CN113190683B - Enterprise ESG index determination method based on clustering technology and related product - Google Patents
Enterprise ESG index determination method based on clustering technology and related product Download PDFInfo
- Publication number
- CN113190683B CN113190683B CN202110748931.XA CN202110748931A CN113190683B CN 113190683 B CN113190683 B CN 113190683B CN 202110748931 A CN202110748931 A CN 202110748931A CN 113190683 B CN113190683 B CN 113190683B
- Authority
- CN
- China
- Prior art keywords
- news
- group
- enterprise
- groups
- original
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses an enterprise ESG index determining method based on a clustering technology and a related product. The method comprises the following steps: acquiring M news of an enterprise to be evaluated in a preset time period; clustering the 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 a target public opinion score of a news event corresponding to each first news group according to original news and H pieces of reprinted news included in each second news group in the L second news groups, wherein the target public opinion score is used for representing the influence of the news event corresponding to each first news group on an enterprise to be evaluated; and performing ESG evaluation on the enterprise to be evaluated according to the target public opinion score of the news event corresponding to each first news group to obtain the ESG index of the enterprise to be evaluated.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an enterprise ESG index determining method based on a clustering technology and a related product.
Background
The ESG score of an enterprise is a comprehensive score for the environment (E), the society (S) and the governance (G) of the enterprise. Some successful experience has been accumulated internationally and domestically in scoring ESG performance of enterprises, and internationally known rating agencies such as MSCI, FTSE, etc. have established respective scoring standards and have performed ESG evaluation on internationally known enterprises. With the international society, such as various investment institutions and governments, paying attention to enterprise responsibility, especially with the recent progress of global climate change cooperation, and the international commitment of china to achieve peak carbon reaching in 2030 and carbon neutralization in 2060, investors and governments in china also have a great demand for the grading of the enterprise in the ESG.
When evaluating the ESG performance of a business, news related to the business is needed to score the ESG of the business. At present, ESG scoring is mainly performed on enterprises according to the number of news related to the enterprises, however, a lot of noises exist in the obtained news, for example, because a certain news appears in transfer for many times due to stir-frying, the precision of ESG scoring performed on the enterprises by simply using the number of the news is low, and the precision of investment decision making based on ESG scoring is low.
Disclosure of Invention
The embodiment of the application provides an enterprise ESG index determining method based on a clustering technology and a related product, which are used for distinguishing original news and reprinted news in multiple news of a news event, so that the ESG scoring precision of an enterprise is improved, and the investment decision making precision is improved.
In a first aspect, an embodiment of the present application provides a method for determining an enterprise ESG index based on a clustering technique, including:
acquiring M news of an enterprise to be evaluated in a preset time period, wherein M is an integer greater than or equal to 1;
clustering the M news to obtain K first news groups, wherein each first news group in the K first news groups corresponds to a news event, each first news group comprises one or more news in the M news, and K is an integer greater than or equal to 1;
clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0;
determining a target public opinion score of a news event corresponding to each first news group according to original news and H pieces of reprinted news included in each second news group in the L second news groups, wherein the target public opinion score is used for representing the influence of the news event corresponding to each first news group on the enterprise to be evaluated;
according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated;
and sending the ESG index of the enterprise to be evaluated to target equipment, so that a user of the target equipment can make an investment decision related to the enterprise to be evaluated according to the ESG index of the enterprise to be evaluated.
In a second aspect, an embodiment of the present application provides an apparatus for determining an enterprise ESG index, including:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring M news of an enterprise to be evaluated in a preset time period, and M is an integer greater than or equal to 1;
the processing unit is used for clustering the M news to obtain K first news groups, wherein each first news group in the K first news groups corresponds to a news event, each first news group comprises one or more news in the M news, and K is an integer greater than or equal to 1;
clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0;
determining a target public opinion score of a news event corresponding to each first news group according to original news and H pieces of reprinted news included in each second news group in the L second news groups, wherein the target public opinion score is used for representing the influence of the news event corresponding to each first news group on the enterprise to be evaluated;
according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated;
and the sending unit is used for sending the ESG index of the enterprise to be evaluated to target equipment so that a user of the target equipment can make an investment decision related to the enterprise to be evaluated according to the ESG index of the enterprise to be evaluated.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor coupled to a memory, the memory configured to store a computer program, the processor configured to execute the computer program stored in the memory to cause the electronic device to perform the method of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which stores a computer program, where the computer program makes a computer execute the method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer being operable to cause a computer to perform the method according to the first aspect.
The embodiment of the application has the following beneficial effects:
it can be seen that in the embodiment of the application, after news used for performing ESG evaluation on an enterprise to be evaluated is obtained, the ESG evaluation is performed on the enterprise to be evaluated not directly by using the number of the news, but a clustering method is adopted to group the news belonging to each news event, and the ESG evaluation is performed from the granularity of the news event, so that more accurate evaluation is realized; then, aiming at the news group under each news event, the ESG evaluation is not directly carried out by using the news number in the news group, but ESG evaluation is further carried out on the enterprises to be evaluated from the dimensionality of the original news and the reprinted news by further clustering, the original news and the reprinted news are distinguished differently, the accuracy of ESG evaluation can be further improved, and the obtained ESG index is higher. Therefore, the ESG index with higher precision can be sent to the target equipment, and the accuracy of the formulated investment decision is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of an enterprise ESG index determining method based on a clustering technique according to an embodiment of the present application;
fig. 2 is a block diagram illustrating functional units of an enterprise ESG index determining apparatus according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an enterprise ESG index determining apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
First, it is explained that the enterprise ESG index or ESG index, i.e. the enterprise ESG score, may also be referred to as ESG score, which are the same in nature and will not be distinguished later. Accordingly, the ESG evaluation of a business or the ESG scoring of a business, which are all essentially the same, are used to determine the ESG index of a business.
Referring to fig. 1, fig. 1 is a method for indexing an enterprise ESG based on a clustering technique according to an embodiment of the present application. The method is applied to the enterprise ESG index determining device. The method comprises the following steps:
101: and acquiring M news of the enterprise to be evaluated in a preset time period, wherein the M news are used for carrying out ESG evaluation, and M is an integer greater than or equal to 1.
For example, the device for determining an ESG index of an enterprise may obtain W news in a preset time period from a plurality of news media platforms through a crawler technology, identify the W news (e.g., classify the W news into texts), and screen N news related to the ESG evaluation from the W news, for example, if the energy consumption of an enterprise is disclosed in a certain news, the news is regarded as the news related to the ESG index.
The preset time period may be any one of historical time periods, for example, the preset time period may be approximately ten days, last month, last year, or the like. The preset time period is not limited in the present application. That is to say, the method for determining the enterprise ESG index according to the present application may perform ESG evaluation on an enterprise based on news in a recent time period to obtain the ESG index of the enterprise in the recent time period; history can also be traced back, ESG evaluation is carried out on the enterprise based on news in a certain historical time period, and ESG indexes of the enterprise in a certain historical time period are obtained.
For example, entity identification may be performed on each of N news items, an entity word in each news item is obtained, and a business related to each news item is determined according to the entity word in each news item, where the entity word may be a name of the business (e.g., a chinese name, an english name), a product of the business, a location of the business, a rank of the business, and so on; then, the businesses involved in each of the N news are merged to obtain all the businesses involved in the N news. Correspondingly, according to the enterprise to which each piece of news relates, the number of the news related to each enterprise in all the enterprises to which the N pieces of news relate can be obtained, and M pieces of news related to the enterprise to be evaluated are obtained, wherein M is smaller than or equal to N, and the enterprise to be evaluated is any one of the enterprises.
102: and clustering the M news to obtain K first news groups, wherein each first news group in the K first news groups corresponds to a news event, each first news group comprises one or more news in the M news, and K is an integer greater than or equal to 1.
Illustratively, the enterprise ESG index determining apparatus extracts semantic information of each of M news items to obtain a semantic vector corresponding to each news item, where the semantic vector corresponding to each news item is used to represent a news event described by each news item. Clustering M news based on semantic vectors of each news to obtain K first news groups, namely determining Euclidean distance between the semantic vectors of any two news in the M news, and taking the Euclidean distance between the semantic vectors of any two news as first similarity between any two news; then, two news with the first similarity larger than the first threshold are classified into one first news group, namely, the two news are classified into one first news group, and K first news groups are obtained. Since the first similarity between the semantic vectors of the two news items is greater than the first threshold, the two news items describe a news event, and therefore one or more news items included in each first news group are the same news event.
103: and clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0.
For example, the enterprise ESG index determining apparatus determines a second similarity between any two news in each first news group, and classifies the news with the second similarity greater than a second threshold into one category, that is, classifies the news into one second news group, to obtain L second news groups. Specifically, the second similarity between any two news in each first news group may be a similarity between news contents of the two news, for example, a similarity between a title and an abstract of the two news may be calculated, the similarity between the title and the abstract is taken as the similarity between the two news, and if the similarity is greater than a second threshold, the two news are the same news (i.e., one of the two news is original news and one is reprinted of the original news; or both are reprinted of the news). After the clustering, an original news and all the reprinted news of the original news can be clustered into a second news group. And because the content between the two original news items is different, the two original news items are clustered into two different second news groups. Therefore, by the clustering method, all original news can be separated, and the reprinted news corresponding to each original news can be clustered together to obtain L second news groups.
In addition, each second news group necessarily includes one original news and H reprinted news, and when H is greater than or equal to 1, if the original news in each second news group is determined, the posting time of each news in each second news group can be obtained. The publication time is necessarily the earliest for the original news, so the news with the earliest publication time in each second news group can be used as the original news in each second news group, and the rest news are the reprinted news in each second news group.
104: and determining a target public opinion score of the news event corresponding to each first news group according to original news and H pieces of reprinted news included in each second news group in the L second news groups, wherein the target public opinion score is used for representing the influence of the news event corresponding to each first news group on the enterprise to be evaluated.
Illustratively, the scaling of each first news group is determined from the news amount, and the original public opinion score of each first news group is determined from the news content; and finally, fusing the scaling of each first news group and the original public opinion score to obtain the target public opinion score of each first news group. The scaling of each first news group represents the social attention to the news event corresponding to each first news group, and the target public opinion score is used for representing the influence of the news event corresponding to each first news group on the enterprise to be evaluated, namely the influence degree of the enterprise to be evaluated.
Specifically, a preset proportion of the original news in each second news group is obtained, wherein the preset proportion represents the contribution degree of the original news on the social attention degree of the news event corresponding to each first news group. It should be understood that the original news is authored autonomously by the newsreader, regardless of the naval fry, and thus, the attention paid to a news event by all the original news under the news event should be the same, that is, each original news is made in the social attention of the news event. Therefore, a proportion is preset for each original news event, so that the contribution of the original news in the attention degree is not influenced by the number of the reprinted news; and determining the scaling of each second news group according to the preset proportion of the original news in each second news group and the number H of the reprinted news contained in each second news group.
Illustratively, the scaling of each second newsgroup may be represented by equation (1):
heatj= log2(Hj+1) + a formula (1)
Among them, heatjFor the scaling of the jth second news group of the L second news groups, HjThe number of the reprinted news included in the jth second news group is a, and a is a preset proportion of the original news in each second news group, and the value is generally 1.
It can be seen that, when the above formula (1) calculates the scaling of each second newsgroup, as the number of the reprinted news increases, the increase of the scaling gradually decreases, so that the behavior of the deliberate reprinting or frying is decreased, that is, the behavior of the deliberate reprinting or frying by the naval is decreased by the formula (1), so that the determined scaling (attention) is more accurate, that is, the scaling is not easily affected by the frying by the naval.
Illustratively, the scaling of each second newsgroup may also be represented by formula (2):
it can be seen that HjWhen =0, that is, the number of the reprinted news in each second news group is zero, the scaling of the second news group is a, that is, the scaling column is only related to the number of the original news; when H is presentjAt infinity, the second newsgroup has a zoom ratio of 1+ a, i.e., an upper limit. Therefore, even if the water army stir-frying exists, the stir-frying behavior can be converged at the 1+ a position, the influence of the stir-frying behavior can not be endless, the unlimited amplification of the social attention to the news event can not be realized, and the unlimited amplification of the social attention to a certain news event can not be realized, so that the determined scaling ratio is more accurate, and the finally calculated target public opinion score is more accurate.
Further, the scaling of each second newsgroup is summed to obtain a scaling column for each first newsgroup. Thus, the scaling of each first news group can be represented by equation (3):
where heat is the scaling of each first news group.
In one embodiment of the application, in determining the public sentiment score of the news event corresponding to each first news group, a group of second news groups can be randomly selected from L second news groups corresponding to each first news group, sentiment identification can be performed on any news in the second news groups to obtain a sentiment tag corresponding to the news, and the sentiment tag of the news is used as the sentiment tag corresponding to each first news group; or randomly selecting a news from all news corresponding to each first news group for emotion recognition to obtain an emotion tag of the news, and taking the emotion tag of the news as the emotion tag corresponding to each first news group. The news events described by all news under each first news group are the same. Therefore, the manner of adding the emotion tags to each first news group is flexible, and is not limited to the manner of adding the emotion tags to each first news group. Wherein, the emotion label corresponding to each first news group is used for representing whether the news event corresponding to each first news group is a positive news event or a negative news event.
Further, when the emotion tag is used for representing that the news event described by each first news group is a negative news event, the specific content of the negative news event is determined, such as the number of fines, service interruption, high management criminal or prohibition of government purchase, and the like; when the emotion tags are used for representing that the news events described by each first news group are positive news events, specific content of the positive news events is determined, and the method can be effective in energy conservation and emission reduction.
Further, determining published media of all news in the L second news groups; for example, the news content of each news in the L second news groups is subjected to text recognition, and the published media of each news is recognized from each news content, for example, some of the published media of the news are located at the last drop of the news content, and some of the published media of the news are located at the initial position of the news content. Therefore, text recognition is carried out on the news content of each news, and published media of each news can be obtained; and determines the highest ranking published media in each first newsgroup based on the published media of all the news in the L second newsgroups. It should be understood that the enterprise ESG index determines the priority relationship in which published media is pre-set in the device. In general, the priority is as follows: national level publication media > provincial level publication media > municipal level publication media > self media > entertainment media, and so on. Therefore, after identifying the published media of each news in the L second news groups, the highest-level published media in each first news group is determined according to the preset priority relationship.
And finally, determining the original public opinion score corresponding to each first news group according to the mapping relation among the published media, the emotion labels and the public opinion scores, the published media with the highest level in each first news group and the emotion labels corresponding to each first news group.
For example, the mapping between published media, emotion labels and public opinion scores may be: if the news event is characterized as a neutral news event (i.e. no criticism or no raise), setting the public opinion score to be 0, if the news event is characterized as a negative news event, deducting from 0 to-10, and the deduction degree is related to the specific content of the negative news event and the level of published media, for example, if the news event corresponding to each first news group is high-managed and detained, and the published media with the highest level is the published media with the national level, deducting 10, namely, the original public opinion score corresponding to each first news group is-10; if the news event is characterized as a positive news event, adding from 0 to 5, and similarly, the degree of the deduction is related to the specific content of the negative news event and the level of published media; for example, if the news event is the annual final award coverage rate of 100%, and the highest-level publication medium is the provincial publication medium, 2 points are added, that is, the original public opinion score corresponding to the news event is 2 points. That is, mapping relationships between news events of respective types, respective publication levels, and public opinion scores are previously configured. After the published media with the highest level of each first news group and the types of news events are determined, the original public opinion score corresponding to each first news group can be determined according to the mapping relation.
In addition, since the negative news is initiated by other parties (such as media, government and the like) and plays a role in public opinion supervision, and the positive news is possibly initiated by the self-public department of the enterprise, the deduction range (-10) of the negative news is wider than the additional point range (+ 5) of the positive news, so that the public opinion score is more reasonably distributed.
And finally, performing product operation on the original public opinion score of each first news group and the scaling to obtain a target public opinion score corresponding to each first news group.
Therefore, the target public opinion score corresponding to each first news group can be represented by formula (4):
and the adjscoreeevent is a target public opinion score corresponding to each first news group, and the adjscorore is an original public opinion score of each first news group.
Wherein the scaling heat plays a role of an amplifier in formula (4), i.e. the original public opinion score of each news event is enlarged or reduced. For example, if the scaling is 1.5, the original public opinion score is enlarged by 1.5 times. Since the scaling reflects the social attention to the news event, negative public sentiments are deducted more and positive public sentiments are added more through multiplicative fusion in the formula (4), so that the finally calculated target public sentiment score is more reasonable and accurate.
105: and according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated.
For example, the target public opinion score corresponding to each first news group can be used as an ESG index when ESG evaluation is performed on a business to be evaluated from a news dimension.
106: and sending the ESG index of the enterprise to be evaluated to target equipment, so that a user of the target equipment can make an investment decision related to the enterprise to be evaluated according to the ESG index of the enterprise to be evaluated.
It can be seen that in the embodiment of the application, after news used for performing ESG evaluation on an enterprise to be evaluated is obtained, the ESG evaluation is performed on the enterprise to be evaluated not directly by using the number of the news, but a clustering method is adopted to group the news belonging to each news event, and the ESG evaluation is performed from the granularity of the news event, so that more accurate evaluation is realized; then, aiming at the news group under each news event, the ESG evaluation is not directly carried out by using the news number in the news group, but ESG evaluation is further carried out on the enterprises to be evaluated from the dimensionality of the original news and the reprinted news by further clustering, the original news and the reprinted news are distinguished differently, the accuracy of ESG evaluation can be further improved, and the obtained ESG index is higher. Therefore, the ESG index with higher precision can be sent to the target equipment, and the accuracy of the formulated investment decision is improved.
In one embodiment of the present application, the decision related to the enterprise to be evaluated may be made according to the role of the target device, and the ESG index of the present application has the following application scenarios:
scene 1: when the target device is a device of the investment organization, the ESG index of the enterprise to be evaluated is sent to the investment organization, and the decision that the investment organization can make about the enterprise to be evaluated is as follows: investment decisions associated with the enterprise to be assessed. For example, since the ESG index of an enterprise reflects the value and sustainable development capability of the enterprise, when the ESG index of an enterprise to be evaluated is high, the investment decision may be to add an investment amount and an investment period to the enterprise to be evaluated; when the ESG index of the enterprise to be evaluated is low, the investment may be withdrawn from the enterprise to be evaluated or reduced, and so on. In general, the ESG index of the enterprise to be evaluated is sent to the investment institution, so that a direction guide can be provided for making an investment decision of the investment institution, and the investment risk is reduced.
Scene 2: when the target device is a device of an enterprise to be evaluated, the ESG index of the enterprise to be evaluated is sent to the enterprise to be evaluated, and the enterprise to be evaluated can make a decision related to the enterprise to be evaluated, namely a management decision related to the enterprise to be evaluated. Illustratively, as the ESG index of an enterprise reflects the value and sustainable development ability of the enterprise, higher enterprises willing to invest in the ESG index pay more attention to the social responsibility of the enterprise as the investor increases in acceptance of the ESG index. Therefore, when the ESG index of the enterprise to be evaluated is higher, the management decision makes a decision for reinforcing enterprise management for the enterprise to be evaluated, and the excellent performance in the aspect of ESG is continuously maintained; when the ESG index of the enterprise to be evaluated is low, the management decision is to adjust the development strategy of the enterprise, improve the sustainable development of the enterprise and improve the ESG index. Generally, the ESG index of the enterprise to be evaluated is sent to the enterprise to be evaluated, so that the enterprise to be evaluated is promoted to strive to improve the ESG evaluation condition of the enterprise to be evaluated, and the benign development of the enterprise to be evaluated is guided.
Scene 3: when the target device is a device of a government or a social organization, the ESG index of the enterprise to be evaluated is sent to the government or the social organization, and the government or the social organization can make a decision related to the enterprise to be evaluated, namely, make a support decision related to the enterprise to be evaluated. Illustratively, the ESG index of a business reflects the value and sustainable ability of the business. Therefore, when the ESG index of the enterprise to be evaluated is higher, the development potential of the enterprise to be evaluated is higher, and the supporting decision can greatly promote the enterprise to be evaluated so as to provide more development opportunities for the enterprise; when the ESG index of the enterprise to be evaluated is low, which indicates that the development potential of the enterprise to be evaluated is low, the support decision can adjust the development strategy of the enterprise to be evaluated for the order, or reduce the support so as to guide the adjustment of the enterprise to be evaluated to the benign development direction.
Referring to fig. 2, fig. 2 is a block diagram illustrating functional units of an enterprise ESG index determination apparatus according to an embodiment of the present application. The enterprise ESG index determining apparatus 200 includes: an acquisition unit 201, a processing unit 202 and a transmission unit 203, wherein:
the obtaining unit 201 is configured to obtain M pieces of news of an enterprise to be evaluated in a preset time period, where M is an integer greater than or equal to 1;
a processing unit 202, configured to cluster the M news items to obtain K first news groups, where each first news group in the K first news groups corresponds to a news event, each first news group includes one or more news items in the M news items, and K is an integer greater than or equal to 1;
clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0;
determining a target public opinion score of a news event corresponding to each first news group according to original news and H pieces of reprinted news included in each second news group in the L second news groups, wherein the target public opinion score is used for representing the influence of the news event corresponding to each first news group on the enterprise to be evaluated;
according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated;
a sending unit 203, configured to send the ESG index of the enterprise to be evaluated to a target device, so that a user of the target device makes an investment decision related to the enterprise to be evaluated according to the ESG index pair of the enterprise to be evaluated.
In some possible embodiments of the present application, in terms of determining the target public opinion score of the news event corresponding to each first news group according to the original news and the H reprinted news included in each of the L second news groups, the processing unit 202 is specifically configured to:
determining the scaling of the news event corresponding to each first news group according to the original news included in each second news group in the L second news groups and the number H of the reprinted news, wherein the scaling of the news event corresponding to each first news group represents the attention degree of the news event corresponding to each first news group;
determining the original public opinion score of a news event corresponding to each first news group according to the news content of original news and the news content of H pieces of reprinted news included in each second news group in the L second news groups;
and multiplying the scaling of the news event corresponding to each first news group and the original public opinion score to obtain the target public opinion score of the news event corresponding to each first news group.
In some possible embodiments of the present application, in terms of determining a scaling ratio of the news event corresponding to each first news group according to an original news included in each of the L second news groups and the number H of reprinted news, the processing unit 202 is specifically configured to:
acquiring a preset proportion of the original news in each second news group, wherein the preset proportion represents the contribution degree of the original news on the social attention degree of the news events corresponding to each first news group;
determining the scaling ratio of each second news group according to the preset ratio of the original news in each second news group and the number H of the reprinted news included in each second news group;
and summing the scaling ratios of the L second news groups to obtain the scaling ratio of the news event corresponding to each first news group.
In some possible embodiments of the present application, in terms of determining the original public opinion score of the news event corresponding to each first news group according to the news content of an original news item and the news content of H reprinted news items included in each second news group of the L second news groups, the processing unit 202 is specifically configured to:
performing emotion recognition on the news in each first news group to obtain an emotion tag corresponding to each first news group, wherein the emotion tag corresponding to each first news group is used for representing that the news event corresponding to each first news group is a positive news event or a negative news event;
acquiring published media of each news in each first news group;
determining the published media of the highest level in each first news group according to the published media of each news in each first news group;
and determining the original public opinion score of the news event corresponding to each first news group according to the mapping relation among the published media, the emotion labels and the public opinion score, the published media with the highest level in each first news group and the emotion labels corresponding to each first news group.
In some possible embodiments of the present application, in the aspect of performing emotion recognition on the news in each first news group to obtain an emotion tag corresponding to each first news group, the processing unit 202 is specifically configured to:
randomly selecting a second news group from the L second news groups, carrying out emotion recognition on any news in the second news group to obtain an emotion tag of the news, and taking the emotion tag of the news as an emotion tag corresponding to each first news group;
alternatively, the first and second electrodes may be,
randomly selecting a piece of news from one or more pieces of news included in each first news group, carrying out emotion recognition on the news to obtain an emotion tag corresponding to the news, and taking the emotion tag corresponding to the news as the emotion tag corresponding to each first news group.
In some possible embodiments of the application, in clustering the M news items to obtain K first news groups, the processing unit 202 is specifically configured to:
extracting semantic information of each news in the M news to obtain a semantic vector of each news, wherein the semantic vector of each news is used for representing news events described by each news;
determining a first similarity between semantic vectors of any two news in the M news;
clustering the M news according to a first similarity between semantic vectors of any two news in the M news to obtain K first news groups, wherein the first similarity between the semantic vectors of any two news in each of the K first news groups is larger than a first threshold value.
In some possible embodiments of the present application, in clustering one or more news items in each of the first news groups to obtain L second news groups corresponding to each of the first news groups, the processing unit 202 is specifically configured to:
determining a second similarity between any two news in each first news group, wherein the second similarity between any two news in each first news group is used for representing the similarity between the news contents of any two news in each first news group;
and clustering one or more news included in each first news group according to the second similarity between any two news in each first news group to obtain L second news groups, wherein the second similarity between any two news in each second news group is greater than a second threshold value.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 3, the electronic device 300 includes a transceiver 301, a processor 302, and a memory 303. Connected to each other by a bus 304. The memory 303 is used to store computer programs and data, and may transfer data stored in the memory 303 to the processor 302.
The processor 302 is configured to read the computer program in the memory 303 to perform the following operations:
controlling the transceiver 301 to acquire M news of an enterprise to be evaluated in a preset time period, wherein M is an integer greater than or equal to 1;
clustering the M news to obtain K first news groups, wherein each first news group in the K first news groups corresponds to a news event, each first news group comprises one or more news in the M news, and K is an integer greater than or equal to 1;
clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0;
determining a target public opinion score of a news event corresponding to each first news group according to original news and H pieces of reprinted news included in each second news group in the L second news groups, wherein the target public opinion score is used for representing the influence of the news event corresponding to each first news group on the enterprise to be evaluated;
according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated;
a sending unit 203, configured to send the ESG index of the enterprise to be evaluated to a target device, so that a user of the target device makes an investment decision related to the enterprise to be evaluated according to the ESG index pair of the enterprise to be evaluated.
In some possible embodiments of the present application, in terms of determining the target public opinion score of the news event corresponding to each first news group according to the original news and the H reprinted news included in each of the L second news groups, the processing unit 202 is specifically configured to:
determining the scaling of the news event corresponding to each first news group according to the original news included in each second news group in the L second news groups and the number H of the reprinted news, wherein the scaling of the news event corresponding to each first news group represents the attention degree of the news event corresponding to each first news group;
determining the original public opinion score of a news event corresponding to each first news group according to the news content of original news and the news content of H pieces of reprinted news included in each second news group in the L second news groups;
and multiplying the scaling of the news event corresponding to each first news group and the original public opinion score to obtain the target public opinion score of the news event corresponding to each first news group.
In some possible embodiments of the present application, in determining a scaling ratio of the news event corresponding to each first news group according to an original news included in each of the L second news groups and the number H of reprinted news, the processor 302 is specifically configured to:
acquiring a preset proportion of the original news in each second news group, wherein the preset proportion represents the contribution degree of the original news on the social attention degree of the news events corresponding to each first news group;
determining the scaling ratio of each second news group according to the preset ratio of the original news in each second news group and the number H of the reprinted news included in each second news group;
and summing the scaling ratios of the L second news groups to obtain the scaling ratio of the news event corresponding to each first news group.
In some possible embodiments of the present application, in determining the original public opinion score of the news event corresponding to each first news group according to the news content of an original news item and the news content of an H piece of reprinted news included in each of the L second news groups, the processor 302 is specifically configured to perform the following operations:
performing emotion recognition on the news in each first news group to obtain an emotion tag corresponding to each first news group, wherein the emotion tag corresponding to each first news group is used for representing that the news event corresponding to each first news group is a positive news event or a negative news event;
acquiring published media of each news in each first news group;
determining the published media of the highest level in each first news group according to the published media of each news in each first news group;
and determining the original public opinion score of the news event corresponding to each first news group according to the mapping relation among the published media, the emotion labels and the public opinion score, the published media with the highest level in each first news group and the emotion labels corresponding to each first news group.
In some possible embodiments of the present application, in the aspect of performing emotion recognition on the news in each first news group to obtain an emotion tag corresponding to each first news group, the processor 302 is specifically configured to:
randomly selecting a second news group from the L second news groups, carrying out emotion recognition on any news in the second news group to obtain an emotion tag of the news, and taking the emotion tag of the news as an emotion tag corresponding to each first news group;
alternatively, the first and second electrodes may be,
randomly selecting a piece of news from one or more pieces of news included in each first news group, carrying out emotion recognition on the news to obtain an emotion tag corresponding to the news, and taking the emotion tag corresponding to the news as the emotion tag corresponding to each first news group.
In some possible embodiments of the application, in clustering the M news items to obtain K first news groups, the processor 302 is specifically configured to:
extracting semantic information of each news in the M news to obtain a semantic vector of each news, wherein the semantic vector of each news is used for representing news events described by each news;
determining a first similarity between semantic vectors of any two news in the M news;
clustering the M news according to a first similarity between semantic vectors of any two news in the M news to obtain K first news groups, wherein the first similarity between the semantic vectors of any two news in each of the K first news groups is larger than a first threshold value.
In some possible embodiments of the present application, in clustering one or more news items in each of the first news groups to obtain L second news groups corresponding to each of the first news groups, the processor 302 is specifically configured to:
determining a second similarity between any two news in each first news group, wherein the second similarity between any two news in each first news group is used for representing the similarity between the news contents of any two news in each first news group;
and clustering one or more news included in each first news group according to the second similarity between any two news in each first news group to obtain L second news groups, wherein the second similarity between any two news in each second news group is greater than a second threshold value.
Specifically, the transceiver 301 may be the acquiring unit 201 and the transmitting unit 203 of the enterprise ESG index determination apparatus 200 according to the embodiment shown in fig. 2, and the processor 302 may be the processing unit 202 of the enterprise ESG index determination apparatus 200 according to the embodiment shown in fig. 2.
Embodiments of the present application also provide a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement part or all of the steps of any one of the clustering-technique-based enterprise ESG index determination methods as described in the above method embodiments.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program, the computer program being operable to cause a computer to perform part or all of the steps of any one of the clustering technique based enterprise ESG index determination methods as recited in the above method embodiments.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that the acts and modules referred to are not necessarily required in this application.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.
The integrated units, if implemented in the form of software program modules and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (9)
1. A method for determining an enterprise ESG index based on clustering technology is characterized by comprising the following steps:
acquiring M news of an enterprise to be evaluated in a preset time period, wherein M is an integer greater than or equal to 1;
clustering the M news to obtain K first news groups, wherein each first news group in the K first news groups corresponds to a news event, each first news group comprises one or more news in the M news, and K is an integer greater than or equal to 1;
clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0;
according to an original news and an H piece of reprinted news included in each of the L second news groups, determining a target public opinion score of a news event corresponding to each first news group, where the target public opinion score is used to represent an influence of the news event corresponding to each first news group on the enterprise to be evaluated, and specifically includes: determining the scaling of the news event corresponding to each first news group according to the original news included in each second news group in the L second news groups and the number H of the reprinted news, wherein the scaling of the news event corresponding to each first news group represents the social attention degree of the news event corresponding to each first news group; determining the original public opinion score of a news event corresponding to each first news group according to the news content of original news and the news content of H pieces of reprinted news included in each second news group in the L second news groups; multiplying the scaling of the news event corresponding to each first news group and the original public opinion score to obtain a target public opinion score of the news event corresponding to each first news group;
according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated;
and sending the ESG index of the enterprise to be evaluated to target equipment, so that a user of the target equipment can make an investment decision related to the enterprise to be evaluated according to the ESG index of the enterprise to be evaluated.
2. The method of claim 1, wherein the determining the scaling of the news event corresponding to each first news group according to an original news item included in each of the L second news groups and the number H of reprinted news comprises:
acquiring a preset proportion of the original news in each second news group, wherein the preset proportion represents the contribution degree of the original news on the social attention degree of the news events corresponding to each first news group;
determining the scaling ratio of each second news group according to the preset ratio of the original news in each second news group and the number H of the reprinted news included in each second news group;
and summing the scaling ratios of the L second news groups to obtain the scaling ratio of the news event corresponding to each first news group.
3. The method of claim 1 or 2, wherein determining the original public opinion score of the news event corresponding to each first news group according to the news content of an original news item and the news content of an H piece of reprinted news included in each of the L second news groups comprises:
performing emotion recognition on the news in each first news group to obtain an emotion tag corresponding to each first news group, wherein the emotion tag corresponding to each first news group is used for representing that the news event corresponding to each first news group is a positive news event or a negative news event;
acquiring published media of each news in each first news group;
determining the published media of the highest level in each first news group according to the published media of each news in each first news group;
and determining the original public opinion score of the news event corresponding to each first news group according to the mapping relation among the published media, the emotion labels and the public opinion score, the published media with the highest level in each first news group and the emotion labels corresponding to each first news group.
4. The method of claim 3, wherein the emotion recognition of the news in each first news group to obtain the emotion tag corresponding to each first news group comprises:
randomly selecting a second news group from the L second news groups, carrying out emotion recognition on any news in the second news group to obtain an emotion tag of the news, and taking the emotion tag of the news as an emotion tag corresponding to each first news group;
alternatively, the first and second electrodes may be,
randomly selecting a piece of news from one or more pieces of news included in each first news group, carrying out emotion recognition on the news to obtain an emotion tag corresponding to the news, and taking the emotion tag corresponding to the news as the emotion tag corresponding to each first news group.
5. The method of claim 4, wherein clustering the M news items to obtain K first groups of news comprises:
extracting semantic information of each news in the M news to obtain a semantic vector of each news, wherein the semantic vector of each news is used for representing news events described by each news;
determining a first similarity between semantic vectors of any two news in the M news;
clustering the M news according to a first similarity between semantic vectors of any two news in the M news to obtain K first news groups, wherein the first similarity between the semantic vectors of any two news in each of the K first news groups is larger than a first threshold value.
6. The method of claim 5, wherein clustering the one or more news in each of the first news groups to obtain L second news groups corresponding to each of the first news groups comprises:
determining a second similarity between any two news in each first news group, wherein the second similarity between any two news in each first news group is used for representing the similarity between the news contents of any two news in each first news group;
and clustering one or more news included in each first news group according to the second similarity between any two news in each first news group to obtain L second news groups, wherein the second similarity between any two news in each second news group is greater than a second threshold value.
7. An apparatus for determining an enterprise ESG index, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring M news of an enterprise to be evaluated in a preset time period, and M is an integer greater than or equal to 1;
the processing unit is used for clustering the M news to obtain K first news groups, wherein each first news group in the K first news groups corresponds to a news event, each first news group comprises one or more news in the M news, and K is an integer greater than or equal to 1;
clustering one or more news in each first news group to obtain L second news groups corresponding to each first news group, wherein each second news group comprises original news and H pieces of reprinted news corresponding to the original news, and H is an integer greater than or equal to 0;
according to an original news and an H piece of reprinted news included in each of the L second news groups, determining a target public opinion score of a news event corresponding to each first news group, where the target public opinion score is used to represent an influence of the news event corresponding to each first news group on the enterprise to be evaluated, and specifically used to: determining the scaling of the news event corresponding to each first news group according to the original news included in each second news group in the L second news groups and the number H of the reprinted news, wherein the scaling of the news event corresponding to each first news group represents the social attention degree of the news event corresponding to each first news group; determining the original public opinion score of a news event corresponding to each first news group according to the news content of original news and the news content of H pieces of reprinted news included in each second news group in the L second news groups; multiplying the scaling of the news event corresponding to each first news group and the original public opinion score to obtain a target public opinion score of the news event corresponding to each first news group;
according to the target public opinion score of the news event corresponding to each first news group, carrying out ESG evaluation on the enterprise to be evaluated to obtain an ESG index of the enterprise to be evaluated;
and the sending unit is used for sending the ESG index of the enterprise to be evaluated to target equipment so that a user of the target equipment can make an investment decision related to the enterprise to be evaluated according to the ESG index of the enterprise to be evaluated.
8. An electronic device, comprising: a processor coupled to the memory, and a memory for storing a computer program, the processor for executing the computer program stored in the memory to cause the electronic device to perform the method of any of claims 1-6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method according to any one of claims 1-6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110748931.XA CN113190683B (en) | 2021-07-02 | 2021-07-02 | Enterprise ESG index determination method based on clustering technology and related product |
| PCT/CN2022/071253 WO2023273295A1 (en) | 2021-07-02 | 2022-01-11 | Enterprise esg index determination method based on clustering technology, and related product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110748931.XA CN113190683B (en) | 2021-07-02 | 2021-07-02 | Enterprise ESG index determination method based on clustering technology and related product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113190683A CN113190683A (en) | 2021-07-30 |
| CN113190683B true CN113190683B (en) | 2021-09-17 |
Family
ID=76976971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110748931.XA Active CN113190683B (en) | 2021-07-02 | 2021-07-02 | Enterprise ESG index determination method based on clustering technology and related product |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113190683B (en) |
| WO (1) | WO2023273295A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113190683B (en) * | 2021-07-02 | 2021-09-17 | 平安科技（深圳）有限公司 | Enterprise ESG index determination method based on clustering technology and related product |
| CN113570281A (en) * | 2021-08-20 | 2021-10-29 | 瑞格人工智能科技有限公司 | ESG index compiling method |
| CN113837630A (en) * | 2021-09-28 | 2021-12-24 | 平安科技（深圳）有限公司 | Text recognition-based ESG index determination method in area and related product |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000627A (en) * | 2007-01-15 | 2007-07-18 | 北京搜狗科技发展有限公司 | Method and device for issuing correlation information |
| CN103226577A (en) * | 2013-04-01 | 2013-07-31 | 儒豹（苏州）科技有限责任公司 | News clustering method |
| CN104995650A (en) * | 2011-12-27 | 2015-10-21 | 汤姆森路透社全球资源公司 | Methods and systems for generating composite index using social media sourced data and sentiment analysis |
| CN108875018A (en) * | 2018-06-19 | 2018-11-23 | 网智天元科技集团股份有限公司 | News influence appraisal procedure, device and electronic equipment |
| CN110399478A (en) * | 2018-04-19 | 2019-11-01 | 清华大学 | Event finds method and apparatus |
| CN110472884A (en) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | ESG index monitoring method, device, terminal device and storage medium |
| CN110532357A (en) * | 2019-09-04 | 2019-12-03 | 深圳前海微众银行股份有限公司 | Generation method, device, equipment and the readable storage medium storing program for executing of ESG score-system |
| CN111630518A (en) * | 2017-11-23 | 2020-09-04 | 持续可能发展所株式会社 | ESG-based enterprise evaluation execution device and operation method thereof |
| CN112418591A (en) * | 2020-09-22 | 2021-02-26 | 中财绿指(北京)信息咨询有限公司 | Enterprise ESG (electronic service guide) rating method based on weight distribution model |
| CN112613296A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | News importance degree acquisition method and device, terminal equipment and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8719279B2 (en) * | 2012-02-24 | 2014-05-06 | Strategic Communication Advisors, LLC. | System and method for assessing and ranking newsworthiness |
| CN104317881B (en) * | 2014-04-11 | 2017-11-24 | 北京理工大学 | One kind is based on the authoritative microblogging method for reordering of user's topic |
| KR101741509B1 (en) * | 2015-07-01 | 2017-06-15 | 지속가능발전소 주식회사 | Device and method for analyzing corporate reputation by data mining of news, recording medium for performing the method |
| CN106776609B (en) * | 2015-11-19 | 2020-05-22 | 北京国双科技有限公司 | Statistical method and device for website reprint quantity |
| CN108804701A (en) * | 2018-06-19 | 2018-11-13 | 苏州大学 | Personage's portrait model building method based on social networks big data |
| CN109359857B (en) * | 2018-10-12 | 2021-08-27 | 网智天元科技集团股份有限公司 | Media influence evaluation method and device and electronic equipment |
| CN109508373B (en) * | 2018-11-13 | 2021-08-06 | 深圳前海微众银行股份有限公司 | Method and device for calculating enterprise public opinion index and computer readable storage medium |
| CN111177508A (en) * | 2019-10-16 | 2020-05-19 | 李多 | Spreading index query method and device for specified news topic and storage medium |
| CN113190683B (en) * | 2021-07-02 | 2021-09-17 | 平安科技（深圳）有限公司 | Enterprise ESG index determination method based on clustering technology and related product |
-
2021
- 2021-07-02 CN CN202110748931.XA patent/CN113190683B/en active Active
-
2022
- 2022-01-11 WO PCT/CN2022/071253 patent/WO2023273295A1/en unknown
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000627A (en) * | 2007-01-15 | 2007-07-18 | 北京搜狗科技发展有限公司 | Method and device for issuing correlation information |
| CN104995650A (en) * | 2011-12-27 | 2015-10-21 | 汤姆森路透社全球资源公司 | Methods and systems for generating composite index using social media sourced data and sentiment analysis |
| CN103226577A (en) * | 2013-04-01 | 2013-07-31 | 儒豹（苏州）科技有限责任公司 | News clustering method |
| CN111630518A (en) * | 2017-11-23 | 2020-09-04 | 持续可能发展所株式会社 | ESG-based enterprise evaluation execution device and operation method thereof |
| CN110399478A (en) * | 2018-04-19 | 2019-11-01 | 清华大学 | Event finds method and apparatus |
| CN108875018A (en) * | 2018-06-19 | 2018-11-23 | 网智天元科技集团股份有限公司 | News influence appraisal procedure, device and electronic equipment |
| CN110472884A (en) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | ESG index monitoring method, device, terminal device and storage medium |
| CN110532357A (en) * | 2019-09-04 | 2019-12-03 | 深圳前海微众银行股份有限公司 | Generation method, device, equipment and the readable storage medium storing program for executing of ESG score-system |
| CN112418591A (en) * | 2020-09-22 | 2021-02-26 | 中财绿指(北京)信息咨询有限公司 | Enterprise ESG (electronic service guide) rating method based on weight distribution model |
| CN112613296A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | News importance degree acquisition method and device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023273295A1 (en) | 2023-01-05 |
| CN113190683A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113190683B (en) | Enterprise ESG index determination method based on clustering technology and related product | |
| Kordonis et al. | Stock price forecasting via sentiment analysis on Twitter | |
| CN109087163B (en) | Credit assessment method and device | |
| CN108460082B (en) | Recommendation method and device and electronic equipment | |
| US9213733B2 (en) | Computerized internet search system and method | |
| CN108133013A (en) | Information processing method, device, computer equipment and storage medium | |
| US20110119208A1 (en) | Method and system for developing a classification tool | |
| CN111159341A (en) | Information recommendation method and device based on user investment and financing preference | |
| WO2023064933A1 (en) | A decentralized social news network website application (dapplication) on a blockchain including a newsfeed, nft marketplace, and a content moderation process for vetted content providers | |
| Chatterjee et al. | Investor classification and sentiment analysis | |
| CN110909120A (en) | Resume searching/delivering method, device and system and electronic equipment | |
| CN110909540A (en) | Method and device for identifying new words of short message spam and electronic equipment | |
| WO2023050652A1 (en) | Text recognition-based method for determining esg index in region, and related product | |
| CN111429214A (en) | Transaction data-based buyer and seller matching method and device | |
| CN113378090B (en) | Internet website similarity analysis method and device and readable storage medium | |
| CN111476657A (en) | Information pushing method, device and system | |
| Liang et al. | Detecting novel business blogs | |
| Pak et al. | Shock waves of political risk on the stock market: The case of Korean companies in the US | |
| CN103377381A (en) | Method and device for identifying content attribute of image | |
| CN112434126B (en) | Information processing method, device, equipment and storage medium | |
| KR102041915B1 (en) | Database module using artificial intelligence, economic data providing system and method using the same | |
| CN112115258B (en) | Credit evaluation method and device for user, server and storage medium | |
| CN112036730A (en) | Virtual asset data processing method and device and computer readable storage medium | |
| Sasaki et al. | Evaluation of VI Index Forecasting Model by Machine Learning for Yahoo! Stock BBS Using Volatility Trading Simulation. | |
| CN113392213B (en) | Event extraction method, electronic equipment and storage device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40054455 Country of ref document: HK |