CN113780667A - Enterprise operation prediction method and system based on AI artificial intelligence - Google Patents
Enterprise operation prediction method and system based on AI artificial intelligence Download PDFInfo
- Publication number
- CN113780667A CN113780667A CN202111081156.3A CN202111081156A CN113780667A CN 113780667 A CN113780667 A CN 113780667A CN 202111081156 A CN202111081156 A CN 202111081156A CN 113780667 A CN113780667 A CN 113780667A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise operation
- prediction
- processed
- model
- 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.)
- Pending
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an enterprise operation prediction method and system based on AI artificial intelligence, which obtains data to be processed input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation; taking data to be processed as an evaluation object, and dividing the data to be processed into management data and service data according to a self-defined classification rule of the data to be processed; obtaining the classified characteristic quantities of all parts, and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities; and inputting the key characteristic quantity into a pre-established machine learning model, and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data. The scheme can analyze the performance of the existing prediction result in different time periods, and further predict future operation data. The method is convenient for enterprises to deploy resources in advance, take more optimized decision-making measures and implement healthy development.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an enterprise operation prediction method and system based on AI artificial intelligence.
Background
In the data era, each enterprise is submerged in a data ocean, too much data, incomplete data and fake data can cause the blind area of operation and management decision-making to be increased, the uncertainty of the enterprise operation in the future is greatly increased, and the limitation of human perception and cognition determines that the future cannot be predicted in the complex data ocean. Thus, businesses call for new scientific forecasting methods so that enterprises can deploy resources in advance and adopt more effective strategic strategies to develop business.
In the business intelligence BI technology in the prior art, various business IT systems of an enterprise, such as ERP, CRM and the like, are collected, tabular analysis and processing of data are carried out, and corresponding query and analysis tools are utilized to output reports for showing and analyzing so as to provide data analysis support for the enterprise. It includes three important parts: data source collection, data preparation of a data warehouse, visualization report display and data analysis.
The data collected by the business intelligence BI is a result, and only tells the enterprise what the decision maker is, but not what the reason is, what the cause of the problem is; let alone the pattern and regularity behind the data. Thus, BI can only be used as a query effect, which cannot directly generate a prediction decision, and enterprises use the data processed by BI to support the decision. This deficiency of BI is fundamentally, in essence, business intelligence BI is an IT system, without autonomous machine learning.
Disclosure of Invention
Aiming at the defects and shortcomings in the prior art, the invention is based on big data artificial intelligence and innovation of mobile internet technology, integrates new business management ideas, invents an enterprise operation prediction method and system based on AI artificial intelligence based on SAAS and AI alpha enterprise operation prediction, and provides an operation prediction visualization solution from daily operation tracking, operation performance evaluation, future operation prediction and optimization measures for enterprise decision makers, managers and business personnel.
In order to achieve the purpose, the technical scheme of the invention is as follows:
an AI artificial intelligence based enterprise operation prediction method, the method comprising:
acquiring data to be processed input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation;
taking data to be processed as an evaluation object, and dividing the data to be processed into management data and service data according to a self-defined classification rule of the data to be processed;
obtaining the classified characteristic quantities of all parts, and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities;
and inputting the key characteristic quantity into a pre-established machine learning model, and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data.
Preferably, the step of inputting the key feature quantity into a pre-established machine learning model, and analyzing to obtain the enterprise operation prediction result and the corresponding prediction decision data includes:
a: establishing an enterprise operation historical database for storing enterprise historical operation data and corresponding key characteristic quantities of enterprise operation in a certain past time period;
b: constructing a machine learning model on the basis of an enterprise operation historical database;
c: predicting the change trend of the enterprise operation data by using a prediction layer of a machine learning model, and comprehensively analyzing the prediction result from the model aiming at each future stage to obtain a global prediction result;
d: and checking whether the prediction result of the machine learning model is accurate, and carrying out parameter adjustment on the sub-models of the machine learning model according to the check result to optimize the structure of the machine learning model.
Further, in step B, the machine learning model is an LSTM model, and the LSTM model can discover the price change rule and the potential change logic of the enterprise operation through training, and realize the prediction of the future price change trend of the enterprise operation through the processing of the price rule and the change logic.
Furthermore, the LSTM model divides historical data of enterprise operation to generate a model training data set, the model training data set is divided into two parts, namely training input and training output, the length of the training input and the training output is L, and the distance between the training input and the training output is T time periods; meanwhile, a ReLU function is used as an activation function of a state processing and model output link in an LSTM model, and the activation function is defined as:
Y＝Max(0，x)
wherein x is an independent variable.
Further, the LSTM model is a recurrent neural network of a multi-layer structure, the multi-layer including an input layer, an output layer, and a prediction layer, wherein,
the input layer is used for controlling how much information can flow into the memory of the model, and the data processed by the input layer flows into the current state;
the prediction layer is used for controlling how much model memory information at the previous moment can be accumulated in a memory at the current moment, and data information processed by the prediction layer flows into the current state;
the output layer is used for controlling how much information of the current state can flow into a memory body of the next learning stage, the data information is processed by three layer structures to complete a round of circulation, and the processed data information enters the model learning circulation of the next stage through the output layer, so that the process is repeated until the LSTM model training is completed;
wherein the layer structure adopts a Sigmoid function as an activation function.
Further, the step B further includes:
s1: carrying out noise reduction processing on historical data of enterprise operation by adopting a wavelet transform method so as to obtain effective market data with low noise and high quality;
s2: performing machine learning model modeling on the enterprise operation historical data subjected to wavelet transformation denoising treatment;
in step S1, the historical data of the business operation is used as a kind of noisy signal data, which is defined by the following formula:
f(i)＝s(i)+e(i)
wherein, i is each time period for recording the historical data, e (i) is noise carried by the signal data, s (i) is a real and effective historical data signal for the enterprise operation, and a wavelet transformation method is adopted to obtain a real and effective historical data signal part s (i) for the enterprise operation by denoising f (i).
Further, in step C, the process of predicting the enterprise business data change trend by using the machine learning model includes:
c1: forecasting enterprise operation by using the trained deep learning model;
c2: and synthesizing the prediction results of the models to obtain a final prediction result, wherein in the step C2, a weighted average method is adopted for comprehensive treatment.
Further, the pre-constructing of the machine learning model comprises:
initializing data, and determining an input vector and a target vector;
building a neural network model;
performing error back propagation algorithm training to obtain node outputs of a prediction layer and an output layer;
adjusting the connection weight to obtain the adjusted node outputs of the prediction layer and the output layer;
and if the convergence condition is met, finishing the training and obtaining the machine learning model.
An AI artificial intelligence based enterprise operation prediction system, the system comprising:
the acquisition module is used for acquiring to-be-processed data input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation;
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for dividing data to be processed into management data and service data according to a user-defined classification rule of the data to be processed by taking the data to be processed as an evaluation object;
the characteristic extraction module is used for acquiring the classified characteristic quantities of all the parts and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities;
and the prediction module is used for inputting the key characteristic quantity into a pre-established machine learning model and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data.
The invention has the beneficial effects that:
the invention provides an enterprise operation prediction method and system based on AI artificial intelligence, which comprises the steps of obtaining data to be processed input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation; taking data to be processed as an evaluation object, and dividing the data to be processed into management data and service data according to a self-defined classification rule of the data to be processed; obtaining the classified characteristic quantities of all parts, and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities; and inputting the key characteristic quantity into a pre-established machine learning model, and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data. According to the scheme, the learning model is introduced into enterprise operation prediction, and a business prediction result for each day of 1-3 months in the future can be output one second; and analyzing the performance of the existing prediction results in different time periods, and further predicting the trend of future business data reports. The proposal of the invention fills the blank of the technical market, and for enterprise users, the invention is opened by one key, and the operation prediction and analysis result is obtained in one second, which is equivalent to the user having the ability of foreknowledge and the upgraded decision intelligence, thereby facilitating the enterprise to deploy resources in advance, take more optimized decision measures and implement the healthy development.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a flowchart of an AI-based artificial intelligence based enterprise business prediction method according to an embodiment of the present invention;
FIG. 2 is a logic diagram of business intelligence BI and artificial intelligence in the background of the invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
The embodiment of the invention provides an AI artificial intelligence-based enterprise business prediction method, which can also be called an AI alpha financial business prediction method. An AI alpha financial forecasting method is an implementation method of an intelligent system based on machine learning, and the core problem to be solved is the limitation problem of human thinking, judgment and decision in three-dimensional space and time, and how to use artificial intelligence to think and see the rules and modes of future business in multi-vector space, such as tensor.
Tensor is a way of representing physical quantities, i.e. a combination of basis vectors and components; since the basis vectors can be combined in a rich manner, the tensor can express a rich and colorful physical quantity. Moreover, the physical quantity described by the tensor is invariant to the observer or the reference system, and when the reference system is changed, its components are changed, while the combination of the basis vectors and the components (i.e., the tensor) remains unchanged. Tensor is a more powerful way of thinking, and the fact that tensor can represent a powerful representation without changing with different observers is considered by many scientists as a universe. This is the most essential difference between AI and other IT technologies.
The inventive thought and principle of the alpha financial business prediction system are constructed according to the tensor principle. The selection and calculation of various dimensions and elements in the system are based on the original indexes, the expanded indexes and the conversion indexes of sales business and financial reports, 520 indexes and the checking relation dimension are generated, daily business data (such as ERP and CRM), the economic data dimension of industry, market, region and international and the time dimension are added, more than 6000 vector spaces can be generated to observe business problems and business future trends, and an endless autonomous learning high-dimensional space-time model is created.
As shown in fig. 1, the specific implementation process of the method includes:
the method comprises the following steps:
s101, acquiring to-be-processed data input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation;
s102, taking data to be processed as an evaluation object, and dividing the data to be processed into management data and service data according to a self-defined classification rule of the data to be processed;
s103, acquiring the classified characteristic quantities of all the parts, and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities;
and S104, inputting the key characteristic quantity into a pre-established machine learning model, and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data.
In step S103, the pre-constructing of the machine learning model includes:
initializing data, and determining an input vector and a target vector;
building a neural network model;
performing error back propagation algorithm training to obtain node outputs of a prediction layer and an output layer;
adjusting the connection weight to obtain the adjusted node outputs of the prediction layer and the output layer;
and if the convergence condition is met, finishing the training and obtaining the machine learning model.
Step S104, inputting the key characteristic quantity into a pre-established machine learning model, and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data comprises the following steps:
a: establishing an enterprise operation historical database for storing enterprise historical operation data and corresponding key characteristic quantities of enterprise operation in a certain past time period;
b: constructing a machine learning model on the basis of an enterprise operation historical database;
c: predicting the change trend of the enterprise operation data by using a prediction layer of a machine learning model, and comprehensively analyzing the prediction result from the model aiming at each future stage to obtain a global prediction result;
d: and checking whether the prediction result of the machine learning model is accurate, and carrying out parameter adjustment on the sub-models of the machine learning model according to the check result to optimize the structure of the machine learning model.
In the step B, the machine learning model is an LSTM model, the LSTM model can discover the price change rule and the potential change logic of the enterprise operation through training, and the forecast of the future price change trend of the enterprise operation is realized through the processing of the price rule and the change logic. The LSTM model divides the historical data of enterprise operation to generate a model training data set, the model training data set is divided into two parts of training input and training output, the length of the training input and training output data is L, and the distance between the training input and the training output is T time periods; meanwhile, a ReLU function is used as an activation function of a state processing and model output link in an LSTM model, and the activation function is defined as:
Y＝Max(0，x)
wherein x is an independent variable.
The LSTM model is a recurrent neural network of a multi-layer structure, the multi-layer including an input layer, an output layer, and a prediction layer, wherein,
the input layer is used for controlling how much information can flow into the memory of the model, and the data processed by the input layer flows into the current state;
the prediction layer is used for controlling how much model memory information at the previous moment can be accumulated in a memory at the current moment, and data information processed by the prediction layer flows into the current state;
the output layer is used for controlling how much information of the current state can flow into a memory body of the next learning stage, the data information is processed by three layer structures to complete a round of circulation, and the processed data information enters the model learning circulation of the next stage through the output layer, so that the process is repeated until the LSTM model training is completed;
wherein the layer structure adopts a Sigmoid function as an activation function.
The step B also comprises the following steps:
s1: carrying out noise reduction processing on historical data of enterprise operation by adopting a wavelet transform method so as to obtain effective market data with low noise and high quality;
s2: performing machine learning model modeling on the enterprise operation historical data subjected to wavelet transformation denoising treatment;
in step S1, the historical data of the business operation is used as a kind of noisy signal data, which is defined by the following formula:
f(i)＝s(i)+e(i)
wherein, i is each time period for recording the historical data, e (i) is noise carried by the signal data, s (i) is a real and effective historical data signal for the enterprise operation, and a wavelet transformation method is adopted to obtain a real and effective historical data signal part s (i) for the enterprise operation by denoising f (i).
In step C, the process of predicting the enterprise operation data change trend by using the machine learning model includes:
c1: forecasting enterprise operation by using the trained deep learning model;
c2: and synthesizing the prediction results of the models to obtain a final prediction result, wherein in the step C2, a weighted average method is adopted for comprehensive treatment.
Based on the same technical concept, the specific embodiment of the invention also provides an enterprise operation prediction system based on AI artificial intelligence, the system comprises:
the acquisition module is used for acquiring to-be-processed data input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation;
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for dividing data to be processed into management data and service data according to a user-defined classification rule of the data to be processed by taking the data to be processed as an evaluation object;
the characteristic extraction module is used for acquiring the classified characteristic quantities of all the parts and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities;
and the prediction module is used for inputting the key characteristic quantity into a pre-established machine learning model and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (9)
1. An AI artificial intelligence based enterprise operation prediction method, the method comprises:
acquiring data to be processed input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation;
taking data to be processed as an evaluation object, and dividing the data to be processed into management data and service data according to a self-defined classification rule of the data to be processed;
obtaining the classified characteristic quantities of all parts, and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities;
and inputting the key characteristic quantity into a pre-established machine learning model, and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data.
2. The method of claim 1, wherein inputting the key feature quantities into a pre-established machine learning model, and analyzing the enterprise business prediction results and the corresponding prediction decision data comprises:
a: establishing an enterprise operation historical database for storing enterprise historical operation data and corresponding key characteristic quantities of enterprise operation in a certain past time period;
b: constructing a machine learning model on the basis of an enterprise operation historical database;
c: predicting the change trend of the enterprise operation data by using a prediction layer of a machine learning model, and comprehensively analyzing the prediction result from the model aiming at each future stage to obtain a global prediction result;
d: and checking whether the prediction result of the machine learning model is accurate, and carrying out parameter adjustment on the sub-models of the machine learning model according to the check result to optimize the structure of the machine learning model.
3. The method of claim 2, wherein: in the step B, the machine learning model is an LSTM model, the LSTM model can discover the price change rule and the potential change logic of the enterprise operation through training, and the forecast of the future price change trend of the enterprise operation is realized through the processing of the price rule and the change logic.
4. The method of claim 3, wherein: the LSTM model divides historical data of enterprise operation to generate a model training data set, the model training data set is divided into two parts, namely training input and training output, the length of the training input and training output data is L, and the distance between the training input and the training output is T time periods; meanwhile, a ReLU function is used as an activation function of a state processing and model output link in an LSTM model, and the activation function is defined as:
Y＝Max(0，x)
wherein x is an independent variable.
5. The method of claim 3, wherein: the LSTM model is a recurrent neural network of a multi-layer structure, the multi-layer including an input layer, an output layer, and a prediction layer, wherein,
the input layer is used for controlling how much information can flow into the memory of the model, and the data processed by the input layer flows into the current state;
the prediction layer is used for controlling how much model memory information at the previous moment can be accumulated in a memory at the current moment, and data information processed by the prediction layer flows into the current state;
the output layer is used for controlling how much information of the current state can flow into a memory body of the next learning stage, the data information is processed by three layer structures to complete a round of circulation, and the processed data information enters the model learning circulation of the next stage through the output layer, so that the process is repeated until the LSTM model training is completed;
wherein the layer structure adopts a Sigmoid function as an activation function.
6. The method of claim 2, wherein: the step B also comprises the following steps:
s1: carrying out noise reduction processing on historical data of enterprise operation by adopting a wavelet transform method so as to obtain effective market data with low noise and high quality;
s2: performing machine learning model modeling on the enterprise operation historical data subjected to wavelet transformation denoising treatment;
in step S1, the historical data of the business operation is used as a kind of noisy signal data, which is defined by the following formula:
f(i)＝s(i)+e(i)
wherein, i is each time period for recording the historical data, e (i) is noise carried by the signal data, s (i) is a real and effective historical data signal for the enterprise operation, and a wavelet transformation method is adopted to obtain a real and effective historical data signal part s (i) for the enterprise operation by denoising f (i).
7. The method of claim 2, wherein: in step C, the process of predicting the enterprise operation data change trend by using the machine learning model includes:
c1: forecasting enterprise operation by using the trained deep learning model;
c2: and synthesizing the prediction results of the models to obtain a final prediction result, wherein in the step C2, a weighted average method is adopted for comprehensive treatment.
8. The method of claim 2, wherein the pre-building of the machine learning model comprises:
initializing data, and determining an input vector and a target vector;
building a neural network model;
performing error back propagation algorithm training to obtain node outputs of a prediction layer and an output layer;
adjusting the connection weight to obtain the adjusted node outputs of the prediction layer and the output layer;
and if the convergence condition is met, finishing the training and obtaining the machine learning model.
9. An AI artificial intelligence based enterprise operation prediction system, the system comprising:
the acquisition module is used for acquiring to-be-processed data input by a user; the data to be processed comprises business data, sales data and financial data in enterprise operation;
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for dividing data to be processed into management data and service data according to a user-defined classification rule of the data to be processed by taking the data to be processed as an evaluation object;
the characteristic extraction module is used for acquiring the classified characteristic quantities of all the parts and selecting key characteristic quantities for enterprise operation prediction from the characteristic quantities;
and the prediction module is used for inputting the key characteristic quantity into a pre-established machine learning model and analyzing to obtain an enterprise operation prediction result and corresponding prediction decision data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111081156.3A CN113780667A (en) | 2021-09-15 | 2021-09-15 | Enterprise operation prediction method and system based on AI artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111081156.3A CN113780667A (en) | 2021-09-15 | 2021-09-15 | Enterprise operation prediction method and system based on AI artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113780667A true CN113780667A (en) | 2021-12-10 |
Family
ID=78844074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111081156.3A Pending CN113780667A (en) | 2021-09-15 | 2021-09-15 | Enterprise operation prediction method and system based on AI artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113780667A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115375190A (en) * | 2022-10-18 | 2022-11-22 | 北京北方科诚信息技术股份有限公司 | Enterprise operation management system and method |
| CN116151870A (en) * | 2023-04-20 | 2023-05-23 | 北京融信数联科技有限公司 | Enterprise operation analysis prediction method, system and medium based on cognitive map |
| CN117151345A (en) * | 2023-10-30 | 2023-12-01 | 智唐科技(北京)股份有限公司 | Enterprise management intelligent decision platform based on AI technology |
| CN117435582A (en) * | 2023-10-11 | 2024-01-23 | 广东美尼科技有限公司 | Method and device for capturing and processing ERP temporary data |
-
2021
- 2021-09-15 CN CN202111081156.3A patent/CN113780667A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115375190A (en) * | 2022-10-18 | 2022-11-22 | 北京北方科诚信息技术股份有限公司 | Enterprise operation management system and method |
| CN116151870A (en) * | 2023-04-20 | 2023-05-23 | 北京融信数联科技有限公司 | Enterprise operation analysis prediction method, system and medium based on cognitive map |
| CN117435582A (en) * | 2023-10-11 | 2024-01-23 | 广东美尼科技有限公司 | Method and device for capturing and processing ERP temporary data |
| CN117435582B (en) * | 2023-10-11 | 2024-04-19 | 广东美尼科技有限公司 | Method and device for capturing and processing ERP temporary data |
| CN117151345A (en) * | 2023-10-30 | 2023-12-01 | 智唐科技(北京)股份有限公司 | Enterprise management intelligent decision platform based on AI technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rajput et al. | Connecting circular economy and industry 4.0 | |
| Pasquadibisceglie et al. | Using convolutional neural networks for predictive process analytics | |
| CN113780667A (en) | Enterprise operation prediction method and system based on AI artificial intelligence | |
| CN103559380B (en) | Real-time across spot probability analogy method and device | |
| CN112291807B (en) | Wireless cellular network traffic prediction method based on deep migration learning and cross-domain data fusion | |
| KR102198904B1 (en) | Distributed Deep Learning Model-based Artificial Intelligence System for Technology Appraisal | |
| Ievtushenko et al. | Review of cost estimation techniques and their strategic importance in the new product development process of textile products | |
| Chatterjee et al. | Artificial neural network and the financial markets: A survey | |
| Kolomytseva et al. | System-dynamic model of managing the budgetary financial resources in targeted programs | |
| Wang et al. | Large-scale inventory optimization: A recurrent neural networks–inspired simulation approach | |
| Zhang | A deep learning model for ERP enterprise financial management system | |
| Dorrer et al. | Numerical modeling of business processes using the apparatus of GERT networks | |
| Sakhno et al. | Use of the urban logic theory with development projects management | |
| Deng | Construction of a digital platform for enterprise financial management based on visual processing technology | |
| Turktarhan et al. | Re-architecting the firm for increased value: How business models are adapting to the new AI environment | |
| CN114154696A (en) | Method, system, computer device and storage medium for predicting fund flow | |
| Smith et al. | Stock Closing Price and Trend Prediction with LSTM-RNN | |
| Xu | An Intelligent Classification Method of Multisource Enterprise Financial Data Based on SAS Model | |
| Mu et al. | E‐Commerce Intelligent Logistics Data Based on Neural Network Model | |
| Xia et al. | A Process Mining Framework Based on Deep Learning Feature Fusion | |
| Supriyanto | Comparison of Grid Search and Evolutionary Parameter Optimization with Neural Networks on JCI Stock Price Movements during the Covid 19 | |
| Loumos et al. | Change management and quality of service through business process modeling: The n-vis, a public sector project | |
| Sona et al. | Analyzing factors in production management using fuzzy cognitive mapping | |
| Golubin et al. | Agent-Based Modeling Using Artificial Intelligence as a Method for Creating Rational Consumption and Production Models | |
| UmaDevi et al. | Fostering a Predictive Model with Neural Networks Trading in the Forex Market using AI Technology |
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 |