CN117033561B

CN117033561B - ESG (electronic service guide) index optimization-based enterprise assessment model generation method and system

Info

Publication number: CN117033561B
Application number: CN202311280518.0A
Authority: CN
Inventors: 郭一彤; 王海林; 肖亚飞; 毛祯
Original assignee: Cscec Southwest Consulting Co ltd
Current assignee: Cscec Southwest Consulting Co ltd
Priority date: 2023-10-07
Filing date: 2023-10-07
Publication date: 2023-12-26
Anticipated expiration: 2043-10-07
Also published as: CN117033561A

Abstract

The invention discloses an enterprise evaluation model generation method and system based on ESG index optimization, which are applied to the technical field of natural language analysis, and the method comprises the following steps: extracting keywords from the secondary bottom hierarchy as reference keywords; assigning a value to the bottommost layer grade corresponding to the sub-bottom layer grade to form a bottom layer index parameter; acquiring enterprise information of a target enterprise, and extracting enterprise parameters from the enterprise information; ESG indexes matched with the target enterprise are selected from the bottommost hierarchy; and constructing an enterprise assessment model. According to the method and the system for generating the enterprise evaluation model based on ESG index optimization, through the technical scheme, intelligent selection of the ESG evaluation related indexes of the enterprise is realized, ESG index selection efficiency is effectively improved, meanwhile, the cost caused by manual selection and the precision problem caused by subjective factors are reduced, and the method and the system are suitable for most ESG index selection scenes and are beneficial to large-scale popularization.

Description

ESG (electronic service guide) index optimization-based enterprise assessment model generation method and system

Technical Field

The invention relates to a natural language analysis technology, in particular to an enterprise evaluation model generation method and system based on ESG index optimization.

Background

ESG rating systems, also known as ESG ratings, are created by business and non-profit organizations to assess how an enterprise's commitments, performance, business patterns and architecture are consistent with sustainable development goals. They are first used by investment companies to screen or evaluate companies in their various funds and portfolios. The ratings may also be used by job seekers, customers, and others in evaluating business relationships, and the rated company itself may be better informed of their advantages, disadvantages, risks, and opportunities.

In the prior art, application number is CN20211074893. X discloses an enterprise ESG index determination method based on a clustering technology and related products. The method comprises the following steps: acquiring M news of an enterprise to be evaluated in a preset time period; clustering M news to obtain K first news groups; clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group; determining target public opinion scores of news events corresponding to each first news group according to original news and H transfer news contained in each second news group in the L second news groups, wherein the target public opinion scores are used for representing influence of the news events corresponding to each first news group on enterprises to be evaluated; and carrying out ESG evaluation on the enterprises to be evaluated according to the target public opinion scores of the news events corresponding to each first news group to obtain ESG indexes of the enterprises to be evaluated. However, with the development of the ESG technology, the index for performing the ESG evaluation is more and more complex, and after a plurality of ESG evaluation systems are combined, the index that can be used for the ESG evaluation of the enterprise reaches thousands, so how to select the ESG index suitable for the enterprise has become a serious problem for researchers.

Disclosure of Invention

In order to at least overcome the above-mentioned shortcomings in the prior art, an object of the present application is to provide an enterprise evaluation model generating method and system based on ESG index optimization.

In a first aspect, an embodiment of the present application provides an enterprise assessment model generating method based on ESG index optimization, including:

extracting keywords from the sub-bottom hierarchy of ESG index hierarchy data as reference keywords; the secondary bottom layer is classified as the upper layer of the lowest layer;

assigning a value to the bottommost layer classification corresponding to the secondary layer classification according to the reference keyword of the secondary layer classification to form a bottom layer index parameter;

acquiring enterprise information of a target enterprise, and extracting enterprise parameters from the enterprise information according to the reference keywords;

selecting ESG indexes matched with the target enterprise from the bottommost hierarchy according to the bottom index parameters and the enterprise parameters;

and constructing an enterprise evaluation model according to the selected ESG indexes.

When the embodiment of the application is implemented, the ESG index rating data generally has multiple levels of data, and for different evaluation systems, the corresponding levels of the ESG index rating data are often different; for all ESG index rating data, it may be characterized as a tree structure, the topmost data of which is three items: the bottom-layer classification of the environment (E), the society (S) and the treatment (G) is generally a qualitative or quantitative question after the classification of the first-level, for example, the treatment (G) has a next-level "treatment mechanism", the treatment mechanism "has a next-level" risk management ", the risk management" has a next-level "weather risk identification and prevention", the weather risk identification and prevention "has a next-level" enterprise whether or not takes measures and effects of preventing physical risks and transformation risks caused by weather changes ", at this time" whether or not the enterprise takes measures and effects of preventing physical risks and transformation risks caused by weather changes "as the bottom-layer classification, and" weather risk identification and prevention "as the last-level classification of the bottom-layer classification is referred to as the sub-bottom-layer classification in the embodiment of the application.

In the embodiment of the application, in order to realize automatic identification of the ESG indexes, the hierarchical data of the ESG indexes need to be digitally identified first. The corresponding reference keywords need to be extracted from the sub-bottom hierarchy to be used for assigning values to the corresponding sub-bottom hierarchy. The extraction of the reference keywords can be carried out according to the semantics in the sub-bottom hierarchical level, the extraction can be carried out by adopting the prior art, and the extracted reference keywords need to be capable of representing the whole semantics of the sub-bottom hierarchical level. For example, for "climate risk identification and prevention", the reference keywords to be extracted are "climate", "risk", "identification" and "prevention"; for "wastewater use management", the reference keywords to be extracted are "wastewater" and "management".

In the embodiment of the application, according to the mode that the reference keywords are assigned to the bottommost hierarchy, the corresponding keywords in the bottommost hierarchy can be extracted through the reference keywords, and information such as phrases, phrase sets and the like corresponding to the bottommost hierarchy is constructed to form the bottom index parameters. Meanwhile, the enterprise information of the target enterprise can be obtained by adopting enterprise information disclosed in a disclosure channel, and related reports provided by the target enterprise, such as news information, a stranding book, a financial report and the like, wherein the extraction process and the bottommost hierarchical assignment process are matched.

In the embodiment of the application, the bottommost hierarchy of the best matching target enterprise can be selected as the ESG index through the bottom index parameter and the enterprise parameter, and an enterprise evaluation model is constructed according to the ESG index. The construction process of the enterprise evaluation model belongs to the prior art, and is mainly constructed in a weighting mode and the like, and the embodiment of the application will not be repeated. According to the technical scheme, intelligent selection of the ESG evaluation related indexes of enterprises is achieved, ESG index selection efficiency is effectively improved, meanwhile, cost caused by manual selection and precision caused by subjective factors are reduced, the method and the device are suitable for most ESG index selection scenes, and large-scale popularization is facilitated.

In one possible implementation manner, forming the bottom layer index parameter for the bottommost layer hierarchy corresponding to the secondary bottom layer hierarchy according to the reference keyword of the secondary bottom layer hierarchy includes:

processing the characters classified at the bottommost layer according to the reference keywords to extract bottom keywords;

obtaining synonyms, near-meaning words and anti-meaning words of the bottom keywords through a dictionary library to serve as reference words;

assigning values for synonyms, paraphraseology and anti-ambiguity of the bottom keyword to form a reference triplet corresponding to the bottom keyword; the value of the synonym and the value of the paraphrasing are positive values, and the value of the synonym is larger than the value of the paraphrasing; the value of the disambiguation is a negative value;

and taking the bottom keyword and the reference triplet as the bottom index parameter.

In one possible implementation manner, obtaining the enterprise information of the target enterprise, and extracting the enterprise parameters from the enterprise information according to the reference keyword includes:

acquiring the enterprise information through the public information of the target enterprise;

searching and finding out matching keywords from the enterprise information according to the reference keywords; the matching keywords are words with similarity with the reference keywords higher than a preset value;

and carrying out context semantic analysis on sentences in which the matching keywords are located, extracting evaluation words corresponding to the matching keywords, and generating mapping relations between the evaluation words and the reference keywords as the enterprise parameters.

In one possible implementation, selecting, from the lowest hierarchy, an ESG indicator matching the target enterprise according to the bottom level indicator parameter and the enterprise parameter includes:

establishing a corresponding relation between the evaluation words and the bottom keywords according to the corresponding relation between the reference keywords and the bottom keywords and the mapping relation in the enterprise parameters;

comparing the similarity between the evaluation word and the corresponding reference word of the bottom keyword and selecting the reference word most similar to the evaluation word;

extracting the assignment corresponding to the most similar reference words from the corresponding reference triples, and calculating the sum of the assignment of all the evaluation words corresponding to the bottom-layer keywords as a reference assignment;

and acquiring reference assignment values of the enterprise parameters in all the bottom keywords, and taking ESG indexes corresponding to a plurality of bottom keywords with highest reference assignment values as ESG indexes matched with the target enterprise.

In one possible implementation manner, processing the text of the bottommost hierarchy according to the reference keyword to extract the bottom keyword includes:

extracting adjectives or verbs of the basic keywords from the characters of the bottommost hierarchy as first-layer keywords;

extracting a word next to the reference keyword from the characters in the lowest hierarchy as a second bottom keyword; if the next word of the reference keyword is a fluxing word, skipping over the fluxing word and taking the next word of the fluxing word as a second bottom keyword;

and taking the first bottom keywords and the second bottom keywords as the bottom keywords.

In a second aspect, an embodiment of the present application provides an enterprise assessment model generating system based on ESG index optimization, including:

an extraction unit configured to extract keywords from a sub-bottom hierarchy of the ESG index hierarchy data as reference keywords; the secondary bottom layer is classified as the upper layer of the lowest layer;

the assignment unit is configured to assign a value to the bottommost layer grade corresponding to the secondary layer grade according to the reference keyword of the secondary layer grade to form a bottom layer index parameter;

the analysis unit is configured to acquire enterprise information of a target enterprise and extract enterprise parameters from the enterprise information according to the reference keywords;

a matching unit configured to select an ESG indicator matching the target enterprise from a lowest hierarchy according to the bottom level indicator parameter and the enterprise parameter;

and the modeling unit is configured to construct an enterprise evaluation model according to the selected ESG indexes.

In a possible implementation, the assignment unit is further configured to:

In one possible implementation, the analysis unit is further configured to:

In a possible implementation, the matching unit is further configured to:

In a possible implementation, the assignment unit is further configured to:

Compared with the prior art, the invention has the following advantages and beneficial effects:

according to the method and the system for generating the enterprise evaluation model based on ESG index optimization, through the technical scheme, intelligent selection of the ESG evaluation related indexes of the enterprise is realized, ESG index selection efficiency is effectively improved, meanwhile, the cost caused by manual selection and the precision problem caused by subjective factors are reduced, and the method and the system are suitable for most ESG index selection scenes and are beneficial to large-scale popularization.

Drawings

The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:

FIG. 1 is a schematic flow chart of a method according to an embodiment of the present application;

fig. 2 is a schematic diagram of assignment of bottom keywords in an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the accompanying drawings in the present application are only for the purpose of illustration and description, and are not intended to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this application, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to the flow diagrams and one or more operations may be removed from the flow diagrams as directed by those skilled in the art.

In addition, the described embodiments are only some, but not all, of the embodiments of the present application. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.

Referring to fig. 1 in combination, a flow chart of an enterprise evaluation model generating method based on ESG-index optimization according to an embodiment of the present invention is shown, and further, the enterprise evaluation model generating method based on ESG-index optimization may specifically include the following descriptions of steps S1 to S5.

S1: extracting keywords from the sub-bottom hierarchy of ESG index hierarchy data as reference keywords; the secondary bottom layer is classified as the upper layer of the lowest layer;

s2: assigning a value to the bottommost layer classification corresponding to the secondary layer classification according to the reference keyword of the secondary layer classification to form a bottom layer index parameter;

s3: acquiring enterprise information of a target enterprise, and extracting enterprise parameters from the enterprise information according to the reference keywords;

s4: selecting ESG indexes matched with the target enterprise from the bottommost hierarchy according to the bottom index parameters and the enterprise parameters;

s5: and constructing an enterprise evaluation model by the selected ESG indexes.

When the embodiment of the application is implemented, the bottom keyword needs to be extracted first in the assignment process of the bottommost hierarchical assignment, and the same reference keyword may correspond to at least one bottom keyword in the bottommost hierarchical; for example, for the sub-floor classification of "exhaust gas usage management", the extracted reference keyword is "exhaust gas"; the bottom layer grades corresponding to the sub-bottom layer grades are respectively subjected to bottom layer keyword extraction, wherein the bottom layer grades are respectively provided with exhaust emission licenses and are subjected to declaration of exhaust emission ports; the bottom keyword corresponding to the "whether the exhaust emission license is provided" license "and the bottom keyword corresponding to the" whether the exhaust emission port is declared "declare". At this time, the correspondence between the reference keywords and the bottom keywords is formed: "exhaust" → "permit" and "exhaust" → "claim"; searching synonyms, paraphraseology and anti-pronouns for 'permission' from a dictionary library, wherein the synonyms are generally defined as the underlying keywords per se, namely 'permission', while the paraphraseology is 'permission', 'approval', 'grant' and 'approval', and the anti-pronouns are 'prohibition'; synonyms, paraphraseology and anticonym may likewise be chosen for "declaration". It should be appreciated that dictionary libraries used in the prior art for natural language processing may be employed for dictionary libraries, which are of the prior art and are widely used, and embodiments of the present application are not repeated.

In this embodiment, referring to fig. 2, a case is shown after assigning values to synonyms, paraphraseology and anticomplements of the underlying keyword, where the synonyms of "permission" are "permission", "approval", "grant" and "approval", and the anticomplements are "prohibition"; assigning a value of 2 for "permit", a value of 1 for "permit", "approve", "grant" and "approve", and a value of-2 for "prohibit", forming a reference triplet as the underlying index parameter. It should be understood that the correspondence between the reference triplet and the reference keyword is inherited from the correspondence between the underlying keyword and the reference keyword. Through the technical scheme, the characters classified at the bottommost layer can be dataized, and subsequent detection and use are facilitated.

When the embodiment of the application is implemented, the enterprise information, such as a poster book, related news and the like, can be obtained through the public information of the target enterprise; the matching keywords are found out from the enterprise information through the reference keywords, and the matching keywords can be found out according to the Hamming distance and other modes in the prior art for similarity comparison and finding. And carrying out semantic analysis on sentences in the enterprise information by matching keywords, extracting corresponding evaluation words, and generating corresponding mapping relations for subsequent use. It should be understood that the extraction of the evaluation word may also be performed by adopting the extraction method of the bottom keyword in the above embodiment.

When the embodiment of the application is implemented, the corresponding relation between the evaluation word and the bottom keyword is required to be formed through the corresponding relation established in the embodiment; and comparing the evaluation word with the reference word, and extracting corresponding assignment from the reference triplet. And after summarizing all the reference assignments, selecting ESG indexes corresponding to the highest plurality of bottom keywords as selected ESG indexes.

In the embodiment of the application, a method for extracting bottom keywords is provided, and since the characters of the bottommost hierarchy generally appear in the form of question sentences and have a certain standard sentence pattern, the basic keywords are limited by adjectives or verbs, namely, the words are extracted as part of the bottom keywords. Meanwhile, the next word of the reference keyword is also used for limiting the reference keyword, and the part also needs to be extracted as a part of the underlying keyword. It should be understood that sequential continuation is required if the word following the reference keyword is a helper word, such as "and the like, which cannot directly express meaning.

Based on the same inventive concept, the embodiment of the application also provides an enterprise evaluation model generation system based on ESG index optimization, which comprises:

In a possible implementation, the assignment unit is further configured to:

In one possible implementation, the analysis unit is further configured to:

In a possible implementation, the matching unit is further configured to:

In a possible implementation, the assignment unit is further configured to:

Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.

The elements described as separate components may or may not be physically separate, and it will be apparent to those skilled in the art that elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the elements and steps of the examples have been generally described functionally in the foregoing description so as to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a grid device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, randomAccess Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims

1. The enterprise evaluation model generation method based on ESG index optimization is characterized by comprising the following steps:

constructing an enterprise evaluation model according to the selected ESG indexes;

assigning values to the bottommost layer grades corresponding to the secondary layer grades according to the reference keywords of the secondary layer grades to form bottom layer index parameters comprises the following steps:

taking the bottom keyword and the reference triplet as the bottom index parameter;

acquiring enterprise information of a target enterprise, and extracting enterprise parameters from the enterprise information according to the reference keywords comprises:

performing context semantic analysis on sentences in which the matching keywords are located, extracting evaluation words corresponding to the matching keywords, and generating mapping relations between the evaluation words and the reference keywords as the enterprise parameters;

selecting the ESG index matched with the target enterprise from the bottommost hierarchy according to the bottom index parameter and the enterprise parameter comprises the following steps:

2. The method for generating the enterprise evaluation model based on ESG index optimization of claim 1, wherein processing the bottom-level hierarchical text according to the reference keywords to extract bottom-level keywords comprises:

3. An enterprise assessment model generation system based on ESG-index optimization, wherein the method of claim 1 or 2 is used, the system comprising:

4. The ESG-index optimized enterprise valuation model generation system of claim 3, wherein the assignment unit is further configured to:

5. The ESG-index-optimized enterprise valuation model generation system of claim 4, wherein the analysis unit is further configured to:

6. The ESG-index-optimized enterprise valuation model generation system of claim 5, wherein the matching unit is further configured to:

7. The ESG-index-optimized enterprise valuation model generation system of claim 4, wherein the assignment unit is further configured to: