WO2020259716A1 - Esg指标监控方法、装置、设备及存储介质 - Google Patents
Esg指标监控方法、装置、设备及存储介质 Download PDFInfo
- Publication number
- WO2020259716A1 WO2020259716A1 PCT/CN2020/107320 CN2020107320W WO2020259716A1 WO 2020259716 A1 WO2020259716 A1 WO 2020259716A1 CN 2020107320 W CN2020107320 W CN 2020107320W WO 2020259716 A1 WO2020259716 A1 WO 2020259716A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- esg
- data
- key
- information
- alternative data
- 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.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Definitions
- This application relates to the field of Fintech (financial technology) technology, and in particular to an ESG indicator monitoring method, device, equipment and storage medium.
- ESG End, Social Responsibility, corporate governance: environmental, social and corporate governance, refers to the three core factors that measure the sustainability and ethical impact of a company or company’s investment) indicators to help investors better determine the future financial performance (returns and risks of the company concerned) ), is being adopted and used by more and more investors.
- the main purpose of this application is to provide an ESG indicator monitoring method, device, terminal equipment, and storage medium, which aims to solve the traditional method of obtaining ESG indicators of financial market companies, and the resulting ESG-related information has low accuracy and outdated data. problem.
- this application provides an ESG indicator monitoring method, which includes the following steps:
- the alternative data includes entity data, business process data, and sensor data
- the step of obtaining alternative data includes:
- the knowledge graph includes: a key information graph,
- the step of processing the alternative data to determine a knowledge graph includes:
- Extracting key information from the alternative data based on artificial intelligence technology where the key information includes: key nodes and key relationships;
- a key information map is determined.
- the knowledge graph further includes: a structural relationship graph,
- the step of processing the alternative data to determine a knowledge graph further includes:
- the structured data is extracted from the alternative data to determine the structure relationship map.
- the step of extracting ESG events from the alternative data and combining the knowledge graph to score the ESG indicators on the ESG event includes:
- the step of combining the knowledge graph to score ESG indicators includes:
- Score ESG indicators according to the analysis result of analyzing the impact information and conduction information of the ESG event.
- the step of outputting early warning information to parties related to the ESG event according to the scoring result of ESG index scoring includes:
- this application also provides an ESG indicator monitoring device, and the ESG indicator monitoring device includes:
- the determining module is used to obtain alternative data and process the alternative data to determine the knowledge graph
- a scoring module configured to extract ESG events from the alternative data, and perform ESG index scoring on the ESG events in combination with the knowledge graph;
- the output module is used for outputting early warning information to parties related to the ESG event according to the scoring result of the ESG indicator scoring.
- the ESG indicator monitoring device includes: a memory, a processor, and an ESG indicator monitoring program stored in the memory and running on the processor, the ESG When the indicator monitoring program is executed by the processor, the steps of the ESG indicator monitoring method described above are implemented.
- the present application also provides a storage medium applied to a computer, and an ESG indicator monitoring program is stored on the storage medium, and the ESG indicator monitoring program is executed by a processor to implement the steps of the ESG indicator monitoring method as described above.
- This application obtains alternative data and processes the alternative data to determine the knowledge graph; extracts ESG events from the alternative data, and combines the knowledge graph to score the ESG indicators; according to the ESG index
- the scoring result of the scoring outputs early warning information to the parties related to the ESG event.
- This application realizes that the acquisition of ESG indicators has been changed from passive to active, avoiding the situation that individual ESG indicators cannot effectively provide references for individual parties due to the involuntary disclosure of data by industry individuals, and improving the quantity and overall value of ESG related information , And based on the combination of artificial intelligence technology, real-time monitoring and ESG index scoring of ESG events triggered by industry individuals in alternative data, and updating and maintaining the influence relationship between industry individuals based on real-time monitoring, and based on the scoring results of ESG index scoring Timely output of early warning information to trigger individual parties has improved the accuracy of ESG-related information and the real-time and effectiveness of data.
- Figure 1 is a schematic structural diagram of a hardware operating environment involved in a solution of an embodiment of the present application
- FIG. 3 is a detailed flowchart of step S100 in an embodiment of an ESG indicator monitoring method of this application;
- FIG. 4 is a schematic flowchart of a second embodiment of the ESG indicator monitoring method of this application.
- FIG. 5 is a schematic diagram of an application scenario in an embodiment of an ESG indicator monitoring method of this application.
- Fig. 6 is a schematic diagram of modules of the ESG indicator monitoring device of this application.
- Fig. 1 is a schematic structural diagram of a hardware operating environment involved in a solution of an embodiment of the present application.
- Fig. 1 can be a structural diagram of the hardware operating environment of the terminal device.
- the terminal device in the embodiment of the present application may be a terminal device such as a PC and a portable computer.
- the terminal device may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002.
- the communication bus 1002 is used to implement connection and communication between these components.
- the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
- the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
- the memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a magnetic disk memory.
- the memory 1005 may also be a storage device independent of the foregoing processor 1001.
- the structure of the terminal device shown in FIG. 1 does not constitute a limitation on the terminal device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange different components.
- the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an ESG indicator monitoring program.
- the operating system is a program that manages and controls the hardware and software resources of the sample terminal equipment, and supports the operation of the ESG indicator monitoring program and other software or programs.
- the user interface 1003 is mainly used for data communication with various terminals;
- the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server;
- the processor 1001 can be used for calling the memory 1005
- the ESG indicator monitoring program stored in and perform the following operations:
- processor 1001 may also be used to call the ESG indicator monitoring program stored in the memory 1005 and execute the following steps:
- processor 1001 may also be used to call the ESG indicator monitoring program stored in the memory 1005 and execute the following steps:
- Extracting key information from the alternative data based on artificial intelligence technology where the key information includes: key nodes and key relationships;
- a key information map is determined.
- processor 1001 may also be used to call the ESG indicator monitoring program stored in the memory 1005 and execute the following steps:
- the structured data is extracted from the alternative data to determine the structure relationship map.
- processor 1001 may also be used to call the ESG indicator monitoring program stored in the memory 1005 and execute the following steps:
- processor 1001 may also be used to call the ESG indicator monitoring program stored in the memory 1005 and execute the following steps:
- Score ESG indicators according to the analysis result of analyzing the impact information and conduction information of the ESG event.
- processor 1001 may also be used to call the ESG indicator monitoring program stored in the memory 1005 and execute the following steps:
- FIG. 2 is a schematic flowchart of the first embodiment of the ESG indicator monitoring method of this application.
- the embodiments of the present application provide an embodiment of the ESG indicator monitoring method. It should be noted that although the logical sequence is shown in the flowchart, in some cases, the sequence shown or shown may be executed in a different order than here. Describe the steps.
- the ESG indicator monitoring method of the embodiment of this application is applied to the above-mentioned terminal device.
- the terminal device of the embodiment of this application may be a terminal device such as a PC, a portable computer, etc., which is not specifically limited here.
- Step S100 Obtain alternative data, and process the alternative data to determine a knowledge graph.
- the alternative data includes: entity data, business process data, and sensor data.
- the step of obtaining alternative data includes:
- Step A Extract the specified entity data, business process data and sensor data from the preset data platform.
- the entity data, business process data and sensor data related to the designated industry are extracted from each preset data platform in the big environmental data.
- each preset data platform includes: major platforms that publish data information in large environmental data, such as government/structure networks, news media, post bar forums, etc., and entity data includes entities related to individuals, companies, or products. data.
- FIG. 3 is a detailed flowchart of step S100 of an embodiment of the ESG indicator monitoring method of this application.
- the knowledge graph includes: a key information graph.
- the alternative The steps of data processing to determine the knowledge graph include:
- Step S101 extracting key information from the alternative data based on artificial intelligence technology, where the key information includes: key nodes and key relationships.
- the data information such as the external procurement contract or bidding announcement issued by the listed company is screened out, and the NLP (natural language processing: natural language processing technology) extract the upstream and downstream nodes of the listed company and the supply relationship related to the listed company from the data information such as the external procurement contract or the bidding announcement.
- NLP natural language processing: natural language processing technology
- Step S102 Determine a key information graph according to the key nodes and key relationships in the key information.
- the key information map Based on the extracted key nodes and key relationships and other data information, it is detected whether the key information map has been established. If it is detected that the key information map has not been established, the key information used to represent the influence relationship between the operating individuals in the industry is newly constructed Atlas, if it is detected that a key information atlas has been established, the established key information atlas will be updated and maintained based on real-time key nodes and key relationships and other data information.
- the upstream and downstream nodes of the listed company and the supply relationship related to the listed company are extracted when it is detected that there is no
- a new key information map is established, and when the key information map is detected.
- the upstream supplier enterprises and the downstream purchaser enterprise nodes and influence control relationships in the key information map are continuously updated and maintained.
- the knowledge graph further includes: a structural relationship graph.
- the step of processing the alternative data to determine the knowledge graph further includes:
- Step B Extract structured data from the alternative data to determine the structure relationship map.
- structured data such as industry and commerce, financing, investment, etc. are extracted, and when it is detected that there is no structural relationship graph, the industry and commerce data are used to construct a new representation of equity, investment
- the structural relationship map that affects the relationship, the use of financial transaction registration and settlement data to establish a structural relationship map that represents the financing relationship, and when a structural relationship map is detected, the business data in the alternative data and the financial transaction registration are monitored in real time Settlement data, and continuously update and maintain the constructed structural relationship graph.
- the professional business personnel who maintain the completed knowledge graph can also manually maintain the knowledge graph.
- professional business personnel monitor alternative data in real time, and in data information such as external procurement contracts or bidding announcements issued by a listed company, detect the upstream and downstream nodes of the listed company and the related information of the listed company When the supply relationship of the company changes, it will immediately report the change to the professional business personnel maintaining the knowledge map, so that the professional business personnel maintaining the knowledge map will be based on the relationship between the listed company and the new upstream supplier company and the new downstream purchaser company.
- Step S200 Extract ESG events from the alternative data, and perform ESG index scoring on the ESG events in combination with the knowledge graph.
- the same NLP natural language processing technology is used to extract ESG incidents from environmental pollution penalties for a chemical company from the environmental protection government data on an alternative data platform constructed on the basis of the acquired alternative data that includes the financial industry.
- Step S300 Output early warning information to the parties related to the ESG event according to the scoring result of the ESG indicator scoring.
- the early warning information is output to each related party that has an influence relationship with the industry individual that triggered the current ESG event.
- step S300 includes:
- Step S301 detecting whether the scoring result of scoring the ESG index on the ESG event meets a preset condition.
- the preset condition is that the current judgment is based on the scoring result of the ESG indicator scoring of the industry individual that triggered the ESG event, and the judgment standard for outputting early warning information to the parties in the industry that triggered the ESG event.
- any scoring value is greater than or equal to the standard threshold, that is, it is determined that the scoring result meets the conditions for outputting early warning information.
- Step S302 When it is detected that the scoring result meets a preset condition, output risk warning information to the party related to the ESG event.
- any score value is greater than or equal to the standard threshold
- the key information graph or structural relationship graph that is constructed can be used to trigger the current
- the related parties that affect or restrict the relationship between industry operating entities of basic ESG events such as regulatory agencies, investors, upstream and downstream node companies, provide risk warning, risk monitoring and other risk warning information, and in particular, can also provide investors Services such as the discovery of investment opportunities will help "green finance”.
- This application extracts entity data, business process data, and sensor data related to the designated industry from each preset data platform in the big environmental data based on the existing data acquisition method, and will acquire the entity data of the designated industry,
- the business process data and the sensor data are classified and statistically processed to form a data platform containing alternative data of various industries, using mature artificial intelligence technology to extract from the established data platform containing alternative data of various industries
- Real-time key nodes and key relationships and other data information based on the extracted key nodes and key relationships and other data information, establish a key information graph that represents the influence relationship between operating individuals in the industry, and based on real-time key nodes and key Relations and other data information update and maintain the established key information map, or extract real-time structured data information from the established data platform containing alternative data for various industries, so as to establish a way to represent the influence of various operating individuals in the industry
- the structure relationship map of the relationship, and based on the real-time structured data information of the monitoring, the established structure relationship map is updated and maintained, and the artificial intelligence technology is
- the industry Middle individuals score ESG indicators, and according to the scoring results of ESG indicator scores, timely output early warning information to other parties that have an influential relationship with the current industry individual, thereby changing the acquisition of ESG indicators from passive to active, avoiding industry individuals’ inactivity Disclosure of data results in the inability of individual ESG indicators to effectively provide references for individual related parties, increasing the amount and overall value of ESG-related information, and based on the combination of artificial intelligence technology, real-time monitoring of ESG events triggered by industry individuals in alternative data Based on real-time monitoring and ESG indicator scoring, the relationship between industry individuals is updated and maintained, and based on the scoring results of ESG indicator scoring, early warning information is output to the triggering individual parties in a timely manner, which improves the accuracy of ESG-related information and data Timeliness and effectiveness.
- FIG. 4 is a schematic flowchart of the second embodiment of the ESG indicator monitoring method of this application.
- the above step S200 is to extract ESG from the alternative data Events, combined with the knowledge graph to score ESG indicators, including:
- Step S201 Extract ESG events from the alternative data based on artificial intelligence technology based on a preset extraction method.
- NLP natural language processing technology is used to randomly sample from the environmental protection government data on the alternative data platform of the financial industry constructed based on the obtained alternative data and from the financial market or the chemical market.
- Step S202 Perform ESG index scoring on the ESG event in combination with the knowledge graph.
- ESG indicators are performed on the industry individuals that trigger the current ESG event score.
- the ESG incident after the environmental pollution penalty of a chemical company is extracted , Continuously track and monitor the spread of the ESG event in the public opinion data of the entire network in real time, the spread of the heat, and the current government’s attention to the relevant social topics caused by the current ESG event, etc., and the key nodes and
- the key information map constructed by the key relationship, or in the structural relationship map constructed based on structured data the impact of the current ESG event is estimated based on the influence and restriction relationship between the chemical company and the upstream and downstream node companies, thereby affecting the current chemical industry Score each ESG indicator of the company.
- step S202 the step of scoring ESG indicators in combination with the knowledge graph includes:
- Step D Analyze the impact information and conduction information of the ESG event in combination with the knowledge graph.
- Step E Perform ESG index scoring according to the analysis result of analyzing the impact information and conduction information of the ESG event.
- a key information graph constructed based on key nodes and key relationships in alternative data or a structural relationship graph constructed based on structured data, upstream and downstream based on investors, regulatory agencies, and industry individuals that trigger current ESG events
- the relationship between the node companies and other related parties, and the industry individuals that trigger the current ESG event analyzes the impact of the current ESG event on each related party, and monitors the public opinion data in the entire network through continuous real-time tracking.
- This application uses existing artificial intelligence technology to randomly extract ESG events from the obtained data platform containing alternative data in the financial industry through a preset random extraction method.
- a more comprehensive and accurate ESG indicator scoring based on ESG events in alternative data is realized, thereby further improving the accuracy of ESG-related information and the effectiveness of providing references to investors, regulatory agencies, etc. for ESG-related information.
- an embodiment of the present application also proposes an ESG indicator monitoring device, and the ESG indicator monitoring device includes:
- the determining module is used to obtain alternative data and process the alternative data to determine the knowledge graph
- a scoring module configured to extract ESG events from the alternative data, and perform ESG index scoring on the ESG events in combination with the knowledge graph;
- the output module is used for outputting early warning information to parties related to the ESG event according to the scoring result of the ESG indicator scoring.
- the determining module includes:
- the first extraction unit is used to extract specified entity data, business process data and sensor data from the preset data platform.
- the determining module further includes:
- the extraction unit is configured to extract key information from the alternative data based on artificial intelligence technology, where the key information includes: key nodes and key relationships;
- the first determining unit is configured to determine the key information map according to the key nodes and key relationships in the key information.
- the determining module further includes:
- the second determining unit is used to extract structured data from the alternative data to determine the structure relationship map.
- the scoring module includes:
- the second extraction unit is configured to extract ESG events from the alternative data based on artificial intelligence technology based on a preset extraction method
- the scoring unit is used to score the ESG index on the ESG event in combination with the knowledge graph.
- the scoring unit includes:
- An analysis unit configured to analyze the impact information and conduction information of the ESG event in combination with the knowledge graph
- the scoring subunit is used for scoring ESG indicators according to the analysis result of analyzing the impact information and conduction information of the ESG event.
- the output module includes:
- the detecting unit is configured to detect whether the scoring result of ESG index scoring on the ESG event meets a preset condition
- the output unit is configured to output risk warning information to parties related to the ESG event when it is detected that the scoring result meets a preset condition.
- the embodiment of the present application also proposes a storage medium applied to a computer, that is, the storage medium is a computer-readable storage medium, and the ESG indicator monitoring program is stored on the medium, and the ESG indicator monitoring program is executed by the processor When realizing the steps of the ESG indicator monitoring method as described above.
- the method implemented when the ESG indicator monitoring program running on the processor is executed can refer to the various embodiments of the ESG indicator monitoring method of this application, which will not be repeated here.
- the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. ⁇
- the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes a number of instructions to enable a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the method described in each embodiment of the present application.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种ESG指标监控方法、装置、设备及存储介质,该ESG指标监控方法包括:获取另类数据,并对所述另类数据进行处理以确定知识图谱(S100);从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分(S200);根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息(S300)。
Description
本申请要求于2019年8月20日申请的、申请号为201910776692.1、名称为“ESG指标监控方法、装置、终端设备及存储介质”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。
本申请涉及Fintech(金融科技)技术领域,尤其涉及一种ESG指标监控方法、装置、设备及存储介质。
伴随着金融科技,尤其是互联网金融科技的快速发展,已经有越来越多的技术应用于金融领域,其中,基于获取的ESG(Environment、Social Responsibility、Corporate
Governance:环境,社会和公司治理,是指衡量公司或企业投资的可持续性和道德影响的三个核心因素)指标,以帮助投资者更好的确定被关注企业未来的财务业绩(回报和风险),正被越来越多的投资者所采纳和运用。
然而,现有获取市场ESG指标的传统做法是通过类似MSCI(Morgan Stanley Capital International:摩根士丹利资本国际公司)的机构通过给被调查对象(即相关市场内的企业)分发调查问卷进行获取,或者通过相关市场内的企业主动披露出来,如此,企业通常基于谨慎角度考虑而不披露对于企业相关方(投资者、监管机构等)真正有价值参考的数据,导致ESG相关信息准确度低且数据陈旧。
本申请的主要目的在于提供一种ESG指标监控方法、装置、终端设备及存储介质,旨在解决传统的获取金融市场企业ESG指标的做法,得出的ESG相关信息准确度低且数据陈旧的技术问题。
为实现上述目的,本申请提供一种ESG指标监控方法,所述ESG指标监控方法包括以下步骤:
获取另类数据,并对所述另类数据进行处理以确定知识图谱;
从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;
根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
在一实施例中,所述另类数据包括:实体数据、商业过程数据以及传感器数据,所述获取另类数据的步骤,包括:
从预设数据平台中抽取指定的实体数据、商业过程数据以及传感器数据。
在一实施例中,所述知识图谱包括:关键信息图谱,
所述对所述另类数据进行处理以确定知识图谱的步骤,包括:
基于人工智能技术从所述另类数据中提取关键信息,其中,所述关键信息包括:关键节点和关键关系;
根据所述关键信息中的关键节点和关键关系,确定关键信息图谱。
在一实施例中,所述知识图谱还包括:结构关系图谱,
所述对所述另类数据进行处理以确定知识图谱的步骤,还包括:
从所述另类数据中提取结构化数据,以确定结构关系图谱。
在一实施例中,所述从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分的步骤,包括:
基于人工智能技术从所述另类数据中,基于预设抽取方式抽取出ESG事件;
结合所述知识图谱对所述ESG事件进行ESG指标评分。
在一实施例中,所述结合所述知识图谱进行ESG指标评分的步骤,包括:
结合所述知识图谱分析所述ESG事件的影响信息和传导信息;
根据分析所述ESG事件的影响信息和传导信息的分析结果进行ESG指标评分。
在一实施例中,所述根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息的步骤,包括:
检测对所述ESG事件进行ESG指标评分的评分结果是否符合预设条件;
当检测到所述评分结果符合预设条件时,向所述ESG事件的关系方输出风险预警信息。
此外,本申请还提供一种ESG指标监控装置,所述ESG指标监控装置包括:
确定模块,用于获取另类数据,并对所述另类数据进行处理以确定知识图谱;
评分模块,用于从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;
输出模块,用于根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
本申请提出的ESG指标监控装置各个模块运行时实现如上所述的ESG指标监控方法的步骤,在此不再赘述。
此外,本申请还提供一种ESG指标监控设备,所述ESG指标监控设备包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的ESG指标监控程序,所述ESG指标监控程序被所述处理器执行时实现如上所述的ESG指标监控方法的步骤。
此外,本申请还提供一种存储介质,应用于计算机,所述存储介质上存储有ESG指标监控程序,所述ESG指标监控程序被处理器执行时实现如上所述的ESG指标监控方法的步骤。
本申请通过获取另类数据,并对所述另类数据进行处理以确定知识图谱;从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。基于大数据时代的背景,从各大数据平台中获取与行业相关的另类数据,结合人工智能技术依据获取到的另类数据确定与表示行业中各运行个体(如上市企业、投资者和监管机构等)之间影响关系的知识图谱,并进一步结合人工智能技术从获取到的另类数据中抽取ESG事件,从而基于构建的知识图谱对触发当前ESG事件的行业个体进行ESG指标评分,并基于检测进行ESG指标评分的评分结果,向与触发当前ESG事件行业个体之间存在影响的关系方输出预警信息。
本申请实现了,将ESG指标获取从被动变为主动,避免了行业个体不主动披露数据的导致个体ESG指标无法有效的为个体关系方提供参考的情况,提升了ESG相关信息的数量和整体价值,并基于结合人工智能技术,对另类数据中行业个体触发的ESG事件进行实时监控和ESG指标评分,并基于实时监控对行业个体之间影响关系进行更新维护,并基于进行ESG指标评分的评分结果及时向触发个体关系方输出预警信息,提升了ESG相关信息的准确度以及数据的实时性和有效性。
图1是本申请实施例方案涉及的硬件运行环境的结构示意图;
图2为本申请ESG指标监控方法第一实施例的流程示意图;
图3为本申请ESG指标监控方法一实施例中步骤S100的细化流程示意图;
图4为本申请ESG指标监控方法第二实施例的流程示意图;
图5为本申请ESG指标监控方法一实施例中应用场景示意图;
图6为本申请ESG指标监控装置的模块示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
如图1所示,图1是本申请实施例方案涉及的硬件运行环境的结构示意图。
需要说明的是,图1即可为终端设备的硬件运行环境的结构示意图。本申请实施例终端设备可以是PC,便携计算机等终端设备。
如图1所示,该终端设备可以包括:处理器1001,例如CPU,网络接口1004,用户接口1003,存储器1005,通信总线1002。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是稳定的存储器(non-volatile memory),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解,图1中示出的终端设备结构并不构成对终端设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图1所示,作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及ESG指标监控程序。其中,操作系统是管理和控制样本终端设备硬件和软件资源的程序,支持ESG指标监控程序以及其它软件或程序的运行。
在图1所示的终端设备中,用户接口1003主要用于与各个终端进行数据通信;网络接口1004主要用于连接后台服务器,与后台服务器进行数据通信;而处理器1001可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下操作:
获取另类数据,并对所述另类数据进行处理以确定知识图谱;
从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;
根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
进一步地,处理器1001还可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下步骤:
从预设数据平台中抽取指定的实体数据、商业过程数据以及传感器数据。
进一步地,处理器1001还可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下步骤:
基于人工智能技术从所述另类数据中提取关键信息,其中,所述关键信息包括:关键节点和关键关系;
根据所述关键信息中的关键节点和关键关系,确定关键信息图谱。
进一步地,处理器1001还可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下步骤:
从所述另类数据中提取结构化数据,以确定结构关系图谱。
进一步地,处理器1001还可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下步骤:
基于人工智能技术从所述另类数据中,基于预设抽取方式抽取出ESG事件;
结合所述知识图谱对所述ESG事件进行ESG指标评分。
进一步地,处理器1001还可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下步骤:
结合所述知识图谱分析所述ESG事件的影响信息和传导信息;
根据分析所述ESG事件的影响信息和传导信息的分析结果进行ESG指标评分。
进一步地,处理器1001还可以用于调用存储器1005中存储的ESG指标监控程序,并执行以下步骤:
检测对所述ESG事件进行ESG指标评分的评分结果是否符合预设条件;
当检测到所述评分结果符合预设条件时,向所述ESG事件的关系方输出风险预警信息。
基于上述的结构,提出本申请ESG指标监控方法的各个实施例。
请参照图2,图2为本申请ESG指标监控方法第一实施例的流程示意图。
本申请实施例提供了ESG指标监控方法的实施例,需要说明的是,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。
本申请实施例ESG指标监控方法应用于上述终端设备,本申请实施例终端设备可以是PC,便携计算机等终端设备,在此不做具体限制。
本实施例ESG指标监控方法包括:
步骤S100,获取另类数据,并对所述另类数据进行处理以确定知识图谱。
基于时下大数据时代的技术背景,从大环境数据中,提取出与行业(诸如金融市场、化工市场等金融行业)相关的另类数据,以建立与行业运行相关的另类数据平台,结合AI人工智能技术,从获取到的另类数据提取关键信息,从而确定用以表示行业中各个体之间影响和制约关系的知识图谱。
进一步地,本实施例中,另类数据包括:实体数据、商业过程数据以及传感器数据,步骤S100中,获取另类数据的步骤,包括:
步骤A,从预设数据平台中抽取指定的实体数据、商业过程数据以及传感器数据。
基于现有的数据获取方式,从大环境数据中的各预设数据平台上,抽取出与指定行业相关的实体数据、商业过程数据以及传感器数据。
本实施例中,各预设数据平台包括:大环境数据中发布数据信息的各大平台,例如政府/结构网络、新闻媒体、贴吧论坛等等,实体数据包括与个人、企业或者产品等实体相关的数据。
具体地,例如,通过利用接入政府/结构网络的方式,从政府/结构网络平台上所发布的政务数据、司法数据、金融监管数据中,抽取出与指定化工市场相关的实体数据、商业过程数据以及传感器数据,或者,基于数据爬虫技术,从主流新闻媒体、贴吧、论坛、app、公众号、卫星数据、电商数据、金融行情等数据中,抽取出与指定的化工市场或者金融市场相关的实体数据、商业过程数据以及传感器数据。
进一步地,请参照图3,图3为本申请ESG指标监控方法一实施例步骤S100的细化流程示意图,本实施例中,知识图谱包括:关键信息图谱,在步骤S100中,对所述另类数据进行处理以确定知识图谱的步骤,包括:
步骤S101,基于人工智能技术从所述另类数据中提取关键信息,其中,所述关键信息包括:关键节点和关键关系。
利用成熟的人工智能技术,从建立的包含有各行业另类数据的数据平台中,抽取实时的关键节点和关键关系等数据信息。
具体地,例如,从构建的包含有金融行业中某一上市公司的另类数据平台中,筛选出该上市公司所发布的对外采购合同或者招投标公告等数据信息,利用NLP(natural language
processing:自然语言处理技术)从该外采购合同或者招投标公告等数据信息中,提取出该上市公司的上下游节点以及与该上市公司相关的供给关系。
步骤S102,根据所述关键信息中的关键节点和关键关系,确定关键信息图谱。
基于抽取出的关键节点和关键关系等数据信息,检测当前是否已经建立了关键信息图谱,若检测到未建立关键信息图谱,则新构建用于表示行业中各运行个体之间影响关系的关键信息图谱,若检测到已经建立了关键信息图谱,则基于实时的关键节点和关键关系等数据信息对建立的关键信息图谱进行更新维护。
具体地,例如,根据从某上市公司所发布的对外采购合同或者招投标公告等数据信息中,提取出的该上市公司的上下游节点以及与该上市公司相关的供给关系,在检测到不存在用以表示当前上市公司与上游供给方企业以及与下游采购方企业之间,影响制约关系的关键信息图谱时,则建立一新的关键信息图谱,并在检测到已经存在该关键信息图谱时,根据实时监控该上市公司另类数据中,持续发展的相关舆情信息等另类数据,对关键信息图谱中上游供给方企业以及下游采购方企业节点和影响制约关系进行持续的更新维护。
进一步地,在另一个实施例中,知识图谱还包括:结构关系图谱,步骤S100中,对所述另类数据进行处理以确定知识图谱的步骤还包括:
步骤B,从所述另类数据中提取结构化数据,以确定结构关系图谱。
从建立的包含有各行业另类数据的数据平台中,抽取实时的结构化数据信息,并检测当前是否已经建立了结构关系图谱,若检测到未建立结构关系图谱,则新构建用于表示行业中各运行个体之间影响关系的结构关系图谱,若检测到已经建立了结构关系图谱,则基于监控实时的结构化数据信息对建立的结构关系图谱进行更新维护。
具体地,例如,从构建的包含有金融行业的另类数据平台中,提取出工商、融资、投资等结构化数据,在检测到不存在结构关系图谱时,利用工商数据构建新的表示股权、投资影响关系的结构关系图谱,利用金融交易登记结算数据来建立用于表示融资关系的结构关系图谱,并在检测到已经存在结构关系图谱时,根据实时监控另类数据中的工商数据、以及金融交易登记结算数据,对构建的结构关系图谱进行持续的更新维护。
进一步地,在另一个实施例中,对已经构建完成的知识图谱进行维护的专业业务人员,还可以手动对知识图谱进行维护。
专业业务人员通过从另类数据中所提取出的关键节点和关键关系等数据信息,或者根据提取出的结构化数据信息对已经构建的关键信息图谱和结构关系图谱进行更新维护。
具体地,例如,专业业务人员实时对另类数据进行监控,并在某上市公司所发布的对外采购合同或者招投标公告等数据信息中,检测到该上市公司的上下游节点以及与该上市公司相关的供给关系发生变化时,随即向维护知识图谱的专业业务人员反馈该变化事件,从而维护知识图谱的专业业务人员便根据该上市公司与新的上游供给方企业以及新的与下游采购方企业之间的关键节点关系以及变化事件持续发展的舆情走向等信息,在用以表示当前上市公司与上游下游企业之间影响制约关系的关键信息图谱中,手动的对上游供给方企业以及下游采购方企业节点和影响制约关系进行更新维护。
步骤S200,从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分。
结合人工智能技术从获取到的另类数据中,抽取实时的基础ESG事件,从而基于构建的知识图谱中所表示行业中各个体之间影响制约关系,对触发当前ESG事件的行业个体进行ESG指标评分。
具体地,例如,同样的基于NLP自然语言处理技术,从依据获取到的另类数据所构建的包含有金融行业的另类数据平台上的环保政务数据中,抽取到某化工企业环境污染处罚的ESG事件,并从全网舆情数据中提取该事情的传播途径、传播热度预估事情影响,并通过卫星遥感采集数据和计算机视觉技术结合持续监控该企业的排污治理情况和生产经营状况,从而取得ESG指标中的E(Environment:环境)评分;通过数据分析技术,分析另类数据中当期政府对相关社会主题的关注、社会类上市公司市值与招聘状态、当期社会主题基金规模以及与资本市场对社会主题的关注度,从而综合社会压力、状态与响应,取得ESG指标中的S(Social Responsibility:社会)评分;并根据监控某一公司处罚诉讼情况、经营异类或列入失信名单等另类数据,取得ESG指标中的G(Corporate Governance:公司治理)评分。
步骤S300,根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
基于检测进行ESG指标评分的评分结果,向与触发当前ESG事件的行业个体之间,存在影响关系的各关系方输出预警信息。
具体地,例如,在如图5所示的一个应用场景中,若基于利用人工智能技术中的NLP自然语言处理技术,从获取到的包含有金融行业中某化工生产企业的另类数据平台上,抽取到该化工企业环境污染处罚的ESG事件,并结合基于另类数据构建的用于表示该化工企业上下游节点影响制约的关键信息图谱,以及利用人工智能技术中的图谱挖掘技术,对该化工企业各ESG指标进行评分,将得出的ESG指标中的E(环境)评分、S(社会)评分以及G(公司治理)评分交由ESG预警体系进行判断,并在ESG预警体系判定该化工企业进行ESG指标评分的评分结果符合预设条件时,随即向与该化工企业存在影响制约关系的上下游节点企业、投资企业或者监管机构等关系方,输出风险预警信息。
进一步地,步骤S300,包括:
步骤S301,检测对所述ESG事件进行ESG指标进行评分的评分结果是否符合预设条件。
在获取到对触发当前ESG事件的行业个体进行ESG指标评分的评分结果之后,检测该评分结果是否符合输出预警信息的预设条件。
本实施例中,预设条件为,判断当前是都需要基于对触发ESG事件的行业个体进行ESG指标评分的评分结果,向触发ESG事件行业个的各关系方输出预警信息的判断标准。
具体地,例如,在从依据获取到的另类数据所构建的包含有金融行业的另类数据平台上,基于抽取基础ESG事件并结合结构关系图谱或者关键信息图谱所表示的影响制约关系,得出触发当前基础ESG事件的行业运行个体ESG指标中的E(环境)评分、S(社会)评分以及G(公司治理)评分之后,若检测到各E(环境)评分、S(社会)评分以及G(公司治理)评分中,任意一个评分数值大于等于标准阈值,即确定评分结果符合输出预警信息的条件。
步骤S302,当检测到所述评分结果符合预设条件时,向所述ESG事件的关系方输出风险预警信息。
当检测到对触发当前ESG事件的行业个体进行ESG指标评分的评分结果符合输出预警信息的预设条件时,向知识图谱中与触发当前ESG事件的行业个体之间存在影响关系的各关系方输出风险预警信息。
具体地,例如,在检测到触发当前基础ESG事件的行业运行个体ESG指标中的E(环境)评分、S(社会)评分以及G(公司治理)评分中,任意一个评分数值大于等于标准阈值,从而确定评分结果符合输出预警信息的条件之后,通过短信、微信、SaaS(Software-as-a-Service:软件即服务)等消息平台,向构建的关键信息图谱或者结构关系图谱中,与触发当前基础ESG事件的行业运行个体之间存在影响或者制约关系的各关系方,诸如监管机构、投资者、上下游节点企业等提供风险预警、风险监控等风险预警信息,特别的还可以向投资者提供投资机会发掘等服务,进而助力“绿色金融”。
本申请通过基于现有的数据获取方式,从大环境数据中的各预设数据平台上,抽取出与指定行业相关的实体数据、商业过程数据以及传感器数据,将获取的指定行业的实体数据、所述商业过程数据以及所述传感器数据进行归类统计处理,从而形成包含有各行业另类数据的数据平台,利用成熟的人工智能技术,从建立的包含有各行业另类数据的数据平台中,抽取实时的关键节点和关键关系等数据信息,基于抽取出的关键节点和关键关系等数据信息,建立用于表示行业中各运行个体之间影响关系的关键信息图谱,并基于实时的关键节点和关键关系等数据信息对建立的关键信息图谱进行更新维护,或者从建立的包含有各行业另类数据的数据平台中,抽取实时的结构化数据信息,从而建立用于表示行业中各运行个体之间影响关系的结构关系图谱,并基于监控实时的结构化数据信息对建立的结构关系图谱进行更新维护,结合人工智能技术从获取到的另类数据中,抽取实时的基础ESG事件,从而基于构建的知识图谱中所表示行业中各个体之间影响制约关系,对触发当前ESG事件的行业个体进行ESG指标评分,在获取到对触发当前ESG事件的行业个体进行ESG指标评分的评分结果之后,检测该评分结果是否符合输出预警信息的预设条件,并在符合预设条件时,向知识图谱中与触发当前ESG事件的行业个体之间存在影响关系的各关系方输出风险预警信息。
实现了,结合人工智能技术从各大数据平台中,主动获取行业相关的另类数据,从而建立展示行业个体之间影响关系的知识图谱,基于监控实时的ESG事件并结合构建的知识图谱,对行业中个体进行ESG指标评分,根据ESG指标评分的评分结果及时的向与当前行业个体存在影响关系的其他关系方输出预警信息,从而,将ESG指标获取从被动变为主动,避免了行业个体不主动披露数据的导致个体ESG指标无法有效的为个体关系方提供参考的情况,提升了ESG相关信息的数量和整体价值,并基于结合人工智能技术,对另类数据中行业个体触发的ESG事件进行实时监控和ESG指标评分,并基于实时监控对行业个体之间影响关系进行更新维护,并基于进行ESG指标评分的评分结果及时向触发个体关系方输出预警信息,提升了ESG相关信息的准确度以及数据的实时性和有效性。
进一步地,提出本申请ESG指标监控方法的第二实施例。
请参照图4,图4为本申请ESG指标监控方法第二实施例的流程示意图,基于上述ESG指标监控方法第一实施例,本实施例中,上述步骤S200,从所述另类数据中抽取ESG事件,并结合所述知识图谱进行ESG指标评分,包括:
步骤S201,基于人工智能技术从所述另类数据中,基于预设抽取方式抽取出ESG事件。
调用现有的人工智能技术,从获取到的包含金融行业另类数据的数据平台上,通过预先设定的随机抽取方式,随机抽取出ESG事件。
具体地,例如,调用NLP自然语言处理技术通过随机采样规则,从依据获取到的另类数据所构建的包含有金融行业的另类数据平台上的环保政务数据中,随机抽取金融市场或者化工市场中,任意行业运行个体--某化工生产厂商或者某上市企业的ESG事件,如随机抽取出某化工企业环境污染处罚的ESG事件。
步骤S202,结合所述知识图谱对所述ESG事件进行ESG指标评分。
持续不断的实时跟踪监控另类数据中,当前抽取出的ESG事件的演变过程,并基于构建的知识图谱中所表示行业中各个体之间影响制约关系,对触发当前ESG事件的行业个体进行ESG指标评分。
具体地,例如,在基于NLP自然语言处理技术,从依据获取到的另类数据所构建的包含有金融行业的另类数据平台上的环保政务数据中,抽取到某化工企业环境污染处罚的ESG事件之后,持续不断的实时跟踪监控全网舆情数据中该ESG事件的传播途径、传播热度,以及当期政府对当前ESG事件造成的相关社会主题的关注度等演变过程,并在依据另类数据中关键节点和关键关系构建的关键信息图谱,或者在依据结构化数据构建的结构关系图谱中,基于该化工企业与上下游节点企业之间的影响和制约关系预估当前ESG事件的影响度,从而对当前化工企业的各ESG指标进行评分。
进一步地,步骤S202中,结合所述知识图谱进行ESG指标评分的步骤,包括:
步骤D,结合所述知识图谱分析所述ESG事件的影响信息和传导信息。
步骤E,根据分析所述ESG事件的影响信息和传导信息的分析结果进行ESG指标评分。
在基于另类数据构建的知识图谱中,分析当前抽取出的ESG事件对与触发当前ESG事件的行业个体之间存在影响和制约关系的各关系方所造成的影响信息,以及分析当前ESG事件的传导所引起的社会关注,结合分析结果对触发当前ESG事件的行业个体的ESG指标进行评分。
具体地,例如,在依据另类数据中关键节点和关键关系构建的关键信息图谱,或者在依据结构化数据构建的结构关系图谱中,基于投资者、监管机构以及触发当前ESG事件的行业个体上下游节点企业等各关系方,与触发当前ESG事件的行业个体之间的影响和制约关系,分析当前ESG事件对各关系方所造成的影响,并通过持续不断的实时跟踪监控全网舆情数据中该ESG事件的传播途径、传播热度,以及当期政府对当前ESG事件造成的相关社会主题的关注度等进一步预估当前ESG事件的影响,从而更加全面、准确的对当前化工企业的各ESG指标进行评分。
本申请通过调用现有的人工智能技术,从获取到的包含金融行业另类数据的数据平台上,通过预先设定的随机抽取方式,随机抽取出ESG事件,在基于另类数据构建的知识图谱中,分析当前抽取出的ESG事件对与触发当前ESG事件的行业个体之间存在影响和制约关系的各关系方所造成的影响大小,以及分析当前ESG事件的传导所引起的社会关注,结合分析结果对触发当前ESG事件的行业个体的ESG指标进行评分。
实现了更加全面、准确的基于另类数据中的ESG事件进行ESG指标评分,从而进一步提升了ESG相关信息的准确度,以及针对ESG相关信息对投资者、监管机构等提供参考的有效性。
此外,请参照图5,本申请实施例还提出一种ESG指标监控装置,所述ESG指标监控装置包括:
确定模块,用于获取另类数据,并对所述另类数据进行处理以确定知识图谱;
评分模块,用于从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;
输出模块,用于根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
在一实施例中,确定模块,包括:
第一抽取单元,用于从预设数据平台中抽取指定的实体数据、商业过程数据以及传感器数据。
在一实施例中,确定模块,还包括:
提取单元,用于基于人工智能技术从所述另类数据中提取关键信息,其中,所述关键信息包括:关键节点和关键关系;
第一确定单元,用于根据所述关键信息中的关键节点和关键关系,确定关键信息图谱。
在一实施例中,确定模块,还包括:
第二确定单元,用于从所述另类数据中提取结构化数据,以确定结构关系图谱。
在一实施例中,评分模块,包括:
第二抽取单元,用于基于人工智能技术从所述另类数据中,基于预设抽取方式抽取出ESG事件;
评分单元,用于结合所述知识图谱对所述ESG事件进行ESG指标评分。
在一实施例中,评分单元,包括:
分析单元,用于结合所述知识图谱分析所述ESG事件的影响信息和传导信息;
评分子单元,用于根据分析所述ESG事件的影响信息和传导信息的分析结果进行ESG指标评分。
在一实施例中,输出模块,包括:
检测单元,用于检测对所述ESG事件进行ESG指标评分的评分结果是否符合预设条件;
输出单元,用于当检测到所述评分结果符合预设条件时,向所述ESG事件的关系方输出风险预警信息。
本实施例提出的ESG指标监控装置各个模块运行时实现如上所述的ESG指标监控方法的步骤,在此不再赘述。
此外,本申请实施例还提出一种存储介质,应用于计算机,即所述存储介质为计算机可读存储介质,所述介质上存储有ESG指标监控程序,所述ESG指标监控程序被处理器执行时实现如上所述的ESG指标监控方法的步骤。
其中,在所述处理器上运行的ESG指标监控程序被执行时所实现的方法可参照本申请基于ESG指标监控方法各个实施例,此处不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。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(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,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的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种ESG指标监控方法,其中,所述ESG指标监控方法包括:获取另类数据,并对所述另类数据进行处理以确定知识图谱;从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
- 如权利要求1所述的ESG指标监控方法,其中,所述另类数据包括:实体数据、商业过程数据以及传感器数据,所述获取另类数据的步骤,包括:从预设数据平台中抽取指定的实体数据、商业过程数据以及传感器数据。
- 如权利要求1所述的ESG指标监控方法,其中,所述知识图谱包括:关键信息图谱,所述对所述另类数据进行处理以确定知识图谱的步骤,包括:基于人工智能技术从所述另类数据中提取关键信息,其中,所述关键信息包括:关键节点和关键关系;根据所述关键信息中的关键节点和关键关系,确定关键信息图谱。
- 如权利要求3所述的ESG指标监控方法,其中,所述根据所述关键信息中的关键节点和关键关系,确定关键信息图谱,包括:根据所述关键信息中的关键节点和关键关系,检测当前是否已经建立关键信息图谱;若检测到未建立关键信息图谱,则新构建用于表示行业中各运行个体之间影响关系的关键信息图谱;若检测到已经建立关键信息图谱,则基于所述关键节点和关键关系对建立的关键信息图谱进行更新维护。
- 如权利要求1所述的ESG指标监控方法,其中,所述知识图谱还包括:结构关系图谱,所述对所述另类数据进行处理以确定知识图谱的步骤,还包括:从所述另类数据中提取结构化数据,以确定结构关系图谱。
- 如权利要求5所述的ESG指标监控方法,其中,所述从所述另类数据中提取结构化数据,以确定结构关系图谱,包括:从建立的包含有各行业另类数据的数据平台中,抽取实时的结构化数据信息,并检测当前是否已经建立结构关系图谱,若检测到未建立结构关系图谱,则新构建用于表示行业中各运行个体之间影响关系的结构关系图谱;若检测到已经建立了结构关系图谱,则基于监控实时的结构化数据信息对建立的结构关系图谱进行更新维护。
- 如权利要求1所述的ESG指标监控方法,其中,所述从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分的步骤,包括:基于人工智能技术从所述另类数据中,基于预设抽取方式抽取出ESG事件;结合所述知识图谱对所述ESG事件进行ESG指标评分。
- 如权利要求7所述的ESG指标监控方法,其中,所述结合所述知识图谱进行ESG指标评分的步骤,包括:结合所述知识图谱分析所述ESG事件的影响信息和传导信息;根据分析所述ESG事件的影响信息和传导信息的分析结果进行ESG指标评分。
- 如权利要求1至8所述的ESG指标监控方法,其中,所述根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息的步骤,包括:检测对所述ESG事件进行ESG指标评分的评分结果是否符合预设条件;当检测到所述评分结果符合预设条件时,向所述ESG事件的关系方输出风险预警信息。
- 一种ESG指标监控装置,其中,所述ESG指标监控装置包括:确定模块,用于获取另类数据,并对所述另类数据进行处理以确定知识图谱;评分模块,用于从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;输出模块,用于根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
- 一种ESG指标监控设备,其中,所述ESG指标监控设备包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的ESG指标监控程序,所述ESG指标监控程序被所述处理器执行时实现如下步骤:获取另类数据,并对所述另类数据进行处理以确定知识图谱;从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分;根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息。
- 如权利要求11所述的ESG指标监控设备,其中,所述另类数据包括:实体数据、商业过程数据以及传感器数据,所述获取另类数据的步骤,包括:从预设数据平台中抽取指定的实体数据、商业过程数据以及传感器数据。
- 如权利要求11所述的ESG指标监控设备,其中,所述知识图谱包括:关键信息图谱,所述对所述另类数据进行处理以确定知识图谱的步骤,包括:基于人工智能技术从所述另类数据中提取关键信息,其中,所述关键信息包括:关键节点和关键关系;根据所述关键信息中的关键节点和关键关系,确定关键信息图谱。
- 如权利要求13所述的ESG指标监控设备,其中,所述根据所述关键信息中的关键节点和关键关系,确定关键信息图谱,包括:根据所述关键信息中的关键节点和关键关系,检测当前是否已经建立关键信息图谱;若检测到未建立关键信息图谱,则新构建用于表示行业中各运行个体之间影响关系的关键信息图谱;若检测到已经建立关键信息图谱,则基于所述关键节点和关键关系对建立的关键信息图谱进行更新维护。
- 如权利要求11所述的ESG指标监控设备,其中,所述知识图谱还包括:结构关系图谱,所述对所述另类数据进行处理以确定知识图谱的步骤,还包括:从所述另类数据中提取结构化数据,以确定结构关系图谱。
- 如权利要求15所述的ESG指标监控设备,其中,所述从所述另类数据中提取结构化数据,以确定结构关系图谱,包括:从建立的包含有各行业另类数据的数据平台中,抽取实时的结构化数据信息,并检测当前是否已经建立结构关系图谱,若检测到未建立结构关系图谱,则新构建用于表示行业中各运行个体之间影响关系的结构关系图谱;若检测到已经建立了结构关系图谱,则基于监控实时的结构化数据信息对建立的结构关系图谱进行更新维护。
- 如权利要求11所述的ESG指标监控设备,其中,所述从所述另类数据中抽取ESG事件,并结合所述知识图谱对所述ESG事件进行ESG指标评分的步骤,包括:基于人工智能技术从所述另类数据中,基于预设抽取方式抽取出ESG事件;结合所述知识图谱对所述ESG事件进行ESG指标评分。
- 如权利要求17所述的ESG指标监控设备,其中,所述结合所述知识图谱进行ESG指标评分的步骤,包括:结合所述知识图谱分析所述ESG事件的影响信息和传导信息;根据分析所述ESG事件的影响信息和传导信息的分析结果进行ESG指标评分。
- 如权利要求11至18所述的ESG指标监控设备,其中,所述根据进行ESG指标评分的评分结果向所述ESG事件的关系方输出预警信息的步骤,包括:检测对所述ESG事件进行ESG指标评分的评分结果是否符合预设条件;当检测到所述评分结果符合预设条件时,向所述ESG事件的关系方输出风险预警信息。
- 一种存储介质,其中,应用于计算机,所述存储介质上存储有ESG指标监控程序,所述ESG指标监控程序被处理器执行时实现如权利要求1至9中任一项所述的ESG指标监控方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776692.1A CN110472884A (zh) | 2019-08-20 | 2019-08-20 | Esg指标监控方法、装置、终端设备及存储介质 |
| CN201910776692.1 | 2019-08-20 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020259716A1 true WO2020259716A1 (zh) | 2020-12-30 |
Family
ID=68513464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/107320 Ceased WO2020259716A1 (zh) | 2019-08-20 | 2020-08-06 | Esg指标监控方法、装置、设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110472884A (zh) |
| WO (1) | WO2020259716A1 (zh) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472884A (zh) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Esg指标监控方法、装置、终端设备及存储介质 |
| CN111221978A (zh) * | 2019-12-31 | 2020-06-02 | 北京明略软件系统有限公司 | 一种构建知识图谱的方法、装置、计算机存储介质及终端 |
| CN111222790B (zh) * | 2020-01-06 | 2022-07-26 | 深圳前海微众银行股份有限公司 | 风险事件发生概率的预测方法、装置、设备及存储介质 |
| CN111460260A (zh) * | 2020-03-31 | 2020-07-28 | 上海智芝全智能科技有限公司 | 多类型数据的数据处理系统、方法及介质 |
| CN111798151B (zh) * | 2020-07-10 | 2024-06-11 | 深圳前海微众银行股份有限公司 | 企业欺诈风险评估方法、装置、设备及可读存储介质 |
| CN112070402B (zh) * | 2020-09-09 | 2024-06-07 | 深圳前海微众银行股份有限公司 | 基于图谱的数据处理方法、装置、设备及存储介质 |
| CN112232377A (zh) * | 2020-09-22 | 2021-01-15 | 中财绿指(北京)信息咨询有限公司 | 一种企业esg三优信用模型构建方法及其装置 |
| CN112883739A (zh) * | 2021-02-03 | 2021-06-01 | 深圳前海微众银行股份有限公司 | 评级系统的异常告警方法、装置、电子设备及存储介质 |
| CN113190683B (zh) * | 2021-07-02 | 2021-09-17 | 平安科技(深圳)有限公司 | 基于聚类技术的企业esg指数确定方法及相关产品 |
| CN113570281A (zh) * | 2021-08-20 | 2021-10-29 | 瑞格人工智能科技有限公司 | 一种esg指数编制方法 |
| CN117634997B (zh) * | 2023-12-04 | 2024-08-20 | 北京一点五度科技有限公司 | 一种企业组织价值链资产定位与制图的深度神经网络方法 |
| CN120106636A (zh) * | 2025-01-10 | 2025-06-06 | 中国标准化研究院 | 基于人工智能的企业esg指数确定方法及系统 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103154991A (zh) * | 2010-07-23 | 2013-06-12 | 汤森路透环球资源公司 | 信用风险采集 |
| CN104995650A (zh) * | 2011-12-27 | 2015-10-21 | 汤姆森路透社全球资源公司 | 用于使用源于社交媒体的数据和情绪分析来生成复合索引的方法及系统 |
| US20160117774A1 (en) * | 2014-10-24 | 2016-04-28 | ENSOGO Analytics LLC | Environment, social and governance rating system |
| US20180189803A1 (en) * | 2015-06-15 | 2018-07-05 | Erevalue Limited | A method and system for providing business intelligence |
| CN110472884A (zh) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Esg指标监控方法、装置、终端设备及存储介质 |
-
2019
- 2019-08-20 CN CN201910776692.1A patent/CN110472884A/zh active Pending
-
2020
- 2020-08-06 WO PCT/CN2020/107320 patent/WO2020259716A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103154991A (zh) * | 2010-07-23 | 2013-06-12 | 汤森路透环球资源公司 | 信用风险采集 |
| CN104995650A (zh) * | 2011-12-27 | 2015-10-21 | 汤姆森路透社全球资源公司 | 用于使用源于社交媒体的数据和情绪分析来生成复合索引的方法及系统 |
| US20160117774A1 (en) * | 2014-10-24 | 2016-04-28 | ENSOGO Analytics LLC | Environment, social and governance rating system |
| US20180189803A1 (en) * | 2015-06-15 | 2018-07-05 | Erevalue Limited | A method and system for providing business intelligence |
| CN110472884A (zh) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Esg指标监控方法、装置、终端设备及存储介质 |
Non-Patent Citations (1)
| Title |
|---|
| GRAMATICA, RUGGERO: "How Knowledge Graph Technology Can Put Purpose and Profit into ESG Investments", HTTPS://WWW.LINKEDIN.COM/PULSE/HOW-KNOWLEDGE-GRAPH-TECHNOLOGY-CAN-PUT-PURPOSE-PROFIT-GRAMATICA-PHD, 17 June 2019 (2019-06-17), XP055770698, DOI: 20201015112642Y * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110472884A (zh) | 2019-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020259716A1 (zh) | Esg指标监控方法、装置、设备及存储介质 | |
| Galeazzi et al. | Human mobility in response to COVID-19 in France, Italy and UK | |
| CN110796470B (zh) | 一种面向市场主体监管和服务的数据分析系统 | |
| JP6713238B2 (ja) | 電子装置、小売店舗評価モデルを構築する方法、システム及び記憶媒体 | |
| US8548843B2 (en) | Individual performance metrics scoring and ranking | |
| CN108596439A (zh) | 一种基于知识图谱的企业风险预测方法及系统 | |
| US20160063072A1 (en) | Systems, methods, and apparatuses for detecting activity patterns | |
| CN103123712A (zh) | 一种网络行为数据的监控方法和系统 | |
| CN108053087A (zh) | 反洗钱监测方法、设备及计算机可读存储介质 | |
| CN101655966A (zh) | 一种贷款风险控制方法及系统 | |
| CN108876228A (zh) | 企业风险的监控方法、装置、计算机设备及存储介质 | |
| CN112070402A (zh) | 基于图谱的数据处理方法、装置、设备及存储介质 | |
| Heymann et al. | Turkalytics: analytics for human computation | |
| US20220147863A1 (en) | Machine-learning model for determining post-visit phone call propensity | |
| Schneider et al. | Modelling illiquidity spillovers with Hawkes processes: an application to the sovereign bond market | |
| KR102509748B1 (ko) | 메타데이터 및 딥러닝 보안제어를 이용한 가명처리 서비스 제공 시스템 | |
| KR102103023B1 (ko) | 확정기여형제도 기반 사업자 비교를 이용한 퇴직연금 통합 관리 서비스 제공시스템 및 방법 | |
| Liou et al. | Stakeholder salience: corporate responses during a public health crisis | |
| Taylor et al. | Decreasing work-related movement during a pandemic. Location analytics and the implications of the digital divide | |
| DOLOKSARIBU et al. | The role of audit risk in improving audit quality | |
| CN120687321A (zh) | 异常监测方法、装置、计算机设备及存储介质 | |
| Li et al. | Review and prospect of data asset research: Based on social network analysis method | |
| CN114841815A (zh) | 交易分析方法及装置、电子设备和计算机可读存储介质 | |
| Hsieh et al. | Audit Quality Under Remote Working Arrangement: The Role of Technology Competency | |
| US20130090960A1 (en) | Web browser-based business activity monitoring |
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: 20832337 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20832337 Country of ref document: EP Kind code of ref document: A1 |