Regional industrial chain complement enterprise recommendation method and system based on communication big data

Abstract

The invention discloses a communication big data-based regional industry chain supplement enterprise recommendation method and system. The method comprises the following steps of: obtaining network public data, enterprise basic data and operator communication data; according to the network public data, constructing a first influence quantification factor corresponding to industry chain complement enterprise recommendation based on regional-level industry chain development macroscopic factors; according to the enterprise basic data, constructing a second influence quantification factor corresponding to industry chain complement enterprise recommendation based on the expansion and development demand of the enrollment enterprise; according to the operator communication data, constructing an enterprise entering willingness quantification factor based on communication big data space-time characteristics; and performing enterprise evaluation according to the first influence quantification factor, the second influence quantification factor and the enterprise entering willingness quantification factor to obtain a target enterprise recommendation result of the complement chain area. The method can improve the recommendation accuracy of industry chain supplement enterprises, and can be widely applied to the technical field of big data analysis.

Description

Technical Field

[0001] The present application relates to the field of big data analysis technology, and in particular to a method and system for recommending regional industrial chain supplementary enterprises based on communication big data. Background Art

[0002] Industrial chain refers to the objective and ready-made chain relationship between various industrial sectors based on certain technical and economic connections and spatial and temporal layout relationships. One of the important points in the process of building a modern industrial chain system is to promote the extension, supplement and strengthening of industrial chains, gather key resource elements, and expand the space for industrial development. The important tasks of this point are mainly focused on how to explore the target industrial chains and target enterprises for extending, supplementing and strengthening chains in the region in accordance with the local development characteristics, combining the industrial chain development trends and the panoramic goals of local industrial chain development, and comprehensively analyzing the current status of local enterprises, policy guidance, and precise targeted investment promotion and other industrial circle building and chain strengthening actions to promote the agglomeration and development of key industries along the chain, and realize the regional collaborative construction and development of upstream and downstream industrial chains, industrial supply and marketing, and large, medium and small enterprises.

[0003] In summary, exploring effective methods for selecting target enterprises to complement the industrial chain is a prerequisite for local industrial chain building actions. Through comprehensive, efficient and accurate target enterprise recommendations, it provides a powerful tool for industrial chain complementation and industrial circle building and strengthening actions. A variety of industrial chain enterprise recommendation methods have been proposed in previous technologies, but they all have some problems, such as insufficient data sources, fewer analysis dimensions, and concentrated recommendation results. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a multi-dimensional, multi-scenario method and system for recommending regional industrial chain complementary enterprises based on communication big data.

[0005] To achieve the above purpose, one aspect of an embodiment of the present application proposes a method for recommending regional industrial chain supplementary enterprises based on communication big data, comprising the following steps:

[0006] Obtain network public data, enterprise basic data and operator communication data;

[0007] According to the public network data, the first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the macro factors of regional industrial chain development is constructed;

[0008] Based on the basic data of the enterprises, a second influencing quantitative factor corresponding to the recommendation of enterprises for filling the industrial chain based on the needs of attracting enterprises to expand and develop is constructed;

[0009] Based on the communication data of the operators, a quantitative factor of the willingness to attract enterprises to settle in is constructed based on the spatiotemporal characteristics of the communication big data;

[0010] An enterprise assessment is performed based on the first impact quantitative factor, the second impact quantitative factor, and the quantitative factor of the willingness to attract enterprises to settle in, and a recommendation result for target enterprises in the chain-filling area is obtained.

[0011] In some embodiments, the first influencing quantitative factor includes a regional policy environment influencing factor and a regional industrial supporting influencing factor, and the first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on regional industrial chain development macro factors is constructed according to the network public data, specifically including:

[0012] Quantitatively calculate the impact of the industrial chain policy environment on the complementary region based on the public network data to obtain the regional policy environment impact factor;

[0013] The impact of industrial chain supporting facilities on the chain-filling area is quantitatively calculated based on the public network data to obtain the industrial supporting impact factor of the area.

[0014] In some embodiments, the quantitative calculation of the impact of the industrial chain policy environment on the chain-filling region based on the network public data to obtain the regional policy environment impact factor specifically includes:

[0015] An analysis period is set, and the total amount of regional industrial policies promulgated in the supply chain filling area within the analysis period and the number of the first regional supply chain filling industrial policies in each month are obtained from the online public data;

[0016] From the public network data, obtain the total number of superior industrial policies issued by the superior management department during the analysis period and the number of superior supply chain supplementary industrial policies;

[0017] Calculate the regional policy impact index based on the total number of regional industrial policies promulgated, the number of the first regional industrial policies for complementary industrial chains, the total number of superior industrial policies promulgated, and the number of superior industrial policies for complementary industrial chains;

[0018] The number of statistical months is set, and the number of the second-region supply chain supplementary industrial policies in the policy-issuing months and each of the policy-issuing months is obtained from the online public data;

[0019] An industrial policy change impact index is calculated based on the statistical months, the policy promulgation months, and the number of industrial supply chain supplementary policies in the second region;

[0020] The regional policy environment impact factor is obtained by calculating the mean of the regional policy impact index and the industrial policy change impact index.

[0021] In some embodiments, the quantitative calculation of the industrial chain supporting impact of the chain-filling region based on the network public data to obtain the regional industrial supporting impact factor specifically includes:

[0022] Obtaining the number of upstream enterprises and downstream enterprises in the industrial chain to which the enterprises to be attracted in the supply chain supplementation area belong from the public network data;

[0023] Obtaining the number of enterprises in the industrial chain to which the enterprises to be recruited in the supply chain supplementing area belong from the public network data;

[0024] Calculate the industrial chain saturation of the chain-filling area according to the number of upstream enterprises, the number of downstream enterprises and the number of enterprises;

[0025] Obtaining the total number of enterprises in the supply chain supplement area and the number of industrial enterprises in the preset area from the network public data;

[0026] Calculate the industrial concentration of the chain-filling area according to the total number of enterprises, the number of enterprises, and the number of industrial enterprises;

[0027] The regional policy environment influencing factor, the industrial chain saturation and the industrial agglomeration are averaged to obtain the regional industrial supporting influencing factor.

[0028] In some embodiments, the second influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the needs of attracting enterprises to expand and develop is constructed based on the basic enterprise data, specifically including:

[0029] Based on the basic data of the enterprises, the change rate of registered capital and the change rate of the number of employees of each attracted enterprise are calculated;

[0030] Calculate the change in enterprise scale based on the registered capital change rate and the employee number change rate;

[0031] Based on the basic data of the enterprises, the change in the number of branches of each of the attracted enterprises is calculated;

[0032] The second impact quantification factor is obtained by calculating the mean of the change results of the enterprise scale and the change results of the number of branches.

[0033] In some embodiments, the constructing of a quantitative factor of the willingness to attract enterprises to settle in based on the spatiotemporal characteristics of communication big data according to the operator communication data specifically includes:

[0034] Set a first statistical period, and obtain the monthly call times and non-zero call months of each recruited enterprise in the first statistical period from the operator communication data;

[0035] Calculate the closeness of the business relationship of each of the attracted enterprises according to the first statistical period, the monthly number of calls and the non-zero call months;

[0036] Setting a second statistical period, and obtaining the monthly number of employees of each of the recruited enterprises in the supply chain supplement area and the second statistical period from the operator communication data;

[0037] Obtaining, from the operator communication data, the number of working months and the total number of employees of each of the recruited enterprises in the second statistical period;

[0038] Calculate the job stability of the employees of each of the recruiting enterprises in the supply chain supplement area according to the second statistical period, the monthly number of employees, the number of working months and the total number of employees;

[0039] The business relationship closeness and the job stability are averaged to obtain a quantitative factor of the willingness to attract enterprises to settle in.

[0040] In some embodiments, the enterprise evaluation is performed according to the first quantitative impact factor, the second quantitative impact factor, and the quantitative factor of the willingness to attract enterprises to settle in, to obtain the target enterprise recommendation result of the chain filling area, specifically including:

[0041] Performing a sum operation on the first quantitative impact factor, the second quantitative impact factor, and the quantitative factor of the willingness to attract enterprises to settle in, to obtain a probability of enterprise settlement;

[0042] The target enterprise recommendation result is obtained according to the enterprise settlement probability.

[0043] To achieve the above purpose, another aspect of the embodiment of the present application proposes a regional industrial chain supplementary enterprise recommendation system based on communication big data, including:

[0044] Data source acquisition module, used to obtain network public data, enterprise basic data and operator communication data;

[0045] A business environment quantification module, used to construct, based on the network public data, a first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on regional-level industrial chain development macro factors;

[0046] An enterprise expansion demand quantification module is used to construct, based on the enterprise basic data, a second influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the needs of attracting enterprise expansion and development;

[0047] A module for quantifying the willingness of enterprises to settle in, which is used to construct a quantitative factor for attracting the willingness of enterprises to settle in based on the spatiotemporal characteristics of communication big data according to the communication data of the operator;

[0048] The target enterprise recommendation module is used to evaluate enterprises according to the first influence quantitative factor, the second influence quantitative factor and the quantitative factor of the willingness to attract enterprises to settle in, and obtain the target enterprise recommendation results of the chain filling area.

[0049] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which 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 method for recommending regional industrial chain chain-filling enterprises based on communication big data as described above is realized.

[0050] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes 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 regional-level industrial chain chain-filling enterprise recommendation method based on communication big data as described above.

[0051] The beneficial effects of the present invention are as follows: the method and system for recommending regional industrial chain filling enterprises based on communication big data of the present invention, on the one hand, obtains the first influencing quantitative factor corresponding to the recommendation of industrial chain filling enterprises based on the macro factors of regional industrial chain development by introducing public network data, and obtains the second influencing quantitative factor for recommending industrial chain filling enterprises based on the needs of attracting enterprises to expand and develop by introducing basic enterprise data. On the basis of considering the macro factors of industrial chain development, it further fully considers the development needs of the enterprises themselves and the attractiveness of the regional industrial chain to the enterprises on the chain, and more accurately defines the target enterprises for filling the chain from the perspective of the enterprises. On the other hand, by introducing operator communication data to obtain the quantitative factor of the willingness to attract enterprises to settle in based on the spatiotemporal characteristics of communication big data, it can fully consider the migration willingness shown by enterprises based on their own positioning and needs in the actual operation process, thereby improving the accuracy of the recommendation of industrial chain filling enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] 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.

[0053] Figure 1 A flowchart of a method for recommending regional industrial chain supplementary enterprises based on communication big data provided by an embodiment of the present invention;

[0054] Figure 2 A flowchart of a step of obtaining a first impact quantization factor provided by an embodiment of the present invention;

[0055] Figure 3 A step flow chart of step S1021 provided in an embodiment of the present invention;

[0056] Figure 4 A step flow chart of step S1022 provided in an embodiment of the present invention;

[0057] Figure 5 A flowchart of a step of obtaining a second impact quantization factor provided by an embodiment of the present invention;

[0058] Figure 6 A flowchart of steps for obtaining a quantitative factor of the willingness to attract enterprises to settle in provided by an embodiment of the present invention;

[0059] Figure 7 A flowchart of steps for obtaining target enterprise recommendation results provided by an embodiment of the present invention;

[0060] Figure 8 A schematic diagram of a flow chart of a method for recommending regional industrial chain supplementary enterprises based on communication big data provided by an embodiment of the present invention;

[0061] Fig. 9 A structural schematic diagram of a regional industrial chain supplementary enterprise recommendation system based on communication big data provided by an embodiment of the present invention;

[0062] Fig.10 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0064] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0065] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0066] Before describing the regional industrial chain supplementary enterprise recommendation method based on communication big data of the present invention, it is necessary to clearly state that the method follows the privacy protection principle when processing data. In particular, all data sources involved in the method, including but not limited to network public data, enterprise basic data, and operator communication data, are strictly obtained and used with the explicit authorization and consent of the user.

[0067] Industrial chain refers to the objective and ready-made chain relationship between various industrial sectors based on certain technical and economic connections and spatial and temporal layout relationships. One of the important points in the process of building a modern industrial chain system is to promote the extension, supplement and strengthening of industrial chains, gather key resource elements, and expand the space for industrial development. The important tasks of this point are mainly focused on how to explore the target industrial chains and target enterprises for extending, supplementing and strengthening chains in the region in accordance with the local development characteristics, combining the industrial chain development trends and the panoramic goals of local industrial chain development, and comprehensively analyzing the current status of local enterprises, policy guidance, and precise targeted investment promotion and other industrial circle building and chain strengthening actions to promote the agglomeration and development of key industries along the chain, and realize the regional collaborative construction and development of upstream and downstream industrial chains, industrial supply and marketing, and large, medium and small enterprises.

[0068] In summary, exploring effective methods for selecting target enterprises to complement the industrial chain is a prerequisite for local industrial chain building. Through comprehensive, efficient and accurate target enterprise recommendations, it provides a powerful tool for industrial chain complementation and industrial circle building and strengthening. A variety of industrial chain enterprise recommendation methods have been proposed in previous technologies, but they all have some problems:

[0069] 1) A method for analyzing corporate public opinion sentiment based on news data, which generates a list of recommended companies by combining corporate sentiment tags and knowledge graphs. This method has opened up a new perspective for feature construction for corporate analysis technology to a certain extent, but it has limitations, which may cause the recommendation results to be too concentrated on certain similar companies, which is not conducive to building a diversified industrial chain ecological layout. In addition, this method fails to fully integrate key information such as regional development status, corporate conditions, and industrial chain panoramic requirements, which may cause the generated recommendation list to not match the actual needs of investment promotion.

[0070] 2) A park investment recommendation method based on industrial chain analysis, which establishes an enterprise tag database by integrating the three dimensions of enterprise value, enterprise supply chain and industrial space, and obtains an enterprise recommendation strategy with the goal of maximizing the sum of the priority values ​​of the recommended enterprise tags. This method deeply considers the differences between enterprises at different nodes of the industrial chain, effectively avoids the centralized bias of the recommendation results, and gives play to the advantages of the park by constructing a panoramic map of the industrial chain of the park. However, this method is mainly aimed at the development of the industrial chain of the park, and the data source is not comprehensive enough and the analysis dimensions are relatively few.

[0071] To this end, the embodiment of the present invention proposes a method for recommending regional industrial chain supplementary enterprises based on communication big data. On the one hand, the first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the macro factors of regional industrial chain development is obtained by introducing network public data, and the second influencing quantitative factor based on the expansion and development needs of enterprises is obtained by introducing enterprise basic data. On the basis of considering the macro factors of industrial chain development, the development needs of enterprises themselves and the attractiveness of regional industrial chains to enterprises on the chain are further fully considered, and the target enterprises for supplementary enterprises are more accurately identified from the perspective of enterprises; on the other hand, the quantitative factor of the willingness to attract enterprises to settle in based on the spatiotemporal characteristics of communication big data is obtained by introducing operator communication data, which can fully consider the migration willingness of enterprises based on their own positioning and needs in the actual operation process, thereby improving the accuracy of recommendation of industrial chain supplementary enterprises. The method for recommending industrial chain supplementary enterprises can be applied to the introduction of upstream and downstream supporting enterprises, the introduction and application of key technologies, and other scenarios, but is not limited to them.

[0072] Reference Figure 1 , Figure 1 A flowchart of a method for recommending regional industrial chain supplementary enterprises based on communication big data provided by an embodiment of the present invention. An embodiment of the present invention proposes a method for recommending regional industrial chain supplementary enterprises based on communication big data, and the method includes steps S101 to S105:

[0073] S101, obtaining network public data, enterprise basic data and operator communication data;

[0074] Specifically, first of all, it is necessary to fully consider the development of the industrial chain in the region, confirm the completeness of the current industrial chain and the weak links of the chain, so as to confirm the types of enterprises and industries that need to be supplemented in the current industrial chain in the region, and use this as a basis to determine the scope of enterprises that need to be introduced. In addition, the policy macro-environment should be considered, that is, the policy support for the relevant industrial chain in the current region should be analyzed, such as the subsidy amount and tax incentives after the industrial chain supplement enterprises settle in, so as to achieve a quantitative assessment of the attractiveness of the current macro-environment to enterprises. In addition to considering the support for the relevant chain supplement industries in the region, it is more important to analyze and quantify the willingness of the target enterprises to settle in. On the one hand, quantitative analysis should be conducted from the perspective of supporting the long-term development strategy of the enterprise, that is, the expansion trend of the enterprise, to determine the degree of demand for enterprise expansion; on the other hand, it is necessary to analyze and judge the preferred expansion of the enterprise, and confirm whether the enterprise has already shown a destination for expansion, so as to be able to follow up in advance with enterprises that are willing to establish companies in the chain supplement area, promote the rapid landing of enterprises, and realize the chain supplement.

[0075] Combined with the above analysis of regional chain filling scenarios, we comprehensively collect and integrate regional industrial chain macro-environment information, such as regional industrial chain policy information, regional industrial chain structure information and other regional industrial chain related information, business registration information including basic enterprise information such as the number of employees, number of branches, registered capital, and industry type, external network source information such as official website data and recruitment information, and operators' unique enterprise communication big data behavior information to construct a quantitative evaluation model data set for recommending regional industrial chain filling enterprises.

[0076] In some optional embodiments, the data sources in the embodiments of the present invention include three parts: enterprise basic data, operator communication data, and network public data. Among them, the enterprise basic data includes dimensions such as the year of establishment of the enterprise, registered capital, and social security payment status to show the business status and scale of the enterprise; it also includes the annual report of the enterprise, changes in branches, equity structure, etc., to fully explore the regional expansion of the enterprise and the geographical distribution of branches; it also includes data such as the business scope of the enterprise, main business, and industry classification to show the industry division of the industry to which the enterprise belongs. The network public data includes the macro-level business environment such as industrial support policies, regional industrial completeness, and scale of employees published by the policy platform; it also includes the enterprise organizational structure and development information published on the official website of the enterprise, as well as the recruitment information released by the enterprise through the platform and other information on the development status of the enterprise itself. The above two parts of data (i.e., enterprise basic data and network public data) mainly show information based on the industrial economic environment and enterprise development information published by the enterprise on its own.

[0077] Compared with the above two information sources, the operator's communication data includes real-time dynamic information of the enterprise, such as enterprise employee trajectory information, location information and user communication behavior. Through the communication behavior data such as enterprise call frequency, Internet access time, short message sending and receiving, the location changes of the enterprise's business activities on different time axes and the gathering of enterprise personnel can be mined in real time; it also includes spatial communication data such as the enterprise's communication base station, enterprise business location, network broadband address, etc., to mine the actual location of the enterprise's business production and the scope of business reach in the spatial dimension. Therefore, the operator's unique communication big data can show the characteristics of the actual business activities of the enterprise from the time and space dimensions.

[0078] S102. Based on the public data on the Internet, construct the first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the macro factors of regional industrial chain development;

[0079] Reference Figure 2 , Figure 2 A flowchart of a step of obtaining a first impact quantification factor provided in an embodiment of the present invention, further as an optional implementation mode, the first impact quantification factor includes a regional policy environment impact factor and a regional industrial supporting impact factor, and the step of constructing a first impact quantification factor corresponding to the recommendation of industrial chain supplementary enterprises based on regional industrial chain development macro factors according to online public data can be further divided into the following steps S1021 and S1022:

[0080] S1021. Quantify the impact of the industrial chain policy environment on the complementary areas based on online public data to obtain the regional policy environment impact factor;

[0081] S1022. Quantify the impact of industrial chain supporting facilities on the complementary areas based on the public data on the Internet to obtain the regional industrial supporting impact factor.

[0082] It should be noted that the analysis and quantification of the impact of the macro factors of regional industrial chain development on the recommendation of industrial chain supplementary enterprises is mainly analyzed from the policy environment related to the supplementary industry in the region, and the industrial supporting conditions of the industrial chain of the enterprises to be introduced (i.e., the enterprises to be attracted) in the region. Among them, the regional policy environment influencing factor refers to the preferential policies for the industry to which the target supplementary enterprises belong in the region where the supplementary enterprises are to be introduced, such as the number of relevant industrial chain preferential policies, the time of release, the authority of the issuing unit, etc. These policies that can help enterprises develop better are highly correlated with the willingness of enterprises to settle in.

[0083] Reference Figure 3 , Figure 3A step flow chart of step S1021 provided in an embodiment of the present invention is further provided as an optional implementation mode. The step of quantitatively calculating the impact of the industrial chain policy environment on the complementary region according to the public data on the Internet to obtain the regional policy environment impact factor can be further divided into the following steps S10211 to S10216:

[0084] S10211. Set an analysis period, and obtain from online public data the total number of regional industrial policies issued in the supply chain filling area during the analysis period and the number of the first regional supply chain filling industrial policies in each month;

[0085] S10212. Obtain the total number of superior industrial policies issued by superior management departments during the analysis period and the number of superior supply chain supplementary industrial policies from public data on the Internet;

[0086] S10213. Calculate the regional policy impact index based on the total number of regional industrial policies issued, the number of first-region industrial policies to supplement the supply chain, the total number of superior industrial policies issued, and the number of superior industrial policies to supplement the supply chain;

[0087] It should be noted that the policies related to the development of the industrial chain in the region are mainly divided into two types. One type is the policy formulated by the jurisdiction in the region in accordance with its own positioning in combination with the development of its own industrial chain and supply chain. This part of the policy resources is relatively small but more in line with the actual industrial needs. The other type is the preferential industrial development policy formulated by the superior management department from the perspective of economic development in a larger region. In the process of formulating this part of the policy, not only the development needs of a single industry in a specific region are considered, but also the overall economic and industrial development disk is considered. In addition to focusing on the actual development situation and cultivating advantageous industries to guide industrial upgrading, the relevant policies are more focused on ensuring the balanced development of various industries within the jurisdiction. Therefore, this part of the policy is relatively strong, but it is universal and not targeted. In order to quantify complex policy changes, the embodiment of the present invention integrates two parts of industrial preferential policies, constructs industrial policy impact indicators from the perspective of the time span of policy release and the number of concentrated policy releases, and quantifies the impact of industrial policies on the entry of enterprises.

[0088] Specifically, for the industrial policy impact index, it is mainly related to the number, frequency, and time of industrial policies issued in the chain filling area for the industries that need to be introduced, as well as whether the higher-level management department has issued policy requirements for the relevant chain filling industry direction. Generally speaking, the more industrial policies issued in the region and the closer the policy release time is to the analysis time, the higher the importance attached to industrial development. Therefore, the degree of attention paid to regional policies for the introduction of chain filling enterprises can be analyzed and quantified through two aspects: the proportion of relevant preferential policies for attracting industries in all industrial preferential policies issued in the region and the trend of the number of industrial policy promulgations over time.

[0089] In some optional embodiments, the policies of the superior management department are quantified by whether relevant policies are released within the statistical time. Considering that the time span of the released policy is too long from the analysis, which will lead to the timeliness problem of the policy impact, the analysis period is first set, and then T p represents the total amount of all industrial preferential policies issued during the analysis period (i.e., the total amount of regional industrial policies issued), I m represents the number of industrial policies per month in the chain filling analysis period (i.e., the number of industrial policies for the first region to fill the chain), where month m∈(1,2,...,12); P represents the number of industrial policies issued by the superior management department (i.e., the total number of industrial policies issued by the superior), P i It indicates the number of policies to be introduced into the industry (i.e. the number of superior industrial policies to supplement the supply chain). The regional policy impact index IP (Impact of industrial policies) is obtained by taking the weighted average of the proportion of regional industrial policies and the proportion of superior department policies. The specific calculation formula is as follows:

[0090]

[0091] It is understandable that the analysis period can be set according to actual needs, for example, setting the analysis period to half a year, one year, or two years.

[0092] S10214. Set the number of statistical months, and obtain the policy issuance month and the number of second-region supply chain supplementary industrial policies in each policy issuance month from online public data;

[0093] S10215. Calculate the impact index of industrial policy changes based on the statistical months, the policy promulgation months, and the number of industrial policies for supplementing the supply chain in the second region;

[0094] It should be noted that in addition to the number of industrial policies promulgated, which can reflect the impact of regional industrial preferential policies on the introduction of chain-complementing enterprises, the changing trend in the number of preferential policies promulgated in the region for the introduction of chain-complementing industrial enterprises is also an important basis for reflecting the degree of impact of industrial policies.

[0095] Specifically, to quantify the trend of the number of policies issued in the target industry over time, P t , construct the regional industrial chain policy time series, with m i Indicates the month in which the policy was promulgated, n iIt represents the number of preferential policies for the industrial chain issued in the corresponding policy issuance month (i.e. the number of industrial policies for supplementing the second region’s chain), with s representing the number of statistical months. The slope b of the industrial preferential policies changing with the month is calculated according to the slope formula. The “positive or negative” of the slope b determines whether the number of industrial policies is increasing or decreasing over time. If it is a negative value, the preferential policies are gradually decreasing over time, and if it is a positive value, the preferential policies are increasing. The absolute value of b represents the magnitude of the increase or decrease in the policy. The larger the absolute value, the greater the increase or decrease. The calculation formula for slope b is as follows:

[0096]

[0097] The value range of slope b is (-∞, +∞). In order to facilitate the subsequent comprehensive evaluation with the regional policy impact index IP, the hyperbolic tangent function tanh is used to compress and transform the slope b, and the value range of slope b is mapped to the interval (-1, 1). The normalized value P is t As the impact index of industrial policy changes, the specific conversion formula is as follows:

[0098]

[0099] S10216. Calculate the mean of the regional policy impact index and the industrial policy change impact index to obtain the regional policy environment impact factor.

[0100] Specifically, after the above method is used to calculate the regional policy impact index IP and the industrial policy change impact index P t Calculate and take the weighted average of the two to finally get the regional policy environment impact factor, that is, the quantitative result of the policy impact index on the enterprise settlement and supply chain filling area IRP (Impact of regional industrial policies). The specific calculation formula is as follows:

[0101]

[0102] Reference Figure 4 , Figure 4 A step flow chart of step S1022 provided in an embodiment of the present invention is further provided as an optional implementation mode. The step of quantitatively calculating the impact of industrial chain supporting facilities on the complementary area according to the public data on the Internet to obtain the regional industrial supporting supporting factors can be further divided into the following steps S10221 to S10226:

[0103] S10221. Obtain the number of upstream and downstream enterprises in the industrial chain of the enterprises to be attracted in the supply chain supplementation area from public data on the Internet;

[0104] S10222. Obtain the number of enterprises in the industrial chain to which the enterprises to be recruited in the supply chain supplement area belong from public data on the Internet;

[0105] S10223. Calculate the industrial chain saturation of the chain-filling area based on the number of upstream enterprises, the number of downstream enterprises, and the number of enterprises;

[0106] S10224. Obtain the total number of enterprises in the supply chain supplement area and the number of industrial enterprises in the preset area from public data on the Internet;

[0107] S10225. Calculate the industrial concentration of the supply chain supplement area based on the total number of enterprises, the number of enterprises and the number of industrial enterprises;

[0108] It should be noted that the degree of industrial chain aggregation, the completeness of the industrial chain supply chain, the scale of the industry and other industry-related conditions in the chain-filling area are highly correlated with whether the target chain-filling enterprises can be attracted to settle in. The impact of the regional industrial chain supporting integrity on the willingness of enterprises to settle in mainly depends on the number of upstream and downstream supporting enterprises in the industrial chain in the region, the number of employees in the relevant industries in the region and the local market size of the relevant industrial products. Considering that the more industrial chain enterprises there are in the region, the greater the attraction to employees in the relevant industrial chain, the larger the scale of employees, and there is a positive correlation between the two. In addition, unless the products are targeted at special markets and logistics are constantly improved, the degree of relevant influence has also declined significantly. Therefore, the impact of industrial supporting factors on the introduction of enterprises in the regional industrial chain can be quantified by the number and scale of upstream and downstream supporting enterprises in the industrial chain. The judgment of the degree of influence of the scale of the industrial chain on the introduction of chain-filling enterprises is mainly analyzed from two aspects: the number of upstream and downstream enterprises in the industrial chain link to which the attracting enterprise belongs and the ratio of the number of upstream and downstream enterprises to the number of enterprises in the industrial chain link to which they belong. Among them, the number of upstream and downstream enterprises in the industrial chain to which the attracted enterprises belong can reflect the current degree of aggregation of supporting enterprises. The larger the number, the higher the degree of aggregation. The ratio of the number of upstream and downstream enterprises to the number of enterprises in the industrial chain to which the attracted enterprises belong reflects the degree of saturation of the industrial chain to which the introduced enterprises belong in the region. A large ratio between the number of upstream enterprises and the number of attracted enterprises indicates that a large number of upstream enterprises have surplus products and there are not enough corresponding enterprises to take over, indicating that the saturation is low. After the attracted enterprises settle in, they can quickly obtain sufficient upstream materials and start production, and there is a great demand for enterprises to fill the industrial chain.

[0109] Specifically, N up N represents the number of upstream enterprises in the industrial chain to which the enterprises attracted in the complementary area belong, down N represents the number of downstream enterprises in the industrial chain to which the enterprises attracted in the complementary area belong, c It represents the number of enterprises in the industrial chain of the enterprises attracted in the chain-filling area, and is calculated by calculating the ratio of the number of upstream enterprises to the number of enterprises in the chain-filling link.up / N c , the ratio of the number of downstream enterprises to the number of enterprises in the complementary links of the industrial chain in the complementary region N dowm / N c The saturation of the industrial chain within the region is quantified by the sum of the industrial chain saturation and the specific calculation formula is as follows:

[0110]

[0111] Considering that if the number of enterprises is directly used as a measure of the degree of regional industrial agglomeration, it will be impossible to obtain a reliable assessment due to the lack of a reference standard. Therefore, the proportion of the number of corresponding industrial enterprises in a larger region is used to quantify the degree of regional industrial agglomeration. The total number of enterprises in the complementary chain region is N. z The number of enterprises in the industrial chain links attracted in the chain-filling area is N zc , the number of industrial enterprises in the preset area is N l , ICD (Industrial clustering degree) is used to represent the industrial clustering degree in the complementary chain area. The specific calculation formula is as follows:

[0112]

[0113] Among them, the area of ​​the preset area is larger than the link-filling area.

[0114] S10226. Calculate the mean of the regional policy environment influencing factors, industrial chain saturation and industrial agglomeration to obtain the regional industrial supporting influencing factors.

[0115] Specifically, the regional policy environment impact factor, industrial chain saturation and industrial agglomeration calculated above are averaged to obtain the quantitative calculation result of the industrial chain business environment BEC (Business environment of industrial chain) in the complementary region. The calculation formula of the regional industrial supporting impact factor is as follows:

[0116]

[0117] S103. Based on the basic data of enterprises, construct the second influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the needs of attracting enterprises to expand and develop;

[0118] It should be noted that the factors that affect the attraction of enterprises to settle in the industrial chain supplement area include macro-level factors such as the policy incentives in the supplement area and the degree of industrial chain agglomeration and development. The actual development needs of the enterprise itself, that is, the expansion needs and the strength of the enterprise itself are the core factors that affect the settlement of enterprises in the industrial chain supplement area. For example, if the business of the enterprise itself is shrinking and its overall competitiveness is on a downward track, the possibility that the enterprise will settle in just because of the policy is extremely low. On the contrary, if the business of the enterprise is developing rapidly and is in the stage of business expansion, the more sensitive the enterprise is to the policy incentives, the more likely it is to settle in the supplement area due to regional business environment factors such as preferential policies. Factors that reflect changes in the operation of enterprises, such as changes in the registered capital of enterprises, changes in the number and distribution of enterprise branches, can all show the expansion and development needs of enterprises. Among them, the changes in the registered capital of enterprises and the changes in the number and distribution of enterprise employees mainly reflect the changes in the overall business capabilities and scale of enterprises; the changes in the number and distribution of enterprise branches reflect the expansion needs of enterprises at the regional spatial level.

[0119] Reference Figure 5 , Figure 5 A flowchart of a step of obtaining a second impact quantification factor provided in an embodiment of the present invention is further provided as an optional implementation mode. According to the basic data of the enterprise, the step of constructing a second impact quantification factor corresponding to the recommendation of an industrial chain supplementary enterprise based on the needs of attracting the expansion and development of the enterprise can be further divided into the following steps S1031 to S1034:

[0120] S1031. Calculate the change rate of registered capital and the change rate of number of employees of each attracted enterprise based on the basic data of the enterprise;

[0121] In some optional embodiments, among the indicators for changes in enterprise scale, the change in registered capital of an enterprise generally does not change frequently, so it can be quantified by the proportion of the most recent change in registered capital to the amount before the change, with R being the registered capital before the change, and r being the amount of the most recent increase in registered capital, and the registered capital change rate being r / R. Compared with the change in the registered capital of an enterprise, the number of employees in an enterprise changes more frequently, and there will be occasional situations of increase and decrease due to short-term needs. In order to reduce the impact of occasionality on the quantitative results, for the quantification of employee changes, 6 months can be used as a statistical cycle, and the number of employee increases and decreases in the past 6 months and the rate of change of the number of employees 6 months ago can be calculated as the quantification of employee changes. E represents the number of employees 6 months ago, and e represents the number of changes in employees in the past 6 months, and the rate of change of the number of employees is e / E. Among them, the statistical cycle can also be set according to actual needs, such as 8 months, 9 months, etc.

[0122] S1032. Calculate the change in enterprise scale based on the change rate of registered capital and the change rate of the number of employees;

[0123] Specifically, the change rate of registered capital and the change rate of the number of employees are summed and averaged to obtain the change result CC (Changes in company size). The specific calculation formula is as follows:

[0124]

[0125] S1033. Calculate the change in the number of branches of each attracted enterprise based on the basic data of the enterprise;

[0126] Specifically, the number and distribution changes of enterprise branches reflect the expansion needs of enterprises at the regional spatial level. Generally speaking, the more branches there are and the more regions the branches are distributed, the greater the possibility of expansion of enterprises in regions without branches. Therefore, the expansion capacity of enterprises can be quantified by the recent change rate of the number of enterprise branches. Let the total number of branches of the enterprise six months ago be A and the current number of branches be A. new , then the calculation formula for the Proportion of changes in branch offices (PCB) is as follows:

[0127]

[0128] If the PCB value is negative, it means that the company's branches are decreasing and the company is unlikely to expand to other places; on the contrary, the larger the PCB value, the more rapid the expansion and the greater the possibility of establishing new branches in other places.

[0129] S1034. Calculate the mean of the change results of enterprise scale and the change results of the number of branches to obtain the second impact quantitative factor.

[0130] Specifically, by calculating the mean of the results of the change in enterprise scale and the change in the number of branches, we can obtain the quantitative calculation results of the second influencing quantitative factor EEN (Enterprise expansion needs) corresponding to the recommendation of industrial chain supplementary enterprises based on the needs of attracting enterprise expansion and development. The specific calculation formula is as follows:

[0131]

[0132] S104. Based on the communication data of operators, a quantitative factor of the willingness to attract enterprises to settle in is constructed based on the spatiotemporal characteristics of communication big data;

[0133] It should be noted that the quantitative results of the regional business environment reflect the attractiveness of the chain-filling area to the enterprises in the relevant industrial chain. The quantitative analysis of the enterprise's own strength and development status can reflect whether the enterprise has sufficient strength and resources to support the expansion of the enterprise. Both aspects are pre-positioned objective and qualitative analysis. In addition to the above two influencing factors, whether the chain-filling enterprises to be introduced have a tendency to actually enter the introduction area to conduct business can better reflect the real subjective willingness of the enterprise to settle in the chain-filling area. The big data of the communication behavior of enterprise employees in the region can show the actual business development of the enterprise in the chain-filling area. For example, if the relevant telephone numbers of the enterprise have continuous and frequent communication behaviors with enterprises in the chain-filling area, it means that the enterprise has already carried out corporate business in the chain-filling area and has a relatively close partner. If the current enterprise does not have a local institution, it can be judged based on this that the target chain-filling enterprise is more likely to settle in the chain-filling area.

[0134] Reference Figure 6 , Figure 6 A flowchart of a step of obtaining a quantitative factor of the willingness to attract enterprises to settle in provided in an embodiment of the present invention, further as an optional implementation mode, the step of constructing a quantitative factor of the willingness to attract enterprises to settle in based on the spatiotemporal characteristics of communication big data according to the operator communication data can be further divided into the following steps S1041 to S1046:

[0135] S1041, setting a first statistical period, obtaining the monthly call times and non-zero call months of each recruited enterprise in the first statistical period from the operator's communication data;

[0136] S1042. Calculate the closeness of the business relationship of each attracted enterprise based on the first statistical period, the number of calls per month, and the non-zero call month;

[0137] It should be noted that the number of calls and time span between the communication numbers related to the enterprise in the operator's communication data and the enterprises in the chain supplement area can reflect the closeness of the business relationship between the enterprise and the enterprises in the region, and the number and number of visits by enterprise employees reflect the demand of the enterprise to work on-site in the attraction area. Therefore, the actual tendency of enterprises to settle in the attraction area is quantified by the calls of enterprise employees and the communication location trajectory. Among them, the number of calls shows the closeness of communication between the enterprise and the enterprises in the attraction area, and the time span of the call contact reflects the continuity of the relationship between the enterprise and the enterprises in the chain supplement area from the perspective of communication. Therefore, the embodiment of the present invention mainly uses the number of enterprise calls and the call time span as a correction coefficient to quantify the closeness of the business relationship between the enterprise and the enterprises in the region.

[0138] Specifically, considering the impact of timeliness, we use the M months from the statistical month as the analysis data set, set the first statistical period, and record the number of calls per month in the first statistical period as M.t , the value range of t is (1, 2, ..., 12), among which the month without zero call times (i.e. non-zero call months) is M n , because the average value can show the overall trend and general level of the number of calls, the monthly average of calls is used as the evaluation indicator of communication tightness. At the same time, the proportion of months with calls to the total number of months in the statistical period is introduced as a coefficient to correct the quantitative results. TCR (Tightness of communication relationship) is used to represent the tightness of the business relationship of the introduced enterprise. The specific calculation formula is as follows:

[0139]

[0140] It is understandable that the first statistical period can be set according to actual needs, for example, the first statistical period can be set to six months, nine months, or one year.

[0141] S1043, setting a second statistical period, and obtaining the monthly number of employees of each recruiting enterprise in the supply chain supplement area and the second statistical period from the operator's communication data;

[0142] S1044. Obtaining the number of working months and the total number of employees of each recruiting enterprise in the second statistical period from the operator communication data;

[0143] S1045. Calculate the job stability of employees of each attracting enterprise in the supply chain supplement area based on the second statistical period, the number of employees per month, the number of working months, and the total number of employees;

[0144] It should be noted that the more employees of enterprises who visit the supply chain area and the more times they visit, the more businesses of enterprises need to be carried out in the supply chain area, and the greater the possibility that enterprises will establish branches for business development or move to the local area as a whole. The communication location data in the operator's communication data can clearly show the trajectory of personnel flow. Similarly, the activity area of ​​enterprise employees can also be determined through communication location data. Therefore, the location insight ability of communication big data can be used to confirm the activities of enterprise employees in a specific area. Considering that the long-term office situation of enterprise employees in the region can better reflect the possibility of enterprises setting up branches in the attraction area, when conducting quantitative analysis of the location of enterprise employees, it is necessary to weaken the situation of settling in due to short-term business needs of enterprises by extending the analysis time span. Based on the above analysis, the product of the proportion of the number of months that enterprise employees work in the supply chain area in the second statistical period to the whole year and the proportion of the number of enterprise employees working in the supply chain area to the total number of enterprise employees is used as the quantitative result of the possibility of enterprise settlement.

[0145] Specifically, the number of months in the first statistical period is m, and the number of working months of enterprise employees is M. e , the total number of employees is N, and the number of employees working in the supply chain area each month in the first statistical period (i.e. the number of employees per month) is N j , SEE (Stability of Enterprise Employees) is used to represent the job stability of enterprise employees in the supply chain area. The specific calculation formula is as follows:

[0146]

[0147] It is understandable that the second statistical period can be set according to actual needs, for example, the second statistical period can be set to six months, nine months, or one year.

[0148] S1046. Calculate the mean of business relationship closeness and job stability to obtain a quantitative factor of the willingness to attract enterprises to settle in.

[0149] Specifically, based on the above calculation results, by solving the mean of business relationship closeness and job stability, we can get the quantitative factor of enterprise relocation intention ERI (Enterprise relocation intention). The specific calculation formula is as follows:

[0150]

[0151] S105. Evaluate the enterprises based on the first influencing quantitative factor, the second influencing quantitative factor, and the quantitative factor of the willingness to attract enterprises to settle in, and obtain the recommendation results of target enterprises in the supply chain filling area.

[0152] Reference Figure 7 , Figure 7 A flowchart of steps for obtaining target enterprise recommendation results provided in an embodiment of the present invention, further as an optional implementation mode, the step of performing enterprise evaluation according to the first influence quantitative factor, the second influence quantitative factor and the quantitative factor of the willingness to attract enterprises to settle in, and obtaining the target enterprise recommendation results of the chain supplement area can be further divided into the following steps S1051 and S1052:

[0153] S1051, performing a sum operation on the first influence quantitative factor, the second influence quantitative factor, and the quantitative factor of the willingness to attract enterprises to settle in, to obtain the probability of enterprise settlement;

[0154] S1052. Obtain target enterprise recommendation results based on the enterprise settlement probability.

[0155] Specifically, the above evaluation of regional industrial chain supplement target enterprises was carried out from three aspects: regional industrial chain policy environment, enterprise's own development needs and enterprise's willingness to settle in the industrial chain supplement area. In order to further improve the accuracy of the recommendation of target enterprises for regional introduction, the quantitative results of influencing factors were integrated by summing up to obtain the enterprise settlement probability TE (Target Enterprise) of the target enterprise settling in the supplement area. The specific calculation formula is as follows:

[0156] TE=BEC+EEN+ERI

[0157] The possibility of attracting enterprises can be evaluated based on the size of the enterprise settlement probability TE value. The larger the TE value, the greater the possibility of the enterprise settling in the chain-filling area; conversely, the smaller the TE value, the smaller the possibility of the enterprise settling in the chain-filling area.

[0158] In summary, the processing flow of the method for recommending regional industrial chain supplementary enterprises based on communication big data in an embodiment of the present invention is as follows: Figure 8 As shown, the embodiment of the present invention uses network public data, enterprise basic information and operator communication data as data sources, and quantifies the business environment of the chain supplementing industrial chain enterprises in the region, the development needs of the enterprises themselves and the willingness of the enterprises to settle in the chain supplementing area, and then obtains the enterprise settlement probability of the target enterprise in the chain supplementing area by summing the quantified results. The larger the value of the enterprise settlement probability TE, the greater the possibility of the target enterprise settling in the chain supplementing area. For these enterprises, it can be considered to establish a one-to-one docking channel for fixed-point investment promotion to improve investment promotion efficiency; for enterprises with a small enterprise settlement probability TE value, or even a negative value, no negotiation and docking will be carried out, which can greatly reduce the investment promotion cost.

[0159] The above describes the method for recommending regional industrial chain complementary enterprises based on communication big data in an embodiment of the present invention.

[0160] It can be appreciated that, compared with the industrial chain enterprise recommendation method in the prior art, the embodiment of the present invention has the following advantages:

[0161] 1. A wider range of data sources: Based on the basic business information of enterprises (i.e. basic enterprise data) and regional industrial chain-related policy data (i.e. public network data), by adding the communication behavior data of enterprises and employees, communication trajectory data, network behavior data and other operators' unique enterprise communication big data information (i.e. operator communication data), a more comprehensive analysis of target enterprises in the industrial chain supplementary area can be achieved. Compared with the simple use of basic enterprise data and public network data, the introduction of operator communication data achieves coverage of enterprise employees, with more analysis dimensions, making the analysis results more in line with the actual situation;

[0162] 2. More comprehensive scenario analysis: By introducing the communication spatiotemporal behavior data of enterprises and their employees, taking the communication behavior and communication trajectory behavior of enterprise employees as the entry point, taking the enterprise as the core, standing from the perspective of the enterprise, and based on the long-term development strategy, quantitative calculations are made from two aspects: the closeness of the business between the enterprise and the enterprises in the chain-filling area and the need for the enterprise to conduct on-site office in the chain-filling area, to achieve quantitative analysis of the willingness of enterprises to settle in the chain-filling area of ​​the industrial chain.

[0163] 3. More timely enterprise insights. Based on the quasi-real-time characteristics of operator communication data, more timely and effective insights can be obtained into the tendency of enterprises to settle in chain-filling areas, thereby effectively reducing the situation where the lack of timeliness of prediction results leads to the inability to timely carry out investment promotion for chain enterprises with a tendency to settle in, further enhancing the adaptability and effectiveness of enterprise recommendations.

[0164] Reference Fig. 9 The embodiment of the present invention also provides a regional industrial chain supplement enterprise recommendation system based on communication big data, including:

[0165] Data source acquisition module, used to obtain network public data, enterprise basic data and operator communication data;

[0166] The business environment quantitative module is used to construct the first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the macro factors of regional industrial chain development according to the public data on the Internet;

[0167] The enterprise expansion demand quantification module is used to construct the second influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the expansion and development needs of enterprises according to the basic data of enterprises;

[0168] The enterprise settlement willingness quantification module is used to construct a quantitative factor of enterprise settlement willingness based on the spatiotemporal characteristics of communication big data according to the operator communication data;

[0169] The target enterprise recommendation module is used to evaluate enterprises based on the first impact quantitative factor, the second impact quantitative factor and the quantitative factor of attracting enterprise settlement willingness, and obtain the target enterprise recommendation results in the chain filling area.

[0170] The contents of the above-mentioned embodiments of the method for recommending regional industrial chain chain-filling enterprises based on communication big data are all applicable to the embodiments of the regional industrial chain chain-filling enterprise recommendation system based on communication big data. The functions specifically implemented by the embodiments of the regional industrial chain chain-filling enterprise recommendation system based on communication big data are the same as those in the above-mentioned embodiments of the method for recommending regional industrial chain chain-filling enterprises based on communication big data, and the beneficial effects achieved are also the same as those achieved by the above-mentioned embodiments of the method for recommending regional industrial chain chain-filling enterprises based on communication big data.

[0171] 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 method for recommending regional industrial chain supplementary enterprises based on communication big data is realized. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0172] like Fig.10 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.10 , an embodiment of the present invention provides an electronic device, including:

[0173] The processor 1001 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.

[0174] The memory 1002 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 1002 can store an operating system and other applications. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the regional industrial chain supplement enterprise recommendation method based on communication big data in the embodiment of the present invention;

[0175] Input / output interface 1003, used to implement information input and output;

[0176] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0177] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0178] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0179] An 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, and the one or more programs can be executed by one or more processors to implement the above-mentioned regional industrial chain chain-filling enterprise recommendation method based on communication big data.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the 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 recommending regional industrial chain supplementary enterprises based on communication big data, characterized in that: The following steps are involved: Obtain network public data, enterprise basic data and operator communication data; According to the public network data, the first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the macro factors of regional industrial chain development is constructed; Based on the basic data of the enterprises, a second influencing quantitative factor corresponding to the recommendation of enterprises for filling the industrial chain based on the needs of attracting enterprises to expand and develop is constructed; Based on the communication data of the operators, a quantitative factor of the willingness to attract enterprises to settle in is constructed based on the spatiotemporal characteristics of the communication big data; An enterprise assessment is performed based on the first impact quantitative factor, the second impact quantitative factor, and the quantitative factor of the willingness to attract enterprises to settle in, and a recommendation result for target enterprises in the chain-filling area is obtained.

2. According to claim 1, a method for recommending regional industrial chain supplementary enterprises based on communication big data is characterized in that: The first influencing quantitative factor includes the regional policy environment influencing factor and the regional industrial supporting influencing factor. The first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the regional industrial chain development macro factors is constructed according to the network public data, and specifically includes: Quantitatively calculate the impact of the industrial chain policy environment on the complementary region based on the public network data to obtain the regional policy environment impact factor; The impact of industrial chain supporting facilities on the chain-filling area is quantitatively calculated based on the public network data to obtain the industrial supporting impact factor of the area.

3. According to claim 2, a method for recommending regional industrial chain supplementary enterprises based on communication big data is characterized in that: The quantitative calculation of the impact of the industrial chain policy environment on the complementary region based on the network public data to obtain the regional policy environment impact factor specifically includes: An analysis period is set, and the total amount of regional industrial policies promulgated in the supply chain filling area within the analysis period and the number of the first regional supply chain filling industrial policies in each month are obtained from the network public data; From the public network data, obtain the total number of superior industrial policies issued by the superior management department during the analysis period and the number of superior supply chain supplementary industrial policies; Calculate the regional policy impact index based on the total number of regional industrial policies promulgated, the number of the first regional industrial policies for complementary industrial chains, the total number of superior industrial policies promulgated, and the number of superior industrial policies for complementary industrial chains; The number of statistical months is set, and the number of the second-region supply chain supplementary industrial policies in the policy-issuing months and each of the policy-issuing months is obtained from the online public data; An industrial policy change impact index is calculated based on the statistical months, the policy promulgation months, and the number of industrial supply chain supplementary policies in the second region; The regional policy environment impact factor is obtained by calculating the mean of the regional policy impact index and the industrial policy change impact index.

4. According to claim 2, a method for recommending regional industrial chain supplementary enterprises based on communication big data is characterized in that: The quantitative calculation of the industrial chain supporting impact of the chain-filling area based on the network public data to obtain the regional industrial supporting impact factor specifically includes: Obtaining the number of upstream enterprises and downstream enterprises in the industrial chain to which the enterprises to be attracted in the supply chain supplementation area belong from the public network data; Obtaining the number of enterprises in the industrial chain to which the enterprises to be recruited in the supply chain supplementing area belong from the public network data; Calculate the industrial chain saturation of the chain-filling area according to the number of upstream enterprises, the number of downstream enterprises, and the number of enterprises; Obtaining the total number of enterprises in the supply chain supplement area and the number of industrial enterprises in the preset area from the network public data; Calculate the industrial concentration of the chain-filling area according to the total number of enterprises, the number of enterprises, and the number of industrial enterprises; The regional policy environment influencing factor, the industrial chain saturation and the industrial agglomeration are averaged to obtain the regional industrial supporting influencing factor.

5. According to claim 1, a method for recommending regional industrial chain supplementary enterprises based on communication big data is characterized in that: The second influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the expansion and development needs of the enterprises is constructed based on the basic data of the enterprises, specifically including: Based on the basic data of the enterprises, the change rate of registered capital and the change rate of the number of employees of each attracted enterprise are calculated; Calculate the change in enterprise scale based on the registered capital change rate and the employee number change rate; Based on the basic data of the enterprises, the change in the number of branches of each of the attracted enterprises is calculated; The second impact quantification factor is obtained by calculating the mean of the change results of the enterprise scale and the change results of the number of branches.

6. According to claim 1, a method for recommending regional industrial chain supplementary enterprises based on communication big data is characterized in that: The construction of a quantitative factor of the willingness to attract enterprises to settle in based on the spatiotemporal characteristics of communication big data according to the operator communication data specifically includes: Set a first statistical period, and obtain the monthly call times and non-zero call months of each recruited enterprise in the first statistical period from the operator communication data; Calculate the closeness of the business relationship of each of the attracted enterprises according to the first statistical period, the monthly number of calls and the non-zero call months; Setting a second statistical period, and obtaining the monthly number of employees of each of the recruited enterprises in the supply chain supplement area and the second statistical period from the operator communication data; Obtaining, from the operator communication data, the number of working months and the total number of employees of each of the recruited enterprises in the second statistical period; Calculate the job stability of the employees of each of the recruiting enterprises in the supply chain supplement area according to the second statistical period, the monthly number of employees, the number of working months and the total number of employees; The business relationship closeness and the job stability are averaged to obtain a quantitative factor of the willingness to attract enterprises to settle in.

7. A method for recommending regional industrial chain supplementary enterprises based on communication big data according to any one of claims 1 to 6, characterized in that: The enterprise evaluation is performed according to the first quantitative impact factor, the second quantitative impact factor, and the quantitative factor of the willingness to attract enterprises to settle in, to obtain the target enterprise recommendation results of the supply chain supplement area, specifically including: Performing a sum operation on the first quantitative impact factor, the second quantitative impact factor, and the quantitative factor of the willingness to attract enterprises to settle in, to obtain a probability of enterprise settlement; The target enterprise recommendation result is obtained according to the enterprise settlement probability.

8. A regional industrial chain supplementary enterprise recommendation system based on communication big data, characterized in that: include: Data source acquisition module, used to obtain network public data, enterprise basic data and operator communication data; A business environment quantification module, used to construct, based on the network public data, a first influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on regional-level industrial chain development macro factors; An enterprise expansion demand quantification module is used to construct, based on the enterprise basic data, a second influencing quantitative factor corresponding to the recommendation of industrial chain supplementary enterprises based on the needs of attracting enterprise expansion and development; A module for quantifying the willingness of enterprises to settle in, which is used to construct a quantitative factor for attracting the willingness of enterprises to settle in based on the spatiotemporal characteristics of communication big data according to the communication data of the operator; The target enterprise recommendation module is used to evaluate enterprises according to the first quantitative impact factor, the second quantitative impact factor and the quantitative factor of the willingness to attract enterprises to settle in, and obtain the target enterprise recommendation results of the chain filling area.

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 method for recommending regional industrial chain filling enterprises 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 method for recommending regional industrial chain filling enterprises based on communication big data as described in any one of claims 1 to 7.

Images