Enterprise evaluation method, electronic device, storage medium and program product

Abstract

The embodiment of the invention provides an enterprise evaluation method, electronic equipment, a storage medium and a program product, and relates to the field of financial science and technology. The method comprises the steps that first multi-source data of a target enterprise and second multi-source data of a comparison enterprise are determined, the first multi-source data are associated with the operation state of the target enterprise, the business types of the comparison enterprise and the target enterprise are the same, and the business range coverage of the comparison enterprise and the target enterprise is larger than a preset threshold value; estimating an object produced by the target enterprise based on the first multi-source data and the second multi-source data to obtain a first object value corresponding to the target enterprise; and generating an analysis and evaluation report of the target enterprise based on the first object value. According to the method, the enterprise evaluation efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of financial technology, and in particular to an enterprise evaluation method, an electronic device, a storage medium and a program product. BACKGROUND

[0002] Under the background of the deep integration of the current digital economy and the financial market, financial institutions have an increasingly urgent demand for accurate evaluation of the operational quality and development potential of enterprises.

[0003] In the prior art, subjective evaluation of target enterprises is mainly relied on manual work.

[0004] However, manual work is easily affected by subjective experience and cognitive bias, and the efficiency of evaluating the value of an enterprise is low. SUMMARY

[0005] The present application provides an enterprise evaluation method, an electronic device, a storage medium and a program product to solve the technical problem that manual work is easily affected by subjective experience and cognitive bias, and the efficiency of evaluating the value of an enterprise is low.

[0006] In a first aspect, the present application provides an enterprise evaluation method, comprising:

[0007] determining first multi-source data of a target enterprise and second multi-source data of a comparison enterprise, the first multi-source data being associated with the operational status of the target enterprise, the comparison enterprise having the same business type as the target enterprise, and the business range coverage of the comparison enterprise being greater than a preset threshold value than that of the target enterprise;

[0008] estimating an object produced by the target enterprise based on the first multi-source data and the second multi-source data to obtain a first object value corresponding to the target enterprise;

[0009] generating an analysis and evaluation report of the target enterprise based on the first object value.

[0010] In a second aspect, the present application provides an enterprise evaluation device, comprising:

[0011] an acquisition module configured to determine first multi-source data of a target enterprise and second multi-source data of a comparison enterprise, the first multi-source data being associated with the operational status of the target enterprise, the comparison enterprise having the same business type as the target enterprise, and the business range coverage of the comparison enterprise being greater than a preset threshold value than that of the target enterprise;

[0012] a processing module configured to estimate an object produced by the target enterprise based on the first multi-source data and the second multi-source data to obtain a first object value corresponding to the target enterprise;

[0013] a generation module configured to generate an analysis and evaluation report of the target enterprise based on the first object value.

[0014] In a third aspect, an electronic device is provided, comprising: a memory, a processor;

[0015] The memory stores computer-executable instructions.

[0016] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect.

[0017] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the first aspect and / or various possible implementation manners of the first aspect.

[0018] In a fifth aspect, a computer program product is provided, comprising a computer program. When the computer program is executed by a processor, the computer program implements the first aspect and / or various possible implementation manners of the first aspect.

[0019] The enterprise evaluation method, the electronic device, the storage medium, and the program product provided by the present application clearly indicate that the first and second multi-source data are associated with the operation state, and the quantification filtering condition of the same business type and coverage exceeding the preset threshold is used to replace the experience judgment of manual evaluation, thereby clearly defining the boundary for data collection and significantly improving the processing efficiency in the early stage of evaluation. The first and second multi-source data are used as the estimation basis, and the quantification characteristics of the double-end data enable the estimation process to rely on data processing tools to realize automatic operation, thereby significantly improving the efficiency of the core link of evaluation. The quantified first object value is used as the core of the report, and the standardized output can be realized by relying on the report template. Compared with manual evaluation, the enterprise evaluation efficiency is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0021] Figure 1 Flowchart of the enterprise evaluation method provided by the embodiments of the present application Figure One

[0022] Figure 2 Flowchart of the enterprise evaluation method provided by the embodiments of the present application Figure Two

[0023] Figure 3 Structure diagram of the enterprise evaluation device provided by the embodiments of the present application

[0024] Figure 4 Structure diagram of the electronic device provided by the embodiments of the present application ​​

[0025] The specific embodiments of the application have been shown and described in the above drawings and text. These drawings and text are not meant to limit the scope of the inventive concept in any way but are merely meant to illustrate the inventive concept to one of ordinary skill in the art by reference to a particular embodiment. DETAILED DESCRIPTION

[0026] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same reference numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments are not meant to represent all embodiments consistent with the application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the application as detailed in the appended claims.

[0027] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards of relevant countries and regions, necessary security measures are taken, public order and good customs are not violated, and appropriate operation portals are provided for users to choose authorization or refusal.

[0028] And the present application involves big data analysis of user information (including but not limited to personal biological characteristics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and uses artificial intelligence technology for automatic decision-making, and makes technical solutions based on automatic decision-making results that have a significant impact on personal rights and interests, provides corresponding operation portals for users to choose to agree or refuse automatic decision-making results; if the user chooses to refuse, the expert decision-making process is entered.

[0029] It should be noted that the enterprise evaluation method, electronic device, storage medium and program product provided by the present application can be used in the field of financial technology, and can also be used in any field other than financial technology. The application field of the enterprise evaluation method, electronic device, storage medium and program product in the present application is not limited.

[0030] To solve the technical problems of the above-mentioned artificial susceptibility to subjective experience, cognitive bias, and low efficiency of enterprise value evaluation, the following technical concept is proposed: by establishing a scientific data collection and reference system, replacing experience judgment with objective data correlation analysis, realizing accurate estimation of enterprise core value and efficient output of evaluation results, and ultimately achieving the core goal of de-subjectification of the evaluation process and significant improvement of evaluation efficiency, a systematic solution with precision and efficiency is provided for enterprise evaluation in specific fields.

[0031] The technical solutions of the present application and how the technical solutions of the present application solve the above-mentioned technical problems will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes may not be described again in some examples. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0032] Figure 1 Flowchart of the enterprise evaluation method provided by the embodiments of the present application Figure One The enterprise evaluation method provided by the embodiments of the present application is applied to any electronic device. As shown in Figure 1 The method comprises the following steps.

[0033] S101, determine the first multi-source data of the target enterprise and the second multi-source data of the comparison enterprise, the first multi-source data is associated with the operation state of the target enterprise, the comparison enterprise has the same business type as the target enterprise, and the business range coverage of the comparison enterprise is greater than a preset threshold.

[0034] The target enterprise refers to the core object of the evaluation work, which is usually the financing subject, the credit object or the investment target enterprise focused by the financial institutions (such as banks, securities companies) and investment institutions, and its operation state and value need to be quantitatively evaluated by scientific methods.

[0035] The comparison enterprise is a reference benchmark for the evaluation target enterprise, which needs to meet the two core conditions of "business type homology" and "high matching of business range". In the financial technology scene, it is usually the head enterprise, benchmark enterprise or same-scale competitor enterprise in the target enterprise's own sub-track (such as inclusive financial technology, supply chain financial technology).

[0036] The first multi-source data / second multi-source data is the core support for financial technology evaluation, covering structured and unstructured data. The first multi-source data is for the target enterprise, and the second multi-source data is for the comparison enterprise, which specifically includes: enterprise business information, financial statement data (revenue, profit, cash flow, etc.), core business data (transaction size, customer activity, bad debt rate, etc.), credit record, compliance, public opinion data (industry evaluation, regulatory information), and industry benchmark data provided by third-party data platforms, etc. All data are directly related to the operation state of the enterprise.

[0037] Business scope coverage is a quantitative indicator that measures the degree of overlap between the business of the comparison company and the target company. Calculation dimensions include service area, target customer group, core product / service types, and revenue composition percentage. In the fintech field, this indicator requires precise matching. For example, for a target company focusing on online lending to micro and small enterprises, comparison companies should exclude fintech companies primarily engaged in corporate banking for large enterprises.

[0038] The preset threshold is the minimum standard for business scope coverage set according to the assessment scenario (such as financing assessment, risk rating). It is usually determined through industry data statistics and expert demonstration, and is generally set at no less than 70% to ensure the reference value of the compared companies and avoid assessment deviation due to excessive differences in business.

[0039] Specifically, the target enterprise for this assessment should be clearly identified. Using fintech data collection tools (such as API calls, compliant data crawlers, and third-party data cooperation platforms), comprehensive data related to the enterprise's operational status should be acquired. The compliance and completeness of the data must be ensured. For example, credit data should be obtained through enterprise credit reporting systems, transaction flow data should be extracted through business system interfaces, and industry evaluation data should be captured through public opinion monitoring tools. Ultimately, a multi-source data set for the target enterprise should be formed.

[0040] Using the target company's business type as the core screening criterion, a preliminary scope of companies in the same industry is defined. Subsequently, by quantitatively calculating the coverage of business scope (e.g., constructing a matching algorithm based on dimensions such as customer base and product type), companies with coverage exceeding a preset threshold are selected as comparison companies. The second multi-source data of the comparison companies must be consistent with the first multi-source data of the target company in terms of dimensions and statistical methods. For example, if the target company collects data on "average monthly transaction count," the comparison companies must also obtain corresponding data for the same statistical period to ensure the effectiveness of subsequent comparative analysis.

[0041] S102. Based on the first multi-source data and the second multi-source data, estimate the objects produced by the target enterprise to obtain the first object value corresponding to the target enterprise.

[0042] The target company's outputs are located in the fintech sector, primarily referring to core outputs directly related to its value, including but not limited to quantifiable value indicators such as operating efficiency (net profit, revenue growth rate), risk control results (non-performing loan ratio, risk reserve coverage ratio), and business development potential (user growth, market share increase). The first target value is a quantitative estimate of the target company's core outputs obtained through multi-source data comparative analysis. It serves as the core data basis for assessing the company's value and operational status, possessing objectivity and comparability.

[0043] Specifically, the collected first and second multi-source data undergo cleaning (outlier removal, missing data completion), transformation (unifying data units and statistical standards), and standardization. Using algorithmic models from the fintech field (such as regression analysis models, machine learning prediction models, and industry benchmarking models), and with the second multi-source data of the comparable companies as a reference, a correlation is established between the data and the "output object." For example, if the output object is "annual net profit," a linear regression model can be constructed, using the correlation coefficients between the comparable companies' "revenue scale, cost ratio, risk control level," and net profit as a reference, and substituting these coefficients into the corresponding data of the target company. The pre-processed first multi-source data of the target company is then input into the constructed comparative analysis model. The model calculation yields the estimated result of the target company's core output object, i.e., the first object value. Model parameters need to be optimized based on industry characteristics. For example, considering the risk characteristics of fintech companies, adjustment factors such as "regulatory impact coefficient" are added to the model to ensure the reasonableness and relevance of the estimated results.

[0044] S103. Based on the first object value, generate an analysis and evaluation report for the target company.

[0045] Among them, the analysis and evaluation report is a comprehensive report that integrates multi-source data processing and object value prediction results. It is an important reference document for financial institutions' decision-making and its content must cover core modules such as evaluation methods, data sources, prediction results, risk warnings, and conclusions and recommendations.

[0046] Specifically, the primary target value is systematically integrated with key elements in the evaluation process (data source explanation, basis for selecting comparison companies, model parameter settings, and data processing flow) to clarify the generation logic of the primary target value and ensure report transparency. The primary target value is interpreted, analyzing the target company's strengths (e.g., a primary target value higher than the average of comparison companies indicates superior performance in the corresponding dimension) and potential risks (e.g., data showing the target company's estimated bad debt rate is higher than the industry average, requiring a credit risk warning), and supplemented with trend analysis (e.g., predicting the direction of change in the target value based on historical data). The analysis content is organized into a structured report, typically including modules such as "Evaluation Summary, Data Source and Methodology Explanation, Primary Target Value and Interpretation, Comparative Analysis Conclusions, Risk Warnings, and Decision Recommendations." In some scenarios, data can be presented through visual charts (e.g., comparison bar charts, trend lines) to improve report readability.

[0047] The enterprise evaluation method provided by the embodiments of this application defines that the first and second multi-source data need to be "associated with the operation status", and uses "same business type + coverage exceeding the preset threshold" as the quantitative screening condition to replace the empirical judgment of manual evaluation, thus delineating a clear boundary for data collection and significantly improving the processing efficiency in the early stage of evaluation; it defines that the first and second multi-source data are used as the estimation basis, and the quantitative characteristics of the dual-end data enable the estimation process to rely on data processing tools to achieve automated operations, greatly improving the efficiency of the core link of evaluation; with the quantitative first object value as the core of the report, it can rely on the report template to achieve standardized output, and significantly improves the enterprise evaluation efficiency compared with manual evaluation.

[0048] Figure 2 Schematic diagram of the process of the enterprise evaluation method provided by the embodiments of this application Figure Two As Figure 2 shown, the method includes:

[0049] In a possible implementation manner, based on the first multi-source data, a comparison enterprise screening model is constructed; a list of enterprises with the same business type is obtained; and through the comparison enterprise screening model, comparison enterprises are screened out from the list of enterprises with the same business type.

[0050] Among them, the comparison enterprise screening model: an algorithm model specifically used to screen out comparison enterprises that meet the condition of "business scope coverage greater than the preset threshold" from a large number of enterprises with the same business type. This model uses the characteristics of the target enterprise as a reference standard and achieves precise screening through multi-dimensional matching. List of enterprises with the same business type: a directory set containing all enterprises that are the same as or highly similar to the main business type of the target enterprise. The sources of this list can include industry databases, industrial and commercial registration information platforms, enterprise directories released by industry associations, etc., and it is necessary to ensure the comprehensiveness and timeliness of the list.

[0051] Specifically, taking the first multi-source data of the target enterprise as the core basis, extract the business characteristics (such as business fields, product types, service models), geographical characteristics (such as business coverage areas), customer characteristics (such as target customer groups), etc. of the target enterprise; based on these characteristics, construct a comparison enterprise screening model and preset the threshold of business scope coverage (such as set to 75% or 85% according to industry characteristics). Through various channels such as querying industry databases, retrieving industrial and commercial information platforms, and sorting industry reports, collect the information of all enterprises that are the same as or highly similar to the business type of the target enterprise to form a complete list of enterprises with the same business type. During the acquisition process, it is necessary to conduct a preliminary verification of the enterprise information to ensure that the enterprise is currently in a normal operation state and avoid including enterprises that have been transformed. Input the enterprise information in the list of enterprises with the same business type into the constructed comparison enterprise screening model; the model will compare the business scope coverage of each enterprise with that of the target enterprise one by one, and screen out the enterprises with a coverage greater than the preset threshold; finally, output the list of enterprises that meet the requirements as the comparison enterprises for subsequent analysis.

[0052] S201. Determine the first multi-source data of the target company and the second multi-source data of the comparison company. The first multi-source data is related to the operating status of the target company. The comparison company and the target company have the same business type. Furthermore, the business scope coverage of the comparison company and the target company is greater than a preset threshold.

[0053] S202. Based on the first multi-source data and the second multi-source data, the objects produced by the target enterprise are estimated to obtain the first object value corresponding to the target enterprise.

[0054] In one possible implementation, the first multi-source data is standardized to obtain first standardized data; the second multi-source data is standardized to obtain second standardized data; the first standardized data and the second standardized data are input into a preset enterprise comparison model to obtain the enterprise prediction range of the target enterprise; the first standardized data and the second standardized data are input into a preset object prediction model to obtain the object prediction result of the target enterprise; the enterprise prediction range and the object prediction result are weighted and fused to obtain the first object value of the target enterprise.

[0055] Standardization is the process of converting data of different magnitudes and dimensions into data under a unified standard. Since multi-source data may have differences in units or numerical ranges (e.g., the number of employees is "100-500", and the profit margin is "5%-20%), standardization can eliminate the impact of these differences on model calculations and ensure the comparability of data.

[0056] The enterprise comparison model is a pre-defined algorithmic model used to compare the differences between a target enterprise and comparable enterprises, and to output an estimated range for the target enterprise's operations. Its core function is to define a reasonable range for the target enterprise in a specific dimension based on the reference of similar enterprises. The enterprise estimated range is a range-based result output by the enterprise comparison model, reflecting the possible value range of the target enterprise for a certain type of output object, rather than a single numerical value, reflecting the rigor and feasibility of the assessment.

[0057] The object prediction model is a pre-defined algorithm specifically designed to directly predict the specific numerical values ​​of objects produced by a target company. Compared to the company comparison model, it focuses more on the accurate calculation of "object values." The object prediction result is the specific numerical prediction result of the objects produced by the target company, output by the object prediction model.

[0058] Weighted fusion is a process that assigns appropriate weights to the enterprise prediction range and the object prediction results based on factors such as the credibility and accuracy of the enterprise comparison model and the object prediction model. The resulting comprehensive result is obtained through weighted calculation, effectively combining the advantages of both models to improve prediction accuracy. The first object value is a core numerical value obtained after weighted fusion of the enterprise prediction range and the object prediction results. It comprehensively reflects the object value produced by the target enterprise and is a key basis for generating the subsequent evaluation report.

[0059] Specifically, for the first multi-source data collected from the target companies, a standardization process is performed. This process requires first defining the data's dimensions, value ranges, and other characteristics, selecting an appropriate standardization method, eliminating differences in magnitude between data points, and ultimately outputting first-standardized data to ensure its usability for subsequent model calculations. The second multi-source data from the comparison companies is then processed simultaneously using the same standardization standards and methods as the first multi-source data. This ensures that both types of data are on the same measurement dimension, avoiding comparison biases caused by different processing methods, and ultimately yielding second-standardized data.

[0060] The processed first and second standardized data are used as input parameters and fed into a pre-defined enterprise comparison model. The model calculates and analyzes the target enterprise's advantages, disadvantages, and position relative to the comparison enterprises based on the differences and correlations between the two types of data. It outputs an estimated range for the target enterprise's operational outputs. Similarly, the first and second standardized data are used as inputs and imported into a pre-defined object prediction model. This model focuses on the specific numerical calculations of the target enterprise's outputs, and outputs corresponding object prediction results through the mining and analysis of correlation features in the data.

[0061] First, based on the accuracy and stability of the enterprise comparison model and the object prediction model in historical applications, their respective weights are determined. Then, the enterprise prediction interval (usually the median of the interval or the expected value calculated through the interval probability distribution) and the object prediction results are weighted and calculated together to finally obtain the first object value with higher comprehensiveness and stronger accuracy.

[0062] In one possible implementation, unstructured data is subjected to feature extraction processing to obtain structured feature vectors; the structured data and structured feature vectors are integrated to obtain first standardized data.

[0063] Unstructured data refers to data without a fixed data structure that cannot be directly stored and processed using traditional database tables. Common forms in enterprise scenarios include customer reviews, employee work logs, meeting minutes, product image descriptions, industry news reports, and customer service voice-to-text transcripts. Structured data, on the other hand, has a clear and fixed structure and can be stored and managed in two-dimensional tables. It is a core data type for enterprise operations, such as revenue, cost, and profit data in financial statements; order volume, transaction volume, and user count data in business systems; and employee salary and attendance data in human resources systems. Feature extraction processing is the process of mining and extracting key information with practical significance and analytical value from unstructured data and converting it into a structured form. This process requires the use of technologies such as natural language processing and text mining to quantify and standardize unstructured data. Structured feature vectors are structured data that, after feature extraction processing, represents the key features of unstructured data in vector form. Each element in the vector corresponds to a quantified value of a specific feature, which can be directly identified and used by subsequent data processing and model calculations.

[0064] Specifically, for unstructured data in the first multi-source dataset, the core focus of the assessment needs is first clearly defined (such as customer satisfaction, product competitiveness, market reputation, etc.). Then, appropriate feature extraction techniques (such as bag-of-words model and word embedding techniques for text data) are selected to extract key features related to the core focus from the unstructured data. For example, emotional features such as "good product quality" and "slow after-sales response" and their corresponding intensity values ​​are extracted from customer reviews. These features are then converted into quantified structured feature vectors to achieve the "structured transformation" of unstructured data.

[0065] The original structured data (such as financial and business data) from the first multi-source dataset is merged with the structured feature vectors obtained through feature extraction. During the integration process, it is necessary to ensure the consistency of the two types of data in terms of time and enterprise entity dimensions (such as business data within the same time period and the corresponding customer review feature vectors). Through data alignment, field matching, and other actions, a complete and unified first standardized dataset is formed to prepare for subsequent model input.

[0066] In one possible implementation, the relationship between the target company and the comparison companies is determined; based on the relationship, the weight parameters of the company comparison model are adjusted.

[0067] Among them, the relationship refers to the various connections between the target company and the comparison company. These connections will affect the comparability of the two and the focus of the comparative analysis. Common types include industry chain relationships (such as upstream and downstream companies), competitive relationships (such as direct competitors and indirect competitors), cooperative relationships (such as strategic partners), and scale gradient relationships (such as leading companies and small and medium-sized enterprises).

[0068] Specifically, the process begins by collecting relevant data such as business dealings, industry positioning information, cooperation agreements, and market competition analysis reports between the target company and the comparison company. Then, based on this data, the specific relationship type between the two companies is identified through manual analysis or association rule mining algorithms (such as "direct competition relationship" or "upstream supplier and downstream buyer relationship"). The degree of closeness of the relationship is then quantitatively assessed (e.g., represented by a value between 0 and 1, with a larger value indicating a closer relationship).

[0069] Based on the determined type and degree of correlation, rules for adjusting weighting parameters are established. For example, if the two companies are direct competitors with a close correlation, the weighting parameters of characteristic data such as "market share" and "product pricing" of the compared companies need to be increased to highlight the comparison in terms of competition. If the two companies are upstream and downstream partners, the weighting of characteristic data such as "supply chain stability" and "cooperative order volume" should be increased. Subsequently, the weighting parameters of the company comparison model are specifically adjusted according to the rules to ensure that the model can focus on the core characteristics related to the correlation when calculating the company's prediction range, thereby improving the relevance of the prediction results.

[0070] S203. Process the first object value into natural language and charts to obtain an initial report.

[0071] Specifically, for the first object value, on the one hand, natural language conversion is performed, and the meaning, level and underlying reasons of the data are interpreted by combining industry background and business common sense to form a text description; on the other hand, according to the data characteristics and analysis needs, appropriate chart types are selected to visualize the first object value with the relevant data of the comparison companies and industry benchmark data, so as to make the data differences and changing trends more intuitive; the text description and charts are integrated to form an initial report.

[0072] S204. Divide the initial report into preset formats to obtain the analysis and evaluation report of the target company.

[0073] Specifically, first, clarify the preset format requirements of the evaluation report and determine the core modules to be included in the report (such as report summary, general situation of the target enterprise, description of data sources and processing, core interpretation of the first object value, comparative analysis with comparable enterprises, industry status evaluation, conclusions and development suggestions, etc.); then split, classify, and reorganize the text descriptions, charts, and other content in the initial report according to the modules of the preset format; at the same time, conduct logical sorting and language polishing on the content to ensure smooth connection and detailed content between modules; finally, form an analysis and evaluation report of the target enterprise with a standardized structure and clear content.

[0074] The enterprise evaluation method provided by the embodiment of this application defines that the first and second multi-source data must be "associated with the operating state", and uses "same business type + coverage exceeding the preset threshold" as the quantitative screening condition to replace the empirical judgment of manual evaluation, defining a clear boundary for data collection and significantly improving the processing efficiency in the early stage of evaluation; it is defined that the first and second multi-source data are used as the estimation basis, and the quantitative characteristics of the dual-end data enable the estimation process to rely on data processing tools to achieve automated calculation, greatly improving the efficiency of the core link of evaluation; with the quantitative first object value as the core of the report, standardized output can be achieved relying on the report template, significantly improving the enterprise evaluation efficiency compared with manual evaluation.

[0075] By standardizing the multi-source data of the target enterprise and comparable enterprises, the dimension differences and magnitude interference between different data are effectively eliminated, providing a comparable and reliable data basis for subsequent model calculations; at the same time, with the dual measurement of the enterprise comparison model and the object estimation model, and the combination of weighted fusion to obtain the first object value, both the reference role of the comparable enterprise is used to define a reasonable value range, and the focus on the target enterprise itself achieves accurate estimation. The advantages of the two models complement each other, significantly improving the scientificity and accuracy of the object value estimation result and providing a high-quality core basis for the generation of the evaluation report.

[0076] Regarding the characteristics that the first multi-source data contains unstructured data, through feature extraction, it is transformed into a structured feature vector, breaking through the limitation of traditional evaluation methods that only rely on structured data and fully exploiting the potential value contained in unstructured data (such as customer sentiment, market reputation, etc.); integrating the structured data and the structured feature vector to form the first standardized data makes the data dimensions for evaluation more complete and the information more comprehensive, avoiding evaluation bias caused by data missing, and further enhancing the objectivity and comprehensiveness of subsequent evaluation results.

[0077] By identifying the relationship between the target company and the comparison companies and adjusting the weight parameters of the company comparison model accordingly, the model can dynamically optimize its calculation logic based on the actual relationship between the two. For example, for companies in direct competition, the weight of characteristics such as market share can be strengthened; for companies in upstream and downstream relationships, the impact of characteristics such as supply chain stability can be highlighted. This personalized parameter adjustment makes the output of the company comparison model more closely aligned with actual business scenarios, effectively improving the relevance and accuracy of the company's predicted range, and providing a more valuable reference for the weighted fusion of the first object value.

[0078] By constructing a comparative enterprise screening model and selecting comparable enterprises from a list of companies with similar business types, the traditional manual screening of comparative enterprises is freed from the problems of high subjectivity and low efficiency. The screening model, built on the first multi-source data of the target enterprise, can accurately match the core condition of "business scope coverage greater than a preset threshold", ensuring that the selected comparative enterprises are highly comparable to the target enterprise. This avoids the evaluation distortion caused by improper selection of comparative enterprises, and at the same time, it realizes the standardization and automation of comparative enterprise screening, improving the efficiency and standardization of the evaluation work.

[0079] Transforming abstract first-object values ​​into initial reports in natural language and chart format significantly lowers the barrier to understanding professional data, making the assessment results easier for users with different knowledge backgrounds to quickly grasp. By dividing the initial reports into preset formats to form formal assessment reports, the report structure becomes clearer, the logic more rigorous, and the content presentation more in line with actual usage needs (such as internal decision-making, external communication, etc.), enhancing the readability and practicality of the assessment reports and ensuring that the assessment results can effectively serve various decision-making scenarios of enterprises.

[0080] Figure 3 This is a schematic diagram of the structure of the enterprise evaluation device provided in the embodiments of this application, such as... Figure 3 As shown, the enterprise evaluation device 30 provided in this embodiment includes an acquisition module 301, a processing module 302, and a generation module 303.

[0081] The acquisition module 301 is used to determine the first multi-source data of the target enterprise and the second multi-source data of the comparison enterprise. The first multi-source data is associated with the operating status of the target enterprise, the comparison enterprise has the same business type as the target enterprise, and the business scope coverage of the comparison enterprise and the target enterprise is greater than a preset threshold.

[0082] The processing module 302 is used to estimate the objects produced by the target enterprise based on the first multi-source data and the second multi-source data, and obtain the first object value corresponding to the target enterprise.

[0083] The generation module 303 is used to generate an analysis and evaluation report of the target company based on the first object value.

[0084] In one possible implementation, the processing module 302 is specifically used for:

[0085] The first multi-source data is standardized to obtain the first standardized data.

[0086] The second multi-source data is standardized to obtain the second standardized data.

[0087] Input the first and second standardized data into the preset enterprise comparison model to obtain the enterprise prediction range of the target enterprise;

[0088] Input the first and second standardized data into the preset object prediction model to obtain the object prediction results of the target enterprise;

[0089] The enterprise's estimated range and the target's estimated results are weighted and merged to obtain the first target value of the target enterprise.

[0090] In one possible implementation, the processing module 302 is specifically used for:

[0091] Unstructured data is processed by feature extraction to obtain structured feature vectors;

[0092] By integrating structured data and structured feature vectors, the first standardized data is obtained.

[0093] In one possible implementation, the processing module 302 is further configured to:

[0094] Determine the relationship between the target company and the comparison companies;

[0095] Adjust the weight parameters of the enterprise comparison model based on the correlation.

[0096] In one possible implementation, the acquisition module 301 is further configured to:

[0097] Based on the first multi-source data, a comparative enterprise screening model is constructed;

[0098] Obtain a list of companies with the same business type;

[0099] By comparing enterprise screening models, comparable enterprises are selected from the list of enterprises with the same business type.

[0100] In one possible implementation, the generation module 303 is specifically used for:

[0101] The first object value is processed into natural language and charts to obtain an initial report;

[0102] The initial report is divided into preset formats to obtain the analysis and evaluation report of the target company.

[0103] The enterprise evaluation device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0104] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus.

[0105] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0106] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0107] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0108] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0109] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0110] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0111] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0112] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0113] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0114] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0117] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0119] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for evaluating enterprises, characterized in that, include: The first multi-source data of the target company and the second multi-source data of the comparison company are determined. The first multi-source data is associated with the operational status of the target company. The comparison company has the same business type as the target company. Furthermore, the business scope coverage of the comparison company and the target company is greater than a preset threshold. Based on the first multi-source data and the second multi-source data, the objects produced by the target enterprise are estimated to obtain the first object value corresponding to the target enterprise; Based on the first object value, an analysis and evaluation report of the target enterprise is generated.

2. The method according to claim 1, characterized in that, The step of estimating the objects produced by the target enterprise based on the first multi-source data and the second multi-source data to obtain the first object value corresponding to the target enterprise includes: The first multi-source data is standardized to obtain the first standardized data. The second multi-source data is standardized to obtain the second standardized data; Input the first standardized data and the second standardized data into a preset enterprise comparison model to obtain the enterprise prediction range of the target enterprise; Input the first standardized data and the second standardized data into a preset object prediction model to obtain the object prediction result of the target enterprise; The estimated range of the enterprise and the estimated result of the object are weighted and fused to obtain the first object value of the target enterprise.

3. The method according to claim 2, characterized in that, The first multi-source data includes unstructured data and structured data; the standardization process of the first multi-source data to obtain the first standardized data includes: The unstructured data is subjected to feature extraction processing to obtain a structured feature vector; The structured data and the structured feature vectors are integrated to obtain the first standardized data.

4. The method according to claim 2, characterized in that, Also includes: Determine the relationship between the target company and the comparison company; Based on the aforementioned relationship, the weight parameters of the enterprise comparison model are adjusted.

5. The method according to claim 1, characterized in that, Also includes: Based on the first multi-source data, a comparative enterprise screening model is constructed; Obtain a list of companies with the same business type; The comparison enterprise screening model is used to select comparison enterprises from the list of enterprises with the same business type.

6. The method according to claim 2, characterized in that, The step of generating an analysis and evaluation report for the target enterprise based on the first object value includes: The first object value is processed into natural language and charts to obtain an initial report; The initial report is divided into preset formats to obtain the analysis and evaluation report of the target company.

7. A business evaluation device, characterized in that, include: The acquisition module is used to determine the first multi-source data of the target enterprise and the second multi-source data of the comparison enterprise. The first multi-source data is associated with the operating status of the target enterprise, the comparison enterprise has the same business type as the target enterprise, and the business scope coverage of the comparison enterprise and the target enterprise is greater than a preset threshold. The processing module is used to estimate the objects produced by the target enterprise based on the first multi-source data and the second multi-source data, and obtain the first object value corresponding to the target enterprise. The generation module is used to generate an analysis and evaluation report of the target enterprise based on the first object value.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images