CN114021788A - Prediction method, prediction device, electronic equipment and storage medium - Google Patents

Prediction method, prediction device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114021788A
CN114021788A CN202111244212.0A CN202111244212A CN114021788A CN 114021788 A CN114021788 A CN 114021788A CN 202111244212 A CN202111244212 A CN 202111244212A CN 114021788 A CN114021788 A CN 114021788A
Authority
CN
China
Prior art keywords
data
information
enterprise
development
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111244212.0A
Other languages
Chinese (zh)
Other versions
CN114021788B (en
Inventor
纪培端
余茜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Dimension Data Technology Co ltd
Original Assignee
Shenzhen Dimension Data Technology Co ltd
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 Shenzhen Dimension Data Technology Co ltd filed Critical Shenzhen Dimension Data Technology Co ltd
Priority to CN202111244212.0A priority Critical patent/CN114021788B/en
Publication of CN114021788A publication Critical patent/CN114021788A/en
Application granted granted Critical
Publication of CN114021788B publication Critical patent/CN114021788B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/251—Fusion techniques of input or preprocessed data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to the field of artificial intelligence, and particularly discloses a prediction method, a prediction device, electronic equipment and a storage medium, wherein the prediction method comprises the following steps: preprocessing a historical data set to obtain a historical development data set; acquiring historical market economic data according to a historical time period corresponding to a historical development data set; performing data association on the historical development data set and the historical market economic data to obtain fusion development data; inputting the fusion development data into an initial model for training to obtain an enterprise development prediction model; acquiring enterprise information of an enterprise to be forecasted, and then acquiring relevant policy information and market economic data according to the enterprise information to analyze to obtain forecasted market information; meanwhile, determining development parameters of the enterprise to be predicted according to the enterprise information; and then inputting the forecast market information and the development parameters of the enterprise to be forecasted into the enterprise development forecast model to obtain enterprise development forecast data, so as to realize the forecast of enterprise development.

Description

Prediction method, prediction device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a prediction method, a prediction device, electronic equipment and a storage medium.
Background
The medium and small-sized enterprises are important carriers for accelerating the development and development strategy of new and emerging industries, the vitality army for improving the autonomous innovation capability is provided, and governments all over the country continuously increase the monitoring strength on whether the scientific and technological medium and small-sized enterprises reach the regular enterprises or not in order to accelerate the development of the emerging industries. Currently, the scale monitoring results of the government on scientific and small-sized enterprises are generally obtained by analyzing historical development data of the government. However, the method is low in timeliness and poor in supervision, and only after the monitored enterprise reaches the standard and corresponding historical data are generated can the monitored enterprise be analyzed, so that the time for determining the standard reaching of the scale of a science-technology-type small and medium-sized enterprise is far beyond the actual time for determining the standard reaching of the scale of the small and medium-sized enterprise.
Disclosure of Invention
In order to solve the above problems in the prior art, the embodiments of the present application provide a prediction method, an apparatus, an electronic device, and a storage medium, which can predict the time for an enterprise scale to reach the standard, and then determine the time for the enterprise scale to reach the standard before the actual scale reaches the standard, thereby improving the timeliness and the supervision of monitoring.
In a first aspect, an embodiment of the present application provides a prediction method, including:
preprocessing a historical data set to obtain a historical development data set, wherein the historical development data set is a data set for declaring the development scale of an enterprise in a historical time period;
acquiring historical market economic data according to a historical time period corresponding to a historical development data set;
performing data association on the historical development data set and the historical market economic data to obtain fusion development data;
inputting the fusion development data into an initial model for training to obtain an enterprise development prediction model;
acquiring enterprise information of an enterprise to be predicted, wherein the enterprise information comprises an enterprise name and field information;
acquiring at least one policy information and at least one market economic data of a field corresponding to the field information according to the field information;
analyzing market economy according to the at least one policy message and the at least one market economy data to obtain forecasted market information;
acquiring at least one public opinion information related to the enterprise to be forecasted according to the enterprise name, and determining development parameters of the enterprise to be forecasted according to the at least one public opinion information;
inputting the forecast market information and the development parameters of the enterprise to be forecasted into an enterprise development forecasting model to obtain enterprise development forecasting data, wherein the enterprise development forecasting data is used for recording a forecast curve of enterprise development scale and time;
and in the enterprise development prediction data, the time point when the predicted enterprise development scale is larger than a preset threshold value is taken as a prediction time point, and the prediction time point is sent to the user side.
In a second aspect, an embodiment of the present application provides a prediction apparatus, including:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for preprocessing a historical data set to obtain a historical development data set, and the historical development data set is a data set for declaring the development scale of an enterprise in a historical time period;
the acquisition module is used for acquiring historical market economic data according to a historical time period corresponding to the historical development data set;
the training module is used for carrying out data association on the historical development data set and the historical market economic data to obtain fusion development data, inputting the fusion development data into the initial model for training to obtain an enterprise development prediction model;
the system comprises a receiving module, a prediction module and a prediction module, wherein the receiving module is used for acquiring enterprise information of an enterprise to be predicted, and the enterprise information comprises an enterprise name and field information;
the processing module is used for acquiring at least one policy information and at least one market economy data of a field corresponding to the field information according to the field information, analyzing the market economy according to the at least one policy information and the at least one market economy data to obtain forecast market information, acquiring at least one public opinion information related to the enterprise to be forecasted according to the name of the enterprise, and determining the development parameters of the enterprise to be forecasted according to the at least one public opinion information;
the prediction module is used for inputting the forecast market information and the development parameters of the enterprise to be forecasted into the enterprise development prediction model to obtain enterprise development prediction data, wherein the enterprise development prediction data is used for recording a curve of the forecast enterprise development scale and time;
and the sending module is used for taking the time point of the enterprise development prediction data, of which the predicted enterprise development scale is larger than the preset threshold value, as a prediction time point and sending the prediction time point to the user side.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor coupled to the memory, the memory for storing a computer program, the processor for executing the computer program stored in the memory to cause the electronic device to perform the method of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, the computer program causing a computer to perform the method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program, the computer operable to cause the computer to perform a method according to the first aspect.
The implementation of the embodiment of the application has the following beneficial effects:
in the embodiment of the application, a data set for declaring the development scale of an enterprise in a historical time period is collected, historical market economic data corresponding to the historical time period and the data set for declaring the development scale of the enterprise are fused to obtain fused development data of the declared enterprise under the influence of external economy, and then the fused development data are input into an initial model for training to obtain an enterprise development prediction model; acquiring enterprise information of the enterprise to be forecasted, and determining the field policy, market economy and social public opinion of the enterprise to be forecasted according to the enterprise information; then, inputting the field policy, market economy and social public opinion of the enterprise to be predicted into an enterprise development prediction model to obtain a predicted enterprise development scale and time curve of the enterprise; and finally, the time point of the enterprise development scale predicted in the curve, which is larger than a preset threshold value, is used as a prediction time point and is sent to the user side. Therefore, the automatic prediction of the time for reaching the standard of the enterprise scale is realized, the time for reaching the standard is determined before the actual scale reaches the standard, and the monitoring timeliness and the supervision are improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic hardware structure diagram of a prediction apparatus according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a prediction method according to an embodiment of the present disclosure;
FIG. 3 is a schematic flowchart of a method for preprocessing a historical data set to obtain a historical development data set according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart of a method for using at least one second candidate data meeting a preset screening condition in a second candidate data set as a historical development data set according to an embodiment of the present application;
fig. 5 is a flowchart illustrating a method for obtaining at least one piece of public opinion information related to a business to be forecasted according to a business name and determining a development parameter of the business to be forecasted according to the at least one piece of public opinion information according to an embodiment of the present application;
fig. 6 is a block diagram illustrating functional modules of a prediction apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art without any inventive work based on the embodiments in the present application are within the scope of protection of the present application.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
First, referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of a prediction apparatus according to an embodiment of the present disclosure. The predictive device 100 includes at least one processor 101, a communication link 102, a memory 103, and at least one communication interface 104.
In this embodiment, the processor 101 may be a general processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more ics for controlling the execution of programs according to the present disclosure.
The communication link 102, which may include a path, carries information between the aforementioned components.
The communication interface 104 may be any transceiver or other device (e.g., an antenna, etc.) for communicating with other devices or communication networks, such as an ethernet, RAN, Wireless Local Area Network (WLAN), etc.
The memory 103 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
In this embodiment, the memory 103 may be independent and connected to the processor 101 through the communication line 102. The memory 103 may also be integrated with the processor 101. The memory 103 provided in the embodiments of the present application may generally have a nonvolatile property. The memory 103 is used for storing computer-executable instructions for executing the scheme of the application, and is controlled by the processor 101 to execute. The processor 101 is configured to execute computer-executable instructions stored in the memory 103, thereby implementing the methods provided in the embodiments of the present application described below.
In alternative embodiments, computer-executable instructions may also be referred to as application code, which is not specifically limited in this application.
In alternative embodiments, processor 101 may include one or more CPUs, such as CPU0 and CPU1 of FIG. 1.
In alternative embodiments, prediction apparatus 100 may include multiple processors, such as processor 101 and processor 107 in FIG. 1. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
In an alternative embodiment, if the prediction apparatus 100 is a server, the prediction apparatus 100 may further include an output device 105 and an input device 106. The output device 105 is in communication with the processor 101 and may display information in a variety of ways. For example, the output device 105 may be a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display device, a Cathode Ray Tube (CRT) display device, a projector (projector), or the like. The input device 106 is in communication with the processor 101 and may receive user input in a variety of ways. For example, the input device 106 may be a mouse, a keyboard, a touch screen device, or a sensing device, among others.
The prediction apparatus 100 may be a general-purpose device or a special-purpose device. The present embodiment does not limit the type of the prediction apparatus 100.
Hereinafter, the prediction method disclosed in the present application will be explained:
referring to fig. 2, fig. 2 is a schematic flow chart of a prediction method according to an embodiment of the present disclosure. The prediction method comprises the following steps:
201: and preprocessing the historical data set to obtain a historical development data set.
In the present embodiment, the historical development data set is a data set in which the development scale of the enterprise is declared within a historical time period. Since the data in the historical data set may come from different channels, there is a certain difference in data format and data quality. Based on this, after the historical data set is obtained, the data in the historical data set needs to be preprocessed, for example: data cleansing, data supplementation, etc.
In this embodiment, a method for preprocessing a historical data set to obtain a historical development data set is provided, as shown in fig. 3, the method includes:
301: and determining the missing rate of each historical data in the historical data set according to the standard sample, and taking at least one historical data with the missing rate smaller than a first threshold value in the historical data set as a first candidate data set.
In the present embodiment, the standard sample refers to a preset standard data structure. When the data structure of the historical data in the historical data set is inconsistent with the data structure of the standard sample, it is indicated that the historical data in the historical data set has certain data loss, and whether missing value supplement is required to be performed or not needs to be judged according to the missing rate, or the sample with the over-high missing rate is directly discarded.
For example, the missing rate refers to the number of subdata in the data structure of a certain historical data in the historical data set, and the number of missing subdata is a proportion of the number of subdata in the data structure of the standard sample to the number of subdata in the data structure of the standard sample. The missing subdata refers to subdata that is present in the standard sample but not present in the history data.
Specifically, the data structure of a certain history data in the history data set is [ subdata 1; subdata 4; subdata 6, the data structure of the standard sample is [ subdata 1 ]; subdata 2; subdata 3; subdata 4; subdata 5; subdata 6 ]. Then, with respect to the standard sample, the missing subdata of the certain historical data is [ subdata 2 ], [ subdata 3 ], and [ subdata 5 ], the number is 3, and meanwhile, the number of the subdata in the standard sample is 6, then the missing rate of the certain historical data is: 3/6-50%.
In short, if the missing rate of a certain historical data exceeds the first threshold, it indicates that the data of the data is seriously missing, and even if the missing value is technically complemented, the complemented data has insufficient accuracy due to the deficiency of the basic data, and finally, junk data is formed, which affects the subsequent training of the model. Therefore, the historical data with the missing rate exceeding the first threshold value can be directly discarded, so that the processing efficiency is improved. Specifically, the first threshold may be 30%.
302: and according to the data type of each first candidate data in the first candidate data set, obtaining a completion method to complete each first candidate data to obtain a second candidate data set.
In the present embodiment, since the history data set includes various types of history data, and the data characteristics of the history data of different types are different, different completion methods are used for the history data of different data types. In particular, the completion method may include neighbor supplementation, median supplementation, and mean supplementation.
303: and taking at least one second candidate data meeting preset screening conditions in the second candidate data set as a historical development data set.
In the present embodiment, after steps 301 and 302, data with an excessively high deletion rate is eliminated and data with a low deletion rate is supplemented. However, data with poor data quality may still exist in the remaining data. When the data are trained, the accuracy of the model cannot be improved, and the accuracy and the training efficiency of the model can be reduced. Therefore, it is necessary to screen out such samples by a screening rule.
For example, the present application provides a method for using at least one second candidate data in a second candidate data set that meets a preset screening condition as a historical development data set, as shown in fig. 4, the method includes:
401: a scrambling code rate for each second candidate data in the second candidate data set is determined.
In this embodiment, a character set corresponding to each second candidate data may be obtained according to the data type of the second candidate data, the number of characters that do not belong to the character set and exist in the second candidate data is then determined, and the ratio of the number of characters that do not belong to the character set and the total number of characters of the second candidate data and exist in the second candidate data is used as the scrambling code rate of the second candidate data.
402: and determining the number of code values obtained after the second candidate data are dispersed.
403: and determining at least one second candidate data in a second candidate data set as a historical development data set according to the scrambling code rate of each second candidate data and the number of code values obtained after each second candidate data is dispersed.
In this embodiment, the scrambling code rate corresponding to each of the at least one second candidate data is smaller than the second threshold, or the number of code values obtained by discretizing each of the at least one second candidate data is smaller than the third threshold. For example, in a simple manner, if the scrambling rate of a certain second candidate data exceeds a second threshold, it indicates that the data scrambling of the data is serious, and even if the scrambling is recovered and complemented, the complemented data is not accurate enough due to the deficiency of the basic data, and finally, poor-quality data is formed, which affects the training of the model. Similarly, the number of code values obtained by a second candidate data after dispersion is greater than a third threshold, which indicates that the sample includes many label points, the data dispersion is serious, high-quality data features cannot be extracted, and the training of the model is also affected. Therefore, the second candidate data with the code scrambling rate exceeding the second threshold or the number of the code values obtained after the dispersion being larger than the third threshold can be directly discarded, so as to improve the processing efficiency. Specifically, the second threshold value may be 30%, and the third threshold value may be 500.
202: and acquiring historical market economic data according to the historical time period corresponding to the historical development data set.
203: and carrying out data association on the historical development data set and the historical market economic data to obtain fusion development data.
In this embodiment, the historical time period may be divided into at least one sub-time period according to the historical market economic data, and the historical market economic data may be divided into at least one economic sub-data according to the at least one sub-time period. Specifically, the historical time period may be divided into at least one sub-time period by calculating a market economic fluctuation amplitude within a period of time, for example, a period of time in which the market economic fluctuation amplitude is smaller than a fourth threshold value is divided into one sub-time, and thus, there is a one-to-one correspondence between at least one economic sub-data and at least one sub-time period.
The historical development data set may then be partitioned into at least one sub data set according to the at least one sub time period. Specifically, at least one sub data set corresponds to at least one sub time period, and the historical development data in each sub data set in the at least one sub data set is used for declaring the development condition of the enterprise in the sub time period corresponding to each sub data set.
In this embodiment, after dividing the historical development data set into at least one sub data set, feature extraction may be performed on each sub data set to obtain at least one first data feature, and feature extraction may be performed on each economic sub data to obtain at least one second data feature, where the at least one first data feature and the at least one second data feature are in one-to-one correspondence.
And finally, fusing each first data feature in the at least one first data feature and a second data feature corresponding to each first data feature to obtain at least one fused feature, and taking the at least one fused feature as fusion development data.
204: and inputting the fusion development data into the initial model for training to obtain an enterprise development prediction model.
205: and acquiring enterprise information of the enterprise to be forecasted, wherein the enterprise information comprises an enterprise name and field information.
206: and acquiring at least one policy information and at least one market economic data of the domain corresponding to the domain information according to the domain information.
In the embodiment, the domain information can be subjected to keyword extraction, and then relevant policy information and market economic data can be captured on the network according to the extracted keywords.
207: and analyzing the market economy according to the at least one policy message and the at least one market economy data to obtain forecasted market information.
In the embodiment, the policy information can reflect the regulation degree and the support degree of the country on the development of the field, and the market economic information can reflect the current market development trend and the economic effect trend of the field. Based on the market forecasting method, certain forecasting can be carried out on market conditions in the future period of time in the field by combining at least one piece of policy information and at least one piece of market economic data to obtain forecasted market information.
208: the method comprises the steps of obtaining at least one piece of public opinion information related to the enterprise to be forecasted according to the name of the enterprise, and determining development parameters of the enterprise to be forecasted according to the at least one piece of public opinion information.
In this embodiment, a method for obtaining at least one piece of public opinion information related to a business to be forecasted according to a business name and determining a development parameter of the business to be forecasted according to the at least one piece of public opinion information is provided, as shown in fig. 5, the method includes:
501: and performing data retrieval according to the enterprise name of the enterprise to be predicted to obtain at least one piece of news information.
In this embodiment, each of the at least one news item includes a business name. For example, the search may be performed by a business name, and then news information including the business name may be collected. Further, data association can be performed according to the name of the enterprise, for example: and determining the name of the parent company or the sub-company under the flag to which the enterprise belongs according to the name of the enterprise, searching according to the name of the parent company or the sub-company under the flag to which the enterprise belongs, and obtaining a series of news data as supplementary data.
502: and performing data screening on at least one news information to obtain at least one public opinion information.
In this embodiment, the news confidence of each news information may be determined by determining the publishing platform and the publisher of each news information, and then according to the first platform confidence of the publishing platform and the first personal confidence of the publisher of each news information. Then, the news information with the highest news confidence coefficient is used as mainstream news information, and a correlation coefficient between each news information and the mainstream news information is determined.
In this embodiment, the correlation coefficient may be a Spearman (Spearman) correlation coefficient. Specifically, first, feature extraction may be performed on each piece of news information to obtain a news feature, and feature extraction may be performed on mainstream news information to obtain a mainstream news feature. Then, a difference between the news characteristic and the mainstream news characteristic is determined, and a quantity of the at least one news information. And finally, determining a correlation coefficient between each news information and the mainstream news information according to the difference between the news characteristics and the mainstream news characteristics and the quantity of the at least one news information.
Illustratively, the Spearman correlation coefficient can be expressed by the formula (i):
Figure BDA0003318362850000101
wherein, gjA difference between the news characteristic of each news information and the mainstream news characteristic of the mainstream news information; t denotes the number of at least one news information.
After determining a correlation coefficient between each news information and the mainstream news information, at least one candidate news information may be determined among the at least one news information according to the correlation coefficient. Specifically, the correlation coefficient between each candidate news information of the screened at least one candidate news information and the mainstream news information is larger than the fourth threshold.
And finally, determining the information value of each candidate news information, and determining at least one public opinion information in at least one candidate news information according to the information value. Specifically, the information value of each public opinion information of the at least one public opinion information is greater than the fifth threshold.
In this embodiment, the Information Value (IV) may represent the feature importance of each candidate news Information, and the IV Value may be represented by a formula (ii):
Figure BDA0003318362850000111
wherein, PykAfter the information characteristics of each candidate news information are subjected to box separation, the proportion of elements which do not meet preset conditions in a kth box to the total elements of the kth box is represented; pckRepresenting the proportion of elements meeting the preset conditions in the kth box to the total elements in the kth box; WOEkThe corresponding evidence weight (weight of evidence) of the k box; f represents the number of the box bodies obtained after the information characteristics of each candidate news information are subjected to box separation.
In the present embodiment, WOEkCan be expressed by the formula (c):
Figure BDA0003318362850000112
503: and determining the important coefficient of each public opinion information according to the publishing platform information, the publisher information and the publishing type information of each public opinion information in the at least one public opinion information.
In the present embodiment, first, a platform weight of a platform for distributing each public opinion information and a personal weight of a distributor for each public opinion information may be determined according to a business name of a business to be forecasted. Then, a second platform confidence of a publishing platform of each public opinion information and a second person confidence of a publisher of each public opinion information are determined. And weighting and summing the second platform confidence coefficient of the publishing platform of each public opinion information and the second person confidence coefficient of the publisher of each public opinion information according to the platform weight of the publishing platform of each public opinion information and the personal weight of the publisher of each public opinion information to obtain a first coefficient. Then, determining the publishing weight of each public opinion information according to the publishing type information of each public opinion information, wherein the publishing type information comprises an initial publishing type and a forwarding type, and the publishing type information of the forwarding type also comprises the number of forwarding rounds. And finally, taking the product of the issuing weight and the first coefficient as an important coefficient of each public opinion information.
504: and extracting keywords from each public opinion information to obtain at least one negative keyword.
505: a Term Frequency-Inverse Document Frequency (TF-IDF) index is determined for each of the at least one negative keyword.
506: and determining the development parameters of the enterprise to be predicted according to the product of the important coefficient and the word frequency-inverse document frequency index.
209: and inputting the forecast market information and the development parameters of the enterprise to be forecasted into the enterprise development forecast model to obtain enterprise development forecast data.
In this embodiment, the business development forecast data is used to record a curve of the size of the forecasted business development versus time.
210: and in the enterprise development prediction data, the time point when the predicted enterprise development scale is larger than a preset threshold value is taken as a prediction time point, and the prediction time point is sent to the user side.
In summary, in the prediction method provided by the present invention, a data set for declaring the development scale of an enterprise in a historical time period is collected, and then historical market economic data corresponding to the historical time period is fused with the data set for declaring the development scale of the enterprise to obtain fused development data of the declared enterprise under the influence of external economy, and then the fused development data is input into an initial model for training to obtain an enterprise development prediction model; acquiring enterprise information of the enterprise to be forecasted, and determining the field policy, market economy and social public opinion of the enterprise to be forecasted according to the enterprise information; then, inputting the field policy, market economy and social public opinion of the enterprise to be predicted into an enterprise development prediction model to obtain a predicted enterprise development scale and time curve of the enterprise; and finally, the time point of the enterprise development scale predicted in the curve, which is larger than a preset threshold value, is used as a prediction time point and is sent to the user side. Therefore, the automatic prediction of the time for reaching the standard of the enterprise scale is realized, the time for reaching the standard is determined before the actual scale reaches the standard, and the monitoring timeliness and the supervision are improved.
Referring to fig. 6, fig. 6 is a block diagram illustrating functional modules of a prediction apparatus according to an embodiment of the present disclosure. As shown in fig. 6, the prediction apparatus 600 includes:
the system comprises a preprocessing module 601, a historical development module and a development module, wherein the preprocessing module is used for preprocessing a historical data set to obtain a historical development data set, and the historical development data set is a data set for declaring the development scale of an enterprise in a historical time period;
the acquisition module 602 is configured to acquire historical market economic data according to a historical time period corresponding to a historical development data set;
the training module 603 is used for performing data association on the historical development data set and the historical market economic data to obtain fusion development data, inputting the fusion development data into the initial model for training to obtain an enterprise development prediction model;
a receiving module 604, configured to obtain enterprise information of an enterprise to be forecasted, where the enterprise information includes an enterprise name and field information;
the processing module 605 is configured to obtain at least one policy information and at least one market economic data of a field corresponding to the field information according to the field information, analyze the market economy according to the at least one policy information and the at least one market economic data to obtain forecasted market information, obtain at least one public opinion information related to the enterprise to be forecasted according to the name of the enterprise, and determine a development parameter of the enterprise to be forecasted according to the at least one public opinion information;
the forecasting module 606 is used for inputting the forecast market information and the development parameters of the enterprise to be forecasted into the enterprise development forecasting model to obtain enterprise development forecasting data, wherein the enterprise development forecasting data is used for recording a forecast curve of enterprise development scale and time;
the sending module 607 is configured to use a time point, in the enterprise development prediction data, at which the predicted enterprise development scale is greater than a preset threshold as a predicted time point, and send the predicted time point to the user side.
In an embodiment of the present invention, in terms of preprocessing a historical data set to obtain a historical development data set, the preprocessing module 601 is specifically configured to:
determining the missing rate of each historical data in the historical data set according to the standard sample, and taking at least one historical data of which the missing rate is smaller than a first threshold value in the historical data set as a first candidate data set;
according to the data type of each first candidate data in the first candidate data set, a completion method is obtained to complete each first candidate data to obtain a second candidate data set;
and taking at least one second candidate data meeting preset screening conditions in the second candidate data set as a historical development data set.
In an embodiment of the present invention, in regard to taking at least one second candidate data in the second candidate data set that meets a preset screening condition as the historical development data set, the preprocessing module 601 is specifically configured to:
determining a scrambling code rate of each second candidate data in the second candidate data set;
determining the number of code values obtained after each second candidate data is dispersed;
and determining at least one second candidate data in a second candidate data set as a historical development data set according to the scrambling code rate of each second candidate data and the number of code values obtained by each second candidate data after dispersion, wherein the scrambling code rate corresponding to each second candidate data in the at least one second candidate data is smaller than a second threshold value, or the number of code values obtained by each second candidate data in the at least one second candidate data after dispersion is smaller than a third threshold value.
In an embodiment of the present invention, in the aspect of performing data association on the historical development data set and the historical market economic data to obtain fusion development data, the training module 603 is specifically configured to:
dividing the historical time period into at least one sub-time period according to the historical market economic data, and dividing the historical market economic data into at least one economic subdata according to the at least one sub-time period, wherein the at least one economic subdata is in one-to-one correspondence with the at least one sub-time period, and the market economic fluctuation amplitude in each time period in the at least one sub-time period is smaller than a fourth threshold value;
dividing the historical development data set into at least one sub-data set according to at least one sub-time period, wherein the at least one sub-data set corresponds to the at least one sub-time period one by one, and the historical development data in each sub-data set in the at least one sub-data set is used for declaring the development condition of an enterprise in the sub-time period corresponding to each sub-data set;
respectively extracting features of each subdata set to obtain at least one first data feature, and respectively extracting features of each economic subdata set to obtain at least one second data feature, wherein the at least one first data feature is in one-to-one correspondence with the at least one second data feature;
and respectively fusing each first data feature in the at least one first data feature and a second data feature corresponding to each first data feature to obtain at least one fused feature, and taking the at least one fused feature as fused development data.
In an embodiment of the present invention, in obtaining at least one public opinion information related to the enterprise to be forecasted according to the name of the enterprise, and determining a development parameter of the enterprise to be forecasted according to the at least one public opinion information, the processing module 605 is specifically configured to:
performing data retrieval according to the enterprise name of the enterprise to be predicted to obtain at least one piece of news information, wherein each piece of news information in the at least one piece of news information comprises the enterprise name;
performing data screening on at least one news information to obtain at least one public opinion information;
determining an important coefficient of each public opinion information according to the publishing platform information, the publisher information and the publishing type information of each public opinion information in at least one public opinion information;
extracting keywords from each public opinion information to obtain at least one negative keyword;
determining a word frequency-inverse document frequency index for each of the at least one negative keyword;
and determining the development parameters of the enterprise to be predicted according to the product of the important coefficient and the word frequency-inverse document frequency index.
In an embodiment of the present invention, in the aspect of performing data filtering on at least one news information to obtain at least one public opinion information, the processing module 605 is specifically configured to:
determining a publishing platform and a publisher of each news information;
determining the news confidence coefficient of each news information according to the first platform confidence coefficient of the publishing platform and the first personal confidence coefficient of the publisher of each news information;
taking the news information with the highest news confidence coefficient as mainstream news information;
determining a correlation coefficient between each news information and the mainstream news information;
determining at least one candidate news information in the at least one news information according to the correlation coefficient, wherein the correlation coefficient between each candidate news information in the at least one candidate news information and the mainstream news information is larger than a fourth threshold value;
and determining the information value of each candidate news information, and determining at least one public opinion information in the at least one candidate news information according to the information value, wherein the information value of each public opinion information in the at least one public opinion information is greater than a fifth threshold value.
In an embodiment of the present invention, in determining a correlation coefficient between each news information and the mainstream news information, the processing module 605 is specifically configured to:
extracting the characteristics of each news information to obtain news characteristics;
extracting the features of the mainstream news information to obtain the mainstream news features;
determining a difference between the news characteristic and the mainstream news characteristic, and the quantity of at least one news message;
and determining a correlation coefficient between each news information and the mainstream news information according to the difference between the news characteristics and the mainstream news characteristics and the quantity of the at least one news information.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the electronic device 700 includes a transceiver 701, a processor 702, and a memory 703. Connected to each other by a bus 704. The memory 703 is used to store computer programs and data, and may transfer the data stored in the memory 703 to the processor 702.
The processor 702 is configured to read the computer program in the memory 703 to perform the following operations:
preprocessing a historical data set to obtain a historical development data set, wherein the historical development data set is a data set for declaring the development scale of an enterprise in a historical time period;
acquiring historical market economic data according to a historical time period corresponding to a historical development data set;
performing data association on the historical development data set and the historical market economic data to obtain fusion development data;
inputting the fusion development data into an initial model for training to obtain an enterprise development prediction model;
acquiring enterprise information of an enterprise to be predicted, wherein the enterprise information comprises an enterprise name and field information;
acquiring at least one policy information and at least one market economic data of a field corresponding to the field information according to the field information;
analyzing market economy according to the at least one policy message and the at least one market economy data to obtain forecasted market information;
acquiring at least one public opinion information related to the enterprise to be forecasted according to the enterprise name, and determining development parameters of the enterprise to be forecasted according to the at least one public opinion information;
inputting the forecast market information and the development parameters of the enterprise to be forecasted into an enterprise development forecasting model to obtain enterprise development forecasting data, wherein the enterprise development forecasting data is used for recording a forecast curve of enterprise development scale and time;
and in the enterprise development prediction data, the time point when the predicted enterprise development scale is larger than a preset threshold value is taken as a prediction time point, and the prediction time point is sent to the user side.
In an embodiment of the present invention, in preprocessing the historical data set to obtain a historical development data set, the processor 702 is specifically configured to perform the following operations:
determining the missing rate of each historical data in the historical data set according to the standard sample, and taking at least one historical data of which the missing rate is smaller than a first threshold value in the historical data set as a first candidate data set;
according to the data type of each first candidate data in the first candidate data set, a completion method is obtained to complete each first candidate data to obtain a second candidate data set;
and taking at least one second candidate data meeting preset screening conditions in the second candidate data set as a historical development data set.
In an embodiment of the present invention, in regard to regarding at least one second candidate data satisfying a preset screening condition in the second candidate data set as the historical development data set, the processor 702 is specifically configured to perform the following operations:
determining a scrambling code rate of each second candidate data in the second candidate data set;
determining the number of code values obtained after each second candidate data is dispersed;
and determining at least one second candidate data in a second candidate data set as a historical development data set according to the scrambling code rate of each second candidate data and the number of code values obtained by each second candidate data after dispersion, wherein the scrambling code rate corresponding to each second candidate data in the at least one second candidate data is smaller than a second threshold value, or the number of code values obtained by each second candidate data in the at least one second candidate data after dispersion is smaller than a third threshold value.
In an embodiment of the present invention, in data association between the historical development data set and the historical market economic data to obtain the fusion development data, the processor 702 is specifically configured to perform the following operations:
dividing the historical time period into at least one sub-time period according to the historical market economic data, and dividing the historical market economic data into at least one economic subdata according to the at least one sub-time period, wherein the at least one economic subdata is in one-to-one correspondence with the at least one sub-time period, and the market economic fluctuation amplitude in each time period in the at least one sub-time period is smaller than a fourth threshold value;
dividing the historical development data set into at least one sub-data set according to at least one sub-time period, wherein the at least one sub-data set corresponds to the at least one sub-time period one by one, and the historical development data in each sub-data set in the at least one sub-data set is used for declaring the development condition of an enterprise in the sub-time period corresponding to each sub-data set;
respectively extracting features of each subdata set to obtain at least one first data feature, and respectively extracting features of each economic subdata set to obtain at least one second data feature, wherein the at least one first data feature is in one-to-one correspondence with the at least one second data feature;
and respectively fusing each first data feature in the at least one first data feature and a second data feature corresponding to each first data feature to obtain at least one fused feature, and taking the at least one fused feature as fused development data.
In an embodiment of the present invention, in obtaining at least one public opinion information related to a business to be forecasted according to a business name, and determining a development parameter of the business to be forecasted according to the at least one public opinion information, the processor 702 is specifically configured to perform the following operations:
performing data retrieval according to the enterprise name of the enterprise to be predicted to obtain at least one piece of news information, wherein each piece of news information in the at least one piece of news information comprises the enterprise name;
performing data screening on at least one news information to obtain at least one public opinion information;
determining an important coefficient of each public opinion information according to the publishing platform information, the publisher information and the publishing type information of each public opinion information in at least one public opinion information;
extracting keywords from each public opinion information to obtain at least one negative keyword;
determining a word frequency-inverse document frequency index for each of the at least one negative keyword;
and determining the development parameters of the enterprise to be predicted according to the product of the important coefficient and the word frequency-inverse document frequency index.
In an embodiment of the present invention, in data filtering at least one news information to obtain at least one public opinion information, the processor 702 is specifically configured to perform the following operations:
determining a publishing platform and a publisher of each news information;
determining the news confidence coefficient of each news information according to the first platform confidence coefficient of the publishing platform and the first personal confidence coefficient of the publisher of each news information;
taking the news information with the highest news confidence coefficient as mainstream news information;
determining a correlation coefficient between each news information and the mainstream news information;
determining at least one candidate news information in the at least one news information according to the correlation coefficient, wherein the correlation coefficient between each candidate news information in the at least one candidate news information and the mainstream news information is larger than a fourth threshold value;
and determining the information value of each candidate news information, and determining at least one public opinion information in the at least one candidate news information according to the information value, wherein the information value of each public opinion information in the at least one public opinion information is greater than a fifth threshold value.
In an embodiment of the present invention, in determining a correlation coefficient between each news information and the mainstream news information, the processor 702 is specifically configured to:
extracting the characteristics of each news information to obtain news characteristics;
extracting the features of the mainstream news information to obtain the mainstream news features;
determining a difference between the news characteristic and the mainstream news characteristic, and the quantity of at least one news message;
and determining a correlation coefficient between each news information and the mainstream news information according to the difference between the news characteristics and the mainstream news characteristics and the quantity of the at least one news information.
It should be understood that the prediction device in the present application may include a smart Phone (e.g., an Android Phone, an iOS Phone, a Windows Phone, etc.), a tablet computer, a palm computer, a notebook computer, a Mobile Internet device MID (MID), a robot, a wearable device, etc. The above prediction devices are merely examples, not exhaustive, and include but are not limited to the above prediction devices. In practical applications, the prediction apparatus may further include: intelligent vehicle-mounted terminal, computer equipment and the like.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented by combining software and a hardware platform. With this understanding in mind, all or part of the technical solutions of the present invention that contribute to the background can be embodied in the form of a software product, which can be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods according to the embodiments or some parts of the embodiments.
Accordingly, the present application also provides a computer readable storage medium, which stores a computer program, the computer program being executed by a processor to implement part or all of the steps of any one of the prediction methods as described in the above method embodiments. For example, the storage medium may include a hard disk, a floppy disk, an optical disk, a magnetic tape, a magnetic disk, a flash memory, and the like.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the prediction methods as described in the above method embodiments.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are all alternative embodiments and that the acts and modules referred to are not necessarily required by the application.
In the above embodiments, the description of each embodiment has its own emphasis, and for parts not described in detail in a certain embodiment, reference may be made to the description of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.
The integrated units, if implemented in the form of software program modules and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, and the memory may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the methods and their core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. A method of prediction, the method comprising:
preprocessing a historical data set to obtain a historical development data set, wherein the historical development data set is a data set for declaring the development scale of an enterprise in a historical time period;
acquiring historical market economic data according to a historical time period corresponding to the historical development data set;
performing data association on the historical development data set and the historical market economic data to obtain fusion development data;
inputting the fusion development data into an initial model for training to obtain an enterprise development prediction model;
acquiring enterprise information of an enterprise to be forecasted, wherein the enterprise information comprises an enterprise name and field information;
acquiring at least one policy information and at least one market economic data of a field corresponding to the field information according to the field information;
analyzing market economy according to the at least one policy message and the at least one market economy data to obtain forecasted market information;
acquiring at least one public opinion information related to the enterprise to be forecasted according to the enterprise name, and determining development parameters of the enterprise to be forecasted according to the at least one public opinion information;
inputting the forecast market information and the development parameters of the enterprise to be forecasted into the enterprise development forecasting model to obtain enterprise development forecasting data, wherein the enterprise development forecasting data is used for recording a forecast curve of enterprise development scale and time;
and in the enterprise development prediction data, the time point when the predicted enterprise development scale is larger than a preset threshold value is taken as a prediction time point, and the prediction time point is sent to a user side.
2. The method of claim 1, wherein preprocessing the historical data set to obtain a historical development data set comprises:
determining the missing rate of each historical data in the historical data set according to a standard sample, and taking at least one historical data of which the missing rate is smaller than a first threshold value in the historical data set as a first candidate data set;
according to the data type of each first candidate data in the first candidate data set, a completion method is obtained to complete each first candidate data to obtain a second candidate data set;
and taking at least one second candidate data meeting preset screening conditions in the second candidate data set as the historical development data set.
3. The method according to claim 2, wherein the using at least one second candidate data in the second candidate data set that meets a preset screening condition as the historical development data set comprises:
determining a scrambling code rate for each second candidate data in the second candidate data set;
determining the number of code values obtained after each second candidate data is dispersed;
and determining the at least one second candidate data in the second candidate data set as the historical development data set according to the scrambling code rate of each second candidate data and the number of the code values obtained by each second candidate data after discretization, wherein the scrambling code rate corresponding to each second candidate data in the at least one second candidate data is smaller than a second threshold, or the number of the code values obtained by each second candidate data in the at least one second candidate data after discretization is smaller than a third threshold.
4. The method of claim 1, wherein said data correlating said historical development data set with said historical market economic data to obtain fused development data comprises:
dividing the historical time period into at least one sub-time period according to the historical market economy data, and dividing the historical market economy data into at least one economy sub-data according to the at least one sub-time period, wherein the at least one economy sub-data is in one-to-one correspondence with the at least one sub-time period, and the market economy fluctuation amplitude in each time period in the at least one sub-time period is smaller than a fourth threshold value;
dividing the historical development data set into at least one sub-data set according to the at least one sub-time period, wherein the at least one sub-data set corresponds to the at least one sub-time period one to one, and the historical development data in each sub-data set in the at least one sub-data set is used for declaring the development condition of an enterprise in the sub-time period corresponding to each sub-data set;
respectively performing feature extraction on each subdata set to obtain at least one first data feature, and respectively performing feature extraction on each economic subdata set to obtain at least one second data feature, wherein the at least one first data feature and the at least one second data feature are in one-to-one correspondence;
and respectively fusing each first data feature in the at least one first data feature and a second data feature corresponding to each first data feature to obtain at least one fused feature, and taking the at least one fused feature as the fused development data.
5. The method as claimed in claim 1, wherein the obtaining at least one public opinion information related to the enterprise to be forecasted according to the enterprise name and determining the development parameters of the enterprise to be forecasted according to the at least one public opinion information comprises:
performing data retrieval according to the enterprise name of the enterprise to be forecasted to obtain at least one piece of news information, wherein each piece of news information in the at least one piece of news information comprises the enterprise name;
performing data screening on the at least one news information to obtain the at least one public opinion information;
determining an important coefficient of each public opinion information according to the publishing platform information, the publisher information and the publishing type information of each public opinion information in the at least one public opinion information;
extracting keywords from each public opinion information to obtain at least one negative keyword;
determining a word frequency-inverse document frequency index for each of the at least one negative keyword;
and determining the development parameters of the enterprise to be predicted according to the product of the important coefficient and the word frequency-inverse document frequency index.
6. The method of claim 5, wherein the data filtering the at least one news information to obtain the at least one public opinion information comprises:
determining a publishing platform and a publisher of each news information;
determining the news confidence of each news information according to the first platform confidence of the publishing platform and the first personal confidence of the publisher of each news information;
taking the news information with the highest news confidence coefficient as mainstream news information;
determining a correlation coefficient between each news information and the mainstream news information;
determining at least one candidate news information in the at least one news information according to the correlation coefficient, wherein the correlation coefficient between each candidate news information in the at least one candidate news information and the mainstream news information is larger than a fourth threshold value;
and determining the information value of each candidate news information, and determining the at least one public opinion information in the at least one candidate news information according to the information value, wherein the information value of each public opinion information in the at least one public opinion information is greater than a fifth threshold value.
7. The method of claim 6, wherein determining the relevance coefficient between each of the news information and the mainstream news information comprises:
extracting the characteristics of each news information to obtain news characteristics;
extracting the features of the mainstream news information to obtain mainstream news features;
determining a difference between the news characteristic and the mainstream news characteristic, and a quantity of the at least one news information;
and determining a correlation coefficient between each news information and the mainstream news information according to the difference between the news characteristic and the mainstream news characteristic and the quantity of the at least one news information.
8. A prediction apparatus, characterized in that the apparatus comprises:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for preprocessing a historical data set to obtain a historical development data set, and the historical development data set is a data set for declaring the development scale of an enterprise in a historical time period;
the acquisition module is used for acquiring historical market economic data according to the historical time period corresponding to the historical development data set;
the training module is used for carrying out data association on the historical development data set and the historical market economic data to obtain fusion development data, and inputting the fusion development data into an initial model for training to obtain an enterprise development prediction model;
the system comprises a receiving module, a prediction module and a prediction module, wherein the receiving module is used for acquiring enterprise information of an enterprise to be predicted, and the enterprise information comprises an enterprise name and field information;
the processing module is used for acquiring at least one policy information and at least one market economy data of a field corresponding to the field information according to the field information, analyzing market economy according to the at least one policy information and the at least one market economy data to obtain forecasted market information, acquiring at least one public opinion information related to the enterprise to be forecasted according to the enterprise name, and determining the development parameters of the enterprise to be forecasted according to the at least one public opinion information;
the forecasting module is used for inputting the forecasted market information and the development parameters of the enterprise to be forecasted into the enterprise development forecasting model to obtain enterprise development forecasting data, wherein the enterprise development forecasting data is used for recording a forecasted enterprise development scale and time curve;
and the sending module is used for taking the time point of the enterprise development prediction data, of which the predicted enterprise development scale is larger than a preset threshold value, as a prediction time point and sending the prediction time point to a user side.
9. An electronic device comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, the one or more programs including instructions for performing the steps in the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method according to any one of claims 1-7.
CN202111244212.0A 2021-10-25 2021-10-25 Prediction method, prediction device, electronic equipment and storage medium Active CN114021788B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111244212.0A CN114021788B (en) 2021-10-25 2021-10-25 Prediction method, prediction device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111244212.0A CN114021788B (en) 2021-10-25 2021-10-25 Prediction method, prediction device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114021788A true CN114021788A (en) 2022-02-08
CN114021788B CN114021788B (en) 2022-07-26

Family

ID=80057550

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111244212.0A Active CN114021788B (en) 2021-10-25 2021-10-25 Prediction method, prediction device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114021788B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108038164A (en) * 2017-12-06 2018-05-15 上海宽全智能科技有限公司 Data correlation method, equipment and storage medium
US20180158078A1 (en) * 2016-12-05 2018-06-07 Institute For Information Industry Computer device and method for predicting market demand of commodities
CN109977300A (en) * 2019-02-22 2019-07-05 深圳壹账通智能科技有限公司 Enterprise's public sentiment acquisition methods, device, terminal and computer storage medium
CN110009128A (en) * 2019-01-28 2019-07-12 平安科技（深圳）有限公司 Industry public opinion index prediction technique, device, computer equipment and storage medium
CN110222249A (en) * 2019-05-06 2019-09-10 平安科技（深圳）有限公司 Date storage method, device, computer equipment and storage medium
CN112632218A (en) * 2020-12-15 2021-04-09 西安电子科技大学 Network public opinion monitoring method for enterprise crisis public customs
CN112711705A (en) * 2020-11-30 2021-04-27 泰康保险集团股份有限公司 Public opinion data processing method, equipment and storage medium
CN112767008A (en) * 2020-12-31 2021-05-07 平安科技（深圳）有限公司 Enterprise revenue trend prediction method and device, computer equipment and storage medium
US20210157860A1 (en) * 2019-04-30 2021-05-27 Beijing Bytedance Network Technology Co., Ltd. Object recommendation method and apparatus, storage medium and terminal device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180158078A1 (en) * 2016-12-05 2018-06-07 Institute For Information Industry Computer device and method for predicting market demand of commodities
CN108038164A (en) * 2017-12-06 2018-05-15 上海宽全智能科技有限公司 Data correlation method, equipment and storage medium
CN110009128A (en) * 2019-01-28 2019-07-12 平安科技（深圳）有限公司 Industry public opinion index prediction technique, device, computer equipment and storage medium
CN109977300A (en) * 2019-02-22 2019-07-05 深圳壹账通智能科技有限公司 Enterprise's public sentiment acquisition methods, device, terminal and computer storage medium
US20210157860A1 (en) * 2019-04-30 2021-05-27 Beijing Bytedance Network Technology Co., Ltd. Object recommendation method and apparatus, storage medium and terminal device
CN110222249A (en) * 2019-05-06 2019-09-10 平安科技（深圳）有限公司 Date storage method, device, computer equipment and storage medium
CN112711705A (en) * 2020-11-30 2021-04-27 泰康保险集团股份有限公司 Public opinion data processing method, equipment and storage medium
CN112632218A (en) * 2020-12-15 2021-04-09 西安电子科技大学 Network public opinion monitoring method for enterprise crisis public customs
CN112767008A (en) * 2020-12-31 2021-05-07 平安科技（深圳）有限公司 Enterprise revenue trend prediction method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN114021788B (en) 2022-07-26

Similar Documents

Publication Publication Date Title
US20190108242A1 (en) Search method and processing device
US11741094B2 (en) Method and system for identifying core product terms
CN112818230B (en) Content recommendation method, device, electronic equipment and storage medium
US20220284067A1 (en) Method for pushing information, electronic device
CN108241867B (en) Classification method and device
CN114428677B (en) Task processing method, processing device, electronic equipment and storage medium
CN114330329A (en) Service content searching method and device, electronic equipment and storage medium
US20130325861A1 (en) Data Clustering for Multi-Layer Social Link Analysis
CN116028618A (en) Text processing method, text searching method, text processing device, text searching device, electronic equipment and storage medium
CN113505273B (en) Data sorting method, device, equipment and medium based on repeated data screening
CN115632874A (en) Method, device, equipment and storage medium for detecting threat of entity object
CN107527289B (en) Investment portfolio industry configuration method, device, server and storage medium
CN116304236A (en) User portrait generation method and device, electronic equipment and storage medium
CN114021788B (en) Prediction method, prediction device, electronic equipment and storage medium
CN114647739B (en) Entity chain finger method, device, electronic equipment and storage medium
CN114358879A (en) Real-time price monitoring method and system based on big data
KR102041915B1 (en) Database module using artificial intelligence, economic data providing system and method using the same
CN113612777A (en) Training method, traffic classification method, device, electronic device and storage medium
CN111914136A (en) Resource management method and device, electronic equipment and storage medium
CN112784600A (en) Information sorting method and device, electronic equipment and storage medium
CN113837764B (en) Risk early warning method, risk early warning device, electronic equipment and storage medium
CN114091463B (en) Regional work order random point analysis method and device, electronic equipment and readable storage medium
CN114416174A (en) Model reconstruction method and device based on metadata, electronic equipment and storage medium
CN117809133A (en) Data set management method, device, equipment and medium
CN117290758A (en) Classification and classification method, device, equipment and medium for unstructured document

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant