Data processing method and apparatus

Abstract

The data processing method and device provided in the application relate to the technical field of data analysis. The data processing method can accurately match the main business information of the enterprise to be warehoused with the green industry type in the green enterprise database, and then, the reliability of the class label corresponding to the matching degree of the enterprise to be warehoused and the corresponding green industry type is also high. In this way, when the project to be evaluated needs to be evaluated, the evaluation rule corresponding to the category of the project to be evaluated can be obtained from the database according to the class label, so as to evaluate the project to be evaluated. Since the evaluation rule matches the project to be evaluated, the accuracy is high and the efficiency is high.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a data processing method and apparatus. Background Technology

[0002] Green enterprises are those whose business activities are conducive to supporting environmental improvement, adapting to or mitigating climate change and conserving and efficiently utilizing resources, and which have funding needs.

[0003] Typically, whether a company is a green enterprise is a key indicator for credit lending, project investment, project operation, and risk management. Therefore, it is necessary to assess whether a company is a green enterprise and to include identified green enterprises in a database. However, the accuracy of the green enterprises currently included in the database is low; furthermore, subsequent project evaluations based on these database-included green enterprises suffer from both low accuracy and low efficiency. Summary of the Invention

[0004] This application provides a data processing method and apparatus to address the problem of low accuracy in including green enterprises in a database, resulting in low accuracy and low efficiency in subsequent project evaluations based on these green enterprises.

[0005] Firstly, this application provides a data processing method applied to a server, comprising: the server acquiring the main business information of enterprises to be added to the database. For each green industry type in a pre-configured green industry thesaurus, the server determines the first keyword under the green industry type and its first word frequency score appearing in the main business information, and determines the first keyword under other green industry types and its second word frequency score appearing in the main business information. The server determines the matching degree between the main business information and each green industry type based on the first word frequency score and the second word frequency score. The server marks the enterprises to be added to the database with category tags corresponding to the corresponding green industry types based on the determined matching degree greater than a set threshold. The server adds the enterprises marked with category tags to a preset database. When the server evaluates the project to be evaluated, it retrieves the evaluation rules corresponding to the category of the project to be evaluated from the database according to the category tags to evaluate the project to be evaluated.

[0006] In one possible implementation, determining the second word frequency score of the first keyword under other green industry types besides the green industry type in the main business information includes: the server deduplicating each first keyword in the keyword set under other green industry types besides the green industry type; the server calculating the second word frequency score of each first keyword in the keyword set under other green industry types besides the green industry type after deduplication in the main business information.

[0007] In one possible implementation, the second word frequency score of the first keyword under other green industry types besides the green industry type in the main business information is determined, including: the server removes the first keyword appearing in the currently counted green industry type from the set of keywords of other green industry types besides the green industry type; the server counts the second word frequency score of each first keyword in the other green industry types besides the green industry type after removal in the main business information.

[0008] In one possible implementation, the server determines the matching degree between the main business information and each green industry type based on a first word frequency score and a second word frequency score, including: the server determines the matching degree between the main business information and each green industry type based on the first word frequency score f. C Second word frequency score f C - Using the formula:

[0009]

[0010] Determine the matching degree P between the main business information and each green industry type; where γ is a set hyperparameter; or, use the formula:

[0011]

[0012] Determine the matching degree P between the main business information and each green industry type.

[0013] In one possible implementation, after the server obtains the main business information of the enterprises to be added to the database, the method further includes: the server counting the first number of enterprise information belonging to any first keyword in each green industry type of the green industry terminology database; the server counting the third number of enterprise information belonging to the same green industry type as the first keyword among the enterprise information of the first number of green enterprises; and the server using the formula based on the first number df(s) and the third number dfc(s): The server determines the importance p(s,c) of any first keyword in each green industry type within the green industry thesaurus, within that specific green industry type. The server then determines the frequency score of the first keyword appearing in the main business information for each green industry type, including: the server's score based on the third frequency tf of the first keyword i in the main business information for each green industry type. i The importance of the first keyword "i" in each type of green industry. i The frequency score f of the first keyword appearing in the main business information of each green industry type in the pre-defined green industry thesaurus is calculated. C ;

[0014] The server determines the first keyword under other green industry types besides the green industry type, and the second keyword frequency score appearing in the main business information, including: the server's third keyword frequency tf based on the first keyword i under other green industry types besides the green industry type belonging to the main business information. i The importance of the first keyword "i" in other green industry types besides green industry types. i The formula used is: f C -=∑ i∈j tf i *w i Identify the primary keyword under other green industry types besides the green industry type, and the frequency score f of the secondary keyword appearing in the main business information. C -j represents the set of first keywords under other green industry types besides the aforementioned green industry type.

[0015] In one possible implementation, before the server obtains the main business information of the enterprise to be added to the database, the method further includes: the server extracting a second keyword from the enterprise information of multiple preset green enterprises that does not belong to the green industry terminology database but is associated with the green industry type in the green industry terminology database; the server adding the extracted second keyword to the corresponding green industry type in the green industry terminology database.

[0016] In one possible implementation, the server extracts a second keyword from the enterprise information of multiple preset green enterprises. This second keyword is not part of the green industry terminology library but is associated with green industry types in the library. This includes: the server counting the number of green enterprises whose enterprise information contains any first keyword in each green industry type of the green industry terminology library; the server counting the number of enterprise information containing both the first and second keywords from the enterprise information of multiple green enterprises; and the server using a formula based on the first and second keywords: The probability p(w|s) of the association between the second keyword and the first keyword is determined; the server determines the association based on the total number of first keywords in any green industry type |S. c The probability p(w|s) of any second keyword being associated with each of the first keywords of this green industry type is calculated using the formula... Determine the correlation between the second keyword and the green industry type rel(w, c); the server extracts the second keyword with a correlation greater than a set threshold.

[0017] In one possible implementation, before the server extracts the second keyword whose relevance is greater than a set threshold, the method provided in this application further includes: the server calculating according to a formula... The correlation between the second keyword and the green industry type is initially normalized, where v(w, c) is the correlation between the second keyword and the green industry type after initial normalization, and |C| is the number of green industry types. The server calculates the correlation based on the formula. The correlation between the second keyword and this type of green industry was normalized again, where v c (w, c) represents the correlation between the second keyword after re-normalization and the green industry type. The server calculates the correlation based on the formula... Once again, the correlation between the second keyword and this type of green industry was normalized, where τ w，c This represents the correlation between the second keyword after further normalization and the type of green industry. This approach ensures a higher reliability of the final correlation result.

[0018] In one possible implementation, the project to be evaluated is the green level of the enterprise to be evaluated. When the server evaluates the project, it retrieves the evaluation rules corresponding to the category of the project from the database based on the category label to evaluate the project. This includes: when the server evaluates the project, it retrieves the associated green level evaluation rules based on the category label of the enterprise to be evaluated; the server evaluates the main business information of the enterprise to be evaluated based on the green level evaluation rules to determine the green level of the enterprise to be evaluated, wherein the green level is light green, medium green, or dark green.

[0019] Secondly, this application provides a data processing apparatus applied to a server. The apparatus includes: an information acquisition unit for acquiring the main business information of enterprises to be added to the database; a word frequency determination unit for determining, for each green industry type in a pre-configured green industry terminology database, the first keyword of the green industry type appearing in the main business information, and determining the first keyword of other green industry types appearing in the main business information, and the second keyword of other green industry types appearing in the main business information; a matching degree determination unit for determining the matching degree between the main business information and each green industry type based on the first and second word frequency scores; a category labeling unit for labeling the enterprises to be added to the database with category tags corresponding to the green industry types corresponding to the determined matching degrees greater than a set threshold; a data entry unit for adding the enterprises to be added to the database labeled with category tags to a preset database; and a project evaluation unit for evaluating the project to be evaluated by retrieving the evaluation rules corresponding to the project to be evaluated from the database based on the category tags.

[0020] Thirdly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the computer to perform the method provided in the first aspect.

[0021] Fourthly, this application also provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the server performs the method provided in the first aspect.

[0022] Fifthly, this application also provides a computer program product, including a computer program that, when run, causes a computer to perform the method provided in the first aspect.

[0023] The data processing method provided in this application considers not only the first keyword under the green industry type and its frequency score in the main business information, but also the second keyword frequency score under other green industry types and their corresponding frequency scores in the main business information. Therefore, the accuracy of the matching degree between the main business information and each green industry type is high, based on the first and second frequency scores. This also ensures high reliability of the matching degree between the enterprise tags to be added to the database and the corresponding category labels for the green industry types. Thus, when an evaluation of a project is required, the evaluation rules corresponding to the category of the project to be evaluated can be retrieved from the database based on the category labels to evaluate the project. Because the evaluation rules match the project, the accuracy and efficiency are high. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 One of the flowcharts for the data processing method provided in the embodiments of this application;

[0026] Figure 2 The second flowchart of the data processing method provided in the embodiments of this application;

[0027] Figure 3 for Figure 2 The detailed flowchart of S201 in the document;

[0028] Figure 4 A flowchart of a data processing apparatus provided in an embodiment of this application. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments made by those skilled in the art under the guidance of these embodiments are within the scope of protection of this application.

[0030] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Typically, whether a company is a green enterprise is a key indicator for credit lending, project investment, project operation, and risk management. Therefore, it is necessary to assess whether a company is a green enterprise and to include identified green enterprises in a database. However, the accuracy of the green enterprises currently included in the database is low; furthermore, subsequent project evaluations based on these database-included green enterprises suffer from both low accuracy and low efficiency.

[0032] Based on the aforementioned technical problems, the inventive concept of this application lies in: accurately matching the main business information of enterprises to be included in the database with the green industry types in the green enterprise database; and further, based on the matching degree, the reliability of the enterprise tagging and the corresponding category label of the green industry type is also high. Thus, when it is necessary to evaluate a project, the evaluation rules corresponding to the category of the project to be evaluated can be obtained from the database based on the category label to evaluate the project. Because the evaluation rules match the project to be evaluated, the accuracy and efficiency are high.

[0033] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0034] Please see Figure 1 This application provides a data processing method applied to a server. The method provided in this application includes:

[0035] S101: The server retrieves the main business information of the enterprise to be added to the database.

[0036] For example, a company's main business information can be shown in Table 1 below:

[0037]

[0038] Table 1

[0039] S102: For each green industry type in the pre-configured green industry terminology library, the server determines the first keyword under the green industry type, the first word frequency score appearing in the main business information, and determines the first keyword in the keyword set under other green industry types besides the green industry type, the second word frequency score appearing in the main business information.

[0040] For example, the pre-configured green industry thesaurus can be generated based on the green industry guidance catalog, and each green industry type can be a third-level subdirectory under the green industry guidance catalog.

[0041] Assuming the Green Industry Guidance Catalog includes sub-directories A, B, and C, the service period determines the first word frequency score of each primary keyword in sub-directory A appearing in the main business information, and determines the second word frequency score of each primary keyword in the keyword set composed of sub-directories B and C appearing in the main business information.

[0042] For example, the server determines the first word frequency score of each primary keyword in subdirectory B appearing in the main business information, and determines the second word frequency score of each primary keyword in the keyword set composed of subdirectories A and C appearing in the main business information.

[0043] For example, the server determines the first word frequency score of each primary keyword in subdirectory C appearing in the main business information, and determines the second word frequency score of each primary keyword in the keyword set composed of subdirectories A and B appearing in the main business information.

[0044] In one possible implementation, the server can first deduplicate the first keywords in the keyword sets under other green industry types besides the green industry type; then, it can calculate the second keyword frequency score for each of the first keywords in the keyword sets under other green industry types besides the green industry type, based on their appearance in the main business information. This makes the final second keyword frequency score more reliable.

[0045] In another possible implementation, the server first removes the first keyword appearing in the currently counted green industry type from the keyword set of other green industry types besides the green industry type; then, it calculates the second keyword frequency score of each first keyword in the keyword set of other green industry types besides the green industry type after the removal, based on its appearance in the main business information. This makes the final second keyword frequency score more reliable.

[0046] In addition, to further enhance the reliability of the determined first and second keyword frequency scores, the server can also assign different weights (i.e., importance) to each first keyword.

[0047] Specifically, the server counts the number of enterprise information entries for each green industry type within the green industry thesaurus, corresponding to any first keyword. For example, the server counts the number of enterprise information entries for green enterprises that include the first keyword S within the green industry type.

[0048] Furthermore, the server counts the third number of green enterprises within the first number of green enterprise information that belong to the same green industry type as the first keyword. For example, it counts the third number of green enterprises within the first number of green enterprise information that belong to the same subdirectory C as the first keyword S. Then, the server uses the following formula based on the first number df(s) and the third number dfc(s): Determine the importance p(s, c) of any first keyword in each green industry type within the green industry thesaurus, within that specific green industry type. For example, determine the importance of the first keyword i in subdirectory C within subdirectory C. Finally, the server determines the importance of the third keyword tf in the main business information based on the first keyword i's position within each green industry type. i The importance of the first keyword "i" in each type of green industry. i The frequency score f of the first keyword appearing in the main business information of each green industry type in the pre-defined green industry thesaurus is calculated. C Understandably, this is because determining the first word frequency score f... C The system takes into account the importance of each primary keyword within its respective green industry type, resulting in higher reliability.

[0049] Additionally, the server uses the first keyword "i" from the main business information under other green industry types besides the green industry type as the third keyword frequency "tf". i The importance of the first keyword "i" in other green industry types besides green industry types. i The formula used is: fC -=∑ i∈j tf i *w i Identify the primary keyword under other green industry types besides the green industry type, and the frequency score f of the secondary keyword appearing in the main business information. C -j represents the set of first keywords under other green industry types besides the aforementioned green industry type.

[0050] Assuming the Green Industry Guidance Catalog includes subdirectories A, B, and C, and the current data collection focuses on subdirectory C, the server determines that the first keyword 'i' in subdirectories A and B belongs to the third keyword frequency 'tf' of the main business information. i The importance of the first keyword "i" in subdirectories A and B. i The formula used is: f C -=∑ i∈j tf i *w i Determine the first keyword in subdirectories A and B, and the second keyword frequency score f appearing in the main business information. C -j represents the set of first keywords under other green industry types besides the stated green industry type. Understandably, this is due to the determination of the second word frequency score f. C - It takes into account the importance of each primary keyword in its respective green industry type, making it more reliable.

[0051] S103: The server determines the matching degree between the main business information and each green industry type based on the first word frequency score and the second word frequency score.

[0052] For example, S103 is implemented as follows:

[0053] The server bases the score on the first word frequency f. C Second word frequency score f C - Using the formula: Determine the matching degree P between the main business information and each green industry type; where γ is a set hyperparameter, for example, γ can be equal to 0.01.

[0054] Alternatively, use a formula: Determine the matching degree P between the main business information and each green industry type.

[0055] In determining the aforementioned matching degree, not only the first keyword under the green industry type and its first frequency score appearing in the main business information were considered, but also the second keyword under other green industry types and their second frequency scores appearing in the main business information. Therefore, the accuracy of the matching degree between the main business information and each green industry type is high, based on both the first and second frequency scores.

[0056] S104: The server marks the enterprises to be added to the database with the category label corresponding to the green industry type based on the determined matching degree that is greater than the set threshold.

[0057] Understandably, the higher the match between the main business information of a company to be added to the database and a certain green industry type, the more likely the company belongs to that green industry type. In this way, companies to be added can be labeled with the corresponding category tags for each green industry type, resulting in high accuracy.

[0058] S105: The server adds the enterprises to be added to the preset database, which are tagged with category labels.

[0059] S106: When the server is evaluating a project, it retrieves the evaluation rules corresponding to the category of the project from the database based on the category label in order to evaluate the project.

[0060] For example, if the project to be evaluated is a financial project to determine whether it is a green finance project, when the server is evaluating the project, it uses the category label of the enterprise to be evaluated and the associated green finance evaluation rules. The server then evaluates the main business information of the enterprise to be evaluated according to the green finance evaluation rules to determine whether the financial project is a green finance project.

[0061] For example, the project to be evaluated is the green level of the enterprise to be evaluated. When the server evaluates the project, it uses the category label of the enterprise to be evaluated and the associated green level evaluation rules. The server evaluates the main business information of the enterprise to be evaluated according to the green level evaluation rules to determine the green level of the enterprise to be evaluated, where the green level is light green, medium green or dark green.

[0062] In summary, the data processing method provided in this application not only considers the first keyword under the green industry type and its first word frequency score appearing in the main business information, but also considers the second word frequency score of the first keyword under other green industry types appearing in the main business information. Therefore, the accuracy of the matching degree between the main business information and each green industry type determined based on the first and second word frequency scores is high. Consequently, the reliability of the enterprise tag to be entered into the database and the corresponding category label of the green industry type based on the matching degree is also high. Thus, when it is necessary to evaluate a project, the evaluation rules corresponding to the category of the project to be evaluated can be obtained from the database based on the category label to evaluate the project. Because the evaluation rules match the project to be evaluated, the accuracy and efficiency are high.

[0063] In addition, the embodiments of this application can also optimize the green industry thesaurus, making the content of the green industry thesaurus richer and more reliable.

[0064] Specifically, before S101, such as Figure 2 As shown, the method provided in this application embodiment may further include:

[0065] S201: The server extracts a second keyword from the enterprise information of multiple preset green enterprises that does not belong to the green industry terminology database, but is related to the green industry type in the green industry terminology database.

[0066] S202: The server will add the extracted second keyword to the corresponding green industry type in the green industry thesaurus.

[0067] Since the second keyword is associated with the green industry types in the green industry thesaurus, it means that the second keyword can express the meaning of the green industry types in the green industry thesaurus. In this way, the server will add the extracted second keyword to the corresponding green industry type in the green industry thesaurus, which can make the content of the green industry thesaurus richer and more reliable.

[0068] It should be noted that the process of optimizing the green industry terminology database and the process of matching the enterprise tags to be added to the database with the corresponding category tags for the green industry types are mutually reinforcing and complementary, and can improve the accuracy of each other.

[0069] For example, such as Figure 3 As shown, S201 can be specifically implemented as follows:

[0070] S301: The server counts the number of enterprise information entries for any first keyword in each green industry type of the green industry thesaurus.

[0071] For example, the server counts the first number of enterprise information for green enterprises that include the first keyword S in the green industry type.

[0072] S302: The server counts the second number of enterprise information entries that contain both the first keyword and the second keyword among multiple green enterprise enterprise information entries.

[0073] For example, the server counts a second number of green companies whose information includes both the first keyword S and the second keyword B.

[0074] S303: The server uses the following formula based on the first quantity df(s) and the second quantity df(w, s):

[0075] Determine the probability p(w|s) of the association between the second keyword and the first keyword.

[0076] Understandably, the probability of association between the second keyword and the first keyword determined by the above formula is highly reliable.

[0077] S304: The server calculates the total number of first keywords in any green industry type | S c The probability p(w|s) of any second keyword being associated with each of the first keywords of this green industry type is calculated using the formula... Determine the correlation between the second keyword and the green industry type: rel(w, c).

[0078] Understandably, the reliability of determining the correlation between the second keyword and the type of green industry through the above formula is high.

[0079] Additionally, the correlation can be normalized. The specific normalization method can be: the server uses a formula... The correlation between the second keyword and the green industry type is initially normalized, where v(w, c) is the correlation between the second keyword and the green industry type after initial normalization, and |C| is the number of green industry types. The server calculates the correlation based on the formula. The correlation between the second keyword and this type of green industry was normalized again, where v c (w, c) represents the correlation between the second keyword after re-normalization and the green industry type. The server calculates the correlation based on the formula... Once again, the correlation between the second keyword and this type of green industry was normalized, where τ w，c This represents the correlation between the second keyword after further normalization and the type of green industry. This approach ensures a higher reliability of the final correlation result.

[0080] S304: The server extracts the second keyword with a relevance greater than a set threshold.

[0081] In this way, the reliability of the extracted second keyword is high.

[0082] Please see Figure 4 This application provides a data processing device 400 applied to a server, including: an information acquisition unit 401, used to acquire the main business information of enterprises to be added to the database; a word frequency determination unit 402, used to determine the first keyword of each green industry type in the pre-configured green industry terminology library, the first word frequency score of the main business information, and the second word frequency score of the first keyword of other green industry types; a matching degree determination unit 403, used to determine the matching degree between the main business information and each green industry type based on the first word frequency score and the second word frequency score; a category labeling unit 404, used to label the enterprises to be added to the database with the category label corresponding to the green industry type based on the determined matching degree greater than a set threshold; a data entry unit 405, used to add the enterprises to be added to the database with the category label to a preset database; and a project evaluation unit 406, used to obtain the evaluation rules corresponding to the project to be evaluated from the database based on the category label when evaluating the project to be evaluated.

[0083] In one possible implementation, the word frequency determination unit 402 is specifically used to deduplicate each first keyword in the keyword set under other green industry types besides the green industry type; and to calculate the second word frequency score of each first keyword in the keyword set under other green industry types besides the green industry type when it appears in the main business information.

[0084] In another possible implementation, the word frequency determination unit 402 is specifically used to remove the first keyword appearing in the currently counted green industry type from the keyword set under other green industry types besides the green industry type; and to count the second word frequency score of each of the first keywords in the other green industry types besides the green industry type after removal, in the main business information.

[0085] In one possible implementation, the matching degree determination unit 403 is specifically configured to determine the matching degree based on the first word frequency score f. C Second word frequency score f C - Using the formula:

[0086]

[0087] Determine the matching degree P between the main business information and each green industry type; where γ is a set hyperparameter; or, use the formula:

[0088]

[0089] Determine the matching degree P between the main business information and each green industry type.

[0090] In one possible implementation, the apparatus 400 provided in this application further includes: an importance determination unit, configured to count the first number of enterprise information of green enterprises belonging to any first keyword in each green industry type of the green industry thesaurus; count the third number of enterprise information of green enterprises belonging to the same green industry type as the first keyword among the enterprise information of the first number of green enterprises; and determine the importance determination unit based on the first number df(s) and the third number df(s). c (s), using the formula: Determine the importance p(s,c) of any first keyword in each green industry type of the green industry thesaurus within its respective green industry type.

[0091] The word frequency determination unit 402 is specifically used to determine the third word frequency tf of the main business information in each green industry type based on the first keyword i. i The importance of the first keyword "i" in each type of green industry. i The frequency score f of the first keyword appearing in the main business information of each green industry type in the pre-defined green industry thesaurus is calculated. C According to the first keyword i under other green industry types besides green industry types, which belongs to the third word frequency tf of the main business information, i The importance of the first keyword "i" in other green industry types besides green industry types. i The formula used is: f C -=∑ i∈j tf i *w i Identify the primary keyword under other green industry types besides the green industry type, and the frequency score f of the secondary keyword appearing in the main business information. C -j represents the set of first keywords under other green industry types besides the green industry type.

[0092] In one possible implementation, the apparatus 400 provided in this application embodiment further includes: a lexicon optimization unit, configured to extract a second keyword from the enterprise information of multiple preset green enterprises that does not belong to the green industry lexicon but is associated with the green industry type in the green industry lexicon; and to add the extracted second keyword to the corresponding green industry type in the green industry lexicon.

[0093] In one possible implementation, the lexicon optimization unit is specifically used to count the first number of enterprise information related to any first keyword in each green industry type of the green industry lexicon; to count the second number of enterprise information related to multiple green enterprises that contains both the first keyword and the second keyword; and to use a formula based on the first number df(s) and the second number df(w,s): Determine the probability p(w|s) of the association between the second keyword and the first keyword; based on the total number of first keywords in any green industry type |S c The probability p(w|s) of any second keyword being associated with each of the first keywords of this green industry type is calculated using the formula... Determine the correlation between the second keyword and the green industry type rel(w, c); the server extracts the second keyword with a correlation greater than a set threshold.

[0094] The data entry unit 405 is specifically used to add companies marked with category tags to the preset database when the second keyword in the main business information of the companies to be entered is not included in the preset keyword library. The keyword library includes keywords describing prohibited or eliminated raw materials, technologies, equipment, and products.

[0095] Project evaluation unit 406 is specifically used to evaluate projects under evaluation. Based on the category label of the enterprise under evaluation, it associates the green level evaluation rules with the main business information of the enterprise under evaluation to determine the green level of the enterprise under evaluation. The green level can be light green, medium green, or dark green.

[0096] This application also provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the server to perform the actions described above. Figures 1-3 The methods provided.

[0097] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory including instructions that can be executed by a processor to perform the described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the instructions in this non-transitory computer-readable storage medium are executed by the server's processor, the server is able to perform the described method. Figures 1-3 The method.

[0098] This application also provides a computer program product, including a computer program, which, when executed by a processor, performs the above-described... Figures 1-3 The method.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A data processing method, characterized in that, Applied to a server, the method includes: The server obtains the main business information of the enterprises to be added to the database; The server counts the number of enterprise information entries for any first keyword in each green industry type of the pre-configured green industry thesaurus, and the corresponding green enterprise information. The server counts the third number of green enterprise information that belongs to the same green industry type as the first keyword among the enterprise information of the first number of green enterprises. The server according to the first quantity The third quantity The formula used is: ； Determine the importance of any first keyword in each green industry type of the green industry thesaurus within its respective green industry type. ; For each green industry type in the pre-configured green industry thesaurus, the server determines the third word frequency of the main business information based on the first keyword i in each green industry type. The importance of the first keyword i in each of the green industry types. The first keyword in each green industry type of the pre-defined green industry thesaurus is counted, and its frequency score in the main business information is calculated. And, determine the first keyword under other green industry types besides the aforementioned green industry type, and the second word frequency score of the keyword appearing in the main business information; The server is based on the first word frequency score. and the second word frequency score The formula used is: Determine the matching degree between the main business information and each green industry type. ; in, The hyperparameters are set; Alternatively, use a formula: Determine the matching degree between the main business information and each green industry type. ; The server marks the enterprises to be added to the database with category tags corresponding to the green industry types based on the determined matching degree that is greater than a set threshold. The server will add the enterprises to be added to the database that are tagged with the category label to a preset database; When the server evaluates the project to be evaluated, it retrieves the evaluation rules corresponding to the category of the project to be evaluated from the database according to the category label, so as to evaluate the project to be evaluated. The server determines the first keyword under other green industry types besides the aforementioned green industry type, and the second word frequency score of the keyword appearing in the main business information, including: The server uses the first keyword i from other green industry types besides the aforementioned green industry type, which belongs to the third word frequency of the main business information. The importance of the first keyword i in other green industry types besides the aforementioned green industry types. The formula used is: The first keyword under other green industry types besides the aforementioned green industry type is determined, and the second keyword frequency score appears in the main business information. ,j is the set of first keywords in other green industry types besides the green industry type mentioned above.

2. The method according to claim 1, characterized in that, The determination of the first keyword under other green industry types besides the aforementioned green industry type, and the second word frequency score appearing in the main business information, include: The server removes duplicates from the keyword sets of other green industry types besides the aforementioned green industry type; The server calculates the frequency score of each first keyword in the keyword set of other green industry types besides the green industry type after deduplication, based on the second keyword frequency score of the main business information.

3. The method according to claim 1, characterized in that, The determination of the first keyword under other green industry types besides the aforementioned green industry type, and the second word frequency score appearing in the main business information, include: The server removes the first keyword appearing in the current statistics of green industry types, excluding green industry types. The server calculates the frequency score of each first keyword in the set of green industry types other than green industry types after statistical removal, based on the second keyword frequency score of the main business information.

4. The method according to claim 1, characterized in that, Before the server obtains the main business information of the enterprise to be added to the database, the method further includes: The server extracts second keywords from the enterprise information of multiple preset green enterprises that do not belong to the green industry terminology database, but are associated with the green industry types in the green industry terminology database; The server will extract the second keyword and add it to the corresponding green industry type in the green industry thesaurus.

5. The method according to claim 4, characterized in that, The server extracts second keywords from the enterprise information of multiple preset green enterprises. These keywords are not part of the green industry terminology database, but are associated with green industry types in the database. These include: The server counts the number of enterprise information entries for any first keyword in each green industry type of the green industry thesaurus, and the corresponding green enterprise information. The server counts a second number of enterprise information entries among the enterprise information of multiple green enterprises that contain both the first keyword and the second keyword. The server according to the first quantity The second quantity Formula used: Determine the probability of association between the second keyword and the first keyword. ; The server determines the total number of first keywords in any of the green industry types. The probability of any second keyword being associated with each of the first keywords of the green industry type. Using formulas Determine the correlation between the second keyword and this type of green industry. ; The server extracts the second keyword whose relevance is greater than a set threshold.

6. The method according to claim 5, characterized in that, Before the server extracts the second keyword whose relevance is greater than a set threshold, the method further includes: The server is based on the formula The correlation between the second keyword and this type of green industry was initially normalized, among which, To determine the correlation between the second keyword after preliminary normalization and this type of green industry, The number of green industry types; The server is based on the formula The correlation between the second keyword and this type of green industry was normalized again, whereby... The correlation between the second keyword after re-normalization and this type of green industry; The server is based on the formula The correlation between the second keyword and this type of green industry was normalized again, among which, This represents the correlation between the second keyword after another normalization and the type of green industry.

7. The method according to any one of claims 1-6, characterized in that, The project to be evaluated is the green level of the enterprise being evaluated. When evaluating the project, the evaluation rules corresponding to the category of the project to be evaluated are retrieved from the database based on the category label to evaluate the project, including: When the server evaluates the project to be evaluated, it uses the category label of the enterprise to be evaluated and the associated green level evaluation rules. The server evaluates the main business information of the enterprise to be evaluated according to the green level evaluation rules to determine the green level of the enterprise to be evaluated, wherein the green level is light green, medium green or dark green.

8. A data processing apparatus, characterized in that, Applied to a server, the device includes: The information acquisition unit is used to acquire the main business information of the enterprises to be included in the database. The word frequency determination unit is used to count the first number of green enterprise information belonging to any first keyword in each green industry type of the pre-configured green industry terminology library; to count the third number of green enterprise information belonging to the same green industry type as the first keyword among the first number of green enterprise information; and to determine the third number of green enterprise information belonging to the same green industry type as the first keyword based on the first number. The third quantity , Formula used: ； Determine the importance of any first keyword in each green industry type of the green industry thesaurus within its respective green industry type. ; For each green industry type in the pre-configured green industry thesaurus, the third word frequency of the first keyword i in each green industry type belonging to the main business information is determined. The importance of the first keyword i in each of the green industry types. The first keyword in each green industry type of the pre-defined green industry thesaurus is counted, and its frequency score in the main business information is calculated. And, determine the first keyword under other green industry types besides the aforementioned green industry type, and the second word frequency score of the keyword appearing in the main business information; The matching degree determination unit is used to determine the matching degree based on the first word frequency score. and the second word frequency score , Formula used: Determine the matching degree between the main business information and each green industry type. ; in, The hyperparameters are set; Alternatively, use a formula: Determine the matching degree between the main business information and each green industry type. ; The category labeling unit, based on the determined green industry type corresponding to a matching degree greater than a set threshold, labels the enterprise to be added to the database with the category label corresponding to the green industry type. The data entry unit is used to add enterprises marked with the category labels to a preset database. The project evaluation unit is also used to, when evaluating a project, retrieve evaluation rules corresponding to the category of the project from the database based on the category label, so as to evaluate the project. Specifically, when determining the second word frequency score, the word frequency determination unit is used to determine the third word frequency of the main business information based on the first keyword i belonging to the main business information under other green industry types besides the aforementioned green industry type. The importance of the first keyword i in other green industry types besides the aforementioned green industry types. The formula used is: The first keyword under other green industry types besides the aforementioned green industry type is determined, and the second keyword frequency score appears in the main business information. ,j is the set of first keywords in other green industry types besides the green industry type mentioned above.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the computer to perform the method as described in any one of claims 1 to 7.

10. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the server to perform the method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes a computer program that, when run, causes a computer to perform the method as described in any one of claims 1 to 7.

Images