Enterprise relationship evaluation method, device and equipment based on communication big data and medium

Abstract

The invention discloses an enterprise relationship evaluation method, device and equipment based on communication big data, and a medium, and the method comprises the steps: constructing an undirected graph model according to the actual operation business of an enterprise and the upstream and downstream distribution of an industrial chain, and determining a first compactness quantification function of an operation business relationship between enterprises according to the undirected graph model; determining a second closeness quantification function of the communication relationship between the enterprises according to the communication relationship behavior between the enterprise number libraries; determining a relation compactness comprehensive quantization function according to the first compactness quantization function and the second compactness quantization function; and calculating the compactness relationship between stock enterprises according to the relationship compactness comprehensive quantization function to obtain a compactness evaluation result of the relationship between the enterprises. According to the method, the comprehensiveness, accuracy and real-time performance of enterprise relationship evaluation are improved, and the method can be widely applied to the technical field of big data analysis.

Description

Technical Field

[0001] The present invention relates to the field of big data analysis technology, and in particular to a method, device, equipment and medium for evaluating enterprise relationships based on communication big data. Background Art

[0002] The closeness of corporate relationships usually refers to the closeness of the relationship between companies in a specific field or network, revealing the degree of cooperation, interaction or dependence between companies, which includes but is not limited to the connection between upstream and downstream companies in the supply chain, the collaborative work between partners, the trust and depth of cooperation between companies and customers or suppliers, etc.

[0003] With the development of globalization and digitalization, cooperation between enterprises has become more frequent. Close cooperative relationships may bring high efficiency and synergy, but at the same time they may also increase the risk of risk transmission. Assessing the closeness of the relationship between the enterprise itself and its cooperative enterprises helps enterprises identify key dependencies and plan risk response measures in advance. In addition, the development of digital technology has promoted the globalization and diversification of the supply chain, promoted the rapid flow of information and resource sharing between enterprises, but also made enterprise relationship management more dynamic and complex, and the complexity and uncertainty of the supply chain have also increased. Enterprise relationship assessment helps enterprises identify key nodes in the supply chain, optimize processes, reduce interruption risks, and strengthen interactions with stakeholders, improve cooperation efficiency, optimize resource allocation, and ensure the robustness of the supply chain. Finally, modern enterprises are increasingly pursuing innovation and competitive advantages. Innovation in the context of globalization is no longer limited to a single enterprise, but occurs more in the enterprise ecosystem. Close cooperative relationships help reduce transaction costs, accelerate knowledge transfer and technology diffusion, and assessing closeness helps build an innovative ecosystem.

[0004] As the modernization of the industrial chain continues to advance, the government can more effectively guide the allocation of social resources by understanding the closeness of the relationship between enterprises. It can also help the government understand the structural characteristics of different industries and markets, so as to formulate more precise industrial policies, trade policies and investment guidance policies, support the development of key industrial chains and industrial clusters, enhance the resilience and stability of the economy, and guide enterprises to build close corporate relationships, which will help create employment opportunities and promote economic growth. In social public construction projects and the construction of government-enterprise relations, the government often needs to cooperate with enterprises. Assessing the closeness of corporate relationships helps the government identify and establish cooperative relationships with key enterprises, promote the smooth implementation of public-private partnership projects, and ensure the quality and efficiency of public facilities and services. In the fields of finance, environment, security, etc., close corporate relationships may bring systemic risks. Through assessment, the government can promptly identify risk concentration areas, take preventive measures, strengthen supervision, and prevent adverse consequences such as market monopoly and environmental pollution.

[0005] In summary, enterprise relationship assessment is of great significance in scenarios such as precision marketing, supply chain optimization, marketing decision-making, competitor analysis, and risk prevention and control.

[0006] The existing technologies in enterprise relationship assessment mainly have the following problems:

[0007] 1) In the corporate relationship assessment of some solutions, the data comes from tax invoice related data to construct a corporate relationship map. This method has a relatively single data source, and the tax invoice data is relatively sensitive. It has fewer application scenarios, and if there is no invoice transaction but the strongly related companies cannot be identified, it can only reflect the supply-related relationships of the companies. It has limitations, the data is single, and it is impossible to comprehensively evaluate the corporate relationships.

[0008] 2) In the enterprise relationship evaluation of some solutions, the enterprise relationship network of multiple industrial chains is mainly constructed by judging the importance of nodes, and the enterprise relationship is evaluated by modeling the node influence range and node importance. Although it can reflect the enterprise relationship, the data is highly subjective in terms of importance and influence range. Although the data heterogeneity is modeled, there are still factors such as insufficient data sources, and the final output of the enterprise relationship is not objective enough.

[0009] 3) In the corporate relationship assessment of some solutions, the data comes from the industrial and commercial registration data, which is obtained by crawling the Internet. Although the industrial and commercial registration information modeling can show the corporate relationship, there are problems such as low data update frequency, data lag, and single data source, which causes the final assessment of the corporate relationship to lag and have limitations.

[0010] Terminology explanation:

[0011] CT (Communication tightness): The tightness of inter-enterprise communication behavior.

[0012] TBR (Tightness of business relationship): The tightness of business relationship between enterprises.

[0013] TER (Tightness of enterprise relationships): A comprehensive quantitative assessment of the tightness of enterprise relationships that combines the tightness of communication and the tightness of operational business relationships. Summary of the invention

[0014] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0015] To this end, an object of an embodiment of the present invention is to provide a method for evaluating enterprise relationships based on communication big data, which improves the comprehensiveness, accuracy and real-time performance of enterprise relationship evaluation.

[0016] Another object of an embodiment of the present invention is to provide a device for evaluating enterprise relationships based on communication big data.

[0017] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0018] On the one hand, an embodiment of the present invention provides a method for evaluating enterprise relationships based on communication big data, comprising the following steps:

[0019] Constructing an undirected graph model according to the actual business operations of the enterprises and the upstream and downstream distribution of the industrial chain, and determining a first closeness quantization function of the business relationship between the enterprises according to the undirected graph model;

[0020] Determine a second closeness quantification function of the communication relationship between enterprises according to the communication contact behavior between the enterprise number databases;

[0021] Determine a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function;

[0022] The closeness relationship between existing enterprises is calculated according to the comprehensive quantitative function of the closeness of the relationship to obtain the closeness evaluation result of the relationship between enterprises.

[0023] Further, in one embodiment of the present invention, the undirected graph model is constructed according to the actual business operations of the enterprise and the upstream and downstream distribution of the industrial chain, which specifically includes:

[0024] Determine the actual business operations of each target enterprise, and determine the industry to which each target enterprise belongs based on the actual business operations;

[0025] Determine the upstream and downstream relationships of the industrial chain between the target enterprises according to the industrial sectors to which they belong;

[0026] Taking each of the target enterprises as a vertex, and determining the connection edges between the vertices according to the upstream and downstream relationships of the industrial chain;

[0027] A plurality of industrial chain links are determined according to the vertices and the connecting edges, and the undirected graph model is constructed according to the industrial chain links.

[0028] Further, in one embodiment of the present invention, the first closeness quantification function for determining the inter-enterprise business relationship according to the undirected graph model specifically includes:

[0029] Determine whether there is a direct connection relationship between the two target enterprises in each of the industrial chain links according to the undirected graph model;

[0030] When the two target enterprises are directly connected in the industrial chain link, the corresponding industrial chain relationship closeness quantification value is determined to be 1;

[0031] When there is no direct connection between the two target enterprises in the industrial chain link, the enterprise distance is determined according to the number of enterprises between the two in the industrial chain link, and then the reciprocal of the corresponding item of the Fibonacci series is calculated according to the enterprise distance to obtain the corresponding quantitative value of the closeness of the industrial chain relationship;

[0032] Determine the result of the quantification of the closeness of the industrial chain relationship according to the sum of the quantified values ​​of the closeness of the industrial chain relationship of the two target enterprises in each of the industrial chain links;

[0033] Determine the corresponding quantitative results of actual business operations according to whether the two target enterprises belong to the same industry;

[0034] The first closeness quantification function of the two target enterprises is determined according to the quantification result of the closeness of the industrial chain relationship and the quantification result related to the actual business operations.

[0035] Further, in one embodiment of the present invention, the second closeness quantification function of determining the communication relationship between enterprises based on the communication contact behavior between the enterprise number databases specifically includes:

[0036] Determine the enterprise number database of each target enterprise;

[0037] Acquire the number of calls between the two target enterprises and the corresponding single call duration within a preset historical period according to the enterprise number database, wherein the preset historical period includes multiple historical periods;

[0038] Filtering the target number of calls within the target call duration range according to the single call duration, and obtaining the target total call duration between the two target enterprises according to the target number of calls;

[0039] Performing a logarithmic transformation on the target total call duration to obtain a call duration variable, and determining a quantified result of the communication density of the historical period by multiplying the call duration variable by the number of calls between the two target enterprises in a single historical period;

[0040] The second closeness quantization function of the two target enterprises is determined according to the average of the communication closeness quantization results of each of the historical periods.

[0041] Furthermore, in one embodiment of the present invention, the enterprise relationship evaluation method further includes a step of optimizing the communication closeness quantification result, which specifically includes:

[0042] Obtain the number of employees who have had communication contact between the two target enterprises during the historical period;

[0043] Determine the optimization coefficient according to the ratio of the number of employees making calls to the total number of employees of the two target enterprises;

[0044] The product of the optimization coefficient and the communication closeness quantization result is used as the optimized communication closeness quantization result.

[0045] Further, in one embodiment of the present invention, determining the relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function specifically includes:

[0046] Obtaining preset business relationship weights and communication relationship weights;

[0047] The first closeness quantization function and the second closeness quantization function are summed according to the business relationship weight and the communication relationship weight to obtain the relationship closeness comprehensive quantization function.

[0048] Furthermore, in one embodiment of the present invention, the calculation of the closeness relationship between existing enterprises according to the comprehensive quantitative function of the closeness relationship is performed to obtain the closeness evaluation result of the relationship between enterprises, which specifically includes:

[0049] The enterprise relationship closeness value between the two target enterprises is calculated according to the comprehensive quantitative function of the relationship closeness;

[0050] When the enterprise relationship closeness value is greater than or equal to a preset first threshold, determining that the closeness evaluation result of the two target enterprises is closely related;

[0051] When the enterprise relationship closeness value is less than the first threshold, it is determined that the closeness evaluation result of the two target enterprises is a loose relationship.

[0052] On the other hand, an embodiment of the present invention provides a device for evaluating enterprise relationships based on communication big data, comprising:

[0053] A first closeness quantization function determination module is used to construct an undirected graph model according to the actual business operations of the enterprise and the upstream and downstream distribution of the industrial chain, and determine a first closeness quantization function of the business relationship between the enterprises according to the undirected graph model;

[0054] A second closeness quantization function determination module, used to determine a second closeness quantization function of the communication relationship between enterprises according to the communication contact behavior between the enterprise number databases;

[0055] A relationship closeness comprehensive quantization function determination module, configured to determine a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function;

[0056] The closeness evaluation module is used to calculate the closeness relationship between existing enterprises according to the comprehensive quantitative function of the closeness relationship to obtain the closeness evaluation result of the relationship between enterprises.

[0057] On the other hand, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein the program, when executed by the processor, realizes the enterprise relationship evaluation method based on communication big data as described above.

[0058] On the other hand, an embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the enterprise relationship evaluation method based on communication big data as described above.

[0059] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0060] The embodiment of the present invention constructs an undirected graph model based on the actual business operations of enterprises and the upstream and downstream distribution of the industrial chain, and determines the first closeness quantification function of the business operation relationship between enterprises based on the undirected graph model, determines the second closeness quantification function of the communication relationship between enterprises based on the communication contact behavior between the enterprise number databases, determines the relationship closeness comprehensive quantification function based on the first closeness quantification function and the second closeness quantification function, calculates the closeness relationship between existing enterprises based on the relationship closeness comprehensive quantification function, and obtains the closeness evaluation result of the relationship between enterprises. The embodiment of the present invention quantitatively evaluates the closeness of the relationship between enterprises based on the two dimensions of business operation relationship between enterprises and communication relationship between enterprises, makes full use of the business operation data, industrial chain data and communication behavior data between enterprises, and improves the comprehensiveness, accuracy and real-time performance of enterprise relationship evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0062] Figure 1 A flowchart of a method for evaluating enterprise relationships based on communication big data provided by an embodiment of the present invention;

[0063] Figure 2 A step flow chart of step S101 provided in an embodiment of the present invention;

[0064] Figure 3 Another step flow chart of step S101 provided in an embodiment of the present invention;

[0065] Figure 4 A step flow chart of step S102 provided in an embodiment of the present invention;

[0066] Figure 5 A flowchart of steps for optimizing the communication closeness quantification result provided by an embodiment of the present invention;

[0067] Figure 6 A step flow chart of step S103 provided in an embodiment of the present invention;

[0068] Figure 7 A step flow chart of step S104 provided in an embodiment of the present invention;

[0069] Figure 8 A schematic diagram of the structure of an enterprise relationship evaluation device based on communication big data provided by an embodiment of the present invention;

[0070] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention;

[0071] Fig.10 A schematic diagram of the structure of a storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0072] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limitations on the present application. It should be noted that, although the functional module division is performed in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order from the module division in the system schematic diagram or the flow chart. For the step numbers in the following embodiments, they are only set for the convenience of explanation, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0073] In the description of the present invention, the meaning of "a plurality" is two or more. If there is a description of the first or the second, it is only for the purpose of distinguishing the technical features, and it cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by technicians in the technical field of this application. The terms used in this document are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0074] Enterprise relationship evaluation is of great significance in various scenarios such as supply chain optimization, precision marketing, competition analysis, and risk prevention and control. However, in existing technologies, whether using industrial and commercial registration information data, industrial chain related data, tax invoice data, etc., the enterprise relationships analyzed by modeling generally have limitations, lags, and singleness. There is a lack of cleaning of multi-source heterogeneous data, and no high-quality data set has been formed, resulting in the inability to effectively analyze enterprise associations and the closeness of relationships. Therefore, enterprise relationship evaluation under the current situation still has great research value.

[0075] The embodiment of the present application proposes a corporate relationship evaluation method based on communication big data, which not only takes into account the company-related information and industrial and commercial registration information on the Internet, but also comprehensively uses real-time data such as communication data, current affairs data, and public opinion data. While increasing the data dimension, it also expands the accuracy, real-timeness and applicability of the evaluation method.

[0076] The enterprise relationship evaluation method based on communication big data provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a set-top box, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the enterprise relationship evaluation method based on communication big data, etc., but is not limited to the above forms.

[0077] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0078] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0079] In the process of production and operation, enterprises will have various complex intersections and connections due to business interactions, thus forming close or distant inter-enterprise relationships. How to evaluate the closeness of inter-enterprise relationships can be measured by the closeness of the relationship. The closeness of inter-enterprise relationships can be analyzed from the following scenarios.

[0080] First of all, when there is a relationship between enterprises, there will inevitably be business dealings, or there will be a cooperative relationship because of the upstream and downstream relationships of products, or there will be a competitive relationship because of the same business competitors. Therefore, the closeness of the relationship between enterprises can be evaluated from the correlation between the business operations between enterprises; secondly, the closeness of the relationship between enterprises can be reflected through the communication links between enterprises. Generally speaking, the more communication links between enterprises, the more business dealings there will be between enterprises, which in turn proves that there may be a closer relationship between enterprises, otherwise the relationship may not be close.

[0081] The inter-enterprise relationship situation generated by the relevance of the business operations of enterprises can be obtained through the industrial and commercial information data registered by the enterprises, the official website of the enterprises, and the industry-related network sources. The equity investment relationship contained in the industrial and commercial data shows the relationship between the management and influence of enterprises. The industry classification and business scope of the enterprises can reflect the degree of relevance of the business products of the enterprises. The introduction of the business operations of enterprises in the official website of the enterprises often includes the introduction of the actual related enterprises. This part of the data can supplement and audit the industry classification of industrial and commercial data enterprises. The industry-related network source data contains the upstream, midstream and downstream relationship maps between different types of enterprises. Different enterprises can be connected through the industry attributes of the enterprises to achieve the evaluation of the closeness of the relationship between related enterprises.

[0082] The analysis and evaluation of inter-enterprise communication can be evaluated through the call behavior between enterprises and the call behavior between employees of different enterprises, that is, the interactive information data generated by employees or enterprises using the communication services provided by operators. Among them, the operator communication big data not only contains call behavior data, but also contains base station signaling data related to employee locations. Therefore, based on the real-time and spatial location insight capabilities of the operator communication big data, a basic capability information source for analyzing the closeness of enterprise relationships on the time axis and spatial location distribution is formed.

[0083] Based on the above analysis, we will next conduct a quantitative assessment of the closeness of enterprise relationships from two dimensions: the degree of relevance of business operations between enterprises and the frequency of communication between enterprises.

[0084] like Figure 1 FIG. 1 is a flow chart showing a method for evaluating enterprise relationships based on communication big data provided by an embodiment of the present invention. Figure 1The embodiment of the present invention provides a method for evaluating enterprise relationships based on communication big data, which specifically includes the following steps:

[0085] S101. Construct an undirected graph model based on the actual business operations of the enterprises and the upstream and downstream distribution of the industrial chain, and determine the first closeness quantification function of the business relationship between the enterprises based on the undirected graph model.

[0086] Specifically, the analysis and quantification of the closeness of the correlation between the business operations of enterprises mainly combines the actual business operations of the enterprises and the upstream and downstream relationships of the industries to which the enterprises belong. In order to judge the actual business operations, the business scope field and the industry classification field of the enterprise in the industrial and commercial data were first used. However, considering that the actual business division of enterprises in the industrial and commercial data mainly comes from the self-declaration of enterprises, in this process, enterprises may have incorrect declarations in order to reflect the breadth of their own business. Therefore, by obtaining relevant information such as products on the official website of the enterprise, the accuracy of the industrial type classification of the enterprise is supplemented and optimized to obtain the actual industry to which the enterprise belongs; the data basis for the upstream, midstream and downstream division of the industry to which the enterprise belongs is mainly derived from relevant research results such as government public documents and industry research reports. The actual industry division of the enterprise is matched with the upstream, midstream and downstream industries to achieve the upstream, midstream and downstream division of the industry to which the enterprise belongs.

[0087] The relationship between the businesses of enterprises is not a simple straight line with only up-down and down-to-front and down-to-back relationships. Because of the diversity of business operations, when enterprises are divided into upstream, midstream and downstream of the industrial chain, there will be situations where the same enterprise is located in different upstream and downstream of the industrial chain. Based on this judgment, the business relationship between enterprises is a complex network diagram. In addition, although there are directional factors between enterprises from the perspective of the industrial chain relationship, when evaluating the closeness of enterprise relationships, the business directionality has no effect on the evaluation results. Therefore, in order to accurately evaluate the closeness of the business relationship between enterprises, it is necessary to abstract it into an undirected graph model and then conduct a quantitative evaluation.

[0088] like Figure 2 FIG. 1 is a flowchart of step S101 provided in an embodiment of the present invention, referring to FIG. Figure 2 As an optional implementation method, an undirected graph model is constructed according to the actual business operations of the enterprise and the upstream and downstream distribution of the industrial chain, which specifically includes:

[0089] S1010. Determine the actual business operations of each target enterprise, and determine the industry to which each target enterprise belongs based on the actual business operations;

[0090] S1011. Determine the upstream and downstream relationships of the industrial chain between target enterprises based on their respective industries;

[0091] S1012, taking each target enterprise as a vertex, and determining the connection edges between the vertices according to the upstream and downstream relationships of the industrial chain;

[0092] S1013. Determine multiple industrial chain links based on vertices and connecting edges, and construct an undirected graph model based on the industrial chain links.

[0093] Specifically, according to the theoretical basis of undirected graphs, the construction of an undirected relationship graph between enterprises requires the definition of the vertices of the graph and the connecting edges between each vertex. Obviously, the vertices of the relationship graph are all enterprises. Let the number of enterprises be n, and the vertex set of the relationship graph is V = {v1, v2, ..., v n The connection edge of the enterprise closeness relationship graph has two meanings. One is that there is a certain correlation between two related enterprises, that is, two companies are connected by an edge. The other meaning is the degree of association between the relationship between enterprises, that is, the value of the connection edge between two vertices. Let E represent the set of all vertex connection edges, m represents the number of connection edges, then the edge set E of the undirected graph = {e1,e2,...,e m}, the value range of m is [0, n(n-1) / 2]. When all vertices are independent and there is no connection relationship, the value of m is 0. When each pair of different vertices in the vertex set V is connected by exactly one edge, the value of m is n(n-1) / 2. After determining the definition of the undirected graph of inter-enterprise relations, the next step is to define the calculation method for the value of the connecting edge.

[0094] like Figure 3 FIG. 1 is another step flow chart of step S101 provided in an embodiment of the present invention, referring to FIG. Figure 3 As an optional implementation, a first closeness quantification function of the business relationship between enterprises is determined according to the undirected graph model, which specifically includes:

[0095] S1014. Determine whether there is a direct connection between two target enterprises in each industrial chain link according to the undirected graph model;

[0096] S1015. When two target enterprises have a direct connection relationship in the industrial chain link, the corresponding industrial chain relationship closeness quantification value is determined to be 1;

[0097] S1016. When there is no direct connection between two target enterprises in the industrial chain link, the enterprise distance is determined according to the number of enterprises between the two in the industrial chain link, and then the reciprocal of the corresponding item of the Fibonacci sequence is obtained according to the enterprise distance to obtain the corresponding quantitative value of the closeness of the industrial chain relationship;

[0098] S1017, determining the result of the quantification of the closeness of the industrial chain relationship according to the sum of the quantified values ​​of the closeness of the industrial chain relationship of the two target enterprises in each industrial chain link;

[0099] S1018. Determine the corresponding quantitative results of actual business operations based on whether the two target enterprises belong to the same industry;

[0100] S1019. Determine the first closeness measurement function of the two target enterprises based on the measurement results of the closeness of the industrial chain relationship and the measurement results related to the actual business operations.

[0101] Specifically, based on the previous analysis of the correlation between the actual business operations of enterprises, the values ​​of the correlation edges of the business relationships between enterprises can be quantitatively calculated based on the correlation between the industry attributes of the enterprises and the correlation between the industrial chains of the enterprises.

[0102] For the value of the correlation graph edge of the enterprise industrial chain, quantitative calculation is performed from the upstream, midstream and downstream correlation of the industrial chain to which the enterprise belongs. First, based on the industry categories and division rules contained in the industrial chain nodes in the industrial chain map of the entire industry, each enterprise to be quantitatively analyzed, that is, the vertex of the graph, is matched with it, and the corresponding industrial chain link node identification is marked for the enterprise. Considering that in the link of the same industry industrial chain, there are situations where two enterprises are directly connected and not directly related. Generally speaking, in the same industrial chain link, the closeness of the relationship between two enterprises is negatively correlated with the length of the link between the enterprises, that is, the higher the closeness of the relationship, the shorter the link between the two enterprises, and vice versa, the more link enterprises are separated, the lower the closeness. The quantitative calculation of the enterprise relationship in the industry dimension of the industry to which the actual business of the enterprise belongs is mainly based on the following analysis. If there is a certain competitive relationship between the two enterprises, there is a negative impact on the closeness of the enterprise relationship. If there is no correlation, there is no correlation between the two.

[0103] Based on the above analysis, for the enterprise relationship graph E = {e1, e2, ..., e m The assignment rules for the edge are as follows: for enterprises with direct upstream and downstream relationships, the e value is assigned to 1; for enterprises with indirect relationships, because the closeness of the relationship between two enterprises is negatively correlated with the length of the link between the enterprises, a weight coefficient needs to be added for correction. In order to quantify the relevant changes, the reciprocal of the Fibonacci number is added as the weight coefficient according to the distance between the two companies in the industrial chain, denoted as F i , where i is the number of enterprises between the two + 1, and the weighted coefficient calculation formula is as follows:

[0104]

[0105] Based on the above analysis, in the same industry supply chain j, the closeness quantification value T between two enterprises j It can be expressed as:

[0106]

[0107] Because the node industry divisions on the industrial chain of each industry are not independent of each other, and because most companies have diversified their business in order to improve their competitiveness during their continuous growth, the industry to which their business scope belongs is not unique. Therefore, the same node company may be at different industrial chain link nodes. By calculating the single industrial chain method, all vertices V = {v1,v2,...,v n That is, the correlation of all enterprises on different supply chain links is calculated and quantified to obtain the quantitative value of the correlation closeness on all chains between enterprises. Then, the calculated closeness values ​​are summed up to obtain the quantitative results of the closeness on different links. T represents the vertex v in the vertex set V. a ,v b The business closeness between enterprises, with t representing the number of related industrial chains between enterprises, can be expressed as follows:

[0108]

[0109] According to the above calculation method of the closeness of the industrial supply chain relationship between enterprises, we can obtain the quantitative value data set of the closeness of the industrial supply chain relationship between all enterprises, denoted as T, where v a ∈V,v b ∈V.

[0110] Next, we further correct the closeness of the enterprise relationship by calculating the actual business relevance of the enterprise. The industry classification of the actual industry to which the enterprise belongs is IND. If the industries of two enterprises are exactly the same, then The value is -1, if there is a correlation, it is -0.5, and if there is no correlation, it is 0.

[0111] The quantitative calculation of actual business-related metrics can be used as a correction factor for the closeness of corporate relationships, thereby improving the accuracy and generalization of the closeness of corporate relationships.

[0112] The final index of the tightness of business relationship between enterprises, TBR (Tightness of business relationship), is calculated by summing up the quantified value of the tightness of the industrial supply chain relationship and the quantified results related to the actual business operations. The calculation formula is as follows:

[0113]

[0114] The above formula can be used as the first closeness measurement function of the business relationship between enterprises.

[0115] S102. Determine a second closeness quantification function of the communication relationship between enterprises based on the communication contact behavior between the enterprise number databases.

[0116] Specifically, the operator's communication data includes inter-enterprise calls and inter-employee calls generated by business dealings between enterprises. Parsing the relevant call behavior information can confirm and obtain the call time point, duration, and trajectory location information in the time dimension. Among them, the quantification of the frequency of inter-enterprise call behavior can reflect the degree of correlation between the businesses of the enterprises. For example, if the frequency of calls between the business phones handled by two enterprises is high, it means that the business connection between the enterprises is relatively close. If there is no call interaction between the two enterprises, it means that there is no relationship intersection between the two companies. The characteristic of communication data being updated at a quasi-real-time frequency can effectively avoid the problem of lagging in the evaluation of the closeness of enterprise activities due to timeliness.

[0117] Taking the enterprise as a whole, the communication numbers of enterprise employees and the communication numbers handled by the enterprise are used as the basic number pool for quantifying the closeness of inter-enterprise calls. By analyzing and integrating the communication behaviors such as the duration, time, and frequency of calls between numbers in different enterprise number pools over a period of time, a communication closeness label is constructed as a quantitative indicator to measure the closeness of inter-enterprise communications.

[0118] Considering that the closeness of inter-enterprise relations is a long-term process, short-term occasional abnormal calls will affect the accuracy of enterprise closeness assessment. Therefore, in order to effectively avoid the impact of abnormal data on the result evaluation, when conducting inter-enterprise call closeness analysis and evaluation, the call closeness is calculated by lengthening the statistical step and counting period. Next, the call closeness will be analyzed with a statistical step of month and a statistical period of year.

[0119] like Figure 4 FIG. 1 is a flow chart of step S102 provided in an embodiment of the present invention, referring to FIG. Figure 4 As an optional implementation, a second closeness quantification function of the communication relationship between enterprises is determined according to the communication contact behavior between the enterprise number databases, which specifically includes:

[0120] S1021. Determine the enterprise number database of each target enterprise;

[0121] S1022. Acquire the number of calls between two target enterprises and the corresponding single call duration within a preset historical period according to the enterprise number database, wherein the preset historical period includes multiple historical periods;

[0122] S1023, filtering to obtain a target number of calls within a target call duration range according to a single call duration, and obtaining a target total call duration between two target enterprises according to statistics of the target number of calls;

[0123] S1024, performing logarithmic transformation on the target total call duration to obtain a call duration variable, and multiplying the call duration variable by the number of calls between the two target enterprises in a single historical period to determine a quantified result of the communication density of the historical period;

[0124] S1025: Determine a second closeness quantization function of the two target enterprises according to the average of the communication closeness quantization results of each historical period.

[0125] Specifically, we first trace back the enterprise call records of 12 full natural months from the statistical month, denoted as M, and then analyze the call density in a single month with a natural month as the analysis step. D represents the duration of a single call between the enterprise numbers to be analyzed, n represents the number of calls between the enterprise numbers to be analyzed within 12 full natural months, and T m Indicates the number of calls between the companies to be analyzed within the statistical month. Considering the specific scenarios of business calls between companies, a single call that is too long or too short is considered an abnormal call. Therefore, call records with abnormal call durations of less than 2 minutes and greater than 60 minutes are removed to obtain the quantitative data set D i In order to fully explore the call duration and frequency information and prevent the influence of different dimensions on the results, the call duration is logarithmically transformed to complete the scale compression of the call duration variable. The communication density quantification function is constructed based on the statistical month as the cycle as follows:

[0126]

[0127] In order to further improve the accuracy of judging the tightness between enterprises, based on the quantification of the tightness of communication between enterprises in a single statistical month, the expectation of the tightness of communication between enterprises in the past year is calculated, and the final quantitative calculation formula of the tightness of communication between enterprises CT (Communication tightness) is obtained as follows:

[0128]

[0129] The above formula can be used as the second closeness quantification function of the communication relationship between enterprises.

[0130] like Figure 5 FIG. 1 is a flowchart of a step of optimizing the communication closeness quantization result provided by an embodiment of the present invention, referring to FIG. Figure 5 As an optional implementation, the enterprise relationship evaluation method further includes a step of optimizing the communication closeness quantification result, which specifically includes:

[0131] S201, obtaining the number of employees who had communication contact between two target enterprises during the historical period;

[0132] S202, determining an optimization coefficient according to the ratio of the number of employees making calls to the total number of employees of the two target enterprises;

[0133] S203: taking the product of the optimization coefficient and the communication closeness quantization result as the optimized communication closeness quantization result.

[0134] Specifically, in addition to the number and duration of calls, the number of employees who communicate between different companies is also an important indicator that affects the quantitative results of building communication closeness. Let s be the number of employees who communicate between companies to be quantified, S represents the number of employees in the corresponding company, and the ratio of the number of employees who communicate to the total number of employees is s. As the coefficient, the communication density is optimized according to the number of employees on the phone. The calculation formula is as follows:

[0135]

[0136] Substituting Te1 with Te into the inter-enterprise communication closeness quantification formula, the optimized second closeness quantification function can be obtained.

[0137] S103 , determining a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function.

[0138] like Figure 6 FIG. 1 is a flow chart of step S103 provided in an embodiment of the present invention, referring to FIG. Figure 6 As an optional implementation, determining a comprehensive quantization function of relationship closeness according to the first closeness quantization function and the second closeness quantization function specifically includes:

[0139] S1031. Obtaining preset business relationship weights and communication relationship weights;

[0140] S1032: sum the first closeness quantization function and the second closeness quantization function according to the business relationship weight and the communication relationship weight to obtain a comprehensive quantization function of relationship closeness.

[0141] Specifically, based on the quantitative evaluation function of the closeness of the inter-enterprise business relationship and the inter-enterprise communication relationship calculated in the above steps, a fusion model is constructed to conduct a quantitative evaluation of the enterprise relationship.

[0142] The closeness index of business relationships constructed based on industrial and commercial registration data and other public channel data enables the ability to quantitatively evaluate the closeness between enterprises from the perspective of their actual business; based on the analysis of inter-enterprise voice communications, the closeness between the overall enterprise traffic information and the call closeness between employees of different enterprises over a long period of time are fully considered in this process, so as to achieve a quasi-real-time evaluation and quantification of communication closeness on the time axis. Therefore, by integrating the evaluation results of the two aspects, the closeness of enterprise relationships is evaluated, expressed as TER (Tightness of enterprise relationships), and a weighted model is constructed to quantify the calculation of the closeness of enterprise relationships. According to the weights of the enterprise communication closeness index and the closeness index of business relationships, the weights are set from large to small and recorded as The final quantitative calculation formula for the close relationship between enterprises is as follows:

[0143]

[0144] The above formula can be used as a comprehensive quantitative function of the closeness of the relationship that integrates the business relationship between enterprises and the communication relationship between enterprises.

[0145] S104. Calculate the closeness relationship between existing enterprises according to the comprehensive quantitative function of the closeness relationship to obtain the closeness evaluation result of the relationship between enterprises.

[0146] like Figure 7 FIG. 1 is a flowchart of step S104 provided in an embodiment of the present invention, referring to FIG. Figure 7 As an optional implementation method, the closeness relationship between existing enterprises is calculated according to the comprehensive quantitative function of the closeness relationship to obtain the closeness evaluation result of the relationship between enterprises, which specifically includes:

[0147] S1041. Calculate the enterprise relationship closeness value between the two target enterprises according to the comprehensive quantitative function of relationship closeness;

[0148] S1042: When the enterprise relationship closeness value is greater than or equal to a preset first threshold, the closeness evaluation result of the two target enterprises is determined to be close;

[0149] S1043: When the enterprise relationship closeness value is less than a first threshold, determine that the closeness evaluation result of the two target enterprises is a loose relationship.

[0150] Specifically, according to the calculated enterprise relationship closeness value, a quantitative assessment of the enterprise relationship closeness can be achieved. The larger the value, the closer the relationship between enterprises, and vice versa, the looser the relationship between enterprises.

[0151] Specifically, the method steps of the embodiment of the present invention are described above. It can be recognized that the embodiment of the present invention analyzes and calculates the enterprise number pool containing enterprise business telephone numbers and enterprise employee telephone numbers based on the communication behavior of local enterprise users, and constructs the enterprise communication contact closeness calculation function for the call frequency, call duration and number of employee numbers between the enterprise number pool numbers with a natural month as the step length, and obtains the second closeness quantification function of the enterprise communication relationship. At the same time, the business relationship graph of the enterprise is constructed using industrial and commercial data and network source public data, and the enterprise business closeness evaluation quantification function is formed according to the point and edge relationship of the graph, and the first closeness quantification function of the business relationship between enterprises is obtained. Finally, the weighted average calculation of the two is performed to obtain the final relationship closeness comprehensive quantification function, and the relationship closeness between enterprises is quantitatively evaluated according to the calculated enterprise relationship closeness value. The larger the value, the closer the relationship, and the smaller the value, the looser the relationship. The embodiment of the present invention quantitatively evaluates the closeness of the relationship between enterprises based on the two dimensions of business relationship between enterprises and communication relationship between enterprises, making full use of the business data, industrial chain data and communication behavior data between enterprises, and improving the comprehensiveness, accuracy and real-time performance of enterprise relationship evaluation.

[0152] Compared with the prior art, the embodiments of the present invention also have the following advantages:

[0153] 1) Comprehensive and high-quality data sources: expanded operator communication data, relevant policy and regulatory data, and public opinion data released by authoritative media. In particular, operator communication data includes relevant communication behavior data and network behavior data of enterprises and their employees. Compared with traditional business registration information data and Internet public data, communication data and public opinion data have a wide coverage and provide good data support for enterprise relationship evaluation, making the analyzed enterprise relationships and their closeness more comprehensive.

[0154] 2) Higher accuracy and real-time performance: The high-quality data including communication data used in the present invention has the important feature of high-frequency real-time update, so that the analyzed corporate relationships and closeness have strong real-time and accuracy. Especially in scenarios such as precision marketing, competition analysis, and risk prevention and control, more accurate and real-time data analysis results can make corporate decisions more reliable, detect risks in advance, and take management measures.

[0155] 3) The evaluation method is objective: Different from the subjective definition of the closeness of the relationship, the closeness of the relationship between enterprises is quantified by using the communication behavior data of operators. For example, the duration of call bills, the frequency of communication behaviors, the residence time of base stations, etc. This type of data can objectively reflect the true situation of the closeness of enterprise relationships through big data modeling and analysis.

[0156] like Figure 8FIG. 1 is a schematic diagram of a structure of an enterprise relationship evaluation device based on communication big data provided by an embodiment of the present invention, referring to FIG. Figure 8 The embodiment of the present invention provides a device for evaluating enterprise relationships based on communication big data, comprising:

[0157] A first closeness quantization function determination module is used to construct an undirected graph model according to the actual business operations of the enterprise and the upstream and downstream distribution of the industrial chain, and determine a first closeness quantization function of the business relationship between the enterprises according to the undirected graph model;

[0158] A second closeness quantization function determination module, used to determine a second closeness quantization function of the communication relationship between enterprises according to the communication contact behavior between the enterprise number databases;

[0159] A relationship closeness comprehensive quantization function determination module, configured to determine a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function;

[0160] The closeness evaluation module is used to calculate the closeness relationship between existing enterprises based on the comprehensive quantitative function of relationship closeness, and obtain the closeness evaluation result of the relationship between enterprises.

[0161] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0162] The embodiment of the present invention also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and when the program is executed by the processor, the above-mentioned enterprise relationship evaluation method based on communication big data is realized. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0163] like Fig. 9 FIG. 1 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention, referring to FIG. Fig. 9 , an embodiment of the present invention provides an electronic device, including:

[0164] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention;

[0165] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the enterprise relationship evaluation method based on communication big data in the embodiment of the present invention;

[0166] Input / output interface 903, used to implement information input and output;

[0167] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0168] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0169] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0170] like Fig.10 FIG. 1 is a schematic diagram of a storage medium according to an embodiment of the present invention. Fig.10 The embodiment of the present invention also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs 1001, and the one or more programs 1001 can be executed by one or more processors to implement the above-mentioned enterprise relationship evaluation method based on communication big data.

[0171] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0172] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0173] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0174] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0175] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0176] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0177] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0178] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0179] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0180] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0181] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for evaluating enterprise relationships based on communication big data, characterized in that: The following steps are involved: Constructing an undirected graph model according to the actual business operations of the enterprises and the upstream and downstream distribution of the industrial chain, and determining a first closeness quantization function of the business relationship between the enterprises according to the undirected graph model; Determine a second closeness quantification function of the communication relationship between enterprises according to the communication contact behavior between the enterprise number databases; Determine a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function; The closeness relationship between existing enterprises is calculated according to the comprehensive quantitative function of the closeness of the relationship to obtain the closeness evaluation result of the relationship between enterprises.

2. According to claim 1, a method for evaluating enterprise relationships based on communication big data is characterized in that: The undirected graph model is constructed based on the actual business operations of the enterprise and the upstream and downstream distribution of the industrial chain, which specifically includes: Determine the actual business operations of each target enterprise, and determine the industry to which each target enterprise belongs based on the actual business operations; Determine the upstream and downstream relationships of the industrial chain between the target enterprises according to the industrial sectors to which they belong; Taking each of the target enterprises as a vertex, and determining the connection edges between the vertices according to the upstream and downstream relationships of the industrial chain; A plurality of industrial chain links are determined according to the vertices and the connecting edges, and the undirected graph model is constructed according to the industrial chain links.

3. The enterprise relationship evaluation method based on communication big data according to claim 2 is characterized in that: The first closeness quantification function of determining the business relationship between enterprises according to the undirected graph model specifically includes: Determine whether there is a direct connection relationship between the two target enterprises in each of the industrial chain links according to the undirected graph model; When the two target enterprises are directly connected in the industrial chain link, the corresponding industrial chain relationship closeness quantification value is determined to be 1; When there is no direct connection between the two target enterprises in the industrial chain link, the enterprise distance is determined according to the number of enterprises between the two in the industrial chain link, and then the reciprocal of the corresponding item of the Fibonacci series is calculated according to the enterprise distance to obtain the corresponding quantitative value of the closeness of the industrial chain relationship; Determine the result of the quantification of the closeness of the industrial chain relationship according to the sum of the quantified values ​​of the closeness of the industrial chain relationship of the two target enterprises in each of the industrial chain links; Determine the corresponding quantitative results of actual business operations according to whether the two target enterprises belong to the same industry; The first closeness quantification function of the two target enterprises is determined according to the quantification result of the closeness of the industrial chain relationship and the quantification result related to the actual business operations.

4. The enterprise relationship evaluation method based on communication big data according to claim 1 is characterized in that: The second closeness quantification function for determining the communication relationship between enterprises based on the communication contact behavior between the enterprise number databases specifically includes: Determine the enterprise number database of each target enterprise; Acquire the number of calls between the two target enterprises and the corresponding single call duration within a preset historical period according to the enterprise number database, wherein the preset historical period includes multiple historical periods; Filtering the target number of calls within the target call duration range according to the single call duration, and obtaining the target total call duration between the two target enterprises according to the target number of calls; Performing a logarithmic transformation on the target total call duration to obtain a call duration variable, and determining a quantified result of the communication density of the historical period by multiplying the call duration variable by the number of calls between the two target enterprises in a single historical period; The second closeness quantization function of the two target enterprises is determined according to the average of the communication closeness quantization results of each of the historical periods.

5. The enterprise relationship evaluation method based on communication big data according to claim 4 is characterized in that: The enterprise relationship evaluation method further includes a step of optimizing the communication closeness quantification result, which specifically includes: Obtain the number of employees who have had communication contact between the two target enterprises during the historical period; Determine the optimization coefficient according to the ratio of the number of employees making calls to the total number of employees of the two target enterprises; The product of the optimization coefficient and the communication closeness quantization result is used as the optimized communication closeness quantization result.

6. The enterprise relationship evaluation method based on communication big data according to claim 1 is characterized in that: The step of determining a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function specifically includes: Obtaining preset business relationship weights and communication relationship weights; The first closeness quantization function and the second closeness quantization function are summed according to the business relationship weight and the communication relationship weight to obtain the relationship closeness comprehensive quantization function.

7. A method for evaluating enterprise relationships based on communication big data according to claims 1 to 6, characterized in that: The calculation of the closeness relationship between existing enterprises according to the comprehensive quantitative function of the closeness relationship is performed to obtain the closeness evaluation result of the relationship between enterprises, which specifically includes: The enterprise relationship closeness value between the two target enterprises is calculated according to the comprehensive quantitative function of the relationship closeness; When the enterprise relationship closeness value is greater than or equal to a preset first threshold, determining that the closeness evaluation result of the two target enterprises is closely related; When the enterprise relationship closeness value is less than the first threshold, it is determined that the closeness evaluation result of the two target enterprises is a loose relationship.

8. An enterprise relationship evaluation device based on communication big data, characterized in that: include: A first closeness quantization function determination module is used to construct an undirected graph model according to the actual business operations of the enterprise and the upstream and downstream distribution of the industrial chain, and determine a first closeness quantization function of the business relationship between the enterprises according to the undirected graph model; A second closeness quantization function determination module, used to determine a second closeness quantization function of the communication relationship between enterprises according to the communication contact behavior between the enterprise number databases; A relationship closeness comprehensive quantization function determination module, configured to determine a relationship closeness comprehensive quantization function according to the first closeness quantization function and the second closeness quantization function; The closeness evaluation module is used to calculate the closeness relationship between existing enterprises according to the comprehensive quantitative function of the closeness relationship to obtain the closeness evaluation result of the relationship between enterprises.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the enterprise relationship evaluation method based on communication big data as described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the enterprise relationship evaluation method based on communication big data as described in any one of claims 1 to 7.

Images