core issues of concern to the enterprise decision-making level by coordinating the data support subsystem, the brain work analysis subsystem, the brain application subsystem, the database engine subsystem and the data pool resource management subsystem, realizes the ability to assist the target enterprise in making decisions and the ability of self-learning and self-solving, and fills the gap in the current market for enterprise decision-making analysis based on the industrial brain.
  • Fig. 4 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
  • the electronic device 400 includes a processor 410, a memory 420 and a bus 430.
  • the memory 420 stores machine-readable instructions executable by the processor 410.
  • the processor 410 communicates with the memory 420 through the bus 430.
  • the machine-readable instructions are executed by the processor 410, the steps of the industrial brain processing method in the method embodiment shown in Figure 3 above can be executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.
  • An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon.
  • the computer program is executed by a processor, the steps of the industrial brain processing method in the method embodiment shown in FIG. 3 above can be executed.
  • the specific implementation method can be found in the method embodiment and will not be repeated here.
  • modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
  • the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that can be executed by a processor.
  • the technical solution of the present application can be embodied in the form of a software product in essence or in other words, the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种工业大脑处理系统,工业大脑处理系统包括数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统。通过数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统之间的协调作用,解决了企业决策层关注的核心问题。还公开了一种工业大脑处理方法、电子设备及存储介质。

Description

一种工业大脑处理系统、方法、电子设备及存储介质
相关申请的交叉引用
本申请要求于2022年11月08日提交中国国家知识产权局的申请号为202211389249.7、名称为“一种工业大脑处理系统、方法、电子设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息技术领域,尤其是涉及一种工业大脑处理系统、方法、电子设备及存储介质。
背景技术
近年世界经济在快速发展,科技也得到了快速提升,人们迎来了全球一体化的新时代,大数据在各行各业都得到充分利用,企业在做出决策前需要基于数据考虑更多的因素,如果企业想要全方位、多角度地发展,管理决策必须进行创新改革,满足企业快速发展的管理需求,为了在大数据时代做到可持续发展,对相关决策机制进行一系列变革是有必要的。
在互联网经济时代下,人工智能的发展为企业经营管理提供了方法和手段。新技术的涌现,由信息系统和人工智能技术构成的企业大脑不仅能够支持企业数据采集、汇集、聚合以及深度挖掘,还能够表现信息多维度、多层面的特征,同时监控着企业运营、管理协同以及决策支持。
然而,现有技术中,企业管理中存在决策效率底、决策层对各层级数据和经营状况掌握不足、全局意识不强、规划执行不到位、管理不科学、评估机制缺失等一系列的问题制约了企业正常的经营发展,而目前市场对基于工业大脑的企业决策分析尚属于空白。
发明内容
有鉴于此,本申请的目的在于提供一种工业大脑处理系统、方法、电子设备及存储介质,通将数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统之间的协调作用,解决了企业决策层关注的核心问题,实现了辅助目标企业决策的能力和自学习以及自解决的能力。
本申请实施例提供了一种工业大脑处理系统,所述工业大脑处理系统包括数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统;
所述数据支撑子系统,用于接收不同数据源的外部企业数据,并根据所述外部企业数据的数据源,将所述外部企业数据发送至所述数据库引擎子系统和/或数据池资源管理子系统;
所述数据库引擎子系统,用于为所述大脑工作分析子系统提供核心功能库,以便所述大脑工作分析子系统完成对所述企业决策的编辑和推理;
所述数据池资源管理子系统,用于为所述大脑工作分析子系统提供企业数据知识和企业数据支 撑;
所述大脑工作分析子系统,用于接收所述大脑应用子系统发送的目标企业的待处理业务,针对所述待处理业务进行数据分析,从所述数据支撑子系统中获取与所述待处理业务对应的企业业务数据,以及从所述数据库引擎子系统中获取所述待处理业务对应的预设模型算法;根据所述企业业务数据和预设模型算法,确定所述待处理业务的目标算法模型;并根据所述目标算法模型,生成所述目标企业的目标企业决策,并将所述目标企业决策发送至所述大脑应用子系统;
所述大脑应用子系统,用于根据所述目标企业决策,对所述目标企业进行对应的决策管理和决策应用。
进一步的,所述数据支撑子系统包括分布式文件管理模块、文件管理模块以及不同类型的数据库;
所述文件管理模块,用于接收不同数据源的外部企业数据;
不同类型的所述数据库,用于将所述外部企业数据按照对应的结构类型的进行分类,确定各个类型的所述外部企业数据;
所述分布式文件管理模块,用于将各个类型的所述外部企业数据发送至所述数据库引擎子系统和/或数据池资源管理子系统。
进一步的,所述数据库引擎子系统包括算法库管理模块、语料库管理模块、知识库管理模块以及模型库管理模块;
所述算法库管理模块用于基本算法管理、聚类算法管理、分类算法管理、深度学习算法管理、决策树学习管理以及集成算法管理;
所述语料库管理模块用于语音去燥管理、标识分类管理、多维度分析管理以及算法模型管理;
所述知识库管理模块用于指数图谱管理、文件上传管理、知识创建管理、类索引管理、移动查阅管理以及收藏订阅管理;
所述模型库管理模块用于系统仿真管理、故障预测管理、生产预测管理以及工艺流程管理。
进一步的,所述数据池资源管理子系统包括专利池管理模块、专家池管理模块和标准池管理模块;
所述专利池管理模块用于机理模型管理、工艺流程管理、工况安全管理、质量管理、预测性维护管理以及增益管理;
所述专家池管理模块用于热门专家管理、服务专家管理、技术专家管理以及行业专家管理;
所述标准池管理模块用于国际标准管理、国家标准管理、行业标准管理以及企业标准管理。
进一步的,所述数据池资源管理子系统包括专利池管理模块、专家池管理模块和标准池管理模块;
所述专利池管理模块用于机理模型管理、工艺流程管理、工况安全管理、质量管理、预测性维护管理以及增益管理;
所述专家池管理模块用于热门专家管理、服务专家管理、技术专家管理以及行业专家管理;
所述标准池管理模块用于国际标准管理、国家标准管理、行业标准管理以及企业标准管理。
进一步的,所述大脑工作分析子系统还包括权限管理模块、企业应用市场管理模块、企业应用编辑模块、企业应用项目管理模块以及后台帮助模块;
所述权限管理模块,用于对外部企业应用的企业权限进行管理;
所述企业应用市场管理模块,用于对外部企业应用的应用市场中进行管理;
所述企业应用编辑模块,用于根据目标企业决策,确定对应的外部企业应用;
所述企业应用项目管理模块,用于对发送给大脑应用子系统的目标企业决策进行管理;
所述后台帮助模块,用于处理大脑工作分析子系统在运行过程中存在的问题。
进一步的,若目标企业的待处理业务为确定所述目标企业的企业经营发展指数,则所述目标算法模型为指数计算模型,所述指数计算模型的公式为:
其中,IPM用于表征指企业收入利润率;ROE是指净资产收益率;ALR用于表征资产负债率;TGOR用于表征两金占流动资产比重;IRTP用于表征技术进步投入占比;APLP用于表征全员劳动生产率;WOR用于表征工资产出比;PCNA用于表征人均净资产;a、β、η、λ、μ、κ、π以及ω用于表征所述指数计算模型的参数。
本申请实施例还提供了工业大脑处理方法,所述工业大脑处理方法包括:
获取标企业的待处理业务;
针对所述待处理业务进行数据分析,确定所述待处理业务对应的企业业务数据以及所述待处理业务对应的预设模型算法;
根据所述企业业务数据和所述预设模型算法,确定所述待处理业务的目标算法模型;
根据所述目标算法模型,生成所述目标企业的目标企业决策,以便所述目标企业进行对应的决策管理和决策应用。
本申请实施例还提供一种电子设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如上述的工业大脑处理方法的步骤。
本申请实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如上述的工业大脑处理方法的步骤。
本申请实施例提供的工业大脑处理系统、方法电子设备及存储介质,与现有技术中相比,本申请提供的实施例通过本申请的目的在于提供一种工业大脑处理系统、方法、电子设备及存储介质,通将数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统之间的协调作用,解决了企业决策层关注的核心问题,实现了辅助目标企业决策的能力和自学习以及自解决的能力,填补了目前市场对基于工业大脑的企业决策分析的空白。
为使本申请的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。
附图说明
为了更清楚地说明本申请实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,应当理解,以下附图仅示出了本申请的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1示出了本申请实施例所提供的一种工业大脑处理系统的结构图之一;
图2示出了本申请实施例所提供的一种工业大脑处理系统的结构图之二;
图3示出了本申请实施例所提供的一种工业大脑处理方法的流程图;
图4示出了本申请实施例所提供的一种电子设备的结构示意图。
图中:
100-工业大脑处理系统;110-数据支撑子系统;111-分布式文件管理模块;112-文件管理模块;
113-不同类型的数据库;120-数据库引擎子系统;130-数据池资源管理子系统;140-大脑工作分析子系统;150-大脑应用子系统;400-电子设备;410-处理器;420-存储器;430-总线。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚,下面将结合本申请实施例中附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。因此,以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围,而是仅仅表示本申请的选定实施例。基于本申请的实施例,本领域技术人员在没有做出创造性劳动的前提下所获得的每个其他实施例,都属于本申请保护的范围。
首先,对本申请可适用的应用场景进行介绍。本申请可应用于信息信息技术领域。
经研究发现,现有技术中,企业管理中存在决策效率底、决策层对各层级数据和经营状况掌握不足、全局意识不强、规划执行不到位、管理不科学、评估机制缺失等一系列的问题制约了企业正常的经营发展,而目前市场对基于工业大脑的企业决策分析尚属于空白。
且现有技术中,对与工业行业(制铝、汽车、造船、食品、电子、建筑等属于工业企业)类型的覆盖范围小,现仅覆盖一些类似的工业企业类型,其方案向不同类型工业企业转移存在短板,且现有技术中,仅能够解决工业企业的局部问题,尚未能提供整套从制造、业务、管理以及决策的解决方案,且互联网行业企业需要提高自身学习能力和数据分析计算能力,且互联网行业没有足够的工业领域知识的积累。
基于此,本申请实施例提供了一种工业大脑处理系统、方法、电子设备及存储介质,通过通将数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统之间的协调作用,解决了企业决策层关注的核心问题,实现了辅助目标企业决策的能力和自 学习以及自解决的能力,填补了目前市场对基于工业大脑的企业决策分析的空白。
请参阅图1,图1为本申请实施例所提供的一种工业大脑处理系统的结构图之一。如图1中所示,本申请实施例提供的一种工业大脑处理系统100,所述工业大脑处理系统100包括数据支撑子系统110、大脑工作分析子系统140、大脑应用子系统150、数据库引擎子系统120以及数据池资源管理子系统130。
上述中,不同数外部企业数据源通过下行的数据接口(API接口)发送至两室(云端应用工作室和云端业务工作室)、两站(企业上云服务站和中小企业服务站)以及信息资源(企业内部基本信息、企业外部信息)组成的工业互联网平台,并在工业互联网平台上通过数据总线接口发送至大脑工作分析子系统140。
所述数据支撑子系统110,用于接收不同数外部企业数据源的,并根据所述外部企业数据的数据源,将所述外部企业数据发送至所述数据库引擎子系统120和/或数据池资源管理子系统130。
这里,数据支撑子系统110支持跨平台异构数据实时或批量传输,兼容主流的RDBMS以及NoSQL数据库等主流的数据库。
上述中,数据支撑子系统110收集的外部企业数据均来自于工业互联网平台、两室(云端应用工作室和云端业务工作室)、两站(企业上云服务站和中小企业服务站)以及信息资源(企业内部基本信息、企业外部信息),这些外部企业数据需要沉淀在工业互联网平台,且上述中,两室(云端应用工作室和云端业务工作室)内的外部企业数据发送至数据库引擎子系统120;两站(企业上云服务站和中小企业服务站)内的外部企业数据发送至数据池资源管理子系统130。
其中,数据支撑子系统110可以根据其他合作厂商提供的数据传输(API)接口爬取接收不同数据源的外部企业数据。
所述数据库引擎子系统120,用于为所述大脑工作分析子系统140提供核心功能库,以便所述大脑工作分析子系统140完成对所述企业决策的编辑和推理。
这里,目标企业的策层可直观的认识基于数据库引擎子系统120具体搭建的基础平台和基础模型,方便决策层了解数据库引擎子系统120推演的理论基础。
其中,所述数据库引擎子系统120包括算法库管理模块、语料库管理模块、知识库管理模块以及模型库管理模块。
所述算法库管理模块包括基本算法管理、聚类算法管理、分类算法管理、深度学习算法管理、决策树学习管理以及集成算法管理。
所述语料库管理模块包括语音去燥管理、标识分类管理、多维度分析管理以及算法模型管理。
所述知识库管理模块包括指数图谱管理、文件上传管理、知识创建管理、类索引管理、移动查阅管理以及收藏订阅管理。
所述模型库管理模块包括系统仿真管理、故障预测管理、生产预测管理以及工艺流程管理。
所述数据池资源管理子系统130,用于为所述大脑工作分析子系统140提供企业数据知识和企业数据支撑。
上述中,本申请的实施例提供的数据池资源管理子系统130和数据库引擎子系统120能够通过大脑工作分析子系统140的集中管理,实现深度学习,进而能够实现辅生成目标企业决策的能力和自学习以及自解决的能力。
这里,所述数据池资源管理子系统130包括专利池管理模块、专家池管理模块和标准池管理模块。
所述专利池管理模块用于机理模型管理、工艺流程管理、工况安全管理、质量管理、预测性维护管理以及增益管理。
所述专家池管理模块用于热门专家管理、服务专家管理、技术专家管理以及行业专家管理。
所述标准池管理模块用于国际标准管理、国家标准管理、行业标准管理以及企业标准管理。
所述大脑工作分析子系统140,用于接收所述大脑应用子系统150发送的目标企业的待处理业务,针对所述待处理业务进行数据分析,从所述数据支撑子系统110中获取与所述待处理业务对应的企业业务数据,以及从所述数据库引擎子系统120中获取所述待处理业务对应的预设模型算法;根据所述企业业务数据和预设模型算法,确定所述待处理业务的目标算法模型;并根据所述目标算法模型,生成所述目标企业的目标企业决策,并将所述目标企业决策发送至所述大脑应用子系统150。
上述中,大脑工作分析子系统140通过用户数据填报收集外部企业数据,后期从工业互联网平台中采集外部企业数据,工且业互联网平台应存储有大脑工作分析子系统140所需要的外部企业数据,且大脑工作分析子系统140应该将机理模型沉淀到工业互联网平台中,供其它子系统调用,而发送至大脑应用子系统150的目标企业决策对应着决策应用的业务应用场景。
这里,所述大脑工作分析子系统140包括应用接口管理模块、数据库引擎管理模块、机理建模模块、数据池资源管理模块以及数据分析管理模块。
所述应用接口管理模块,用于接收所述大脑应用子系统150发送的目标企业的待处理业务。
所述数据分析管理模块,用于针对所述待处理业务进行数据分析,确定数据分析结果。
所述数据库引擎管理模块,用于根据所述数据分析结果,从所述数据库引擎子系统120中获取与待处理业务相对应的预设模型算法。
所述数据池资源管理模块,用于根据所述数据分析结果,从所述数据池资源管理子系统130中获取与所述待处理业务对应的企业业务数据。
所述机理建模模块,用于根据所述企业业务数据和预设模型算法,确定所述待处理业务的目标算法模型;并根据所述目标算法模型,生成所述目标企业的目标企业决策。
这里,大脑工作分析子系统140,主要用于负责工业大脑处理系统100中的各个其他子系统的管理工作。
所述大脑工作分析子系统140还用于权限管理模块、企业应用市场管理模块、企业应用编辑模块、企业应用项目管理模块以及后台帮助模块。
所述权限管理模块,用于对外部企业应用的企业权限进行管理。
所述企业应用市场管理模块,用于对外部企业应用的应用市场中进行管理。
所述企业应用编辑模块,用于根据目标企业决策,确定对应的外部企业应用。
所述企业应用项目管理模块,用于对发送给大脑应用子系统150的目标企业决策进行管理。
所述后台帮助模块,用于处理大脑工作分析子系统140在运行过程中存在的问题。
所述大脑应用子系统150,用于根据所述目标企业决策,对所述目标企业进行对应的决策管理和决策应用。
上述中,大脑应用子系统150包括但不限制于包括可视化大屏,可视化大屏重点应用于企业多维度横向定性和纵向定量展示。
目标企业的待处理业务包括但不限制于为确定目标企业的企业经营发展指数,目标企业的企业经营发展指数(Enterprise development index,EDI)体现了企业的整体发展趋势和综合能力,体现了企业对社会的整体经济贡献指数。
且根据企业的财务报表数据和基本企业信息数、可以得到如下销售利润、营业总收入、母公司所有者的净利润、平均归属母公司所有者权益、资产总额、负债总额,应收账款、存货款、流动资本、营业总收入、本年度科技支出总额、工业增加值、全部从业人员平均人数、工资支出总额以及企业员工总数等参数。
下面以一个实施例说明目标企业的待处理业务为目标企业的企业经营发展指数,则所述目标算法模型为指数计算模型,所述指数计算模型的公式为:
其中,IPM用于表征指企业收入利润率;ROE是指净资产收益率;ALR用于表征资产负债率;TGOR用于表征两金占流动资产比重;IRTP用于表征技术进步投入占比;APLP用于表征全员劳动生产率;WOR用于表征工资产出比;PCNA用于表征人均净资产;a、β、η、λ、μ、κ、π以及ω用于表征所述指数计算模型的参数。
且企业经营发展指数的指数计算模型中的各个参数的设定是由同行业企业实践经验数据训练得出的。
上述中,

销售(营业)利润=营业总收入-营业成本-营业税金及附加;







且ω处于分母的位置,只是对企业发展指数值EDI:f(KPI)的放缩,对企业发展指数模型的求解没有影响,故将其设定为1,即令ω=1;考虑企业发展指数模型公式的分子部分,对分子部分进行分析发现,企业发展指数是关于自变量的线性模型,记η=-1/η,μ=1/μ,分子即可转换为下面公式:
上述中,下表1是不同等级下企业评价标准值。其中规定各等级下EDI取值的范围是:优秀(90-100),良好(80-90),平均(70-80),较低(60-70),较差(0-60)。
表1:塑料制品业不同等级下企业评价标准值
给定训练数据集S={(x1,y1),(x2,y2),...,(xn,yn)},其中xi=(IPM,ROE,TGOR,ALR,IRTP,APLP,WOR,PCNG)表示目标企业的发展状况数据,yi表示目标企业等级。g1,g2,g3,g4,g5表示目标企业五种等级下的评价标准值,对应的EDI值记为EDI(gi)。对于某等级企业的EDI(xi)值,应尽可能与该等级标准值下的EDI(gyi)值接近,因此我们期望最小化他们的距离1/2(EDI(xi)-EDI(gyi))2,并且相同等级下的企业发展指数值应该在既定的范围内。通过最小化所有样本与他们所属等级下的标准EDI值的距离,得到如下优化目标问题:
其中,
xi=(IPM,ROE,TGOR,ALR,IRTP,APLP,WOR,PCNG)。
这里,具体的目标企业决策分析过程如下:
IPM<5,企业收入利润率较低,建议提高营业收入,缩减营业成本。
IPM>=5,企业收入利润率良好。
这里,具体的目标企业决策分析过程如下:
ROE>=10,净资产收益率良好。
2<=ROE<10,净资产收益率一般,建议调整经营结构,降低成本,提高利润。
ROE<2,净资产收益率较差,经营风险预警,建议积极调整投资策略,降低成本,提高利润。
这里,具体的目标企业决策分析过程如下:
ALR<40,资产负债率过小,可适当增加负债率,提高经营规模。
40<=ALR<60,资产负债率在合理范围。
ALR>=60,资产负债率过重,容易发生资不抵债风险,建议及时采取措施,降低资产负债率。
这里,具体的目标企业决策分析过程如下:
TGOR>60,两金占流动资产比重过高,建议增加流动资产,加紧应收账款回流,减少存货量。
TGOR<=60,两金占流动资产比重正常。
这里,具体的目标企业决策分析过程如下:
IRTP>2.6,企业技术投入较高,科技发展潜力较大。
IRTP<=2.6,企业技术投入一般。
这里,具体的目标企业决策分析过程如下:
APLP<=1.65(万元/人),全员劳动生产率低于标准值,建议提高工业增加值,调整人员结构,裁减冗余人员,
这里,上述提到的企业经营发展数据项具体可以参见表2:
表2
上述中,本申请提供的企业经营发展指数分为五个状态:优秀、良一般、较差以及差,其中,如表3所示:
表3
这里,本申请实施例提供的根据企业经营发展指数,确定的指数计算模型,可以根据计算模型算出结果,并根据结果给出目标企业决策,企业经营发展指数中各个参数设定由同行业企业实现数据训练得出。
本申请实施例提供的工业大脑处理系统100,与现有技术中相比,本申请通过将数据支撑子系统110、大脑工作分析子系统140、大脑应用子系统150、数据库引擎子系统120以及数据池资源管理子系统130之间的协调作用,解决了企业决策层关注的核心问题,实现了辅助目标企业决策的能力和自学习以及自解决的能力,填补了目前市场对基于工业大脑的企业决策分析的空白。
请参阅图2,图2为本申请另一实施例提供的一种工业大脑处理系统100的流程图。如图2中所示,本申请实施例提供的一种工业大脑处理系统100,包括:
所述工业大脑处理系统100包括数据支撑子系统110、大脑工作分析子系统140、大脑应用子系统150、数据库引擎子系统120以及数据池资源管理子系统130。
所述数据支撑子系统110,用于接收不同数据源的外部企业数据,并根据所述外部企业数据的数据源,将所述外部企业数据发送至所述数据库引擎子系统120和/或数据池资源管理子系统130。
所述数据库引擎子系统120,用于为所述大脑工作分析子系统140提供核心功能库,以便所述大脑工作分析子系统140完成对所述企业决策的编辑和推理。
所述数据池资源管理子系统130,用于为所述大脑工作分析子系统140提供企业数据知识和企业数据支撑。
所述大脑工作分析子系统140,用于接收所述大脑应用子系统150发送的目标企业的待处理业务,针对所述待处理业务进行数据分析,从所述数据支撑子系统110中获取与所述待处理业务对应的企业业务数据,以及从所述数据库引擎子系统120中获取所述待处理业务对应的预设模型算法;根据所述企业业务数据和预设模型算法,确定所述待处理业务的目标算法模型;并根据所述目标算法模型,生成所述目标企业的目标企业决策,并将所述目标企业决策发送至所述大脑应用子系统150。
所述大脑应用子系统150,用于根据所述目标企业决策,对所述目标企业进行对应的决策管理和决策应用。
进一步的,所述数据支撑子系统110包括分布式文件管理模块111、文件管理模块112以及不同类型的数据库113。
所述文件管理模块112,用于接收不同数据源的外部企业数据。
不同类型的所述数据库,用于将所述外部企业数据按照对应的结构类型的进行分类,确定各个类型的所述外部企业数据。
所述文件管理模块112,用于将各个类型的所述外部企业数据发送至所述数据库引擎子系统120和/或数据池资源管理子系统130。
本申请实施例提供的工业大脑处理系统,与现有技术中相比,本申请通过将数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统之间的协调作用,解决了企业决策层关注的核心问题,实现了辅助目标企业决策的能力和自学习以及自解决的能力,填补了目前市场对基于工业大脑的企业决策分析的空白。
请参阅图3,图3为本申请实施例所提供的一种工业大脑处理方法的流程图。如图3中所示,所述一种工业大脑处理方法的流程图,包括以下步骤:
获取标企业的待处理业务。
针对所述待处理业务进行数据分析,确定所述待处理业务对应的企业业务数据以及所述待处理业务对应的预设模型算法。
根据所述企业业务数据和所述预设模型算法,确定所述待处理业务的目标算法模型。
根据所述目标算法模型,生成所述目标企业的目标企业决策,以便所述目标企业进行对应的决策管理和决策应用。
本申请实施例提供的工业大脑处理方法,与现有技术中相比,本申请通过将数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统之间的协调作用,解决了企业决策层关注的核心问题,实现了辅助目标企业决策的能力和自学习以及自解决的能力,填补了目前市场对基于工业大脑的企业决策分析的空白。
请参阅图4,图4为本申请实施例所提供的一种电子设备的结构示意图。如图4中所示,所述电子设备400包括处理器410、存储器420和总线430。
所述存储器420存储有所述处理器410可执行的机器可读指令,当电子设备400运行时,所述处理器410与所述存储器420之间通过总线430通信,所述机器可读指令被所述处理器410执行时,可以执行如上述图3所示方法实施例中的工业大脑处理方法的步骤,具体实现方式可参见方法实施例,在此不再赘述。
本申请实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时可以执行如上述图3所示方法实施例中的工业大脑处理方法的步骤,具体实现方式可参见方法实施例,在此不再赘述。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和模块的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,又例如,多个模块或组件可以结合或者可以集成到另 一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口,装置或模块的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理模块,即可以位于一个地方,或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理模块中,也可以是各个模块单独物理存在,也可以两个或两个以上模块集成在一个模块中。
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时,可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上所述实施例,仅为本申请的具体实施方式,用以说明本申请的技术方案,而非对其限制,本申请的保护范围并不局限于此,尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化,或者对其中部分技术特征进行等同替换;而这些修改、变化或者替换,并不使相应技术方案的本质脱离本申请实施例技术方案的精神和范围,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以权利要求的保护范围为准。

Claims (10)

  1. 一种工业大脑处理系统,其特征在于,所述工业大脑处理系统包括数据支撑子系统、大脑工作分析子系统、大脑应用子系统、数据库引擎子系统以及数据池资源管理子系统;
    所述数据支撑子系统,用于接收不同数据源的外部企业数据,并根据所述外部企业数据的数据源,将所述外部企业数据发送至所述数据库引擎子系统和/或数据池资源管理子系统;
    所述数据库引擎子系统,用于为所述大脑工作分析子系统提供核心功能库,以便所述大脑工作分析子系统完成对企业决策的编辑和推理;
    所述数据池资源管理子系统,用于为所述大脑工作分析子系统提供企业数据知识和企业数据支撑;
    所述大脑工作分析子系统,用于接收所述大脑应用子系统发送的目标企业的待处理业务,针对所述待处理业务进行数据分析,从所述数据支撑子系统中获取与所述待处理业务对应的企业业务数据,以及从所述数据库引擎子系统中获取所述待处理业务对应的预设模型算法;根据所述企业业务数据和预设模型算法,确定所述待处理业务的目标算法模型;并根据所述目标算法模型,生成所述目标企业的目标企业决策,并将所述目标企业决策发送至所述大脑应用子系统;
    所述大脑应用子系统,用于根据所述目标企业决策,对所述目标企业进行对应的决策管理和决策应用。
  2. 根据权利要求1所述的工业大脑处理系统,其特征在于,所述数据支撑子系统包括分布式文件管理模块、文件管理模块以及不同类型的数据库;
    所述文件管理模块,用于接收不同数据源的外部企业数据;
    不同类型的所述数据库,用于将所述外部企业数据按照对应的结构类型的进行分类,确定各个类型的所述外部企业数据;
    所述分布式文件管理模块,用于将各个类型的所述外部企业数据发送至所述数据库引擎子系统和/或数据池资源管理子系统。
  3. 根据权利要求1所述的工业大脑处理系统,其特征在于,所述数据库引擎子系统包括算法库管理模块、语料库管理模块、知识库管理模块以及模型库管理模块;
    所述算法库管理模块,用于基本算法管理、聚类算法管理、分类算法管理、深度学习算法管理、决策树学习管理以及集成算法管理;
    所述语料库管理模块,用于语音去燥管理、标识分类管理、多维度分析管理以及算法模型管理;
    所述知识库管理模块,用于指数图谱管理、文件上传管理、知识创建管理、类索引管理、移动查阅管理以及收藏订阅管理;
    所述模型库管理模块,用于系统仿真管理、故障预测管理、生产预测管理以及工艺流程管理。
  4. 根据权利要求1所述的工业大脑处理系统,其特征在于,所述数据池资源管理子系统包括专利池管理模块、专家池管理模块和标准池管理模块;
    所述专利池管理模块,用于机理模型管理、工艺流程管理、工况安全管理、质量管理、预测性维护管理以及增益管理;
    所述专家池管理模块,用于热门专家管理、服务专家管理、技术专家管理以及行业专家管理;
    所述标准池管理模块,用于国际标准管理、国家标准管理、行业标准管理以及企业标准管理。
  5. 根据权利要求1所述的工业大脑处理系统,其特征在于,所述大脑工作分析子系统包括应用接口管理模块、数据库引擎管理模块、机理建模模块、数据池资源管理模块以及数据分析管理模块;
    所述应用接口管理模块,用于接收所述大脑应用子系统发送的目标企业的待处理业务;
    所述数据分析管理模块,用于针对所述待处理业务进行数据分析,确定数据分析结果;
    所述数据库引擎管理模块,用于根据所述数据分析结果,从所述数据库引擎子系统中获取与待处理业务相对应的预设模型算法;
    所述数据池资源管理模块,用于根据所述数据分析结果,从所述数据池资源管理子系统中获取与所述待处理业务对应的企业业务数据;
    所述机理建模模块,用于根据所述企业业务数据和预设模型算法,确定所述待处理业务的目标算法模型;并根据所述目标算法模型,生成所述目标企业的目标企业决策。
  6. 根据权利要求5所述的工业大脑处理系统,其特征在于,所述大脑工作分析子系统还包括权限管理模块、企业应用市场管理模块、企业应用编辑模块、企业应用项目管理模块以及后台帮助模块;
    所述权限管理模块,用于对外部企业应用的企业权限进行管理;
    所述企业应用市场管理模块,用于对外部企业应用的应用市场中进行管理;
    所述企业应用编辑模块,用于根据目标企业决策,确定对应的外部企业应用;
    所述企业应用项目管理模块,用于对发送给大脑应用子系统的目标企业决策进行管理;
    所述后台帮助模块,用于处理大脑工作分析子系统在运行过程中存在的问题。
  7. 根据权利要求1所述的工业大脑处理系统,其特征在于,若目标企业的待处理业务为确定所述目标企业的企业经营发展指数,则所述目标算法模型为指数计算模型,所述指数计算模型的公式为:
    其中,IPM用于表征指企业收入利润率;ROE是指净资产收益率;ALR用于表征资产负债率;TGOR用于表征两金占流动资产比重;IRTP用于表征技术进步投入占比;APLP用于表征全员劳动 生产率;WOR用于表征工资产出比;PCNA用于表征人均净资产;α、β、η、λ、μ、κ、π以及ω用于表征所述指数计算模型的参数。
  8. 一种工业大脑处理方法,应用于如权利要求1-7任一所述的工业大脑处理系统,其特征在于,所述工业大脑处理方法包括:
    获取标企业的待处理业务;
    针对所述待处理业务进行数据分析,确定所述待处理业务对应的企业业务数据以及所述待处理业务对应的预设模型算法;
    根据所述企业业务数据和所述预设模型算法,确定所述待处理业务的目标算法模型;
    根据所述目标算法模型,生成所述目标企业的目标企业决策,以便所述目标企业进行对应的决策管理和决策应用。
  9. 一种电子设备,其特征在于,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过所述总线进行通信,所述机器可读指令被所述处理器运行时执行如权利要求8所述的工业大脑处理方法的步骤。
  10. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有计算机程序,所述计算机程序被处理器运行时执行如权利要求8所述的工业大脑处理方法的步骤。
PCT/CN2023/134955 2022-11-08 2023-11-29 一种工业大脑处理系统、方法、电子设备及存储介质 WO2024099462A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211389249.7A CN115796614A (zh) 2022-11-08 2022-11-08 一种工业大脑处理系统、方法、电子设备及存储介质
CN202211389249.7 2022-11-08

Publications (1)

Publication Number Publication Date
WO2024099462A1 true WO2024099462A1 (zh) 2024-05-16

Family

ID=85436010

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/134955 WO2024099462A1 (zh) 2022-11-08 2023-11-29 一种工业大脑处理系统、方法、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN115796614A (zh)
WO (1) WO2024099462A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115796614A (zh) * 2022-11-08 2023-03-14 北京航天数据股份有限公司 一种工业大脑处理系统、方法、电子设备及存储介质
CN116384710B (zh) * 2023-06-02 2023-10-13 国网福建省电力有限公司管理培训中心 基于客户和资产管理的决策系统、介质及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150262095A1 (en) * 2014-03-12 2015-09-17 Bahwan CyberTek Private Limited Intelligent Decision Synchronization in Real Time for both Discrete and Continuous Process Industries
CN109492773A (zh) * 2018-10-17 2019-03-19 南京昊瀛天成信息技术有限公司 一种基于工业大数据的智能决策系统
CN113177698A (zh) * 2021-04-12 2021-07-27 北京科技大学 一种工业大数据分析辅助决策平台系统
CN113743883A (zh) * 2021-08-02 2021-12-03 上海工程技术大学 基于类脑启发的工业制造通用智能决策协同优化系统
CN115796614A (zh) * 2022-11-08 2023-03-14 北京航天数据股份有限公司 一种工业大脑处理系统、方法、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150262095A1 (en) * 2014-03-12 2015-09-17 Bahwan CyberTek Private Limited Intelligent Decision Synchronization in Real Time for both Discrete and Continuous Process Industries
CN109492773A (zh) * 2018-10-17 2019-03-19 南京昊瀛天成信息技术有限公司 一种基于工业大数据的智能决策系统
CN113177698A (zh) * 2021-04-12 2021-07-27 北京科技大学 一种工业大数据分析辅助决策平台系统
CN113743883A (zh) * 2021-08-02 2021-12-03 上海工程技术大学 基于类脑启发的工业制造通用智能决策协同优化系统
CN115796614A (zh) * 2022-11-08 2023-03-14 北京航天数据股份有限公司 一种工业大脑处理系统、方法、电子设备及存储介质

Also Published As

Publication number Publication date
CN115796614A (zh) 2023-03-14

Similar Documents

Publication Publication Date Title
WO2024099462A1 (zh) 一种工业大脑处理系统、方法、电子设备及存储介质
Kayikci et al. Exploring barriers to smart and sustainable circular economy: The case of an automotive eco-cluster
US12002096B1 (en) Artificial intelligence supported valuation platform
US11526859B1 (en) Cash flow forecasting using a bottoms-up machine learning approach
Tao et al. Research on marketing management system based on independent ERP and business BI using fuzzy TOPSIS
Wang et al. Internet financial risk management in the context of big data and artificial intelligence
Luo et al. Supply Chain Flexibility Evaluation Based on Matter‐Element Extension
Ma Research on the development of hospital intelligent finance based on artificial intelligence
KR101550973B1 (ko) 기업 컨설팅 정보 제공 방법
CN117171145B (zh) 一种企业管理系统数据的分析处理方法、设备及存储介质
CN105260931A (zh) 一种基于mot模型的金融服务平台系统
KR20210099879A (ko) 기업 맞춤형 성과지표 기반의 경영 지원 방법
Tallón-Ballesteros The design of ERP intelligent sales management system
CN114757448B (zh) 一种基于数据空间模型的制造环节间最优价值链构建方法
Zhang [Retracted] Intelligent Optimization of the Financial Sharing Path Based on Accounting Big Data
Liu et al. Risk assessment and regulation algorithm for financial technology platforms in smart city
CN110263156B (zh) 面向政企服务大数据的智能派单方法
Zhuang et al. Discrete dynamic modeling analysis of engineering management and quality optimization innovation mode based on big data intelligent algorithm
CN114020814A (zh) 一种流程工业制造全链条数据集成与分析方法和系统
Wei et al. Advanced Artificial Intelligence Model for Financial Accounting Transformation Based on Enterprise Unstructured Text Data
Sun Research on risk management of engineering project
Liu et al. The Design of ERP Intelligent Sales Management System.
STANEK et al. The knowledge components in DDMKCC model as the catalyst of a hybrid DSS–The IT company case study
CN115292274B (zh) 一种数据仓库主题模型构建方法和系统
Zhou et al. Research on Performance Management in the Digital Management System of Commercial Assets of Tobacco Enterprises

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23888147

Country of ref document: EP

Kind code of ref document: A1