WO2022141883A1 - Procédé et appareil de prédiction de tendance de revenu d'entreprise et dispositif informatique et support de stockage - Google Patents

Procédé et appareil de prédiction de tendance de revenu d'entreprise et dispositif informatique et support de stockage Download PDF

Info

Publication number
WO2022141883A1
WO2022141883A1 PCT/CN2021/084531 CN2021084531W WO2022141883A1 WO 2022141883 A1 WO2022141883 A1 WO 2022141883A1 CN 2021084531 W CN2021084531 W CN 2021084531W WO 2022141883 A1 WO2022141883 A1 WO 2022141883A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
enterprise
trend
target
revenue
Prior art date
Application number
PCT/CN2021/084531
Other languages
English (en)
Chinese (zh)
Inventor
张春玲
刘云风
刘懿祺
王磊
谭韬
汪伟
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2022141883A1 publication Critical patent/WO2022141883A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Definitions

  • the present application relates to the technical field of data analysis, and in particular, to a method for predicting a corporate revenue trend, a device for predicting a corporate revenue trend, computer equipment, and a computer-readable storage medium.
  • operating income refers to various incomes obtained by an enterprise in the production and operation activities of selling products or providing labor services. It is related to the survival and development of the enterprise and is of great significance to the operation of the enterprise. Revenue trends are an important part of investment analysis.
  • the main purpose of the present application is to provide a method for predicting a company's revenue trend, a device for predicting a company's revenue trend, computer equipment and a computer-readable storage medium.
  • the present application provides a method for predicting the revenue trend of an enterprise, comprising the following steps:
  • the enterprise data includes at least two dimensions of financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data; each the dimension includes at least one type of factor data;
  • the prosperity and decline index of each dimension in the target period is determined, wherein the welfare and decline index is used to determine the The change trend of the target period, the change trend includes an upward trend or a downward trend;
  • the revenue trend of the target enterprise in the target period is predicted.
  • the present application also provides a device for predicting the revenue trend of an enterprise, and the device for predicting the revenue trend of the enterprise includes:
  • the acquisition module is used to acquire multi-dimensional enterprise data of the target enterprise, wherein the enterprise data includes at least two of financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data. dimensions; each of the dimensions includes at least one type of factor data;
  • a first prediction module configured to predict a second rate of change of the factor data in the target period according to the first rate of change of the factor data in a plurality of periods before the target period;
  • the second prediction module is configured to determine, according to the second rate of change of all the factor data corresponding to each of the dimensions, the welfare and decline index of each of the dimensions in the target period, wherein the welfare and decline index is calculated by using for determining the change trend of the dimension in the target period, and the change trend includes an upward trend or a downward trend;
  • the third prediction module is configured to predict the revenue trend of the target enterprise in the target period according to the prosperity and decline indices corresponding to all the dimensions.
  • the present application also provides a computer device, the computer device comprising:
  • the computer device includes a memory, a processor, and a program for predicting business revenue trends stored on the memory and executable on the processor, when the program for predicting business revenue trends is executed by the processor Implement forecasting methods for business revenue trends;
  • the steps of the method for predicting the revenue trend of the enterprise include:
  • the enterprise data includes at least two dimensions of financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data; each the dimension includes at least one type of factor data;
  • the prosperity and decline index of each dimension in the target period is determined, wherein the welfare and decline index is used to determine the The change trend of the target period, the change trend includes an upward trend or a downward trend;
  • the revenue trend of the target enterprise in the target period is predicted.
  • the present application also provides a computer-readable storage medium, on which is stored a forecasting program for an enterprise's revenue trend, and the forecasting program for an enterprise's revenue trend is implemented when executed by a processor. Prediction of corporate revenue trends;
  • the steps of the method for predicting the revenue trend of the enterprise include:
  • the enterprise data includes at least two dimensions of financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data; each the dimension includes at least one type of factor data;
  • the prosperity and decline index of each dimension in the target period is determined, wherein the welfare and decline index is used to determine the The change trend of the target period, the change trend includes an upward trend or a downward trend;
  • the revenue trend of the target enterprise in the target period is predicted.
  • the forecasting method of enterprise revenue trend, the forecasting device for enterprise revenue trend, computer equipment and computer-readable storage medium provided by this application by considering multiple dimensions such as macro data, industrial data, financial data, capital data, public opinion data, etc. Automatically obtain the multi-dimensional data that affects the target company's revenue, establish multiple quantitative indicators to reflect the multi-dimensional explanatory factors of the target company's revenue, and build an explanation system for the target company's revenue on this basis, so as to improve the forecast of corporate revenue. While improving the efficiency of trends, the accuracy of forecasting corporate revenue trends has been improved.
  • 1 is a schematic diagram of the steps of a method for predicting the revenue trend of an enterprise in an embodiment of the application
  • FIG. 2 is a schematic block diagram of an apparatus for predicting an enterprise revenue trend according to an embodiment of the application
  • FIG. 3 is a schematic structural block diagram of a computer device according to an embodiment of the present application.
  • the method for predicting the revenue trend of the enterprise includes:
  • Step S10 acquiring multi-dimensional enterprise data of the target enterprise, wherein the enterprise data includes at least two dimensions in financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data ; each of the dimensions includes at least one type of factor data;
  • Step S20 predicting the second rate of change of the factor data in the target period according to the first rate of change of the factor data in multiple periods before the target period;
  • Step S30 According to the second rate of change of all factor data corresponding to each dimension, determine the independence and decline index of each dimension in the target period, wherein the welfare and decline index is used to determine the the change trend of the dimension in the target period, and the change trend includes an upward trend or a downward trend;
  • Step S40 Predict the revenue trend of the target enterprise in the target period according to the prosperity and decline indices corresponding to all the dimensions.
  • the execution terminal of the embodiment may be a computer device, or may be an apparatus for predicting the revenue trend of an enterprise.
  • the target enterprise is the enterprise to be analyzed, that is, the enterprise whose revenue trend needs to be analyzed.
  • the enterprise data includes at least two dimensions (or types) of financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data.
  • financial data may include the target company's operating costs, cash flow data, corporate assets, etc.
  • capital market data may include the target company's stock price, capital flow, price-earnings ratio, market value, etc.
  • corporate public opinion enthusiasm may include the target company's operations Good/bad news in the field (for example, good news will increase the popularity of corporate public opinion, while good news will reduce the public opinion enthusiasm of the company), brokerage evaluations (for example, positive comments will increase corporate public opinion enthusiasm, and negative comments will reduce corporate public opinion enthusiasm), Market expectations (for example, if the market expectations are met, the popularity of corporate public opinion will increase, and if market expectations are not met, the popularity of corporate public opinions will be reduced), the search volume of the target company (the higher the search volume, the higher the public opinion enthusiasm of the company), etc.;
  • the macro data can include industry GDP (Gross Domestic Product), industrial added value, etc.
  • the industry GDP is the manufacturing GDP
  • the industry data corresponding to the industry to which the target company belongs can include industry products.
  • Output, industry product sales, such as the industry product output corresponding to the smartphone industry is the smartphone output.
  • the enterprise data collected by the terminal is all data related to or affecting the corporate revenue of the target company. It should be understood that the good performance of corporate data will affect the positive growth of corporate revenue, and the poor performance of corporate data will lead to negative growth of corporate revenue. Therefore, the process of predicting corporate revenue trends is to analyze the performance of corporate data. process.
  • the terminal configures a corresponding dimension for each type of enterprise data by analyzing the data type of the enterprise data, that is, each dimension of the target enterprise is determined according to the type of enterprise data corresponding to the dimension (that is, each type of enterprise data).
  • Enterprise data corresponds to one dimension).
  • the terminal analyzes the main business structure of the target company (for querying corresponding macro data), upstream and downstream industrial links (for querying corresponding industrial data), financial operation status (for obtaining financial data), secondary market The transaction status (used to obtain capital market data) and the attention of market public opinion (used to obtain the popularity of corporate public opinion), etc., build a multi-dimensional database.
  • the terminal when it obtains the enterprise data, it can extract the descriptions about the business structure and main products of the enterprise from the enterprise financial report and enterprise research report of the target enterprise by means of keyword extraction, and then use the business keywords to compare the data in the database.
  • the relevant dimensions are correlated and matched to construct a related dimension system.
  • the keyword extraction here can use the traditional textrank algorithm. First, the important texts of the company's business operations in the financial statements are analyzed through the rules, and the descriptive texts of the company's main products and recent business hotspots are disassembled.
  • Keywords Through the traditional textrank algorithm Extract keywords, then correct the keywords through rules (such as word frequency, sequence positioning) to determine the keywords of the enterprise's business operations and industrial links, and finally determine the keywords corresponding to each dimension of the target enterprise based on the industry in which the enterprise is located.
  • rules such as word frequency, sequence positioning
  • the terminal uses the crawler script to capture the enterprise data corresponding to the dimension from the information related to each dimension.
  • the information related to each dimension For example, for capital market data, it can be obtained from the corporate information published by the target company on the exchange; the public opinion of the company can be captured from the research reports of securities companies; financial data can be captured from the financial statements of the target company; macroscopic Data and industrial data can be captured from economic information published by national authorities.
  • the terminal may record the dimension corresponding to the financial data as the first dimension (or financial indicator), record the dimension corresponding to the capital market data as the second dimension (or capital indicator), and record the dimension corresponding to the public opinion of the enterprise.
  • the dimension is recorded as the third dimension (or public opinion index)
  • the dimension corresponding to macro data is recorded as the fourth dimension (or macro index)
  • the dimension corresponding to industrial data is recorded as the fifth dimension (or industry index).
  • the terminal may only capture specific enterprise data through the crawler script, or after capturing a large amount of enterprise data, it may first filter the enterprise data, and then filter each factor data in the enterprise data, that is added to the subsequent analysis process.
  • the enterprise data of each dimension includes at least one type of factor data, but generally includes multiple types of factor data.
  • the financial data may include factor data such as operating costs, cash flow data, and corporate assets of the target company.
  • the terminal when the terminal acquires enterprise data, for any factor data, it not only acquires the current value of the factor data, but also acquires the value of the factor data in multiple past historical periods.
  • the target period is characterized as the period corresponding to the currently predicted revenue trend of the target company, which may be a future period after the current period (or the current time point), and for each period (including the target period, the current period and the historical period)
  • the time division of the time period) can be set according to the actual situation, such as one month, one quarter, etc.
  • the following description takes the length of each time period as one quarter as an example.
  • the terminal when the terminal obtains the specific values of any factor data in multiple time periods before the target time period (including the current time period and the historical time period), it can calculate the numerical value change of the factor data in each time period (except the target time period). rate (calculated according to the specific values of the adjacent two time periods before and after), as the first rate of change.
  • each industry has its corresponding economic cycle (for example, the economic cycle of the real estate industry is 2-3 years, and the economic cycle of the manufacturing industry is half a year to one year). Therefore, the terminal can determine the target company according to the industry to which the target company belongs. The corresponding industry economic cycle, and then further determine at least one complete industry economic cycle before the target period. It should be understood that the target period belongs to the current industry economic cycle, and what is determined here is the industry economic cycle before the current industry economic cycle.
  • the terminal analyzes the first numerical relationship between the first rate of change of each time period in the same industry economic cycle according to the first rate of change of the factor data corresponding to each time period in at least one industry economic cycle.
  • the more industry economic cycles analyzed by the terminal the more accurate the first numerical relationship between the first change rates of the same factor data obtained between each time period.
  • the terminal can predict that the factor data will be in the target period according to the first rate of change of the factor data in the current industry economic cycle other than the target period and the first numerical relationship between the first rate of change The second rate of change in . It should be understood that for other time periods in the current industry economic cycle other than the target time period, the time nodes are before the target time period. It should be noted that the first change rate is an actual value, and the second change rate is a predicted value.
  • the second rate of change in the fourth quarter of this year based on the first numerical relationship and the first rate of change in the first three quarters of this year (for example, calculating the rate of change in the first three quarters of this year) 50% of the total real growth rate in the third quarter is the second rate of change).
  • the process of the second rate of change of the actual predictor data in the target period is more complicated, which is only exemplified here.
  • the terminal can also analyze the economic cycle of each industry based on the first rate of change of the factor data in each period of previous industry economic cycles.
  • the first rate of change of , and the second numerical relationship between the first period of the next industrial economic cycle of the industry economic cycle (for example, the growth rate of a certain factor data in the first period of the next industrial economic cycle is obtained as A numerical relationship of 10% of the sum of the growth rate of an industry economic cycle), and using the second numerical relationship obtained from the analysis, and the first rate of change of each period in the previous industry economic cycle of the current industry economic cycle, we can predict Obtain the second rate of change of the factor data in the target period (for example, the second rate of change is calculated as 10% of the sum of the growth rates of the previous industry economic cycle in the current industry economic cycle).
  • the terminal may predict the second rate of change of each type of factor data in the target period according to the first rate of change of each type of factor data in multiple periods before the target period.
  • the second rate of change may be a negative value, which is represented as a negative growth of the factor data during the target period.
  • step S30 after obtaining the second rate of change of all factor data in the enterprise data corresponding to each dimension, the terminal can determine the welfare and decline index corresponding to each dimension based on this.
  • the welfare and decline index is used to determine the change trend of the dimension in the target period, and the change trend includes an upward trend or a downward trend.
  • a benchmark value such as a value of 50
  • the concept of poverty and decline index is equivalent to the line of poverty and decline.
  • the line of poverty and decline is the critical value of the Purchasing Managers' Index (PMI) and the Entrepreneur Confidence Index, which can reflect the macroeconomic developments, development trends, and entrepreneurs' views and confidence in the macroeconomy.
  • the PMI value usually takes 50% as the dividing point of economic strength, while the entrepreneur confidence index takes 100% as the line of prosperity and decline.
  • the terminal is pre-configured with its corresponding first weight for each type of factor data, and the method for determining the first weight can be determined according to the correlation coefficient between the factor data and the target company's corporate revenue, or it can be determined by a relevant engineer. pre-set and type in the terminal's.
  • the correlation coefficient is a statistical index in statistics, and is a statistical index for studying the closeness of the linear correlation between two variables.
  • the calculation formula of the welfare and decline index corresponding to each dimension is as follows:
  • n is the number of all factor data in the enterprise data corresponding to the dimension
  • Xi is the second rate of change corresponding to the factor data
  • Wi is the first weight corresponding to the factor data.
  • the terminal can separately calculate and obtain the decisions and decline index corresponding to each dimension.
  • step S40 the terminal obtains the second weight corresponding to each dimension index, and then predicts the revenue trend of the target company in the target period (ie, the company's operating income trend) according to the prosperity and decline indices and the second weight corresponding to all dimension indices. .
  • the second weight corresponding to each dimension index may be determined according to the correlation coefficient between the dimension index and the corporate revenue of the target enterprise, and the greater the positive correlation coefficient, the greater the second weight (or The smaller the correlation coefficient that is negatively correlated, the larger the second weight); the second weight can also be preset by the relevant engineer after considering the impact of each dimension index on the company's revenue, and input the preset weight of the terminal, For example, set the second weight corresponding to the financial dimension to 0.3, set the second weight corresponding to the macro dimension to 0.25, set the second weight corresponding to the industry dimension to 0.15, set the second weight corresponding to the capital dimension to 0.2, and set the second weight corresponding to the public opinion dimension to 0.2.
  • the second weight is 0.1.
  • the terminal may use the welfare and decline index predicted by each dimension in the target period as the first province and decline index, and obtain the behaviour and decline index actually calculated in the previous period of the target period as the second province and decline index, and then calculate Compared with the change rate of the second province and decline index, the third change rate corresponding to each dimension is obtained (the third change rate can be a negative number, which means that the welfare and decline index in the target period is higher than that of the previous period. decreased).
  • the target period is equivalent to the future period, and the period before the target period is the period that has already occurred, in the period before the target period, all the data used to calculate the second welfare and decline index are the ones that have already occurred. (that is, directly substitute the first rate of change of the relevant factor data in this period into the calculation formula of the welfare and decline index, without using the predicted second rate of change), and then directly calculate the corresponding period before the target period. the second boom-and-bust index.
  • the formula for calculating the revenue trend of the target company is as follows:
  • N is the total number of dimensions
  • O i is the third rate of change corresponding to the dimension
  • P i is the second weight corresponding to the dimension.
  • the terminal when it predicts the revenue trend of the target company, it may also directly perform weighted sum calculation according to the prosperity and decline index and the second weight corresponding to all dimension indices to obtain the revenue trend of the target company.
  • the specific calculation formula is as follows:
  • N is the total number of dimensions
  • Y i is the welfare and decline index of the dimension in the target period
  • P i is the second weight corresponding to the dimension.
  • the multi-dimensional data affecting the target company's revenue is automatically obtained, and multiple quantitative indicators are established to reflect the target company's revenue.
  • an explanation system for the target company's revenue is constructed, so as to improve the efficiency of predicting the company's revenue trend, and at the same time improve the accuracy of predicting the company's revenue trend.
  • the method further includes:
  • Step S50 analyzing the correlation coefficient between the sub-data in each of the dimensions and the historical revenue of the target company, wherein the data in each of the dimensions is divided into multiple types of the sub-data;
  • Step S51 Use the sub-data whose correlation coefficient is outside the preset value range as the factor data.
  • the terminal uses the crawler script to capture the enterprise data corresponding to each dimension
  • the data in each dimension of the enterprise data will be divided into multiple types of sub-data.
  • the sub-data that is related to the target company's corporate revenue is screened out, and the sub-data obtained by screening is used as factor data for subsequent analysis of the target company's revenue trend.
  • the terminal obtains the enterprise revenue of the target enterprise in multiple periods before the target period as historical revenue, and then also obtains multiple periods of each type of subdata before the target period for each type of sub-data in the enterprise data.
  • the correlation analysis between each type of sub-data and historical revenue is performed to calculate the correlation coefficient between each type of sub-data and historical revenue.
  • the calculation method of the correlation coefficient may be a calculation method of a Spearman correlation coefficient, a calculation method of a Pearson correlation coefficient, or the like. It should be noted that the correlation is a non-deterministic relationship, and the correlation coefficient is a measure of the degree of linear correlation between the research variables.
  • the value of the correlation coefficient is between -1 and 1.
  • the value of the correlation coefficient is 0, it represents the two observational quantities for calculating the correlation coefficient (the observational quantity here is the historical revenue and any data in the enterprise data).
  • the observational quantity here is the historical revenue and any data in the enterprise data.
  • There is no correlation between a class of sub-data when the correlation coefficient is greater than 0, it indicates a positive correlation between the two observations; when the correlation coefficient is less than 0, it indicates a negative correlation between the two observations.
  • a preset numerical interval (which can be recorded as the first interval) can be set, and it is defined that when the correlation coefficient is within the preset numerical interval, there is no correlation between the two observations corresponding to the correlation coefficient; When it is set outside the value interval, there is a correlation between the two observations corresponding to the correlation coefficient.
  • the value range of the lower limit of the interval of the preset value interval is less than or equal to 0 and greater than -1
  • the value range of the upper limit of the interval is greater than or equal to 0 and less than 1. It should be understood that the specific value of the preset value interval can be set according to the actual situation, for example, it is set to [-0.3, 0.3]
  • the terminal after analyzing and obtaining the correlation coefficient between each type of sub-data in the enterprise data and historical revenue, the terminal further detects whether the correlation coefficient corresponding to each type of sub-data is within a preset value range.
  • the terminal detects that the correlation coefficient corresponding to any type of sub-data is outside the preset numerical range, then the type of sub-data is used as factor data to calculate the honor of the dimension corresponding to the enterprise data.
  • Dry index that is, applying factor data to the subsequent analysis of the target company's revenue trend.
  • the terminal when the terminal detects that the correlation coefficient corresponding to any type of sub-data is within the preset value range, it may remove this type of sub-data, and no longer use this type of sub-data to calculate the corresponding enterprise data.
  • the growth and decline index of the dimension is no longer used in the analysis of revenue trends.
  • the terminal can establish a factor screening model according to the calculation principle of the correlation coefficient and the preset value interval. It only needs to input the data value and historical revenue of each type of sub-data in multiple time periods into the factor screening model, and then the filter can be obtained. factor data.
  • the factor data that has a certain correlation with the company's revenue can be obtained by analyzing the correlation coefficient, and there are some factor data (referred to as the first factor data) in these factor data that are strongly correlated with the company's revenue, However, it cannot be ruled out that some of the factor data (referred to as the second factor data) are only because of their strong correlation with the first factor data, so that the numerical changes of the second factor data seem to be related to the company's revenue. There is no or weak correlation between the second factor data and the company's revenue.
  • the first factor data is positively correlated with the company's revenue, and it is also positively correlated with the second factor data, then the second factor data will appear to be positively correlated with the company's revenue, but in fact, if the first factor data is ignored may not have a necessary correlation between the second factor data and corporate revenue. Therefore, if the second factor data in the factor data is further eliminated, the accuracy of the final predicted corporate revenue trend can be further improved.
  • the terminal may first determine the first factor data from the factor data, and use other factor data other than the first factor data as the second factor data.
  • the first factor data may be preset factor data preset by a relevant engineer, and the terminal only needs to detect whether the factor data belongs to the preset factor data, if so, it is the first factor data, and if not, it is the second factor data.
  • the terminal may also determine the first factor data according to the correlation coefficient between the factor data and historical revenue, and specifically detect whether the correlation coefficient corresponding to the factor data is within the second interval (that is, a preset different from the first interval). Numerical interval), if it is the first factor data, otherwise it is the second factor data. Among them, the second interval is used to measure the correlation strength between factor data and historical revenue, and its specific value range can be set according to actual needs, such as [-1,-0.6] ⁇ [0.6,1].
  • the terminal determines the second expansion and contraction index actually calculated in the period before the target period, and then uses the first factor data to calculate the third expansion and contraction index for the period, and determines the difference between the third expansion and contraction index and the second expansion and contraction index. The first difference between .
  • the terminal adds the second factor data to the first factor data one by one to calculate the fourth expansion and contraction index of the period, and determines the second difference between the fourth expansion and contraction index and the second expansion and contraction index;
  • the first difference is compared with the second difference, and if it is detected that the second difference is smaller than the first difference, it indicates that the second factor data used to calculate the fourth decisions and decline index is useful for improving the accuracy of calculating the province and decline index.
  • the second factor data is related to the company's revenue, so the second factor data can be updated to the first factor data; if it is detected that the second difference is greater than or equal to the first difference, It shows that the second factor data used to calculate the fourth profits and decline index is not helpful for improving the accuracy of calculating the prosperity and decline index, which means that the second factor data may not be related to the company's revenue.
  • the second factor data is used as the data to be excluded.
  • the terminal after determining the data to be excluded in the factor data, the terminal removes the factor data corresponding to the data to be excluded, and uses the remaining factor data to calculate the welfare and decline index of the dimension corresponding to the enterprise data to which the factor data belongs, That is, these factor data are applied to the process of subsequent analysis of the target company's revenue trend, so as to further improve the accuracy of predicting the company's revenue trend.
  • the terminal may further filter the data to be rejected before removing the data to be rejected.
  • the correlation coefficient between the factor data and historical revenue is recorded as the first correlation coefficient, and then the correlation coefficient between the data to be excluded and the first factor data (referred to as the second correlation coefficient) is determined respectively, based on this Analyze whether the data to be excluded has the first factor data with strong correlation with it.
  • the terminal when the terminal detects that in the second correlation coefficient corresponding to the data to be excluded, there is a second correlation coefficient within the third interval, that is, it is determined that the data to be excluded has first factor data with strong correlation with it; otherwise , then it is determined that there is no first factor data with strong correlation with the data to be excluded.
  • the third interval is used to measure the correlation strength between the data to be excluded and the first factor data, and its specific value range can be set according to the actual situation, for example, it is set to [-1,-0.7] ⁇ [0.7 ,1].
  • the terminal when the terminal detects that the data to be excluded does not have the first factor data that is strongly correlated with it, it indicates that the data to be excluded is related to the company's revenue (because its corresponding second correlation index is not does not affect its corresponding first correlation index), then the data to be excluded is changed to the first factor data, and it is no longer excluded; when the terminal detects that the data to be excluded has first factor data with strong correlation with it , it means that the data to be excluded has no correlation with the company’s revenue (because its corresponding first correlation index is affected by its corresponding second correlation index, so that the first correlation index is not within the first interval ), so the to-be-excluded data can be eliminated.
  • the method further includes:
  • Step S52 determining the first weight of the factor data according to the correlation coefficient corresponding to the factor data
  • the step of determining, according to the second rate of change of all factor data corresponding to each of the dimensions, the welfare and decline index of each of the dimensions in the target period includes:
  • Step S31 according to the second change rate and the first weight of all the factor data corresponding to each dimension, determine the prosperity and decline index of each dimension in the target period.
  • the terminal performs correlation analysis between each type of factor data and historical revenue, and obtains a correlation coefficient between each type of factor data and historical revenue.
  • the terminal determines the first weight corresponding to the factor data according to the correlation coefficient, the larger the correlation coefficient corresponding to the factor data, the larger the determined first weight.
  • the terminal determines the first weight corresponding to the factor data according to the correlation coefficient, the smaller the correlation coefficient corresponding to the factor data, the larger the determined first weight.
  • the terminal calculates the corresponding value of each dimension according to the second rate of change and the first weight of all the factor data corresponding to each dimension.
  • the boom and bust index The calculation formula of the welfare and decline index corresponding to each dimension is as follows:
  • n is the number of all factor data in the enterprise data corresponding to the dimension
  • Xi is the second rate of change corresponding to the factor data
  • Wi is the first weight corresponding to the factor data.
  • the method before the step of predicting the revenue trend of the target enterprise in the target period according to the prosperity and decline indices corresponding to all the dimensions, the method further includes:
  • Step S60 determining the second weight corresponding to the dimension according to a preset rule
  • the step of predicting the revenue trend of the target company in the target period according to the province and decline indices corresponding to all the dimensions includes:
  • Step S41 predicting the revenue trend of the target enterprise in the target period according to the province and decline index and the second weight corresponding to all the dimensions.
  • the terminal before determining the revenue trend, the terminal needs to determine the second weight corresponding to each dimension first.
  • the terminal may determine the second weight corresponding to each dimension according to a preset rule.
  • the preset rules include any of the following:
  • the first preset rule the terminal determines the first accuracy rate corresponding to the dimension according to the historical actual expansion and contraction index and the historical predicted expansion index corresponding to the dimension, and determines the second weight according to the first accuracy rate , where the higher the first accuracy, the higher the second weight; or,
  • Second preset rule the terminal generates multiple weight combinations according to the number of the dimensions, and determines the historically predicted revenue trend based on the weight combination and the historical actual decisions and decline index corresponding to each of the dimensions, and according to the historical forecast The revenue trend and the historical actual revenue trend determine the second accuracy rate corresponding to the weight combination, and determine the second weight corresponding to each of the dimensions according to the weight combination with the highest second accuracy rate; or,
  • the terminal uses big data to analyze the degree of correlation between the revenue of each dimension according to the industry to which the target enterprise belongs, and determines the second weight corresponding to each dimension according to the degree of correlation corresponding to each dimension, wherein , the greater the degree of association, the greater the second weight.
  • the terminal uses big data to analyze the degree of correlation between the revenue of each dimension according to the industry to which the target enterprise belongs, and determines the second weight corresponding to each dimension according to the degree of correlation corresponding to each dimension, wherein , the greater the degree of association, the greater the second weight.
  • a higher weight can be assigned to the macro indicators of real estate companies.
  • the terminal may first use the factor data corresponding to each dimension to calculate the historical actual welfare and decline index of each dimension in any period before the target period (denoted as the second period), And according to the factor data of the period before the second period (denoted as the third period), the historical forecastisation and decline index of the second period is calculated. Then, according to the deviation between the historically predicted province and decline index and the historical actual province and decline index of each dimension in the second period, the first accuracy rate corresponding to each dimension is calculated (the first accuracy rate is the calculated prosperity and decline index). accuracy). Among them, the higher the first accuracy rate corresponding to the dimension, the closer the historical forecast decisions and decline index is to the historical actual republic and decline index. Therefore, when the first accuracy rate corresponding to a dimension is higher, a larger first accuracy rate can be assigned to this dimension. Two weights, so that the revenue trend determined by the subsequent rise and fall index corresponding to this dimension will be more accurate.
  • the target period is equivalent to the future period, and the period before the target period is the period that has occurred, in the period before the target period, the data used to calculate the historical actual welfare and decline index are Knowing that, and to calculate the historical forecast welfare and decline index of this period, we only need to use the factor data before this period.
  • the terminal Based on the second preset rule, the terminal generates multiple weight combinations according to the number of dimensions, and each weight combination is set with a second weight corresponding to each dimension.
  • the actual historical welfare and decline index corresponding to each dimension in any period before the target period (referred to as the second period) is obtained, and the historical actual revenue trend corresponding to the second period is obtained.
  • the historical forecast revenue trend determined in different weight combinations is calculated. It should be understood that a historical forecast revenue trend can be calculated for each combination of weights.
  • the terminal analyzes the deviation value between each historical forecasted revenue trend and the historical actual revenue trend to obtain the corresponding value of each weight combination.
  • the second accuracy rate wherein the higher the second accuracy rate, the closer the corresponding historical forecasted revenue trend is to the historical actual revenue trend.
  • the terminal obtains the weight combination with the second highest accuracy rate, and obtains the second weight allocation ratio of each dimension in the weight combination, and finally determines the second weight corresponding to each dimension based on this, so that when these dimensions correspond to the subsequent use The revenue trend determined by the second weight is more accurate.
  • the degree of relevance of each dimension to the corporate revenue of the industry to which the target company belongs may be determined by relevant engineers based on actual experience data (for example, the financial industry is deeply affected by capital market data, and A higher weight can be set for the capital dimension), and the relevant setting information of the second weight corresponding to each dimension is input into the terminal, and the terminal can directly obtain it.
  • the terminal obtains the second weight corresponding to each dimension index, and then predicts the revenue trend of the target company in the target period (ie, the company's operating income trend) according to the prosperity and decline indices and the second weight corresponding to all dimension indices.
  • the preset rule is equivalent to a logical analysis process of the degree of correlation between each dimension and the company's revenue, and based on this, a higher weight is assigned to the dimension with a high degree of correlation, so as to make the revenue trend based on this prediction more accurate. to be accurate.
  • the method further includes:
  • Step S70 Write the enterprise data into the blockchain node to construct the database of the target enterprise.
  • the terminal may first filter the enterprise data, then obtain the enterprise data belonging to the factor data, and write the enterprise data into the blockchain node, so as to be based on the blockchain technology Build a database of target companies.
  • Blockchain is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • the underlying platform of the blockchain can include processing modules such as user management, basic services, smart contracts, and operation monitoring.
  • the user management module is responsible for the identity information management of all blockchain participants, including maintenance of public and private key generation (account management), key management, and maintenance of the corresponding relationship between the user's real identity and blockchain address (authority management), etc.
  • account management maintenance of public and private key generation
  • key management key management
  • authorization management maintenance of the corresponding relationship between the user's real identity and blockchain address
  • the basic service module is deployed on all blockchain node devices to verify the validity of business requests, After completing the consensus on valid requests, record them in the storage.
  • the basic service For a new business request, the basic service first adapts the interface for analysis and authentication processing (interface adaptation), and then encrypts the business information through the consensus algorithm (consensus management), After encryption, it is completely and consistently transferred to the shared ledger (network communication), and records are stored; the smart contract module is responsible for the registration and issuance of contracts, as well as contract triggering and contract execution.
  • contract logic through a programming language and publish to On the blockchain (contract registration), according to the logic of the contract terms, call the key or other events to trigger execution, complete the contract logic, and also provide the function of contract upgrade and cancellation;
  • the operation monitoring module is mainly responsible for the deployment in the product release process , configuration modification, contract settings, cloud adaptation, and visual output of real-time status in product operation, such as: alarms, monitoring network conditions, monitoring node equipment health status, etc.
  • the enterprise data can be stored in the blockchain network, and it is easy to access and use, forming a database of the target enterprise, which improves the security of enterprise data storage, and also improves the security of enterprise data storage. It is convenient for further data analysis based on the database.
  • Step S80 When it is detected that the revenue trend is a downward trend, output alarm information to an associated device of the target enterprise.
  • the terminal after the terminal predicts and obtains the revenue trend of the target company in the target period, it can generate and output the revenue report of the target company by using the revenue trend.
  • the terminal when it detects that the predicted revenue trend is a downward trend, it can further generate alarm information according to the prosperity and decline index and revenue trend corresponding to each dimension, and then output the alarm information to the relevant personnel of the target enterprise.
  • Associate the equipment to remind the relevant personnel of the target enterprise to take risk control measures in time, so as to maximize the interests of the target enterprise.
  • the terminal after the terminal performs step S30, it can also further detect whether the change trend of the welfare and decline index corresponding to each dimension is a downward trend; prompting information, and outputting the first prompting information to the associated equipment of the target enterprise, wherein the first prompting information is risk prompting information to remind the relevant personnel of the target enterprise that the field in which the dimension is located has risks that affect the revenue of the enterprise; if No, the terminal generates second prompt information according to the rising trend of poverty and decline index and its dimensions, and outputs the second prompt information to the associated equipment of the target enterprise, wherein the second prompt information is opportunity prompt information to prompt the target enterprise There are opportunities to increase the company's revenue in the field in which the dimension is located, and the business layout can be strengthened in the field in which the dimension is located.
  • an embodiment of the present application further provides an apparatus 10 for predicting an enterprise revenue trend, including:
  • the acquisition module 11 is used to acquire multi-dimensional enterprise data of the target enterprise, wherein the enterprise data includes at least one of financial data, capital market data, enterprise public opinion, macro data corresponding to the industry to which the target enterprise belongs, and industrial data. two dimensions; each of said dimensions includes at least one type of factor data;
  • a first prediction module 12 configured to predict a second rate of change of the factor data in the target period according to the first rate of change of the factor data in a plurality of periods before the target period;
  • the second prediction module 13 is configured to determine, according to the second rate of change of all the factor data corresponding to each dimension, the welfare and decline index of each dimension in the target period, wherein the welfare and decline index for determining the change trend of the dimension in the target period, and the change trend includes an upward trend or a downward trend;
  • the third prediction module 14 is configured to predict the revenue trend of the target enterprise in the target period according to the prosperity and decline indices corresponding to all the dimensions.
  • an embodiment of the present application further provides a computer device.
  • the computer device may be a server, and its internal structure may be as shown in FIG. 3 .
  • the computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium, an internal memory.
  • the nonvolatile storage medium stores an operating system, a computer program, and a database.
  • the internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium.
  • the database of the computer equipment is used in the forecasting program of the company's revenue trend.
  • the network interface of the computer device is used to communicate with external terminals through a network connection.
  • the computer program when executed by a processor, implements a method of forecasting business revenue trends.
  • FIG. 3 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied.
  • the present application also provides a computer-readable storage medium, where the computer-readable storage medium includes a program for predicting a company's revenue trend, and when the program for predicting a company's revenue trend is executed by a processor, the implementation is as described in the above embodiments. The steps of the forecasting method of the company's revenue trend described above. It can be understood that, the computer-readable storage medium in this embodiment may be non-volatile or volatile.
  • the method for predicting the enterprise revenue trend, the device for predicting the enterprise revenue trend, the computer equipment and the storage medium provided in the embodiments of this application are based on the consideration of macro data, industrial data, financial data, capital data, and public opinion.
  • Data and other dimensions automatically obtain multi-dimensional data affecting the target company's revenue, establish multiple quantitative indicators to reflect the multi-dimensional explanatory factors of the target company's revenue, and build an explanation system for the target company's revenue on this basis, so as to While improving the efficiency of forecasting enterprise revenue trends, the accuracy of predicting enterprise revenue trends is also improved.
  • Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention porte sur un procédé et un appareil de prédiction de tendance de revenu d'entreprise et sur un dispositif informatique et un support de stockage lisible par ordinateur, qui se rapportent au domaine technique des mégadonnées et de l'analyse de données. Le procédé consiste à : obtenir des données d'entreprise multidimensionnelles d'une entreprise cible, chaque dimension comprenant au moins un type de données de facteur ; prédire un second taux de changement des données de facteur dans une période de temps cible en fonction d'un premier taux de changement des données de facteur dans de multiples périodes de temps avant la période de temps cible ; déterminer l'indice des acheteurs de chaque dimension dans la période de temps cible en fonction du second taux de changement de toutes les données de facteur correspondant à chaque dimension ; et prédire la tendance de revenu de l'entreprise cible dans la période de temps cible en fonction des indices des acheteurs correspondant à toutes les dimensions. Le procédé améliore l'efficacité et la précision de la prédiction de la tendance de revenu de l'entreprise.
PCT/CN2021/084531 2020-12-31 2021-03-31 Procédé et appareil de prédiction de tendance de revenu d'entreprise et dispositif informatique et support de stockage WO2022141883A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011633070.2 2020-12-31
CN202011633070.2A CN112767008A (zh) 2020-12-31 2020-12-31 企业营收趋势的预测方法、装置、计算机设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022141883A1 true WO2022141883A1 (fr) 2022-07-07

Family

ID=75699625

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/084531 WO2022141883A1 (fr) 2020-12-31 2021-03-31 Procédé et appareil de prédiction de tendance de revenu d'entreprise et dispositif informatique et support de stockage

Country Status (2)

Country Link
CN (1) CN112767008A (fr)
WO (1) WO2022141883A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115374404A (zh) * 2022-10-20 2022-11-22 国网(宁波)综合能源服务有限公司 基于多维数据对行业月度电能占比偏差的修正方法
CN116450708A (zh) * 2023-06-13 2023-07-18 南京市城市数字治理中心 一种企业数据挖掘方法及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114021788B (zh) * 2021-10-25 2022-07-26 深圳市维度数据科技股份有限公司 预测方法、装置、电子设备和存储介质
CN117422314B (zh) * 2023-12-19 2024-04-12 鲁信科技股份有限公司 一种基于大数据分析的企业数据评估方法及设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150006435A1 (en) * 2013-07-01 2015-01-01 Yaniv Konchitchki Methods and systems for forecasting economic movements
CN109829745A (zh) * 2018-12-19 2019-05-31 平安科技（深圳）有限公司 营收数据预测方法、装置、计算机设备和存储介质
CN110210645A (zh) * 2019-04-19 2019-09-06 平安科技（深圳）有限公司 一种发展趋势数据获取方法、装置及可读存储介质
CN110415106A (zh) * 2019-07-23 2019-11-05 安徽迪科数金科技有限公司 一种经营主体的经营分析预测评估系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150006435A1 (en) * 2013-07-01 2015-01-01 Yaniv Konchitchki Methods and systems for forecasting economic movements
CN109829745A (zh) * 2018-12-19 2019-05-31 平安科技（深圳）有限公司 营收数据预测方法、装置、计算机设备和存储介质
CN110210645A (zh) * 2019-04-19 2019-09-06 平安科技（深圳）有限公司 一种发展趋势数据获取方法、装置及可读存储介质
CN110415106A (zh) * 2019-07-23 2019-11-05 安徽迪科数金科技有限公司 一种经营主体的经营分析预测评估系统

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115374404A (zh) * 2022-10-20 2022-11-22 国网(宁波)综合能源服务有限公司 基于多维数据对行业月度电能占比偏差的修正方法
CN115374404B (zh) * 2022-10-20 2023-01-24 国网(宁波)综合能源服务有限公司 基于多维数据对行业月度电能占比偏差的修正方法
CN116450708A (zh) * 2023-06-13 2023-07-18 南京市城市数字治理中心 一种企业数据挖掘方法及系统
CN116450708B (zh) * 2023-06-13 2023-09-01 南京市城市数字治理中心 一种企业数据挖掘方法及系统

Also Published As

Publication number Publication date
CN112767008A (zh) 2021-05-07

Similar Documents

Publication Publication Date Title
WO2022141883A1 (fr) Procédé et appareil de prédiction de tendance de revenu d'entreprise et dispositif informatique et support de stockage
Bushman et al. Bank competition: Measurement, decision‐making, and risk‐taking
Chuang et al. Causality in quantiles and dynamic stock return–volume relations
de Castro Vieira et al. Machine learning models for credit analysis improvements: Predicting low-income families’ default
Wu et al. The analysis of credit risks in agricultural supply chain finance assessment model based on genetic algorithm and backpropagation neural network
Huang et al. Systemic importance analysis of chinese financial institutions based on volatility spillover network
KR20180060044A (ko) 클라우드 환경에서 개인정보 보호를 지원하는 p2p 중개 보안 시스템
KR20180060005A (ko) 클라우드 환경에서 개인정보 보호를 지원하는 p2p 중개 보안 시스템
Jiang et al. Technical analysis profitability without data snooping bias: evidence from Chinese stock market
Salisu et al. A moving average heterogeneous autoregressive model for forecasting the realized volatility of the US stock market: Evidence from over a century of data
Bouri et al. Uncertainty and daily predictability of housing returns and volatility of the United States: Evidence from a higher-order nonparametric causality-in-quantiles test
Lakhno et al. Methodology for assessing the effectiveness of measures aimed at ensuring information security of the object of informatization
Ji et al. Portfolio diversification strategy via tail‐dependence clustering and ARMA‐GARCH Vine Copula approach
Alshawabkeh et al. Credit risk estimate using internal explicit knowledge
Heckelman et al. Are we there yet? On the convergence of financial reforms
Mitra Scenario generation for operational risk
CN114418776A (zh) 一种数据处理方法、装置、终端设备及介质
Signori et al. Economic links and counterparty risk
CN113298575A (zh) 一种商标价值批量评估的方法、系统、设备及存储介质
Restrepo et al. Operational risk analysis of industrial small and medium enterprises
Chong et al. Executive stock option pricing in China under stochastic volatility
Yang et al. Macroeconomic shocks, investment volatility and centrality in global manufacturing network
Sheu et al. Forecasting the volatility of a combined multi‐country stock index using GWMA algorithms
Zhao et al. Systematic Research on Multi-dimensional and Multiple Correlation Contagion Networks of Extreme Risk in China’s Banking Industry
Foster‐McGregor On the Determinants of Investment in Sub‐S aharan African Manufacturing Firms

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21912653

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21912653

Country of ref document: EP

Kind code of ref document: A1