CN115529602A - Method and system for identifying business demand area of enterprise user - Google Patents
Method and system for identifying business demand area of enterprise user Download PDFInfo
- Publication number
- CN115529602A CN115529602A CN202110706639.1A CN202110706639A CN115529602A CN 115529602 A CN115529602 A CN 115529602A CN 202110706639 A CN202110706639 A CN 202110706639A CN 115529602 A CN115529602 A CN 115529602A
- Authority
- CN
- China
- Prior art keywords
- private network
- tob
- potential
- users
- user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000009826 distribution Methods 0.000 claims abstract description 22
- 238000013136 deep learning model Methods 0.000 claims abstract description 18
- 230000009193 crawling Effects 0.000 claims abstract description 16
- 238000005516 engineering process Methods 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 5
- 230000007774 longterm Effects 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000491 multivariate analysis Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Abstract
The application discloses a method and a system for identifying enterprise user service demand areas, wherein the method comprises the following steps: identifying private network users in the business-oriented business ToB application, wherein the private network users comprise private network users of the existing ToB application and private network users of potential ToB applications in the same industry; adopting a deep learning model, performing portrait learning according to the potential of a private network user, and performing portrait scoring on the private network user of the existing ToB application and the remaining target users except the private network user of the potential ToB application in the same industry to generate a 5G private network user potential value; and determining regional geographical distribution with high ToB service demand according to the user potential value of the 5G private network. By means of two types of customer portrait information of private network customers of operators and non-operator private network customers with specific private network service requirements, expansion crawling and portrait of potential private network requirement customers in the same industry are conducted, private network requirement potential prediction is conducted according to portrait attributes and attribute values, and 5G resources can be guided to be accurately released.
Description
Technical Field
The application relates to the field of vertical industries, in particular to a method and a system for identifying business demand areas of enterprise users.
Background
The main service objects of the 4G network are limited To the common consumer individual user (To Customer, toC) service, while the important goal of the 5G network focuses on how To support the vertical Business development of the enterprise user (To Business, toB) service. The core value of a 5G network is to enable a business, while providing ToC and ToB services. With the development of 5G networks in a global context, the ToB vertical industry application will become the key to the success of 5G networks.
The ToB-oriented 5G network for various industries can provide diversified and deterministic network capabilities, emphasize the convergence networking of a public network and a private network, and can also provide services for deploying private networks according to needs for different industries in a public network sharing mode. In order to meet the requirements of production, management, logistics, office and the like, enterprises currently deploy multiple independent private networks, such as Ultra Wide Band (UWB), industrial wireless communication technology (WIFI), a proprietary Long Term Evolution (LTE) cluster, a wired local area network and the like, and the operation cost is high. For a large number of vertical industries, the 5G private network bearer service has many advantages.
However, in the 5G network planning and construction process, it is very important to predict and identify the vertical industry service requirements in advance.
Disclosure of Invention
The embodiment of the application provides an identification method and system for business demand areas of enterprise users, and aims to solve the problem that business demands of vertical industries cannot be predicted and identified in advance in the prior art.
In order to solve the technical problem, the present application is implemented as follows:
in a first aspect, a method for identifying an enterprise user service demand area is provided, where the method includes:
identifying private network users in the business-oriented business ToB application, wherein the private network users comprise private network users of the existing ToB application and private network users of potential ToB applications in the same industry;
adopting a deep learning model, performing portrait learning according to the potential of a private network user, and performing portrait scoring on the private network user of the existing ToB application and the remaining target users except the private network user of the potential ToB application in the same industry to generate a 5G private network user potential value;
and determining regional geographical distribution with high ToB service demand according to the user potential value of the 5G private network.
In a second aspect, a system for identifying an enterprise user service demand area is provided, the system comprising:
the system comprises an identification module, a service management module and a service management module, wherein the identification module is used for identifying private network users in the ToB application of enterprise-oriented user services, and the private network users comprise private network users of existing ToB applications and private network users of potential ToB applications in the same industry;
the generation module is used for learning the portrait according to the potential of the private network users by adopting a deep learning model, and grading the portrait of the private network users of the existing ToB application and the rest target users except the private network users of the potential ToB application in the same industry to generate the potential value of the 5G private network users;
and the determining module is used for determining the regional geographical distribution with high ToB service requirement according to the 5G private network user potential value.
In a third aspect, a terminal device is provided, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method according to the first aspect.
In a fourth aspect, a computer-readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, carries out the steps of the method according to the first aspect.
In the embodiment of the application, firstly, private network users in the ToB application facing enterprise user services are identified, the private network users comprise private network users of existing ToB applications and private network users of potential ToB applications in the same industry, then, a deep learning model is adopted, portrait learning is carried out according to the potential of the private network users, portrait scoring is carried out on the private network users of the existing ToB applications and the remaining target users except the private network users of the potential ToB applications in the same industry, the potential value of 5G private network users is generated, and finally, regional geographical distribution with high ToB service requirements is determined according to the potential value of the 5G private network users. The embodiment of the application uses crawler and natural language processing technology through the existing private network system of various non-operators, collects and figures the name and the attribute information of the client of an enterprise, meanwhile, the private network client of the operator and the client figure information of the non-operator private network client definitely have private network service requirements, the extension of the client with the same industry potential private network requirements is carried out, the potential of the private network requirements is predicted according to the figure attribute and the attribute value, and the 5G resource can be guided to be accurately released.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a method for identifying an enterprise user service requirement area according to an embodiment of the present application;
FIG. 2 is an example of vocabulary tagging results provided by an embodiment of the present application;
fig. 3 is a schematic diagram of an identification system for an enterprise user service requirement area according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The method and system for identifying an enterprise user service demand area provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.
Fig. 1 is a flowchart of an identification method for an enterprise user service demand area according to an embodiment of the present application. As shown in fig. 1, the method for identifying an enterprise user service demand area may include: contents shown in step S101 to step S103.
In step S101, private network users in the business-oriented business to b application are identified, where the private network users include private network users of existing ToB applications and private network users of potential ToB applications in the same industry.
The private network users of the existing ToB application mainly comprise two parts, wherein one part is a customer who is already providing private network services by an operator, and the other part is a customer who has an existing solution scheme and builds a private network by himself. The part of clients who self-build private networks show that the ToB application requirement exists, the private networks are partially realized, and operators show the advantages and characteristics of the 5G private networks compared with other private network solutions by means of 5G advanced technologies, so that the probability of the 5G to B clients is relatively high.
In step S102, a deep learning model is adopted to perform portrait learning according to the potential of the private network users, and portrait scoring is performed on the private network users of the existing ToB applications and the remaining target users except the private network users of the same industry potential ToB applications, so as to generate 5G private network user potential values thereof.
In step S103, according to the user potential value of the 5G private network, determining regional geographical distribution with high ToB service demand.
In the embodiment of the application, firstly, private network users in the ToB application facing enterprise user services are identified, the private network users comprise private network users of existing ToB applications and private network users of potential ToB applications in the same industry, then, a deep learning model is adopted, portrait learning is carried out according to the potential of the private network users, portrait scoring is carried out on the private network users of the existing ToB applications and the remaining target users except the private network users of the potential ToB applications in the same industry, the potential value of 5G private network users is generated, and finally, regional geographical distribution with high ToB service requirements is determined according to the potential value of the 5G private network users. The embodiment of the application uses crawler and natural language processing technology through the existing private network system of various non-operators, collect and portrait the client name and the client attribute information of using enterprise, simultaneously through the private network client of the operator, the client portrait information that two types of non-operator private network clients have definitely existed the private network service demand, carry out the extension of the potential private network demand client of the same trade and climb and portrait, carry out private network demand potential prediction according to portrait attribute and attribute value, can guide the accurate input of 5G resource.
In one possible embodiment of the present application, identifying a private network user in an enterprise user service-oriented ToB application may include: identifying private network users of existing ToB applications; and crawling the private network users of the potential ToB applications in the same industry according to the private network users of the existing ToB applications.
In this embodiment, the private network users of the existing ToB applications may be identified first, which indicates the existence of the private network solution requirement in the industry, and then the private network users of the potential ToB applications in the same industry are crawled, so that the identification scope can be expanded for the analysis of the 5G ToB service requirement.
Crawling private network users of the same industry potential ToB application may include: firstly, keywords such as cities or industries and the like are limited, and related industries and related enterprises of specific cities are crawled.
In one possible embodiment of the present application, identifying private network users of existing ToB applications may include the following steps.
Crawling equipment providers or service providers corresponding to the private network solution by taking the private network solution of the non-operator as a keyword, wherein the private network solution of the non-operator comprises an ultra wide band, an industrial wireless communication technology, a narrow-band private network and a private long-term evolution technology cluster; and acquiring a private network client directory served by the equipment provider or the service provider from public information of the equipment provider or the service provider.
The method comprises the steps of crawling on the Internet by using a crawler technology through the existing private network solution of a non-operator in the industry, further processing information data, and obtaining equipment merchants or service merchants providing the private network solution. Existing mature solutions for non-carrier-level private networks include ultra-wideband UWB, industrial WIFI, narrowband private networks, private LTE clusters, and the like, and the solutions can be crawled to corresponding equipment providers or service providers by using the solutions as keywords. If industrial WIFI is used as a target, numerous service manufacturers corresponding to the solution are crawled, keywords such as 'industrial WIFI service providers' are crawled, and names of a large number of service providers are obtained.
Then, the private network client directory of the service is obtained from the public information of the private network solution service provider of the non-operator. Still taking the extraction of private network clients such as industrial WIFI as an example, some websites of industrial WIFI service providers or websites in the industrial aspect are listed with relevant contents such as case display, client style and the like, and further crawling and processing are performed to further identify and obtain a large number of industrial WIFI-required clients.
By crawling the served customer objects with the industrial WIFI facilitator "XX network stock limited" as a keyword, successful cases of a large number of industrial WIFI customers providing services are clearly enumerated in cases on the XX network stock limited website. If the industry shrinks within the manufacturing industry, the manufacturing industry is used as a key word for searching, and clients of industrial WIFI solutions relevant to the manufacturing industry such as cigarette factories, automobile manufacturing factories and chemical factories are extracted. The manufacturing industry can also subdivide multiple categories, and the detailed categories represent enterprises which successfully provide industrial WIFI solutions for XX network shares and indicate the existence of private network solution requirements in the industries, so that the identification scope is expanded for the analysis of 5G toB business requirements.
In the crawling of the affiliated segment industry and more related information, because the presentation modes of the information are different, some information is presented in a structured mode such as a table, and some information is presented in a news text mode. Therefore, different portrait methods are adopted for different rendering modes, and the following steps can be included.
The first step is as follows: extracting and converging related company attribute names; such as company name, investor, registered capital, production value, footprint, number of employees, corporate operations, etc.
The second step is that: extracting corresponding attribute values from a data table or news text obtained by the crawler according to the attribute names, wherein the total assets are XXX hundred million, and the marketing condition of a company is as follows: if not; number of company employees: XXX, etc.
Different processing methods are adopted for different data. Aiming at the structured data, the corresponding attribute name and attribute value can be directly extracted by a regular method; for unstructured data such as text news, two steps are needed, the first step adopts attribute name automatic extraction based on word vectors, and the second step adopts a regularization and deep learning method to extract attribute values after determining the attribute names.
In a possible implementation manner of the application, the portrait learning is performed by using a deep learning model according to the potential of the private network user, and the portrait scoring is performed on the remaining targets except the private network user of the existing ToB application and the private network user of the potential ToB application in the same industry, so as to generate the potential value of the 5G private network user thereof, which may include the following steps.
Extracting company attribute names, wherein the company attribute names comprise company names, investors, registered capital, production value and yield, occupied area, employee number and company business; extracting portrait attributes of the private network client according to the acquired private network client directory and the company attribute name based on a deep learning model; and (4) carrying out data analysis on the portrait attributes of the private network client to obtain the confidence score of each user and generate the potential value of the 5G private network user.
Specifically, the automatic extraction may be based on the attribute names of the word vectors: this is a semi-supervised learning, which requires some seed attribute names to be input, such as: the descriptive "seed words" such as rank, english name, registered capital, etc. may be derived from structured data or added by human, and are not limited in this application. And then segmenting words of news corpora of corresponding industries, training Word vectors to establish a semantic model, and adopting a Word2Vec method to convert each Word into a dense space vector by an unsupervised method.
And inputting a predefined seed word bank, inputting the seed word bank into the semantic model, and outputting descriptive words of a specific industry. And finally, filtering in a rule or conditional probability mode to obtain a final attribute name.
The attribute values can also be extracted by adopting a regularization and deep learning method: analyzing a large number of news finds that many attribute values tend to follow the attribute name, for example: xx company total assets reach xx billion dollars. For this, the extraction may be performed in the form of a regular match. However, due to the diversification of languages, the rule-based approach cannot exhaust all templates, and a deep learning end-to-end approach is required. The deep learning method can learn the semantics of the text, thereby achieving the extraction effect. Because the model is supervised learning, samples need to be labeled, and the labeling description of the samples is labeled aiming at each character, three labeling results are obtained: 'B', 'I', 'O'; respectively, the beginning, middle or end of the vocabulary, the extraneous word, as shown in fig. 2.
The deep learning model is based on attribute value extraction of a bi-directional LSTM + CRF, where LSTM is a variant of the recurrent neural network RNN, suitable for modeling against natural language sequences. In the output structure, the probability is output according to the maximum value of each word directly through the softmax function. The Softmax function is also called a normalized exponential function, and displays the classification result in a probability form. The Softmax function is expressed as follows.
Further, the Softmax function outputs a probability that the result is between 0 and 1. The output vocabulary may be incomplete and require correction by the CRF model. The CRF is a conditional random field model and is used as a probability map model, so that the maximum probability that the whole word is complete can be ensured, and the integrity of the extracted word can be ensured. Inputting news text, outputting the probability that each word in the text belongs to the categories of B, I and O, and then inputting a CRF model to output a complete extraction result.
In one possible implementation of the present application, the data analysis of the portrait attributes of the private network client to obtain the confidence score of each user and generate the 5G private network user potential value thereof may include the following steps.
Analyzing the distribution of each feature in the portrait attributes of the private network client and the distribution of the labels; analyzing the multivariate, the relation between variables and characteristics, and the correlation between characteristics; and obtaining the confidence score of each user according to the analysis and the neural network model.
Aiming at the previously identified private network users of the existing ToB application and the private network users of the extended crawling potentially applied ToB in the same industry, a portrait model of the 5G private network demand potential is built through machine learning according to the attributes of the crawled enterprise portrait. For example, the customer potential already in the operator enterprise application target customer directory is set to 1, and the private network user potential of the existing ToB application is set to 0.9. And (3) adopting a deep learning model to perform portrait learning according to the potential of the private network user, and scoring portraits of the remaining target clients except the two types of target clients to generate a potential value of the 5G private network user. The specific scheme is as follows.
Firstly, data processing analysis and processing are carried out. Due to uncertainty of data extraction, missing values exist in part of samples, and two schemes can be performed, namely network re-retrieval based on the missing values and sample names, and filling based on similar enterprises.
Then analyzing the distribution of the single characteristics and the distribution of the labels; and carrying out abnormality analysis on each characteristic, and carrying out different treatments on different abnormal values.
And then performing multivariate analysis, analyzing the relation between variables and characteristics, and analyzing the correlation between the characteristics.
And finally, performing data normalization processing and model modeling, wherein due to the fact that the categorical variables and the floating point variables in the data exist at the same time, deep & wide neural network models can be used for modeling.
The core idea of the deep & wide model is to combine the memory capacity of a linear model and the generalization capacity of a deep neural network model. The Deep & Wide model consists of two parts, namely Wide and Deep; the Wide end corresponds to a linear model, the input features can be continuous features or sparse discrete features, and the discrete features can form higher-dimensional discrete features after being crossed. The linear model can be quickly converged into an effective feature combination through regularization in the training process. The Deep part can be a multi-layer feedforward neural network, and models embedding (a way of converting discrete variables into continuous vector representations) of features. And finally, splicing the output of Deep and the output of wide, and finally connecting a softmax function layer to output the confidence score of each enterprise.
Further, model evaluation and parameter optimization can be further included. According to the operation result of the model, the parameters such as the optimal learning rate and the optimal Dropout rate (aiming at solving the overfitting problem during the neural network training), the iteration times, the loss function, the number of the neurons and the like which are suitable for the neural network are found in a grid searching mode, and the confidence degree scoring result is further corrected, so that the optimal potential value required by the 5G private network is obtained.
According to the embodiment of the application, the requirements of potential vertical industry services can be acquired, portrayed and clustered through a crawler and machine learning method, geographical distribution of areas with high possibility of vertical industry service requirements is identified, the key points of resource investment of 5G network construction and optimization are guided, and the purpose of providing 5G network capability support for ToB services is achieved.
In a possible real-time manner of the present application, determining the regional geographic distribution with high ToB service demand according to the user potential value of the 5G private network may include: through the steps, the name, the portrait and the confidence level list of the potential demand user of the 5G private network are extracted, and the position, the range and other geographic data are extracted by the user name in a crawling mode by combining with the information, the frame and other data of the Point of Interest (POI).
And the position, the frame and other information of the crawled potential customers of the 5G private network can be used for displaying the potential of the 5G private network requirements in a thermodynamic diagram.
Because the private network is generally a coverage backbone built by a 5G large network, the clustering radius can be set to be 2 to 3 times of the station spacing of the large network at the position, and potential customer geographic border areas with high potential confidence coefficient of the private network continuously appear in the clustering radius can be clustered into continuous areas.
Fig. 3 is a schematic diagram of an identification system for an enterprise user business requirement area according to an embodiment of the present application. As shown in fig. 3, the identification system for business requirement region of enterprise user is applied to the terminal side of prover, and may include: an identification module 301, a generation module 302 and a determination module 303.
Specifically, the identifying module 301 is configured to identify private network users in an enterprise user service-oriented ToB application, where the private network users include private network users of an existing ToB application and private network users of a potential ToB application in the same industry; the generation module 302 is used for performing portrait learning according to the potential of the private network users by adopting a deep learning model, and grading portraits of the private network users of the existing ToB application and the remaining target users except the private network users of the potential ToB application in the same industry to generate the potential values of the 5G private network users; and the determining module 303 is configured to determine, according to the user potential value of the 5G private network, geographical distribution of an area where the ToB service demand is high.
In this embodiment of the application, firstly, the identification module 301 identifies private network users in the service ToB application facing enterprise users, where the private network users include private network users of existing ToB applications and private network users of potential ToB applications in the same industry, then the generation module 302 performs portrait learning according to the potential of the private network users by using a deep learning model, and performs portrait scoring on the private network users of existing ToB applications and the remaining target users except the private network users of the potential ToB applications in the same industry, so as to generate a 5G private network user potential value, and finally the determination module 303 determines regional geographical distribution with high ToB service requirements according to the 5G private network user potential value. The embodiment of the application uses crawler and natural language processing technology through the existing private network system of various non-operators, collects and figures the name and the attribute information of the client of an enterprise, meanwhile, the private network client of the operator and the client figure information of the non-operator private network client definitely have private network service requirements, the extension of the client with the same industry potential private network requirements is carried out, the potential of the private network requirements is predicted according to the figure attribute and the attribute value, and the 5G resource can be guided to be accurately released.
In one possible embodiment of the present application, the identification module is configured to: identifying private network users of existing ToB applications; and crawling the private network users of the potential ToB applications in the same industry according to the private network users of the existing ToB applications.
In one possible embodiment of the present application, the identification module is further configured to: crawling equipment providers or service providers corresponding to the private network solution by taking the private network solution of the non-operator as a keyword, wherein the private network solution of the non-operator comprises an ultra wide band, an industrial wireless communication technology, a narrow-band private network and a private long-term evolution technology cluster; and acquiring a private network client directory serviced by the equipment provider or the service provider from public information of the equipment provider or the service provider.
In one possible embodiment of the present application, the generation module is configured to: extracting company attribute names, wherein the company attribute names comprise company names, investors, registered capital, production value and yield, occupied area, employee number and company business; extracting portrait attributes of the private network client according to the acquired private network client directory and the company attribute name based on a deep learning model; and (4) carrying out data analysis on the portrait attributes of the private network client to obtain the confidence score of each user and generate the potential value of the 5G private network user.
In one possible embodiment of the present application, the generation module is further configured to: analyzing the distribution of each feature in the portrait attributes of the private network client and the distribution of the labels; analyzing the multivariate, the relation between the variable and the characteristic and the correlation between the characteristic and the characteristic; and obtaining the confidence score of each user according to the analysis and the neural network model.
The functions of the identification system for the enterprise user service requirement area described in the present application have been described in detail in the method embodiments shown in fig. 1-2, so that reference may be made to the relevant description in the foregoing embodiments for details that are not described in detail in the description of the present embodiment, and are not described again here.
Optionally, an embodiment of the present application further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program, when executed by the processor, implements each process of the above embodiment of the method for identifying an enterprise user service requirement area, and can achieve the same technical effect, and details are not repeated here to avoid repetition.
Optionally, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements each process of the embodiment of the method for identifying an enterprise user service requirement area, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the present embodiments are not limited to those precise embodiments, which are intended to be illustrative rather than restrictive, and that various changes and modifications may be effected therein by one skilled in the art without departing from the scope of the appended claims.
Claims (10)
1. An identification method for business demand areas of enterprise users is characterized by comprising the following steps:
identifying private network users in an enterprise user service-oriented ToB application, wherein the private network users comprise private network users of an existing ToB application and private network users of a potential ToB application in the same industry;
adopting a deep learning model, performing portrait learning according to the potential of a private network user, and performing portrait scoring on the private network user of the existing ToB application and the remaining target users except the private network user of the potential ToB application in the same industry to generate a 5G private network user potential value;
and determining regional geographical distribution with high ToB service demand according to the user potential value of the 5G private network.
2. The method according to claim 1, wherein the identifying private network users in the ToB application comprises:
identifying private network users of existing ToB applications;
and crawling the private network users of the potential ToB applications in the same industry according to the private network users of the existing ToB applications.
3. The method according to claim 2, wherein the identifying private network users of existing ToB applications comprises:
crawling an equipment provider or a service provider corresponding to a private network solution of a non-operator by taking the private network solution of the non-operator as a keyword, wherein the private network solution of the non-operator comprises an ultra wide band, an industrial wireless communication technology, a narrow-band private network and a private long term evolution technology cluster;
and acquiring a private network client directory serviced by the equipment provider or the service provider from the public information of the equipment provider or the service provider.
4. The method of claim 1, wherein the step of using the deep learning model to perform portrait learning according to the potential of private network users and score portraits of remaining targets except for the private network users of existing ToB applications and the private network users of potential ToB applications in the same industry to generate the potential value of 5G private network users comprises:
extracting company attribute names, wherein the company attribute names comprise company names, investors, registered capital, production value and yield, occupied area, employee number and company business;
extracting portrait attributes of the private network client according to the acquired private network client directory and the company attribute name based on a deep learning model;
and carrying out data analysis on the portrait attributes of the private network client to obtain the confidence score of each user and generate the potential value of the 5G private network user.
5. The method of claim 4, wherein said analyzing said representation attributes of said private network client to obtain a confidence score for each user to generate a 5G private network user potential value comprises:
analyzing the distribution of each characteristic and the distribution of the labels in the portrait attributes of the private network client;
analyzing the multivariate, the relation between variables and characteristics, and the correlation between characteristics;
and obtaining the confidence score of each user according to the analysis and the neural network model.
6. An identification system for business requirement areas of enterprise users, comprising:
the system comprises an identification module, a service management module and a service management module, wherein the identification module is used for identifying private network users in the ToB application of enterprise-oriented user services, and the private network users comprise private network users of existing ToB applications and private network users of potential ToB applications in the same industry;
the generation module is used for learning the portrait according to the potential of the private network users by adopting a deep learning model, and grading the portrait of the private network users of the existing ToB application and the rest target users except the private network users of the potential ToB application in the same industry to generate the potential value of the 5G private network users;
and the determining module is used for determining the regional geographical distribution with high ToB service requirement according to the 5G private network user potential value.
7. The identification system of claim 6, wherein the identification module is configured to:
identifying private network users of existing ToB applications;
and crawling the private network users of the potential ToB applications in the same industry according to the private network users of the existing ToB applications.
8. The identification system of claim 7, wherein the identification module is further configured to:
crawling an equipment provider or a service provider corresponding to a private network solution by taking the private network solution of a non-operator as a keyword, wherein the private network solution of the non-operator comprises an ultra-wideband, an industrial wireless communication technology, a narrow-band private network and a private long-term evolution technology cluster;
and acquiring a private network client directory serviced by the equipment provider or the service provider from the public information of the equipment provider or the service provider.
9. The identification system of claim 6, wherein the generation module is configured to:
extracting company attribute names, wherein the company attribute names comprise company names, investors, registered capital, production value and yield, occupied area, employee number and company business;
extracting portrait attributes of the private network client according to the acquired private network client directory and the company attribute name based on a deep learning model;
and carrying out data analysis on the portrait attributes of the private network client to obtain the confidence score of each user and generate the potential value of the 5G private network user.
10. The identification system of claim 9, wherein the generation module is further configured to:
analyzing the distribution of each characteristic and the distribution of the labels in the portrait attributes of the private network client;
analyzing the multivariate, the relation between the variable and the characteristic and the correlation between the characteristic and the characteristic;
and obtaining the confidence score of each user according to the analysis and the neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706639.1A CN115529602A (en) | 2021-06-24 | 2021-06-24 | Method and system for identifying business demand area of enterprise user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706639.1A CN115529602A (en) | 2021-06-24 | 2021-06-24 | Method and system for identifying business demand area of enterprise user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115529602A true CN115529602A (en) | 2022-12-27 |
Family
ID=84694882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110706639.1A Pending CN115529602A (en) | 2021-06-24 | 2021-06-24 | Method and system for identifying business demand area of enterprise user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115529602A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090204569A1 (en) * | 2008-02-11 | 2009-08-13 | International Business Machines Corporation | Method and system for identifying companies with specific business objectives |
| US20180053255A1 (en) * | 2016-08-19 | 2018-02-22 | Noonum | System and Method for end to end investment and portfolio management using machine driven analysis of the market against qualifying factors |
| US20180181625A1 (en) * | 2016-12-22 | 2018-06-28 | Aon Global Operations Ltd (Singapore Branch) | Systems and Methods for Intelligent Prospect Identification Using Online Resources and Neural Network Processing to Classify Organizations based on Published Materials |
| CN108509569A (en) * | 2018-03-26 | 2018-09-07 | 河北省科学院应用数学研究所 | Generation method, device, electronic equipment and the storage medium of enterprise's portrait |
| CN109255646A (en) * | 2018-07-27 | 2019-01-22 | 国政通科技有限公司 | Deep learning is carried out using big data to provide method, the system of value-added service |
| US20190268283A1 (en) * | 2018-02-23 | 2019-08-29 | International Business Machines Corporation | Resource Demand Prediction for Distributed Service Network |
| CN111859071A (en) * | 2020-07-21 | 2020-10-30 | 北京北斗天巡科技有限公司 | Business information mining system based on internet information |
| KR102192949B1 (en) * | 2020-04-17 | 2020-12-18 | (주)휘랑 | Apparatus and method for evaluating start-up companies using artifical neural network |
-
2021
- 2021-06-24 CN CN202110706639.1A patent/CN115529602A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090204569A1 (en) * | 2008-02-11 | 2009-08-13 | International Business Machines Corporation | Method and system for identifying companies with specific business objectives |
| US20180053255A1 (en) * | 2016-08-19 | 2018-02-22 | Noonum | System and Method for end to end investment and portfolio management using machine driven analysis of the market against qualifying factors |
| US20180181625A1 (en) * | 2016-12-22 | 2018-06-28 | Aon Global Operations Ltd (Singapore Branch) | Systems and Methods for Intelligent Prospect Identification Using Online Resources and Neural Network Processing to Classify Organizations based on Published Materials |
| US20190268283A1 (en) * | 2018-02-23 | 2019-08-29 | International Business Machines Corporation | Resource Demand Prediction for Distributed Service Network |
| CN108509569A (en) * | 2018-03-26 | 2018-09-07 | 河北省科学院应用数学研究所 | Generation method, device, electronic equipment and the storage medium of enterprise's portrait |
| CN109255646A (en) * | 2018-07-27 | 2019-01-22 | 国政通科技有限公司 | Deep learning is carried out using big data to provide method, the system of value-added service |
| KR102192949B1 (en) * | 2020-04-17 | 2020-12-18 | (주)휘랑 | Apparatus and method for evaluating start-up companies using artifical neural network |
| CN111859071A (en) * | 2020-07-21 | 2020-10-30 | 北京北斗天巡科技有限公司 | Business information mining system based on internet information |
Non-Patent Citations (1)
| Title |
|---|
| 任小强;杨玉忠;张仁轩;王晓龙;: "大数据分析在宽带精准营销业务中的应用", 电信工程技术与标准化, no. 04, 15 April 2018 (2018-04-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210150130A1 (en) | Methods for generating natural language processing systems | |
| CN111026842B (en) | Natural language processing method, natural language processing device and intelligent question-answering system | |
| CN110019616B (en) | POI (Point of interest) situation acquisition method and equipment, storage medium and server thereof | |
| CN111625715B (en) | Information extraction method and device, electronic equipment and storage medium | |
| CN114357197B (en) | Event reasoning method and device | |
| EP3373166A1 (en) | Method and system for mapping attributes of entities | |
| CN112241458A (en) | Text knowledge structuring processing method, device, equipment and readable storage medium | |
| CN114371946B (en) | Information push method and information push server based on cloud computing and big data | |
| CN112015896A (en) | Emotion classification method and device based on artificial intelligence | |
| CN116401379A (en) | Financial product data pushing method, device, equipment and storage medium | |
| CN113254649B (en) | Training method of sensitive content recognition model, text recognition method and related device | |
| CN113112282A (en) | Method, device, equipment and medium for processing consult problem based on client portrait | |
| CN115660695A (en) | Customer service personnel label portrait construction method and device, electronic equipment and storage medium | |
| CN113961811B (en) | Event map-based conversation recommendation method, device, equipment and medium | |
| CN113392920B (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN106407271B (en) | Intelligent customer service system and updating method of intelligent customer service knowledge base thereof | |
| CN115529602A (en) | Method and system for identifying business demand area of enterprise user | |
| CN111615178B (en) | Method and device for identifying wireless network type and model training and electronic equipment | |
| CN114580533A (en) | Method, apparatus, device, medium, and program product for training feature extraction model | |
| CN116541517A (en) | Text information processing method, apparatus, device, software program, and storage medium | |
| CN111523034A (en) | Application processing method, device, equipment and medium | |
| CN113792163B (en) | Multimedia recommendation method and device, electronic equipment and storage medium | |
| KR102649918B1 (en) | System for recommending customized welfare policy based on large language model | |
| CN114385892B (en) | Article grade identification method, device, server and storage medium | |
| CN117333191A (en) | Complaint event association method and device and complaint event association system |
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 |