Data processing method and related device

Abstract

The present invention discloses a data processing method and related devices, wherein the method comprises: after receiving a valuation request for a target company, obtaining multiple comparable companies corresponding to the target company; calculating the similarity between the target company and each comparable company through a similarity model based on standardized Euclidean distance; according to the level of the similarity, calling a relative valuation model, performing weighted calculation on the data of each comparable company, and obtaining the relative valuation of the target company, the higher the similarity, the higher the weight of the comparable company, and the data are financial characteristic data and other quantitative characteristic data related to the company valuation. The present invention can solve the problem of poor accuracy of the comparable company valuation method in the prior art.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular, relates to a data processing method, device, equipment, storage medium and computer program product. Background Art

[0002] At present, when evaluating the value of a company, there are mainly asset-based valuation method, income valuation method and comparable company valuation method. Among them, the comparable company valuation method occupies an important position in the existing company value evaluation system due to its high feasibility. However, the valuation accuracy of the existing comparable company valuation method is relatively poor. Summary of the invention

[0003] The embodiment of the present invention provides a data processing method and related devices, which can solve the problem of poor accuracy of comparable company valuation methods in the prior art.

[0004] In a first aspect, a data processing method is provided, comprising:

[0005] After receiving a valuation request for a target company, obtaining a plurality of comparable companies corresponding to the target company;

[0006] Based on the standardized Euclidean distance, the similarity between the target company and each comparable company is calculated by a similarity model;

[0007] According to the degree of similarity, the relative valuation model is called to perform weighted calculation on the data of each comparable company to obtain the relative valuation of the target company. The higher the similarity, the higher the weight of the comparable company. The data are financial characteristic data and other quantitative characteristic data related to the company's valuation.

[0008] Optionally, the similarity between the target company and each comparable company is calculated by a similarity model based on the standardized Euclidean distance, including:

[0009] Standardizing first data of each comparable company and second data of the target company, the data including the first data, the first data corresponding to the second data;

[0010] Using the standardized second data and the standardized first data of each comparable company as inputs of a distance operator in the similarity model to run the distance operator to obtain the standardized Euclidean distance between the target company and each comparable company;

[0011] The similarity corresponding to the standardized Euclidean distance is obtained through a preset mapping between distance and similarity in the similarity model.

[0012] Optionally, calling the relative valuation model to perform weighted calculation on the data of each comparable company to obtain the relative valuation of the target company includes:

[0013] Analyze and process the data of each comparable company to determine the relative valuation model suitable for the target company;

[0014] The interface of the adapted relative valuation model is called, and the data of each comparable company is weightedly calculated according to the weight of each comparable company to obtain the relative valuation of the target company.

[0015] Optionally, obtaining comparable companies corresponding to the target company includes:

[0016] Obtain the industry category of the target company;

[0017] Reference data matching the industry category is screened out from a preset database, and the companies corresponding to the reference data are comparable companies.

[0018] Optionally, the industry category includes a primary industry category and a subcategory under the primary industry category; and the step of screening out reference data matching the industry category from a preset database includes:

[0019] Acquire first reference data matching the subcategory in the preset database;

[0020] When the number of companies corresponding to the first reference data is greater than or equal to a first preset threshold, the companies corresponding to the first reference data are the comparable companies;

[0021] When the number of companies corresponding to the first reference data is less than a first preset threshold, second reference data matching the primary industry category in the preset database is obtained; the companies corresponding to the second reference data are the comparable companies.

[0022] Optionally, after obtaining the second reference data matching the primary industry category from the preset database, the method further includes:

[0023] When the number of companies corresponding to the second reference data is greater than or equal to a second preset threshold, the companies corresponding to the second reference data are the comparable companies;

[0024] When the number of companies corresponding to the second reference data is less than a second preset threshold, third reference data matching the comprehensive industry is obtained from a preset database; the companies matched by the third reference data and the companies matched by the second reference data are the comparable companies.

[0025] Optionally, after obtaining a plurality of comparable companies corresponding to the target company, the method further includes:

[0026] Perform data cleaning to screen out comparable companies with abnormal data.

[0027] In a second aspect, a data processing device is provided, comprising:

[0028] An acquisition module, configured to acquire a plurality of comparable companies corresponding to the target company after receiving a valuation request for the target company;

[0029] A similarity calculation module, used for calculating the similarity between the target company and each comparable company through a similarity model based on the standardized Euclidean distance;

[0030] The weighted calculation module is used to call the relative valuation model according to the degree of similarity, perform weighted calculation on the data of each comparable company, and obtain the relative valuation of the target company. The higher the similarity, the higher the weight of the comparable company. The data are financial characteristic data and other quantitative characteristic data related to the company's valuation.

[0031] In a third aspect, a data processing device is provided, the data processing device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, the computer program executing the data processing method of the first aspect.

[0032] According to a fourth aspect, a computer storage medium is provided, which implements the data processing method according to the first aspect when executed by a processor.

[0033] According to a fifth aspect, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the data processing method according to the first aspect is implemented.

[0034] Compared with the prior art, the data processing method and related device provided in the embodiment of the present application obtain multiple comparable companies corresponding to the target company after receiving a valuation request for the target company; the relative valuation of the target company is obtained by the calculation of the comparable companies, and because it is based on the standardized Euclidean distance, the similarity between the target company and each comparable company is calculated through a similarity model, and after the similarity calculation, the weighted calculation of the relative valuation is also realized according to the similarity. With such a setting, the relative valuation of the target company finally obtained is weightedly calculated according to the similarity obtained by the standardized Euclidean distance, which can greatly improve the accuracy of the valuation, thereby solving the problem of poor accuracy of the comparable company valuation method in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 It is a schematic flow chart of an embodiment of a data processing method of the present invention.

[0037] Figure 2 It is a detailed flow chart of S110 in an embodiment of the data processing method of the present invention.

[0038] Figure 3 It is a detailed flow chart of S130 in an embodiment of the data processing method of the present invention.

[0039] Figure 4 is a schematic block diagram of a data processing device according to an embodiment of the present invention.

[0040] Figure 5 is a schematic block diagram of a data processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The features and exemplary embodiments of various aspects of the application will be described in detail below. In the detailed description below, many specific details are proposed to provide a comprehensive understanding of the application. However, it is obvious to those skilled in the art that the application can be implemented when some details in these specific details are not needed. The following description of the embodiments is only to provide a better understanding of the application by illustrating the example of the application.

[0042] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The embodiments will be described in detail below in conjunction with the accompanying drawings.

[0043] In addition, it should be noted that the acquisition, storage, use, and processing of data in the following embodiments of this application are in compliance with the relevant provisions of national laws and regulations.

[0044] Company valuation refers to the evaluation of the intrinsic value of a company by focusing on the company itself. The actual assets and profitability of the company determine the intrinsic value of the company. Accurate company valuation is the basis for pricing various transactions. As described in the background technology, current company valuation mainly includes asset-based valuation method, income valuation method and comparable company valuation method.

[0045] Among them, the asset-based valuation method refers to a method of determining the value of the subject of evaluation by reasonably evaluating all the assets and liabilities of the company. The income valuation method refers to a method of determining the value of the subject of evaluation by capitalizing or discounting the company's expected income. The comparable company valuation method refers to predicting the value of the target company by referring to the market value of comparable companies in the market, which belongs to relative value evaluation.

[0046] It should be noted that although the comparable company valuation method has a wider data acquisition channel than the asset-based valuation method and the income valuation method, which improves the feasibility of using the comparable company valuation method, the comparable company valuation method used in the existing technology mainly uses the recent transaction prices of comparable companies in the trading market to predict the target company through direct comparison. This method is less accurate than other methods.

[0047] In order to solve the above problems, the present application provides a data processing method. Figure 1 In an optional embodiment, the method includes:

[0048] S110, after receiving a valuation request for a target company, obtaining a plurality of comparable companies corresponding to the target company.

[0049] S120, calculating the similarity between the target company and each comparable company through a similarity model based on the standardized Euclidean distance;

[0050] S130, according to the similarity, call the relative valuation model, perform weighted calculation on the data of each comparable company, and obtain the relative valuation of the target company. The higher the similarity, the higher the weight of the comparable company. The data are financial characteristic data and other quantitative characteristic data related to the company valuation.

[0051] The embodiment of the present application obtains multiple comparable companies corresponding to the target company after receiving a valuation request for the target company; the relative valuation of the target company is obtained by calculating the comparable companies, and because it is based on the standardized Euclidean distance, the similarity between the target company and each comparable company is calculated through a similarity model, and after the similarity calculation, a weighted calculation of the relative valuation is also achieved based on the similarity. With such a setting, the relative valuation of the target company finally obtained is weightedly calculated based on the similarity obtained by the standardized Euclidean distance, which can greatly improve the accuracy of the valuation, thereby solving the problem of poor accuracy of the comparable company valuation method in the prior art.

[0052] The above data processing method can be applied to an electronic device for company valuation, for example, the electronic device can be a server or a computer device. For example, a user can select a display control corresponding to a target company through a touch panel of the server, and then initiate a valuation request for the target company.

[0053] In S110, the target company is the target company to be valued, and correspondingly, the comparable company is a company that can participate in the calculation and prediction of the target company's valuation and provide important reference value for the target company's valuation. In this application, the similarity between the comparable company and the target company in terms of financial characteristics, core business, growth drivers, and risk factors can be evaluated based on the calculation of similarity.

[0054] It should be noted that each target company may have multiple comparable companies, and the comparable companies corresponding to different target companies are usually not completely consistent. In an optional example, the matching degree between the target company and all companies can be calculated, and then the comparable companies can be determined based on the matching degree between the target company and each company, and the above matching degree can include similarity. The target company's affiliated companies can also be set as comparable companies, or comparable companies can be determined based on the industry to which the target company belongs.

[0055] See also Figure 2 Taking the target company's industry as an example, obtaining comparable companies corresponding to the target company in S110 may include:

[0056] S211, obtaining the industry category of the target company;

[0057] S212, filtering out reference data matching the industry category from a preset database, wherein the companies corresponding to the reference data are comparable companies.

[0058] Among them, industry category can refer to the industry category or market category in which the company is located, and the industry category can be divided according to international or national standards. Industry categories can also be divided into many sub-industry categories (hereinafter referred to as sub-categories or sub-industries), which are sub-industries under the same industry category. The industry in which a company is located can provide a lot of information about the company, such as core drivers, risks and opportunities.

[0059] The preset database can store reference data of all available companies, which can include basic information, financial data, etc. of the available companies, where basic data can include industry category, product category, region, R&D status, etc. Financial data can include asset data, liability data, profit data, etc.

[0060] Exemplarily, the process of obtaining the comparable companies matching the target company can be to obtain the national standard industry (i.e., the industry category of the target company) in which the target company is located, which corresponds to an industry code in the preset database, and then find reference data containing the industry code from the preset database, and the company corresponding to the reference data can be used as the screened comparable company. The industry code can be a combination of characters and / or numbers, for example, industry code A is X1 industry, B is X2 industry, and C is X3 industry.

[0061] In another optional example, in order to select enough comparable company samples, based on the above, the industry categories may include primary industry categories and subcategories under the primary industry categories. In this case, the step S220 may include:

[0062] The first reference data matching the subcategory in the preset database is obtained; when the number of companies corresponding to the first reference data is greater than or equal to a first preset threshold, the company corresponding to the first reference data is the comparable company. When the number of companies corresponding to the first reference data is less than the first preset threshold, the second reference data matching the primary industry category in the preset database is obtained; the company corresponding to the second reference data is the comparable company.

[0063] In this example, priority is given to specifying the subcategories in the industry categories for matching optional companies. However, since this application requires a sufficient number of comparable company samples when performing subsequent similarity and relative valuation calculations, a first preset threshold can be set on this basis to confirm whether the sample size of companies matched based on sub-industry screening is sufficient. When it is greater than or equal to the first preset threshold, the company corresponding to the first reference data based on sub-category matching is directly used as a comparable company.

[0064] It is understandable that the total number of enterprises in some sub-industries is actually small. In this case, if there are target companies in these sub-industries that need to be valued, the number of enterprises in the same sub-industry is not enough to support the accurate valuation of the target companies. At this time, the industry category can be expanded, that is, comparable companies can be obtained based on the primary industry category of the sub-industry, thereby ensuring that a sufficient sample size of comparable companies can be selected, thereby ensuring the accuracy of the relative valuation calculation of the target company.

[0065] Since there may be a situation where the number of companies under the first-level industry category is too small, in this case, the number of comparable companies corresponding to the target company under this category will also be small. Therefore, on this basis, after obtaining the second reference data matching the first-level industry category in the preset database, it is possible to determine whether the number of companies corresponding to the second reference data matching the first-level industry category is greater than or equal to the second preset threshold.

[0066] Among them, when the number of companies corresponding to the second reference data is greater than or equal to the second preset threshold, the companies corresponding to the second reference data are the comparable companies; when the number of companies corresponding to the second reference data is less than the second preset threshold, third reference data with comprehensive industry matching is obtained from the preset database; the companies matched by the third reference data and the companies matched by the second reference data are the comparable companies.

[0067] The numbers of the first preset threshold and the second preset threshold can be set consistently, for example, both are 10, or can be set differently. Comprehensive industries refer to industries that are relatively complex and diverse, and companies in the industry are in diversified operations. Companies in comprehensive industries can represent the general situation of the entire industry and can provide a supplement to the number of comparable companies when there are insufficient comparable companies in the same industry category.

[0068] In the above example, the screening settings from fine to coarse by industry category can help screen out suitable comparable companies for the target company, which is conducive to the subsequent reference for the reasonable valuation of the target company.

[0069] After obtaining the comparable companies corresponding to the target company, data cleaning can be performed on the optional companies to screen out the comparable companies containing abnormal data. Abnormal data may include missing or abnormal data that will affect the accuracy of the model valuation.

[0070] For example, comparable companies with average profits less than M in the reference data can be eliminated, for example, M=1; comparable companies in the top N% of the price-earnings ratio and price-to-book ratio can be eliminated, for example, N% is 5%. By screening out comparable companies with abnormal data, the accuracy of the model valuation process can be prevented from being affected.

[0071] In S120, the similarity can be calculated using the standardized Euclidean distance, and the calculation of the similarity requires data comparison between each comparable company and the target company. In this example, the Euclidean distance calculation includes the first data of each comparable company and the second data of the target company, wherein the first data corresponds to the second data, for example, the data types may be consistent, thereby facilitating the processing and calculation of the similarity.

[0072] The first data of each comparable company used above can be obtained by screening the data involved in each comparable company, and can be at least one of them. In addition, the time dimension of the data can also be limited, such as data in the past five years or the past ten years.

[0073] The data of each comparable company may be indicator data related to the company's valuation. These indicator data are quantifiable characteristic data, for example, may include financial characteristic data and other quantitative characteristic data.

[0074] Among them, other quantitative characteristic data may include, for example, installed capacity, energy storage capacity, etc. The financial characteristic data of each comparable company may include at least one of enterprise assets, owner's equity, asset-liability ratio, return on total assets, net profit, main business income growth rate, and return on net assets. Exemplarily, the first data may be set in accordance with the financial characteristic data.

[0075] The above-mentioned standardized Euclidean distance is an improvement on the ordinary Euclidean distance. The idea of ​​the standardized Euclidean distance is that the distribution of components in each dimension of the data is different. The data needs to be standardized in advance so that the components in each dimension are standardized to have equal mean and variance.

[0076] When calculating the similarity between the comparable companies and the target company in this application, the first data of each comparable company for each of the above dimensions and the second data of the target company can be standardized to have equal mean and variance when converted into vector representation.

[0077] When the first data of each comparable company is input together with the second data of the target company into the distance operator of the similarity model for calculation, it is actually a standardized Euclidean distance calculation between two n-dimensional vectors a (x11, x12, ..., x1n) (i.e. the vector converted from the first data of any comparable company) and b (x21, x22, ..., x2n) (i.e. the vector converted from the second data of the target company), wherein the distance operator can refer to the following formula (1) for calculation and operation.

[0078]

[0079] Among them, n is the data dimension, S is the standard deviation, and d is the standardized Euclidean distance.

[0080] It can be understood that the standardized Euclidean distance can actually reflect the degree of similarity between two vectors. In this application, it can reflect the degree of similarity between the comparable company and the target company. The smaller the standardized Euclidean distance of the data feature vectors corresponding to various data dimensions between the target company and the comparable company, the higher the similarity. According to this rule, a preset mapping of distance and similarity can be set in the similarity model in advance. When the standardized Euclidean distance is obtained, the similarity between the target company and the comparable company can be found according to the preset mapping.

[0081] By introducing the standardized Euclidean distance combined with the similarity model, the similarity between the target company and the comparable companies can be obtained based on data processing operations.

[0082] In S130 , weights may be assigned to comparable companies based on the calculated similarities and according to the degree of similarity. The higher the similarity, the higher the weight value of the comparable company.

[0083] In an optional example, the relative valuation model can be configured specifically according to the different characteristics of the target company. Figure 3 , S130 may include:

[0084] S331, analyzing and processing the data of each comparable company to determine the relative valuation model suitable for the target company;

[0085] S332, calling the adapted interface of the relative valuation model, performing weighted calculation on the data of each comparable company according to the weight of each comparable company, and obtaining the relative valuation of the target company.

[0086] The target company's data is analyzed and processed, mainly to analyze and obtain the target company's corporate development tendency. Different development tendencies can be configured with different relative valuation models.

[0087] For example, if the analysis shows that the target company is a relatively mature company, the first relative valuation model can be used; if the analysis shows that the target company is an investment and research-driven science and technology company, the second relative valuation model can be used; if the analysis shows that the target company is a company with a high turnover rate, the third relative valuation model can be used.

[0088] After each relative valuation model is constructed, a corresponding interface can be set for each relative valuation model. When in use, the model can be used to implement valuation operations by calling the interface.

[0089] Specifically, when calculating the relative valuation model, the data of various comparable companies are referenced. At the same time, the weight of each comparable company is biased and is determined based on the similarity between the comparable company and the target company. By weighting with different weights, the calculation of relative valuation is more biased, which can improve the accuracy of relative valuation.

[0090] Combined with the above Figures 1 to 3 , describes in detail the data processing method of the embodiment of the present application, and will be combined with Figure 4 , describes in detail the data processing device of an embodiment of the present application.

[0091] See also Figure 4 In one embodiment, the data processing device may include:

[0092] An acquisition module 410 is used to acquire a plurality of comparable companies corresponding to the target company after receiving a valuation request for the target company;

[0093] A similarity calculation module 420 is used to calculate the similarity between the target company and each comparable company through a similarity model based on the standardized Euclidean distance;

[0094] The weighted calculation module 430 is used to call the relative valuation model according to the similarity, perform weighted calculation on the data of each comparable company, and obtain the relative valuation of the target company. The higher the similarity, the higher the weight of the comparable company. The data are financial characteristic data and other quantitative characteristic data related to the company valuation.

[0095] In an optional example, the similarity calculation module may include:

[0096] a processing unit, configured to perform standardization processing on first data of each comparable company and second data of the target company, wherein the data includes the first data, and the first data corresponds to the second data;

[0097] an operating unit, configured to use the standardized second data and the standardized first data of each comparable company as inputs of a distance operator in the similarity model to operate the distance operator to obtain the standardized Euclidean distance between the target company and each comparable company;

[0098] The acquisition unit is used to acquire the similarity corresponding to the standardized Euclidean distance through a preset mapping between distance and similarity in the similarity model.

[0099] In another optional example, the weighted calculation module may include:

[0100] A determination unit, configured to parse and process the data of each comparable company to determine the relative valuation model suitable for the target company;

[0101] A calling unit is used to call the interface of the adapted relative valuation model, perform weighted calculation on the data of each comparable company according to the weight of each comparable company, and obtain the relative valuation of the target company.

[0102] In yet another optional example, the acquisition module may include:

[0103] An acquisition unit, used for acquiring the industry category of the target company;

[0104] The screening unit is used to screen out reference data matching the industry category from a preset database, and the companies corresponding to the reference data are comparable companies.

[0105] In yet another optional example, the industry category includes a primary industry category and a subcategory under the primary industry category; and the screening unit may include:

[0106] An acquisition subunit, configured to acquire first reference data matching the subcategory in the preset database;

[0107] A subunit is set, for when the number of companies corresponding to the first reference data is greater than or equal to a first preset threshold, the companies corresponding to the first reference data are the comparable companies;

[0108] The acquisition subunit is also used to obtain second reference data matching the primary industry category in the preset database when the number of companies corresponding to the first reference data is less than a first preset threshold; the company corresponding to the second reference data is the comparable company.

[0109] In yet another optional example, a subunit is provided, further configured to, when the number of companies corresponding to the second reference data is greater than or equal to a second preset threshold, the companies corresponding to the second reference data are the comparable companies;

[0110] The acquisition subunit is also used to obtain third reference data matching the comprehensive industry from a preset database when the number of companies corresponding to the second reference data is less than a second preset threshold; the companies matching the third reference data and the companies matching the second reference data are the comparable companies.

[0111] In yet another optional example, the device further includes:

[0112] The screening module is used for data cleaning to screen out comparable companies with abnormal data.

[0113] Figure 5 The hardware structure diagram of the data processing device provided in the embodiment of the present application is shown. The data processing device may include a processor 501 and a memory 502 storing computer program instructions.

[0114] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0115] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0116] The memory 502 may include a read-only memory (ROM), a flash memory device, a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory 502 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to the above aspects of the present disclosure.

[0117] The processor 501 implements any one of the data processing methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .

[0118] In one example, the data processing device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0119] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0120] Bus 510 includes hardware, software or both, and the parts of data processing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0121] The data processing device can be based on the data processing method to achieve the combination Figures 1 to 4 The data processing method and device described.

[0122] In addition, in combination with the data processing method in the above embodiments, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the data processing methods in the above embodiments is implemented.

[0123] In addition, an embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0124] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0125] It should be understood that in the embodiment of the present application, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0126] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A data processing method, characterized in that: include: After receiving a valuation request for a target company, obtaining a plurality of comparable companies corresponding to the target company; Based on the standardized Euclidean distance, the similarity between the target company and each comparable company is calculated by a similarity model; According to the similarity, the relative valuation model is called to perform weighted calculation on the data of each comparable company to obtain the relative valuation of the target company. The higher the similarity, the higher the weight of the comparable company. The data are financial characteristic data and other quantitative characteristic data related to the company valuation; The relative valuation model is called to perform weighted calculation on the data of each comparable company to obtain the relative valuation of the target company, including: Analyze the data of each comparable company to determine the relative valuation model suitable for the target company, wherein the analysis is used to analyze and obtain the corporate development tendency of the target company, and different relative valuation models are configured accordingly for different development tendencies; The interface of the adapted relative valuation model is called, and the data of each comparable company is weightedly calculated according to the weight of each comparable company to obtain the relative valuation of the target company.

2. The method according to claim 1, characterized in that The similarity between the target company and each comparable company is calculated by a similarity model based on the standardized Euclidean distance, including: Standardizing first data of each comparable company and second data of the target company, the data including the first data, the first data corresponding to the second data; Using the standardized second data and the standardized first data of each comparable company as inputs of a distance operator in the similarity model to run the distance operator to obtain the standardized Euclidean distance between the target company and each comparable company; The similarity corresponding to the standardized Euclidean distance is obtained through a preset mapping between distance and similarity in the similarity model.

3. The method according to claim 1 or 2, characterized in that: The obtaining of comparable companies corresponding to the target company includes: Obtain the industry category of the target company; Reference data matching the industry category is screened out from a preset database, and the companies corresponding to the reference data are comparable companies.

4. The method according to claim 3, characterized in that The industry categories include primary industry categories and subcategories under the primary industry categories; The step of screening out reference data matching the industry category from a preset database includes: Acquire first reference data matching the subcategory in the preset database; When the number of companies corresponding to the first reference data is greater than or equal to a first preset threshold, the companies corresponding to the first reference data are the comparable companies; When the number of companies corresponding to the first reference data is less than a first preset threshold, second reference data matching the primary industry category in the preset database is obtained; the companies corresponding to the second reference data are the comparable companies.

5. The method according to claim 4, characterized in that After obtaining the second reference data matching the primary industry category in the preset database, the method further includes: When the number of companies corresponding to the second reference data is greater than or equal to a second preset threshold, the companies corresponding to the second reference data are the comparable companies; When the number of companies corresponding to the second reference data is less than a second preset threshold, third reference data matching the comprehensive industry is obtained from a preset database; the companies matched by the third reference data and the companies matched by the second reference data are the comparable companies.

6. The method according to claim 1, characterized in that After obtaining a plurality of comparable companies corresponding to the target company, the method further includes: Perform data cleaning to screen out comparable companies with abnormal data.

7. A data processing device, characterized in that: The device comprises: An acquisition module, configured to acquire a plurality of comparable companies corresponding to the target company after receiving a valuation request for the target company; A similarity calculation module, used for calculating the similarity between the target company and each comparable company through a similarity model based on the standardized Euclidean distance; A weighted calculation module is used to call the relative valuation model according to the similarity, perform weighted calculation on the data of each comparable company, and obtain the relative valuation of the target company. The higher the similarity, the higher the weight of the comparable company. The data are financial characteristic data and other quantitative characteristic data related to the company valuation; The weighted calculation module comprises: A determination unit, configured to perform parsing processing on the data of each comparable company to determine the relative valuation model adapted for the target company, wherein the parsing processing is used to parse and obtain the corporate development tendency of the target company, and different relative valuation models are configured corresponding to different development tendencies; A calling unit is used to call the interface of the adapted relative valuation model, perform weighted calculation on the data of each comparable company according to the weight of each comparable company, and obtain the relative valuation of the target company.

8. A data processing device, characterized in that: The data processing device comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the computer program executes the data processing method according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that When the computer storage medium is executed by a processor, the data processing method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the data processing method according to any one of claims 1 to 6 are implemented.

Images