CN114638547A

CN114638547A - Enterprise strategy intelligent early warning method and device, electronic equipment and storage medium

Info

Publication number: CN114638547A
Application number: CN202210423017.2A
Authority: CN
Inventors: 严翠玲; 高加宝
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Ping An International Smart City Technology Co Ltd
Priority date: 2022-04-21
Filing date: 2022-04-21
Publication date: 2022-06-17

Abstract

The invention relates to the field of artificial intelligence, and provides an enterprise strategic intelligence early warning method, which is used for carrying out NLP (non line segment) recognition processing on external operation data to extract external characteristic data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data; acquiring main reference information through a multiple regression model, acquiring auxiliary reference information through a temporal differential autoregressive moving average model, acquiring a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and acquiring risk early warning information of a current enterprise according to the customer throughput trend and preset trend risk comparison information, so that intelligent early warning of customer risks is realized, possible loss discovered afterwards is reduced, namely intelligent early warning of the customer risks is realized, and possible loss discovered afterwards is reduced; and evaluating the accuracy and the practicability of the model, and improving the prediction precision of the throughput.

Description

Enterprise strategy intelligent early warning method and device, electronic equipment and storage medium

Technical Field

The invention relates to the field of artificial intelligence, relates to a data analysis technology, and particularly relates to an enterprise strategic intelligence early warning method, an enterprise strategic intelligence early warning device, electronic equipment and a computer-readable storage medium.

Background

Due to factors such as historical experience limitation of operation and development, technical limitation and the like, most port groups mainly acquire information of large clients at present by visiting the large clients, but factors such as irregular visiting period, incomplete information dimension and the like seriously affect the wind control of the large clients, and in most cases, risk information of the large clients is received afterwards, so that the condition of the clients is not obviously perceived, response is delayed, early warning cannot be carried out in advance or in time, and once risks occur, serious loss is easily caused to port enterprises. Therefore, the method identifies the client business risk behaviors in advance, and makes a strategy in time, and is very important for benign development of port enterprises.

The main business of port enterprises aims at the throughput of the passenger and the goods, and the completion of the throughput of the goods depends on the business scale and the business situation of customers (namely, shippers). Generally speaking, the larger and more concentrated the business of a certain client in an enterprise, the easier it is to form a dependency on the client, and the risk of the client may be transformed into the operational risk of the enterprise at any time. The major client risk of port enterprises mainly comprises two aspects, namely, the client traffic risk; second, the risk of customer churn.

Therefore, a need exists for a data mining-based intelligent early warning method for a harbor enterprise strategy, which integrates a customer traffic risk and a customer loss risk to realize intelligent early warning of the customer risk and reduce possible loss discovered afterwards.

Disclosure of Invention

The invention provides an enterprise strategic intelligent early warning method, which aims to solve the problems that in the prior art, due to factors such as historical experience limitation and technical limitation of operation development, most port groups mainly acquire information of large clients at present by visiting the clients, but factors such as irregular visiting periods and incomplete information dimensions seriously influence the wind control of the large clients, and in most cases, risk information of the large clients is received afterwards, so that the perception of the client conditions is not obvious, the response is delayed, early warning cannot be performed in advance or in time, and once risks occur, serious losses are easily caused to port enterprises.

In order to achieve the above object, the invention provides an enterprise strategic intelligent early warning method, which comprises the following steps:

based on a preset database or a data retrieval platform, retrieving external operation data around a field of a preset external operation environment theme, and retrieving internal evaluation data of an enterprise around a field of a preset internal evaluation theme;

performing natural language identification processing on the external operation data to extract external characteristic data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data;

carrying out node averaging processing on the external characteristic data through a preset time sequence according to a preset time node to obtain a time difference autoregressive moving average model; constructing a regression model by taking the internal reference data as a factor to obtain a multiple regression model;

acquiring main reference information through the multiple regression model, acquiring auxiliary reference information through the temporal difference autoregressive moving average model, acquiring a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and acquiring risk early warning information of the current enterprise according to the customer throughput trend and preset trend risk comparison information.

Optionally, the invoking external business data around a preset external business environment subject field and the invoking internal enterprise evaluation data around a preset internal evaluation subject field based on a preset database or a data invoking platform includes:

dividing internal and external data of a preset service to form an external data set and an internal data set; wherein the external data set at least comprises macro-economic data, industry price and industry development data and media data; the internal data set comprises client traffic data, enterprise basic information data and enterprise operation data in an enterprise group;

setting an enterprise external operation environment theme and an enterprise internal evaluation theme related to the preset service, marking the enterprise external operation environment theme on the external data set, and marking the enterprise internal evaluation theme on the internal data set;

crawling external operation data around a field of the external operation environment theme, and calling internal evaluation data of an enterprise around a field of the internal evaluation theme; wherein, the external operation data at least comprises macro economic environment analysis, policy influence analysis and industry technology development public opinion influence analysis.

Optionally, the retrieving of the enterprise internal evaluation data includes:

acquiring enterprise asset scale change, enterprise operation range change, enterprise management layer change, enterprise administrative punishment labels and enterprise public opinion labels through a preset enterprise assessment plug-in;

assigning values to the enterprise asset scale change, the enterprise operation range change, the enterprise management layer change, the enterprise administrative penalty label and the enterprise public opinion label to obtain an enterprise internal evaluation data table;

and traversing and calculating the internal enterprise evaluation data table through a preset evaluation algorithm to obtain internal enterprise evaluation data.

Optionally, obtaining the macro-economic environmental analysis comprises:

the method comprises the steps that the throughput of a client in an enterprise is obtained through a preset information crawling plug-in, and meanwhile, the GDP present price, the average exchange rate and the import and export policy label are obtained through a preset media information plug-in;

creating a table to be filled according to a preset arrangement rule, and mapping the throughput, the GDP present price, the average exchange rate and the import and export policy label in the table to be filled to form a macro economic environment analysis table;

and inputting the macro economic environment analysis table into a preset intelligent information extraction model, and enabling the intelligent information extraction model to automatically output the macro economic environment analysis according to the macro economic environment analysis table.

Optionally, the performing natural language identification processing on the external operation data to extract external feature data includes:

performing algorithm fitting based on pre-acquired sample data about a preset service to acquire an NLP recognition model for starting NLP semantic recognition service;

training through the sample data about the preset service on the basis of the NLP recognition model to acquire an NLP semantic recognition service process;

performing specification processing on the external operation data to form standard data, inputting the standard data into the NLP semantic recognition service process, and performing semantic recognition on the external operation data by the NLP semantic recognition service process to acquire keywords related to enterprises and data corresponding to the keywords; wherein, the process of the external operation data carrying out specification processing to form standard data changes the external operation data into a form that one project corresponds to one data;

and carrying out synonym replacement on the keywords to obtain near-meaning keywords, and packaging the keywords, the data corresponding to the keywords and the near-meaning keywords to form external feature data.

Optionally, the normalizing and encoding the enterprise internal evaluation data to obtain internal reference data includes:

carrying out standardization processing on the enterprise internal evaluation data to form enterprise asset scale change classification data, enterprise operation range change classification data, enterprise management layer change classification data, enterprise administrative penalty tag classification data and enterprise public opinion tag classification data; the process of forming enterprise asset size change classification data comprises the following steps:

carrying out quantitative extraction on enterprise asset scale change in the enterprise internal evaluation data to obtain client throughput, GDP present price and enterprise asset scale data;

converting the client throughput, GDP present price and enterprise asset scale data into low-dimension client throughput data, GDP data and enterprise asset data through log function conversion;

performing z-score normalization on the customer throughput data, the GDP data, and the enterprise asset data to form enterprise asset size change classification data;

respectively carrying out zero-one-hot encoding processing on the enterprise asset scale change classification data, the enterprise operation range change classification data, the enterprise management layer change classification data, the enterprise administrative penalty label classification data and the enterprise public opinion label classification data to form time comparison analysis data;

and performing parameter extraction on the time contrast analysis data to form internal reference data.

Optionally, the obtaining main reference information through the multiple regression model, obtaining auxiliary reference information through the temporal difference autoregressive moving average model, obtaining a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and obtaining risk early warning information of a current enterprise according to the customer throughput trend and preset trend risk comparison information includes:

acquiring the weight of each factor in the multiple regression model, and performing stage assignment on each factor according to the weight of each factor to acquire the significance of each factor; acquiring a macroscopic economic trend and an enterprise industry price trend in a preset quarter according to the temporal difference autoregressive moving average model;

taking the weight and the significance of each factor as main reference information, taking the macroscopic economic trend in the preset quarter and the enterprise industry price trend as auxiliary reference information, and fitting and solving the main reference information and the auxiliary reference information through a preset optimal model according to a preset fitting algorithm to predict the customer throughput trend;

and acquiring the lifting amplitude of the throughput according to the throughput trend, and corresponding the lifting amplitude with preset early warning information to acquire risk early warning information.

In order to solve the above problem, the present invention further provides an enterprise strategic intelligent early warning device, which comprises:

the data acquisition unit is used for acquiring external operation data around a field of a preset external operation environment theme and acquiring internal evaluation data of an enterprise around a field of a preset internal evaluation theme based on a preset database or a data acquisition platform;

a feature extraction unit configured to perform natural language identification processing on the external operation data to extract external feature data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data;

the average regression unit is used for carrying out node average processing on the external characteristic data through a preset time sequence according to a preset time node to obtain a time difference autoregressive moving average model; constructing a regression model by taking the internal reference data as a factor to obtain a multiple regression model;

and the risk early warning unit is used for acquiring main reference information through the multiple regression model, acquiring auxiliary reference information through the temporal difference autoregressive moving average model, acquiring a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and acquiring the risk early warning information of the current enterprise according to the customer throughput trend and preset trend risk comparison information.

In order to solve the above problem, the present invention also provides an electronic device, including:

a memory storing at least one instruction; and

and the processor executes the instructions stored in the memory to realize the steps of the enterprise strategic intelligent early warning method.

In order to solve the above problem, the present invention further provides a computer-readable storage medium, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned enterprise strategic intelligent early warning method.

The embodiment of the invention firstly establishes an enterprise external operation environment theme and an enterprise internal evaluation theme related to a preset service, calls external operation data around the external operation environment theme and calls the enterprise internal evaluation data around the internal evaluation theme based on a preset database or a data calling platform; performing NLP (non line segment) identification processing on the external operation data to extract external characteristic data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data; carrying out quarterly average processing on external feature data according to the quarterly through a time series technology to obtain a temporal difference autoregressive moving average model; constructing a regression model by taking the internal reference data as a factor to obtain a multiple regression model; acquiring main reference information through a multiple regression model, acquiring auxiliary reference information through a time differential autoregressive moving average model, acquiring and predicting a client throughput trend according to the main reference information and the auxiliary reference information, and acquiring risk early warning information of a current enterprise according to the client throughput trend and preset trend risk comparison information, so that the large client risk early warning model analyzes and monitors the fluctuation rule of the large client historical service data by analyzing the service data of the large client and a port group company, analyzes and evaluates influence factors of different periods of service data by combining factors such as macroscopic economic trend, the industry policy of the large client, the industry supply and demand trend, the industry public opinion, the large client enterprise scale, core personnel and the like, the enterprise public opinion and the like, constructs a risk factor feature library, and realizes early warning on the possible risk and the occurrence probability of the next client in one period by combining with real-time change information and an algorithm model, the intelligent early warning of the client risk is realized, the possible loss found afterwards is reduced, namely the intelligent early warning of the client risk is realized, and the possible loss found afterwards is reduced; and evaluating the accuracy and the practicability of the model, and improving the prediction precision of the throughput.

Drawings

Fig. 1 is a schematic flow chart of an enterprise strategic intelligent warning method according to an embodiment of the present invention;

fig. 2 is a schematic block diagram of an enterprise strategic intelligent warning device according to an embodiment of the present invention;

fig. 3 is a schematic diagram of an internal structure of an electronic device of an enterprise strategic intelligence early warning method according to an embodiment of the present invention;

the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Due to factors such as historical experience limitation of operation and development, technical limitation and the like, most groups mainly acquire information of large clients by visiting the large clients, but factors such as irregular visiting period, incomplete information dimension and the like seriously affect the wind control of the large clients, and in most cases, risk information of the large clients is received afterwards, so that the condition of the clients is not obviously perceived, the response is delayed, early warning cannot be performed in advance or in time, and once risks occur, serious loss is easily caused to enterprises. The method has the advantages that the client business risk behaviors are recognized in advance, the strategy is made in time, and the method is important for the benign development of enterprises.

In order to solve the above problems, embodiments of the present invention provide an intelligent enterprise strategy early warning method.

In this embodiment, the execution subject is an enterprise strategic intelligent early warning system of the whole server cluster, and the enterprise strategic intelligent early warning system is integrated in the server cluster, that is, different modules of the enterprise strategic intelligent early warning system under the server cluster respectively perform different operation steps, wherein the architecture of the server cluster comprises a plurality of servers, a plurality of cluster instances run under each server, and a plurality of timing tasks are stored under each cluster instance, so that the sequential execution of the timing tasks is realized through the following steps.

It should be noted that, the embodiment of the present application may acquire and process relevant data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

As shown in fig. 1, in this embodiment, the method for intelligently early warning an enterprise strategy includes:

s1: based on a preset database or a data retrieval platform, retrieving external operation data around a field of a preset external operation environment theme, and retrieving internal evaluation data of an enterprise around a field of a preset internal evaluation theme;

s2: performing natural language identification processing on the external operation data to extract external characteristic data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data;

s3: carrying out node averaging processing on the external characteristic data through a preset time sequence according to a preset time node to obtain a time difference autoregressive moving average model; constructing a regression model by taking the internal reference data as a factor to obtain a multiple regression model;

s4: acquiring main reference information through the multiple regression model, acquiring auxiliary reference information through the temporal difference autoregressive moving average model, acquiring a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and acquiring risk early warning information of the current enterprise according to the customer throughput trend and preset trend risk comparison information.

In the embodiment shown in fig. 1, step S1 is a step of calling external business data around a pre-established external business environment subject field and calling internal enterprise evaluation data around a pre-established internal evaluation subject field based on a preset database or a data calling platform; in the process, the method comprises the following steps:

s11: dividing internal data and external data of a preset service to form an external data set and an internal data set; wherein the external data set at least comprises macro-economic data, industry price and industry development data and media data; the internal data set comprises client business volume data, enterprise basic information data and enterprise management data in an enterprise group;

s12: setting an enterprise external operation environment theme and an enterprise internal evaluation theme related to the preset service, marking the enterprise external operation environment theme on the external data set, and marking the enterprise internal evaluation theme on the internal data set;

s13: crawling external operation data around a field of the external operation environment theme, and calling internal evaluation data of an enterprise around a field of the internal evaluation theme; the external operation data comprises macro-economic environment analysis, policy influence analysis and industry technology development public opinion influence analysis, and due to the characteristic of high foreign trade proportion of port business, the influence of the external environment has both home and abroad macro-economic and industry environments; the enterprise internal evaluation data comprises enterprise basic conditions and operation management conditions;

wherein the process of obtaining the enterprise internal assessment data comprises:

s1311: acquiring enterprise asset scale change, enterprise operation range change, enterprise management layer change, enterprise administrative penalty label and enterprise public opinion label through a preset enterprise evaluation plug-in;

s1312: assigning values to the enterprise asset scale change, the enterprise operation range change, the enterprise management layer change, the enterprise administrative penalty label and the enterprise public opinion label to obtain an enterprise internal evaluation data table;

s1313: traversing and calculating the internal evaluation data table of the enterprise through a preset evaluation algorithm to obtain internal evaluation data of the enterprise;

wherein the process of obtaining the macro-economic environmental analysis comprises:

s1321: the method comprises the steps that the throughput of a client in an enterprise is obtained through a preset information crawling plug-in, and meanwhile, the GDP present price, the average exchange rate and the import and export policy label are obtained through a preset media information plug-in; in this embodiment, the enterprise is a port group, that is, the throughput of a port is obtained;

s1322: creating a table to be filled according to a preset arrangement rule, and mapping the throughput, the GDP present price, the average exchange rate and the import and export policy label in the table to be filled to form a macro economic environment analysis table;

s1323: and inputting the macro-economic environment analysis table into a preset intelligent information extraction model, so that the intelligent information extraction model automatically outputs macro-economic environment analysis according to the macro-economic environment analysis table.

In this embodiment, all data of the customer traffic and the possible influencing factors thereof are obtained, including the customer traffic data inside the port group, the external macro-economic data, the industry price and industry development data, the enterprise basic information data, the enterprise business data, the related news, and the like.

Still taking a port group as an example, the change reaction of the macro environment and the enterprise operation is often a lagged and non-instant reaction on the operation performance of large import and export business. Accordingly, the design dependent variable characteristic is the throughput of the client in the port group; the macro-economic impact is expressed by GDP present price, average exchange rate, import and export policy labels, and the like, and the industrial environmental impact comprises an industrial price index, an industrial (domestic/export state) policy label, an industrial (domestic/export state) news label, and the like.

In the embodiment shown in fig. 1, step S2 is to perform natural language identification processing on the external business data to extract external feature data; a process of performing standardization processing and coding processing on the enterprise internal evaluation data to acquire internal reference data; in the process, the method comprises the following steps:

the process of performing NLP recognition processing on the external business data to extract external feature data includes:

s211: performing algorithm fitting based on pre-acquired sample data about a preset service to acquire an NLP recognition model for starting NLP semantic recognition service;

s212: training through the sample data about the preset service on the basis of the NLP recognition model to acquire an NLP semantic recognition service process;

s213: performing specification processing on the external operation data to form standard data, inputting the standard data into the NLP semantic recognition service process, and performing semantic recognition on the external operation data by the NLP semantic recognition service process to acquire keywords related to enterprises and data corresponding to the keywords; wherein, the process of the external operation data carrying out specification processing to form standard data changes the external operation data into a form that one project corresponds to one data;

s214: and carrying out synonym replacement on the keywords to obtain near-meaning keywords, and packaging the keywords, the data corresponding to the keywords and the near-meaning keywords to form external feature data.

The process of standardizing and coding the enterprise internal evaluation data to obtain internal reference data comprises the following steps:

s221: carrying out standardization processing on the enterprise internal evaluation data to form enterprise asset scale change classification data, enterprise operation range change classification data, enterprise management layer change classification data, enterprise administrative penalty tag classification data and enterprise public opinion tag classification data; the process of forming enterprise asset size change classification data comprises the following steps:

s222: respectively carrying out zero-one-hot encoding processing on the enterprise asset scale change classification data, the enterprise operation range change classification data, the enterprise management layer change classification data, the enterprise administrative penalty label classification data and the enterprise public opinion label classification data to form time comparison analysis data;

s223: and performing parameter extraction on the time contrast analysis data to form internal reference data.

Specifically, step S2 is a feature engineering, which includes standardization of numerical data, NLP processing of text data, unique hot coding of classified data, feature selection, dimension reduction, etc., for example, log function conversion is used for numerical data such as customer throughput, GDP present price, enterprise asset scale, etc., so as to reduce the influence of dimension, and z-score standardization processing is performed on the converted data, average exchange rate, industry price index, etc., so as to perform factor analysis; performing word segmentation, synonymy substitution, paragraph extraction of keywords, document extraction of abstract and the like on text data of macro policy, industry news, enterprise public opinion and the like, and selecting 5-8 keywords with higher occurrence frequency in each text as feature data of each client at different time; carrying out 0-1 independent hot coding on classified data such as whether the enterprise operation range changes, whether the management layer changes, whether the administrative punishment is classified and whether the punishment is classified; performing correlation analysis on the processed data and the client throughput data, and selecting and reserving the characteristics of large and reasonable correlation; finally, panel data of different clients in different seasons are formed.

In the embodiment shown in fig. 1, step S3 is to perform a quarterly averaging process on the extrinsic feature data by a time-series technique to obtain a temporal differential autoregressive moving average model; a process of constructing a regression model using the internal reference data as a factor to obtain a multiple regression model;

in a specific embodiment, taking a port group as an enterprise as an example, a time series technology is used for constructing a SARIMA (time difference autoregressive moving average model) in external feature data such as GDP (global data processing) of macro economy and an industry price index to predict a short-term (2-quarter) macro trend and an industry price trend, and the SARIMA is used as a decision auxiliary information reference; b. and (2) constructing multiple regression models step by step for characteristic data such as GDP present price, average exchange rate, industry price index, macro policy keyword, industry news keyword, enterprise public opinion keyword, enterprise scale change, whether enterprise management layer changes or not, whether each type of administration penalty of an enterprise lags the first stage, the second stage and the third stage (step regression model step: different factors in different lag stages are gradually added into a regression model, the fitting degree of the model is remarkably improved, the factor coefficient is remarkably estimated to be 90%, the factor is retained, otherwise, the factor is not retained, adding the factors in different orders, and reconstructing the fitting degree of the comparison model to select the optimal model and factor).

In the embodiment shown in fig. 1, in step S4, main reference information is obtained through the multivariate regression model, auxiliary reference information is obtained through the temporal differential autoregressive moving average model, a predicted customer throughput trend is obtained according to the main reference information and the auxiliary reference information, and risk early warning information of a current enterprise is obtained according to the customer throughput trend and preset trend risk comparison information. Wherein, include:

s41: acquiring the weight of each factor in the multiple regression model, and performing stage assignment on each factor according to the weight of each factor to acquire the significance of each factor; acquiring a macroscopic economic trend and an enterprise industry price trend in a preset quarter according to the temporal difference autoregressive moving average model;

s42: taking the weight and the significance of each factor as main reference information, taking the macro economic trend in the preset quarter and the enterprise industry price trend as auxiliary reference information, and performing fitting solution on the main reference information and the auxiliary reference information through a preset optimal model according to a preset fitting algorithm to predict the customer throughput trend;

s43: acquiring the lifting amplitude of the throughput according to the throughput trend, and corresponding the lifting amplitude to preset early warning information to acquire risk early warning information;

setting low, medium and high risk early warning information for the prediction throughput reduction of more than 10%, 30% and 50% respectively;

specifically, in this embodiment, the weight and the significance of each influence factor are analyzed, the throughput trend of the client is predicted by using an optimal model according to the latest data of the factors and the data predicted in the step a, and low, medium and high risk early warning information is set for the predicted throughput degradation exceeding 10%, 30% and 50% respectively; in addition, enterprise change, news, public sentiment and other data popped up for keyword combination with high model influence weight can be used as decision auxiliary information reference to obtain final risk information.

More specifically, the present embodiment aims to research whether the port enterprise has a risk of large-scale reduction in traffic, analyze whether the path is caused by a large change in business traffic generated by the client, and analyze two types of factors affecting the business performance of the client according to the business management theory and the experience of business practice: the method has the advantages that firstly, the external operation environment of an enterprise comprises the macroscopic economy environment, policy influence, the technology, development, public opinion and other influences of the industry, and due to the characteristic of high foreign trade proportion of port business, the influence of the external environment has both domestic and foreign macroscopic economy and industry environments; the other is the inherent quality of the enterprise, namely the basic condition and the operation and management condition of the enterprise; in addition, changing responses of the macro environment and the enterprise operation are often delayed and non-immediate responses in the operation performance of the large import and export business. Accordingly, the design dependent variable characteristic is the throughput of the client in the port group; the influence of macro economy is expressed by GDP present price, average exchange rate, import and export policy labels and the like, the influence of industry environment comprises industry price index, industry (domestic/export state) policy labels and industry (domestic/export state) news labels, the influence of enterprise operation comprises enterprise asset scale change, enterprise operation range change, enterprise management layer change, enterprise administrative punishment labels, enterprise public opinion labels and the like, and accordingly risk information is obtained according to the proportion of each information, and the rigidness and the comprehensiveness of risk evaluation are improved.

In this embodiment, the server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and an artificial intelligence platform, and the like.

As described above, in the enterprise strategic intelligent early warning method provided in the embodiment of the present invention, by setting an external business environment theme and an internal enterprise evaluation theme related to a preset service, external business data is retrieved around the external business environment theme, and internal enterprise evaluation data is retrieved around the internal enterprise evaluation theme; performing NLP (non line segment) identification processing on the external operation data to extract external characteristic data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data, and carrying out quarterly averaging processing on the external characteristic data according to the quarterly through a time series technology to obtain a time differential autoregressive moving average model; the internal reference data is used as a factor to construct a regression model to obtain a multiple regression model, main reference information is obtained through the multiple regression model, auxiliary reference information is obtained through the time difference autoregressive moving average model, the trend of the client throughput is predicted according to the main reference information and the auxiliary reference information, the risk information of the current port is obtained according to preset trend risk comparison information, intelligent early warning of the client risk can be achieved, possible loss discovered afterwards is reduced, model accuracy and practicability can be evaluated, and the throughput prediction precision is improved.

As shown in fig. 2, the present invention provides an enterprise strategic intelligent early warning device 100, which can be installed in an electronic device. According to the realized functions, the enterprise strategic intelligent early warning device 100 can comprise a data acquisition unit 101, a feature extraction unit 102, an average regression unit 103 and a risk early warning unit 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions of the respective modules/units are as follows:

the data acquisition unit 101 is configured to, based on a preset database or a data retrieval platform, retrieve external business data around a field of a preset external business environment theme, and retrieve internal enterprise evaluation data around a field of a preset internal evaluation theme;

a feature extraction unit 102, configured to perform natural language identification processing on the external operation data to extract external feature data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data;

the average regression unit 103 is configured to perform node average processing on the external feature data according to a preset time sequence and a preset time node to obtain a temporal differential autoregressive moving average model; constructing a regression model by taking the internal reference data as a factor to obtain a multiple regression model;

and the risk early warning unit 104 is configured to obtain main reference information through the multiple regression model, obtain auxiliary reference information through the temporal differential autoregressive moving average model, obtain a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and obtain risk early warning information of a current enterprise according to the customer throughput trend and preset trend risk comparison information.

As described above, the enterprise strategic intelligent early warning device 100 provided by the present invention firstly calls external business data around an external business environment theme and internal enterprise evaluation data around an internal evaluation theme by setting the external business environment theme and the internal enterprise evaluation theme related to a preset service based on the data obtaining unit 101; then, the feature extraction unit 102 performs NLP recognition processing on the external operation data to extract external feature data; performing standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data, and performing quarterly averaging processing on the external feature data through an averaging regression unit 103 by a time series technology according to a quarter to obtain a temporal differential autoregressive moving average model; the internal reference data is used as a factor to construct a regression model to obtain a multiple regression model, main reference information is finally obtained through the multiple regression model based on the risk early warning unit 104, auxiliary reference information is obtained through the time difference autoregressive moving average model, the trend of the client throughput is predicted according to the main reference information and the auxiliary reference information, the risk information of the current port is obtained according to preset trend risk comparison information, the intelligent early warning of the client risk can be realized, the possible loss discovered afterwards is reduced, the model accuracy and the practicability can be evaluated, and the throughput prediction precision is improved.

As shown in fig. 3, the present invention provides an electronic device 1 for an enterprise strategic intelligent early warning method.

The electronic device 1 may include a processor 10, a memory 11, and a bus, and may further include a computer program, such as an enterprise strategy intelligent warning program 12, stored in the memory 11 and operable on the processor 10.

The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used to store not only application software installed in the electronic device 1 and various types of data, such as codes of an enterprise strategic intelligence early warning program, but also temporarily store data that has been output or will be output.

The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., an enterprise strategic intelligence early warning program, etc.) stored in the memory 11 and calling data stored in the memory 11.

The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.

Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The memory 11 in the electronic device 1 stores an enterprise strategic intelligent warning program 12 that is a combination of instructions that, when executed in the processor 10, implement:

Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again. It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned enterprise strategic intelligent early warning, the data of the above-mentioned enterprise strategic intelligent early warning is stored in the node of the block chain where the server cluster is located.

The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.

Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

An embodiment of the present invention further provides a computer-readable storage medium, where the storage medium may be nonvolatile or volatile, and the storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements:

Specifically, the specific implementation method of the computer program when being executed by the processor may refer to the description of the relevant steps in the enterprise strategic intelligence early warning method in the embodiment, which is not repeated herein.

In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent early warning method for enterprise strategy is characterized by comprising the following steps:

2. The strategic intelligent early warning method of an enterprise as claimed in claim 1, wherein said step of calling external business data around a pre-established external business environment subject field and internal enterprise evaluation data around a pre-established internal evaluation subject field based on a preset database or a data calling platform comprises:

3. The strategic intelligent warning method of an enterprise as claimed in claim 2, wherein said retrieving of enterprise internal assessment data comprises:

acquiring enterprise asset scale change, enterprise operation range change, enterprise management layer change, enterprise administrative penalty label and enterprise public opinion label through a preset enterprise evaluation plug-in;

4. The strategic intelligent warning method of an enterprise as claimed in claim 2, wherein obtaining said macro-economic environment analysis comprises:

and inputting the macro-economic environment analysis table into a preset intelligent information extraction model, so that the intelligent information extraction model automatically outputs macro-economic environment analysis according to the macro-economic environment analysis table.

5. The strategic intelligent early warning method of an enterprise as claimed in claim 1, wherein said natural language identifying said external business data to extract external characteristic data comprises:

6. The strategic intelligent warning method of an enterprise as claimed in claim 5, wherein said normalizing and encoding said enterprise internal assessment data to obtain internal reference data comprises:

7. The strategic intelligent early warning method of an enterprise as claimed in claim 6, wherein said obtaining of primary reference information through said multivariate regression model, obtaining of secondary reference information through said temporal differential autoregressive moving average model, obtaining of predicted customer throughput trend according to said primary reference information and said secondary reference information, and obtaining of risk early warning information of a current enterprise according to said customer throughput trend and preset trend risk contrast information comprises:

8. An enterprise strategic intelligent early warning device, characterized in that the device comprises:

a feature extraction unit, configured to perform natural language identification processing on the external operation data to extract external feature data; carrying out standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data;

the average regression unit is used for carrying out node average processing on the external feature data through a preset time sequence according to a preset time node to obtain a time difference autoregressive moving average model; constructing a regression model by taking the internal reference data as a factor to obtain a multiple regression model;

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the steps of the enterprise strategy intelligent warning method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the business strategy intelligent warning method according to any one of claims 1 to 7.