Enterprise site selection analysis method and device, equipment and medium

Abstract

The invention discloses an enterprise site selection analysis method and device, equipment and a medium, and relates to the field of data processing, and the method comprises the steps: obtaining enterprise operation data, enterprise basic information and current industrial environment data of an enterprise; inputting the enterprise operation data, the enterprise basic information and the industrial environment data into the constructed enterprise site selection model to obtain an enterprise which is output by the enterprise site selection model and has potential migration site selection conditions; the enterprise site selection model is constructed through historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industry environment data and sample enterprise basic information. According to the method, the enterprise is assisted to carry out accurate site selection, so that the analysis use value and the site selection quality of the enterprise site selection are ensured, and the working efficiency and the success rate of enterprise operation personnel are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an analysis method, device, equipment and medium for enterprise site selection. Background Art

[0002] As the speed of industrial development gradually accelerates, the development of the industry will involve the location selection of industry-related enterprises, so the location selection of enterprises has become a crucial decision in enterprise operations. Enterprise location selection refers to the transfer of part or all of production and / or services to another place. As the main force of regional industrial development, how to accurately grasp the fundamental factors and driving mechanisms of high-quality enterprise location decisions and then formulate more efficient spatial planning and corporate strategies has become the focus of attention of relevant decision-making departments.

[0003] However, at present, corporate site selection often relies on personal subjective experience judgment, which cannot comprehensively consider various key factors. However, this site selection method relies too much on human subjective judgment, such as market demand, competitor layout, industrial environment, etc., which leads to strong subjective factors in the analysis results of corporate site selection and has considerable limitations. The actual selected office location cannot meet the needs of corporate business development in the later stage. This limitation may lead to errors in corporate site selection decisions, thereby affecting the long-term development and operational efficiency of the company.

[0004] Therefore, how to provide more valuable enterprise site selection results to achieve high-quality enterprise site selection is an important issue that needs to be urgently resolved in the current enterprise development process. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide an analysis method, device, equipment and medium for enterprise site selection, so as to solve the problem that enterprise site selection based on personal subjective experience judgment has great limitations.

[0006] According to a first aspect, an embodiment of the present invention provides an analysis method for enterprise site selection, the method comprising: Obtain the enterprise's business operation data, basic enterprise information and current industrial environment data; Input enterprise operation data, enterprise basic information, and industrial environment data into the constructed enterprise site selection model to obtain enterprises with potential relocation site selection conditions output by the enterprise site selection model; the enterprise site selection model is constructed based on the historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information, and, based on the historical site selection behaviors of sample enterprises, relevant site selection motivation factors affecting enterprise relocation site selection are determined. The relevant site selection motivation factors include indicator feature signals that have positive and negative impacts on historical site selection behaviors. The indicator feature signals are extracted from the relevant site selection motivation factors based on sample enterprise basic information; Obtain the enterprise opinion information and enterprise meeting record information of enterprises with potential relocation site selection conditions, and perform semantic intention understanding on the enterprise opinion information and enterprise meeting record information to determine the enterprises with potential relocation site selection tendencies among the enterprises with potential relocation site selection conditions.

[0007] Combined with the first aspect, in the first implementation manner of the first aspect, the enterprise site selection model is constructed through the following steps: Select sample enterprises, obtain sample enterprise operation data and sample industrial environment data, and perform behavior analysis on the historical site selection behaviors that have occurred to the selected sample enterprises based on the sample enterprise operation data and sample industrial environment data to determine all initial site selection motivation factors for the sample enterprises to have historical site selection behaviors; Determine the correlation between each initial site selection motivation factor and the historical site selection behavior of the sample enterprise, and use the initial site selection motivation factors that meet the requirements of the correlation as relevant site selection motivation factors; the relevant site selection motivation factors include: production capacity expansion, new production line construction, and market expansion; Obtain the sample enterprise basic information of the sample enterprises, and perform feature analysis on the relevant site selection motivation factors with the sample enterprise basic information as factor variables to break down the indicator feature signals in the relevant site selection motivation factors; Classify and clean each indicator feature signal according to the feature information to obtain the classified indicator feature signals; According to the time difference between the time when the classified indicator feature signals occur and the current time, determine the decay index of each classified indicator feature signal, and determine the indicator weight of each classified indicator feature signal; Construct an enterprise site selection model based on the classified indicator feature signals and the indicator weights corresponding to the classified indicator feature signals.

[0008] Combined with the first implementation manner of the first aspect, in the second implementation manner of the first aspect, the analysis of the correlation between each initial site selection motivation factor and the historical site selection behavior of the sample enterprise, and using the initial site selection motivation factors that meet the requirements of the correlation as relevant site selection motivation factors specifically includes: Taking the historical site selection behavior of the sample enterprises as the dependent variable and the initial site selection motivation as the independent variable, analyze the correlation between the historical site selection behavior and each initial site selection motivation to obtain the correlation coefficient between each initial site selection motivation and the historical site selection behavior; Eliminate the initial site selection motivations with correlation coefficient values exceeding the preset threshold range to obtain the relevant site selection motivations.

[0009] Combined with the first implementation manner of the first aspect, in the third implementation manner of the first aspect, calculate the attenuation index of each classified index feature signal through a preset time decay model, and the calculation formula of the preset time decay model is:

[0010] Wherein, represents the attenuation index of the th classified index feature signal; represents the time from the time when the th classified index feature signal occurred to the current time; represents the attenuation coefficient; represents the initial influence value; represents the th total number of occurrences of the classified index feature signal.

[0011] Combined with the first implementation manner of the first aspect, in the fourth implementation manner of the first aspect, before the step of constructing the enterprise site selection model according to the classified index feature signals and the index weights corresponding to the classified index feature signals, it further includes: Determine the influence of the classified index feature signals on the historical site selection behavior, and perform standardization processing on the classified index feature signals with different influences by using the range method; the influences include positive influence and negative influence.

[0012] Combined with the fourth implementation manner of the first aspect, in the fifth implementation manner of the first aspect, for the classified index feature signals with positive influence, the calculation formula of the standardization processing is:

[0013] Wherein, represents the original value of the th classified index feature signal; represents the maximum value of the group where the original value of the th classified index feature signal is located; represents the minimum value of the group where the original value of the th classified index feature signal is located; represents the standardized value of the th classified index feature signal with positive influence, The value range of is [0

[0014] Combined with the fifth implementation manner of the first aspect, in the sixth implementation manner of the first aspect, for the classified index feature signals of the negative impact, the calculation formula for the normalization process is:

[0015] wherein, represents the normalized value of the th classified index feature signal of the negative impact, and the value range of is [-1

[0016] According to the second aspect, an embodiment of the present invention further provides an analysis device for enterprise site selection, and the device includes: A data acquisition module, configured to acquire the enterprise operation data, enterprise basic information, and current industrial environment data of the enterprise; A site selection analysis module, configured to input the enterprise operation data, enterprise basic information, and industrial environment data into the constructed enterprise site selection model, and obtain enterprises with potential migration site selection conditions output by the enterprise site selection model; the enterprise site selection model is constructed by the historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information, and, according to the historical site selection behaviors of the sample enterprises, relevant site selection motivation factors affecting enterprise migration site selection are determined, and the relevant site selection motivation factors include index feature signals that have positive and negative impacts on the historical site selection behaviors, and the index feature signals are extracted from the relevant site selection motivation factors based on the sample enterprise basic information; A site selection guidance module, configured to acquire the enterprise opinion information and enterprise meeting record information of enterprises with potential migration site selection conditions, and perform semantic intention understanding on the enterprise opinion information and enterprise meeting record information to determine enterprises with potential migration site selection tendencies among the enterprises with potential migration site selection conditions.

[0017] According to the third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of the analysis method for enterprise site selection as described in any one of the above are implemented.

[0018] According to the fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the analysis method for enterprise site selection as described in any one of the above are implemented.

[0019] According to a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which when executed by a processor, implements the steps of the method for analyzing enterprise location selection as described in any one of the above.

[0020] The method, device, equipment and medium for analyzing enterprise location selection of the present invention subdivide the enterprise location selection decision-making behavior into several location selection motivations, model them, comprehensively consider the influence degree of various location selection motivations on the analysis of enterprise location selection, then disassemble and clean and structure the location selection motivations, and calculate the attenuation of the index feature signal, so as to enhance the authority of the index feature signal. Through the above processing, enterprises with the intention of having potential conditions for relocating the location can be found. After finding the enterprises with potential conditions for relocating the location through the enterprise location selection model, obtain the enterprise opinion information and enterprise meeting record information of the enterprises with potential conditions for relocating the location, and perform semantic intention understanding on the enterprise opinion information and enterprise meeting record information to determine the enterprises with potential tendency to relocate the location among the enterprises with potential conditions for relocating the location, which helps the enterprise to select the location accurately, ensures the use value and quality of the location selection, and improves the efficiency and success rate of the work of enterprise operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings. The drawings are schematic and should not be construed as imposing any limitation on the present invention. In the drawings: Figure 1 A flowchart showing the method for analyzing enterprise location selection provided by the present invention is shown; Figure 2 A structural diagram showing the device for analyzing enterprise location selection provided by the present invention is shown; Figure 3 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] As the speed of industrial development gradually accelerates, the development of the industry will involve the location selection of industry-related enterprises, so the location selection of enterprises has become a crucial decision in enterprise operations. Enterprise location selection refers to the transfer of part or all of production and / or services to another place. As the main force of regional industrial development, how to accurately grasp the fundamental factors and driving mechanisms of high-quality enterprise location decisions and then formulate more efficient spatial planning and corporate strategies has become the focus of attention of relevant decision-making departments.

[0024] However, at present, corporate site selection often relies on personal subjective experience judgment, which cannot comprehensively consider various key factors. However, this site selection method relies too much on human subjective judgment, such as market demand, competitor layout, industrial environment, etc., which leads to strong subjective factors in the analysis results of corporate site selection and has considerable limitations. The actual selected office location cannot meet the needs of corporate business development in the later stage. This limitation may lead to errors in corporate site selection decisions, thereby affecting the long-term development and operational efficiency of the company.

[0025] To sum up, how to provide more valuable enterprise site selection results to achieve high-quality enterprise site selection is an important issue that needs to be urgently solved in the current enterprise development process.

[0026] In order to solve the above problems, an analysis method for enterprise site selection is provided in this specification, which aims to help enterprises to make accurate site selection, so as to ensure the use value of the analysis and site selection quality of enterprise site selection, and improve the efficiency and success rate of the work of enterprise operators. The analysis method for enterprise site selection provided in this specification can be applied to electronic devices with data processing capabilities. The electronic device may include a notebook, a desktop computer, a smart phone, a smart wearable device (virtual reality glasses, smart watches, etc.), a tablet computer, etc. Of course, the analysis method for enterprise site selection provided in this specification can also be applied to applications running in the above-mentioned electronic devices. For example, the analysis method for enterprise site selection can be applied to a browser with data processing capabilities, or it can be applied to a browser with data processing capabilities. Figure 1 FIG. 1 is a flow chart of an analysis method for enterprise site selection according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps: S10. Obtain the enterprise's business operation data and current industrial environment data.

[0027] Among them, enterprise operation data includes various operation-related data provided by the enterprise, including enterprise capacity expansion, new production lines, market expansion and other aspects. Industrial environment data includes relevant foreign policies, local policies, industrial environment, etc.

[0028] S20. Input the enterprise operation data and industrial environment data into the constructed enterprise site selection model to obtain the enterprises with potential relocation site selection conditions output by the enterprise site selection model. Among them, the enterprise site selection model is constructed based on the historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information. Moreover, relevant site selection motivation factors that affect the relocation site selection of enterprises are determined according to the historical site selection behaviors of sample enterprises. The relevant site selection motivation factors include indicator feature signals that have positive and negative impacts on historical site selection behaviors, and the indicator feature signals are extracted from the relevant site selection motivation factors based on the sample enterprise basic information.

[0029] S30. After finding the enterprises with potential relocation site selection conditions through the enterprise site selection model, obtain the enterprise opinion information and enterprise meeting record information of the enterprises with potential relocation site selection conditions, and perform semantic intention understanding on the enterprise opinion information and enterprise meeting record information to determine the enterprises with potential relocation site selection tendencies among the enterprises with potential relocation site selection conditions.

[0030] For the enterprises with site selection conditions, in this embodiment, it will also analyze whether the enterprises have the tendency of site selection according to the enterprise opinion information and enterprise meeting record information that combine enterprise employees and enterprise management, which helps the enterprises to conduct accurate site selection, ensures the use value and quality of site selection, and improves the work efficiency and success rate of enterprise operation personnel. For example, through various trained semantic intention understanding models, perform semantic intention understanding at the enterprise level on the enterprise opinion information and enterprise meeting record information, and finally determine the enterprises with potential relocation site selection tendencies to better guide such enterprises to conduct relocation site selection.

[0031] In this embodiment, the enterprise site selection model is constructed through the following steps: S40. Select sample enterprises, obtain sample enterprise operation data and sample industrial environment data, and perform behavior analysis on the historical site selection behaviors that have occurred to the selected sample enterprises according to the sample enterprise operation data and sample industrial environment data to determine all the initial site selection motivation factors for the sample enterprises to have historical site selection behaviors.

[0032] In this embodiment, behavior analysis will be performed on the historical site selection behaviors of the selected sample enterprises. According to the behavior analysis of the historical site selection behaviors, enterprise site selection mainly includes two aspects: 1) The registered address has changed; 2) It is necessary to set up a subsidiary or branch in other places. For the establishment of any of the above conditions, it is regarded as the sample enterprise has had a site selection behavior.

[0033] Among them, the occurrence of historical site selection behaviors is usually caused by the following site selection motivations: enterprise production capacity expansion, new production line construction, market expansion, attraction of relevant policies in other regions, alleviation of relevant policies in the local area, too high production costs, industrial migration, etc. Taking these site selection motivations as the initial site selection motivations, the initial site selection motivations for the analysis of these enterprises' site selections are the index characteristics corresponding to the enterprise site selection model.

[0034] In this embodiment, candidate site selection motivations can be obtained by acquiring the sample enterprise operation data and sample industrial environment data of the sample enterprises. Then, during the process of analyzing the historical site selection behaviors of the sample enterprises, these candidate site selection motivations will be analyzed to obtain the initial site selection motivations. The acquisition methods of the sample enterprise operation data and sample industrial environment data are as shown in step S10 and will not be elaborated here.

[0035] S50. Analyze the correlation between each initial site selection motivation and the historical site selection behaviors of the sample enterprises respectively, and use the initial site selection motivations whose correlation meets the requirements as the relevant site selection motivations.

[0036] Specifically, step S50 includes: S51. Take the historical site selection behaviors of the sample enterprises as the dependent variable, and take the initial site selection motivations as the independent variables, analyze the correlation between the historical site selection behaviors and each initial site selection motivation, and obtain the correlation coefficients between each initial site selection motivation and the historical site selection behaviors.

[0037] In this embodiment, the differences and significances of the influencing factors of enterprise migration motivation characteristics are analyzed through a multiple Logit model. Specifically, take whether the sample enterprises have historical site selection behaviors as the dependent variable, and take the initial site selection motivations as the independent variables, and analyze which initial site selection motivations strongly affect whether the sample enterprises conduct enterprise site selection.

[0038] S52. Eliminate the initial site selection motivations whose correlation coefficient values exceed the preset threshold range to obtain the relevant site selection motivations.

[0039] Considering that the correlations of some site selection motivation characteristics are relatively strong, during the process of calculating the correlation coefficients between each initial site selection motivation and the historical site selection behaviors, eliminate the initial site selection motivations whose specific correlation coefficient values exceed the preset acceptable threshold range, including the initial site selection motivations with correlation coefficients higher and lower than the threshold range. Finally, screen out the initial site selection motivations that are independent of each other and have a high degree of correlation, including three aspects: production capacity expansion, new production line construction, and market expansion. These three initial motivation characteristics are the relevant site selection motivations.

[0040] S60. Obtain the basic information of the sample enterprises, and use the basic information of the sample enterprises as the factor variables to conduct characteristic analysis on the relevant site selection motivations, and decompose the index characteristic signals in the relevant site selection motivations.

[0041] Among them, the enterprise information includes: the nature of the enterprise, the scale of the enterprise, and the industrial category. Correspondingly, the disassembled index characteristic signals are as follows: Capacity expansion includes the first financing signal, the first product R & D signal, the first product launch signal, the listed additional issuance signal, the news signal, the revenue growth signal, the month-on-month change signal of electricity consumption, and the month-on-month change signal of water consumption. The new production line includes the second financing signal, the second product R & D signal, and the second product launch signal. Market expansion includes the third financing signal, the merger and acquisition signal, the IPO signal, the industrial cooperation signal investigation signal, the project winning bid signal, and the off-site recruitment signal.

[0042] In addition to the analysis of the location selection motivation of enterprise location selection, the basic information of the enterprise also affects the enterprise's location selection decision-making process. In this embodiment, the basic information of the sample enterprises is divided into the following aspects: the nature of the enterprise (state-owned or state-controlled enterprises, private enterprises, wholly foreign-owned enterprises), the scale of the enterprise (large enterprises, medium-sized enterprises, small enterprises), and the industrial category (encouraged category, permitted category, restricted category). Considering that the different specific characteristics of the enterprise will affect the location selection of the above sample enterprises, therefore, the nature of the enterprise, the scale of the enterprise, and the industrial category are selected as factor variables and input into the enterprise location selection model to observe the influence degree of their respective specific characteristics on the enterprise location selection.

[0043] Taking the scale of the enterprise as an example for illustration, large enterprises have a large scale and a relatively complete organizational structure, resulting in higher enterprise relocation costs and greater demand for enterprise reserve funds. Therefore, in the organizational structure adjustment, more factors need to be considered. For example, large enterprises generally attach the most importance to land resources and labor resources, while small and medium-sized enterprises have less capital loss in the regional adjustment after consideration, higher feasibility, faster speed of achieving significant results after adjustment, and can timely make various adjustments to cope with the changing environment.

[0044] The following is an index interpretation of each index characteristic signal: 1) Index characteristic signals disassembled from the relevant location selection motivation of the new production line category The first financing signal: refers to the financing behavior for the R & D of existing category products and the construction of production bases.

[0045] The first product R & D signal: applicable to existing category products, obtained through enterprise news tags, referring to the innovation and improvement development carried out on the basis of the existing product categories or series.

[0046] The first product launch signal: applicable to existing category products, obtained through enterprise news tags, referring to the promotion of improved or iterative products that already belong to an existing category to the market.

[0047] Listing and Rights Issue Signal: It refers to a company that has already been listed on the stock exchange raising more funds from investors by issuing additional shares. This is a common way for listed companies to conduct refinancing, usually used to meet the company's development capital needs, such as expanding business scale, conducting research and development, and acquiring other enterprises.

[0048] News Signal: The purpose is to expand the production capacity demand of the enterprise, which can be obtained through enterprise news tags. It usually refers to the measures taken by the enterprise to expand production capacity in response to the growth of market demand or to enhance its market competitiveness during the industry boom cycle. Such news is common in the manufacturing, technology, and resource-intensive industries.

[0049] Revenue Growth Signal: It refers to the total year-on-year growth of the enterprise's main business income and other business incomes.

[0050] Monthly Change Signal of Power Consumption: It refers to the change in the enterprise's power consumption compared to the previous period.

[0051] Monthly Change Signal of Water Consumption: It refers to the change in the enterprise's water consumption compared to the previous period.

[0052] 2) Index Feature Signals Obtained by Decomposing the Location Selection Motivation Related to New Production Line Second Financing Signal: It refers to the financing behavior aimed at building a production base for new category products.

[0053] Second Product R & D Signal: Applicable to new category products, it refers to the enterprise's design, development, and innovation for brand-new product categories.

[0054] Second Product Listing Signal: Applicable to new category products, it can also be obtained through enterprise news tags, referring to the enterprise's launching of brand-new product categories into the market.

[0055] 3) Index Feature Signals Obtained by Decomposing the Location Selection Motivation Related to Market Expansion Third Financing Signal: It refers to the financing behavior aimed at market expansion.

[0056] Mergers and Acquisitions Signal: It refers to the strategic behavior of an enterprise to expand its market share, enter new markets, or enhance its competitiveness by acquiring or merging other companies.

[0057] IPO Signal: It refers to a company's first issuance of stocks to public investors, thus becoming a listed company.

[0058] Industrial Cooperation Signal: It can be obtained through enterprise news tags, referring to the strategic cooperation between different enterprises or organizations in the same industry or related industries, aiming to achieve resource sharing, complementary advantages, and coordinated development.

[0059] Investigation signal: It can be obtained through enterprise news tags, referring to the fact that the management personnel of an enterprise go to other companies, industries or regions for on-site investigations to obtain market information, learn advanced experience or seek cooperation opportunities.

[0060] Project winning signal: It refers to that in the bidding process, an enterprise or organization is selected through the bidding plan and obtains the right to implement the project.

[0061] Off-site recruitment signal: It refers to that an enterprise conducts recruitment in areas other than its headquarters or main operation locations to attract and recruit suitable talents.

[0062] S70. Classify and clean each index feature signal according to the characteristic information to obtain the classified index feature signals.

[0063] For example, the above three financing signals can be further split into seed round, angel round, round A, round B, round C, round D, round E, round F, Pre-IPO, strategic financing, etc. according to the financing rounds. Then, clean the data according to these financing rounds to realize the induction and classification of the index feature signals.

[0064] S80. According to the time difference between the time when the classified index feature signal occurs and the current time, determine the decay index of each classified index feature signal, and determine the index weight of each classified index feature signal. In this embodiment, by calculating the decay index, the authority of each classified index feature signal is improved. In this embodiment, the decay index of each classified index feature signal is calculated through a preset time decay model. The specific calculation formula of the preset time decay model is:

[0065] Among them, represents the decay index of the th classified index feature signal; represents the number of months between the time when the th classified index feature signal occurs and the current time; represents the decay coefficient, The initial value of is set to represents the initial influence value; represents the total number of times the th classified index feature signal appears. Considering that the sample enterprise may have multiple classified index feature signals, in this embodiment, the influence of the index feature signal on the historical site selection behavior is the sum of multiple influences.

[0066] For example, substituting the index feature signal of the seed round financing into the time decay model, the obtained decay index is: Seed round financing amount × If there are multiple seed rounds, calculate the sum of the seed round amounts after decay processing. The same applies to other rounds.

[0067] The IPO signal can also calculate the decay index of the indicator feature signal of the IPO in each stage according to the IPO stage status. The decay index of the indicator feature signal of the IPO in each stage is: the basic weight of the IPO stage × .

[0068] The merger and acquisition signal is split according to the status and given different basic weights. The decay index of the merger and acquisition signal in each stage is: the merger and acquisition amount × the basic weight of the merger and acquisition stage × , and for multiple mergers and acquisitions, they are accumulated.

[0069] The decay index of the seasoned equity offering signal in each stage is: the seasoned equity offering amount × , and for multiple seasoned equity offerings, they are accumulated.

[0070] The news signal can be divided into stages such as product R & D, product release, executive inspection, strategic cooperation, production capacity expansion demand, and industrial cooperation. These stages all come from the enterprise operation information label data, and multiple similar enterprise operation information is accumulated.

[0071] It should be noted that the enterprise operation data, industrial environment data, sample enterprise operation data, sample industrial environment data, enterprise basic information, sample enterprise basic information, and indicator feature signals involved in this application are all obtained with full consent and authorization, and the collection, use, and processing of relevant information need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0072] In this embodiment, the indicator weight is determined by the regression coefficient of the multivariate Logit model or the correlation coefficient of the grey relational analysis.

[0073] To avoid the imbalance of the discrimination degree of the indicator feature signals caused by too large differences in the original values, the indicator feature signals are standardized before calculating the site selection probability to eliminate the influence of the dimension between indicators. In this embodiment, all indicator feature signals are standardized by the range method.

[0074] Specifically, first determine the influence of the classified indicator feature signals on the historical site selection behavior, and then use the range method to standardize the classified indicator feature signals with different influences. Among them, the influence includes positive influence and negative influence.

[0075] After that, for the classified indicator feature signals with positive influence, the scoring value range is set to [0 1], and the larger the value, the better. The specific calculation formula is:

[0076] For the classified indicator feature signals of negative impacts, the scoring value range is set to [-1 1], and the smaller the value, the better. The specific calculation formula is:

[0077] In the above two formulas, represents the original value of the th classified indicator feature signal; represents the maximum value of the group where the original value of the i th classified indicator feature signal is located; represents the minimum value of the group where the original value of the th classified indicator feature signal is located; represents the normalized value of the th classified indicator feature signal of positive impact; represents the normalized value of the th classified indicator feature signal of negative impact.

[0078] S80. According to the classified indicator feature signals and the corresponding indicator weights of the classified indicator feature signals, construct an enterprise location selection model.

[0079] Construct an enterprise location selection model to determine whether a sample enterprise needs to relocate. The relevant calculation formula of the model is:.

[0080]

[0081] Among them, represents the normalized classified indicator feature signal, ; represents the corresponding indicator weight of the normalized classified indicator feature signal.

[0082] Speculate whether the sample enterprise will relocate in the future based on the existing historical location selection behaviors of the sample enterprise, and use the historical location selection behaviors that occurred after these historical location selection behaviors for accuracy detection.

[0083] In this embodiment, in order to evaluate the performance of the enterprise location selection model, three evaluation indicators, namely precision, accuracy, and recall rate, are selected to evaluate the detection effect of the model. The corresponding evaluation indicators include:

[0084] Among them, represents precision; represents the number of positive samples correctly judged; Indicates the number of positive samples misjudged as negative (should actually be negative).

[0085]

[0086] Among them, Indicates accuracy; Indicates the number of negative samples correctly judged as negative (should actually be positive); Indicates the total number of samples.

[0087]

[0088] Among them, Indicates recall; Indicates the number of negative samples misjudged as negative (should actually be positive).

[0089] The enterprise location selection analysis method of the present invention divides the enterprise location selection decision-making behavior into several location selection motivations, models them, comprehensively considers the influence degree of various location selection motivations on the enterprise location selection analysis, then disassembles and cleans and structures the location selection motivations, and calculates the attenuation of the index characteristic signal, so as to improve the authority of the index characteristic signal. Through the above processing, enterprises with the intention of having potential migration and location selection conditions can be found. After finding the enterprises with potential migration and location selection conditions through the enterprise location selection model, obtain the enterprise opinion information and enterprise meeting record information of the enterprises with potential migration and location selection conditions, and conduct semantic intention understanding on the enterprise opinion information and enterprise meeting record information to determine the enterprises with potential migration and location selection tendencies among the enterprises with potential migration and location selection conditions, assist the enterprise in accurate location selection, ensure the use value and location selection quality of the location selection, and improve the work efficiency and success rate of enterprise operation personnel.

[0090] The enterprise location selection analysis device provided by the embodiments of the present invention will be described below. The enterprise location selection analysis device described below can be correspondingly referred to the enterprise location selection analysis method described above.

[0091] In order to solve the above problems, an enterprise location selection analysis device is provided in this specification, aiming to provide an efficient, low-cost, highly automated and well-scalable database performance optimization solution. Figure 2 It is a structural schematic diagram of the enterprise location selection analysis device according to the embodiments of the present invention, as Figure 2 shown. The device may include: A data acquisition module 10, configured to acquire the enterprise operation data, enterprise basic information and current industrial environment data of the enterprise.

[0092] The site selection analysis module 20 is used to input enterprise operation data, enterprise basic information, and industrial environment data into the established enterprise site selection model to obtain enterprises with potential relocation site selection conditions output by the enterprise site selection model. The enterprise site selection model is constructed based on the historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information. Moreover, relevant site selection motivation factors affecting enterprise relocation site selection are determined according to the historical site selection behaviors of sample enterprises. The relevant site selection motivation factors include indicator characteristic signals that have positive and negative impacts on historical site selection behaviors. The indicator characteristic signals are extracted from the relevant site selection motivation factors based on the sample enterprise basic information.

[0093] The site selection guidance module 30 is used to obtain the enterprise opinion information and enterprise meeting record information of enterprises with potential relocation site selection conditions after finding enterprises with potential relocation site selection conditions through the enterprise site selection model, and perform semantic intention understanding on the enterprise opinion information and enterprise meeting record information to determine enterprises with potential relocation site selection tendencies among enterprises with potential relocation site selection conditions.

[0094] For example, semantic intention understanding at the enterprise level is performed on the enterprise opinion information and enterprise meeting record information through various trained semantic intention understanding models, and finally enterprises with potential relocation site selection tendencies are determined to better guide such enterprises in relocation site selection.

[0095] The enterprise site selection analysis device of the present invention subdivides enterprise site selection decision-making behaviors into several site selection motivation factors, models them, comprehensively considers the analysis influence degree of various site selection motivation factors on enterprise site selection, then disassembles and cleans and structures the site selection motivation factors, and calculates the attenuation of indicator characteristic signals, thereby enhancing the authority of indicator characteristic signals. Through the above processing, enterprises with the intention of having potential relocation site selection conditions can be discovered. After finding enterprises with potential relocation site selection conditions through the enterprise site selection model, the enterprise opinion information and enterprise meeting record information of enterprises with potential relocation site selection conditions are obtained, and semantic intention understanding is performed on the enterprise opinion information and enterprise meeting record information to determine enterprises with potential relocation site selection tendencies among enterprises with potential relocation site selection conditions, assisting enterprises in accurate site selection, ensuring the use value and site selection quality of site selection, and improving the efficiency and success rate of the work of enterprise operation personnel.

[0096] Figure 3 An example of the physical structure diagram of an electronic device is shown in Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logical commands in the memory 330 to execute the analysis method for enterprise location selection, and this method includes: Obtain the enterprise operation data, enterprise basic information, and current industrial environment data of the enterprise; Input the enterprise operation data, enterprise basic information, and industrial environment data into the constructed enterprise location selection model to obtain an enterprise with potential migration location selection conditions output by the enterprise location selection model; the enterprise location selection model is constructed through the historical location selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information, and, based on the historical location selection behaviors of sample enterprises, relevant location selection motivation factors affecting enterprise migration location selection are determined. The relevant location selection motivation factors include index feature signals that have positive and negative impacts on historical location selection behaviors, and the index feature signals are extracted from the relevant location selection motivation factors based on the sample enterprise basic information.

[0097] In addition, when the logical instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memor), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0098] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the analysis method for enterprise location selection provided by the above-mentioned various methods, and this method includes: Obtain the enterprise operation data, enterprise basic information, and current industrial environment data of the enterprise; Input enterprise operation data, enterprise basic information, and industrial environment data into the constructed enterprise site selection model to obtain enterprises with potential relocation site selection conditions output by the enterprise site selection model; the enterprise site selection model is constructed through the historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information, and, based on the historical site selection behaviors of the sample enterprises, relevant site selection motivations affecting enterprise relocation site selection are determined. The relevant site selection motivations include indicator characteristic signals that have positive and negative impacts on the historical site selection behaviors. The indicator characteristic signals are extracted from the relevant site selection motivations based on the sample enterprise basic information.

[0099] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the above-described analysis method for enterprise site selection, and the method includes: Obtain the enterprise operation data, enterprise basic information, and current industrial environment data of the enterprise; Input the enterprise operation data, enterprise basic information, and industrial environment data into the constructed enterprise site selection model to obtain enterprises with potential relocation site selection conditions output by the enterprise site selection model; the enterprise site selection model is constructed through the historical site selection behaviors of sample enterprises, sample enterprise operation data, sample industrial environment data, and sample enterprise basic information, and, based on the historical site selection behaviors of the sample enterprises, relevant site selection motivations affecting enterprise relocation site selection are determined. The relevant site selection motivations include indicator characteristic signals that have positive and negative impacts on the historical site selection behaviors. The indicator characteristic signals are extracted from the relevant site selection motivations based on the sample enterprise basic information.

[0100] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0101] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An analysis method for enterprise site selection, characterized in that: The method comprises: Obtain the enterprise's business operation data, basic enterprise information and current industrial environment data; Inputting enterprise operation data, enterprise basic information and industrial environment data into the constructed enterprise location selection model, and obtaining enterprises with potential relocation conditions output by the enterprise location selection model; the enterprise location selection model is constructed through the historical location selection behavior of sample enterprises, the sample enterprise operation data, the sample industrial environment data and the sample enterprise basic information, and, according to the historical location selection behavior of the sample enterprises, determining the relevant location selection motivations that affect the enterprise relocation location selection, the relevant location selection motivations contain indicator feature signals that have positive and negative effects on the historical location selection behavior, and the indicator feature signals are based on the basic information of the sample enterprises and extracted from the relevant location selection motivations; Obtain the enterprise opinion information and enterprise meeting record information of enterprises with potential relocation site selection conditions, understand the semantic intent of the enterprise opinion information and enterprise meeting record information, and determine the enterprises with potential relocation site selection tendencies among the enterprises with potential relocation site selection conditions.

2. The enterprise site selection analysis method according to claim 1, characterized in that: The enterprise location model is constructed by the following steps: Select sample enterprises, obtain the sample enterprise operation data and sample industry environment data, and conduct behavioral analysis on the historical location selection behaviors of the selected sample enterprises based on the sample enterprise operation data and sample industry environment data to determine all initial location selection motivations for the sample enterprises' historical location selection behaviors; Determine the correlation between each initial location selection motivation and the historical location selection behavior of the sample enterprises, and take the initial location selection motivation that meets the correlation requirements as the relevant location selection motivation; The relevant site selection motivations include: capacity expansion, new production lines and market expansion; Obtain the basic information of sample enterprises, and use the basic information of sample enterprises as factor variables to conduct characteristic analysis on relevant location selection motivations, and disassemble the indicator characteristic signals in the relevant location selection motivations; Classify and clean each indicator characteristic signal according to the characteristic information to obtain the classified indicator characteristic signal; According to the time difference between the occurrence time of the classified indicator characteristic signal and the current time, the attenuation index of each classified indicator characteristic signal is determined, and the indicator weight of each classified indicator characteristic signal is determined; According to the classified indicator characteristic signals and the indicator weights corresponding to the classified indicator characteristic signals, an enterprise location selection model is constructed.

3. The enterprise site selection analysis method according to claim 2, characterized in that: The determination of the correlation between each initial location selection motivation and the historical location selection behavior of the sample enterprise, and taking the initial location selection motivation that meets the correlation requirements as the relevant location selection motivation, specifically includes: Taking the historical location selection behavior of sample enterprises as the dependent variable and the initial location selection motivation as the independent variable, the correlation between the historical location selection behavior and each initial location selection motivation is analyzed, and the correlation coefficient between each initial location selection motivation and the historical location selection behavior is obtained; The initial site selection motivations whose correlation coefficient values ​​exceed the preset threshold range are eliminated to obtain the relevant site selection motivations.

4. The enterprise site selection analysis method according to claim 2, characterized in that: The decay index of each classified indicator feature signal is calculated by a preset time decay model, and the calculation formula of the preset time decay model is: in, Indicates The decay index of the indicator feature signal after item classification; Indicates The time from the occurrence time of the indicator characteristic signal after item classification to the current time; represents the attenuation coefficient; represents the initial impact value; Indicates The total number of occurrences of indicator feature signals after item classification.

5. The enterprise site selection analysis method according to claim 2, characterized in that: Before the step of constructing the enterprise location selection model according to the classified indicator characteristic signals and the indicator weights corresponding to the classified indicator characteristic signals, the step further includes: Determine the influence of the classified indicator characteristic signals on the historical site selection behavior, and use the range method to standardize the classified indicator characteristic signals with different influences; the influence includes positive influence and negative influence.

6. The enterprise site selection analysis method according to claim 5, characterized in that: For the classified indicator characteristic signals of positive impact, the calculation formula for standardization is: in, Indicates The original value of the indicator feature signal after item classification; Indicates The maximum value of the group in which the original value of the indicator characteristic signal after item classification belongs; Indicates The minimum value of the group in which the original value of the indicator characteristic signal after item classification belongs; The positive impact The value of the index characteristic signal after item classification is standardized. The value range is [0 1].

7. The enterprise site selection analysis method according to claim 6, characterized in that: For the classified indicator characteristic signals of negative impact, the calculation formula for standardization is: in, The negative impact The value of the index characteristic signal after item classification is standardized. The value range is [-1 1].

8. An analysis device for enterprise site selection, characterized in that: The device comprises: Data acquisition module, used to obtain the enterprise's business operation data, basic enterprise information and current industrial environment data; A site selection analysis module is used to input enterprise operation data, enterprise basic information and industrial environment data into a constructed enterprise site selection model to obtain enterprises with potential relocation site selection conditions output by the enterprise site selection model; the enterprise site selection model is constructed through the historical site selection behavior of sample enterprises, the sample enterprise operation data, the sample industrial environment data and the sample enterprise basic information, and the relevant site selection factors affecting the enterprise relocation site selection are determined based on the historical site selection behavior of the sample enterprises, and the relevant site selection factors include indicator feature signals that have positive and negative effects on the historical site selection behavior, and the indicator feature signals are extracted from the basic information of the sample enterprises and the relevant site selection factors; The site selection guidance module is used to obtain the enterprise opinion information and enterprise meeting record information of enterprises with potential relocation site conditions, and to understand the semantic intent of the enterprise opinion information and enterprise meeting record information to determine the enterprises with potential relocation site tendencies among the enterprises with potential relocation site conditions.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the enterprise site selection analysis method as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the enterprise location analysis method as claimed in any one of claims 1 to 7 are implemented.

Images