Method and device for selecting target enterprise of investment attraction project, equipment and medium

Abstract

The invention discloses a method for selecting a target enterprise of an investment attraction project. The method comprises the steps of determining a to-be-selected enterprise set according to an industrial chain link evaluation index and an investment attraction demand of an industrial chain to be subjected to investment attraction in a specified area; obtaining enterprise data of all to-be-selected enterprises in the to-be-selected enterprise set and a preset target index set, converting all target indexes into target index functions when any target index does not exist in the enterprise data, and constructing an evaluation matrix of the to-be-selected enterprise set based on all the target index functions; weighting the evaluation matrix by adopting an entropy weight method and a CRITIC method to obtain a first weight and a second weight of each to-be-selected enterprise in the evaluation matrix; according to the first weight, the second weight and the target index function, performing calculation to obtain an enterprise score of each to-be-selected enterprise; determining a target enterprise list of the designated area according to the enterprise scores of all the to-be-selected enterprises; according to the invention, the precision and credibility of target enterprise selection of the investment attraction project can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a method, device, equipment and medium for selecting a target enterprise for an investment promotion project. Background Art

[0002] With the development of computer technology and intelligent information technology, many fields use intelligent machine processing to replace tedious manual processing processes, which not only saves human resources and reduces costs, but also improves the accuracy and stability of work.

[0003] However, in the field of investment promotion, investment attraction and investor placement are mainly carried out through industry interviews, corporate surveys, human recommendations and other methods, with manual matching and screening, lacking efficient intelligent means. This is not only inefficient, but also wastes a lot of manpower costs. In addition, the data source is single, resulting in low accuracy and credibility of the selection results. Summary of the invention

[0004] The embodiment of the present invention provides a method for selecting a target enterprise for an investment project, which can improve the accuracy and credibility of the target enterprise selection result for the investment project.

[0005] In a first aspect, an embodiment of the present invention provides a method for selecting a target enterprise for an investment promotion project, comprising:

[0006] Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment needs of the industrial chain to be invested in the designated area;

[0007] Acquire enterprise data and a preset target indicator set of all the enterprises to be selected in the enterprise set to be selected, and when any target indicator in the enterprise data does not exist, convert all the target indicators into target indicator functions, and construct an evaluation matrix of the enterprise set to be selected based on all the target indicator functions;

[0008] The evaluation matrix is ​​weighted by using the entropy weight method and the CRITIC method to obtain the first weight and the second weight of each candidate enterprise in the evaluation matrix;

[0009] Calculating the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function;

[0010] A list of target enterprises in the designated area is determined based on the enterprise scores of all the selected enterprises.

[0011] Furthermore, the set of enterprises to be selected is determined according to the evaluation index of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area, including:

[0012] Calculate the evaluation indicators of the industrial chain links; wherein the evaluation indicators of the industrial chain links include indicators related to industrial advantage, indicators related to industrial coreness and indicators related to policy fit;

[0013] Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area;

[0014] The calculation process of the policy fit index includes:

[0015] Obtaining the investment target text of the investment project in the designated area; wherein the investment target text includes an investment policy text and an investment planning text;

[0016] Performing data preprocessing on the investment promotion target text;

[0017] Use natural language processing (NLP) technology to extract keywords from the pre-processed investment target text;

[0018] According to the extracted keywords, the degree of fit of each industrial link of the industrial chain to be invested is calculated to obtain the policy fit index.

[0019] Furthermore, the enterprise score of each of the selected enterprises is calculated based on the first weight, the second weight and the target indicator function, including:

[0020] For each of the selected enterprises, a first enterprise score is calculated based on the first weight and the target indicator function, and a second enterprise score is calculated based on the second weight and the target indicator function.

[0021] Furthermore, determining the list of target enterprises in the designated area according to the enterprise scores of all the selected enterprises includes:

[0022] All the enterprises to be selected are sorted in descending order according to the first enterprise scores, and starting from the enterprise with the highest first enterprise score, a preset number of enterprises to be selected are selected in turn to form a first enterprise list;

[0023] All the selected enterprises are sorted in descending order according to the second enterprise scores, and starting from the enterprise with the highest second enterprise score, a preset number of selected enterprises are selected in turn to form a second enterprise list;

[0024] Obtaining the number of repeated enterprises in the first enterprise list and the second enterprise list, and calculating a first repetition coefficient according to the number of repeated enterprises and a preset number of target enterprises;

[0025] Based on the first repetition coefficient, a list of target enterprises in the designated area is determined.

[0026] Furthermore, determining the list of target enterprises in the designated area based on the first repetition coefficient includes:

[0027] When the first repetition coefficient is greater than or equal to a preset first repetition coefficient threshold, merging the first enterprise list with the second enterprise list to obtain a target enterprise list of the designated area;

[0028] When the first repetition coefficient is less than the first repetition coefficient threshold, a comprehensive enterprise score is calculated according to the first enterprise score and the second enterprise score;

[0029] All the enterprises to be selected are sorted in descending order according to the comprehensive enterprise scores, and starting from the enterprise with the highest comprehensive enterprise score, a preset number of enterprises to be selected are selected in turn to form a list of target enterprises in the designated area.

[0030] Furthermore, the method further comprises:

[0031] When all target indicators in the enterprise data exist, a multi-objective optimization model of the candidate enterprise set is constructed based on the target indicator set;

[0032] Using at least two optimization algorithms to solve the multi-objective optimization model to obtain multiple recommended enterprise lists;

[0033] Calculate the second repetition coefficient of each of the recommended enterprise lists and the remaining recommended enterprise lists;

[0034] A list of target enterprises in the designated area is determined according to all the second repetition coefficients and a preset second repetition coefficient threshold.

[0035] Furthermore, determining the target enterprise list of the designated area according to all the second repetition coefficients and a preset second repetition coefficient threshold includes:

[0036] Counting the number of lists whose second repetition coefficient is greater than or equal to a preset second repetition coefficient threshold;

[0037] When the number of the lists is greater than or equal to two, two recommended enterprise lists with the largest second repetition coefficient are selected and merged to obtain a target enterprise list for the designated area;

[0038] When the number of the lists is less than two, all the recommended enterprise lists are merged, and the target enterprise list of the designated area is obtained based on the merged list.

[0039] In a second aspect, an embodiment of the present invention provides a device for selecting a target enterprise for an investment promotion project, comprising:

[0040] The data preparation module is used to determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment needs of the industrial chain to be invested in the designated area;

[0041] A matrix construction module, used to obtain enterprise data of all the enterprises to be selected in the enterprise set and a preset target indicator set, and when any target indicator in the enterprise data does not exist, convert all the target indicators into target indicator functions, and construct an evaluation matrix of the enterprise set to be selected based on all the target indicator functions;

[0042] A matrix weighting module, used for weighting the evaluation matrix by using an entropy weight method and a CRITIC method, to obtain a first weight and a second weight of each candidate enterprise in the evaluation matrix;

[0043] An enterprise score calculation module, used for calculating the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function;

[0044] The target enterprise selection module is used to determine the target enterprise list in the designated area according to the enterprise scores of all the enterprises to be selected.

[0045] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0046] Memory for storing computer programs;

[0047] A processor, configured to execute the computer program;

[0048] Wherein, when the processor executes the computer program, the method for selecting target enterprises for the investment promotion project described in any one of the first aspects above is implemented.

[0049] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed, implements the method for selecting target enterprises for an investment promotion project as described in any one of the first aspects above.

[0050] Compared with the prior art, the method for selecting target enterprises for investment projects provided by the embodiment of the present invention has the following beneficial effects: determining a set of enterprises to be selected according to the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in a designated area; obtaining the enterprise data of all the enterprises to be selected in the set of enterprises to be selected and a preset target indicator set, and when any target indicator in the enterprise data does not exist, converting all the target indicators into target indicator functions, and constructing an evaluation matrix for the set of enterprises to be selected based on all the target indicator functions; using the entropy weight method and the CRITIC method to assign weights to the evaluation matrix, and obtaining the first weight and the second weight of each enterprise to be selected in the evaluation matrix; calculating the enterprise score of each enterprise to be selected according to the first weight, the second weight and the target indicator function; determining the list of target enterprises in the designated area according to the enterprise scores of all the enterprises to be selected; the present invention can improve the accuracy and credibility of the selection of target enterprises for investment projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical features of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 It is a flow chart of an embodiment of a method for selecting a target enterprise for an investment promotion project provided by the present invention;

[0053] Figure 2 It is a structural schematic diagram of an embodiment of a device for selecting a target enterprise for an investment attraction project provided by the present invention;

[0054] Figure 3 It is a structural schematic diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] In the first aspect, the embodiment of the present invention provides a method for selecting a target enterprise for an investment project, see Figure 1 , which is a flow chart of an embodiment of a method for selecting a target enterprise for an investment promotion project provided by the present invention.

[0057] like Figure 1 As shown, the method comprises the following steps:

[0058] S1: Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment needs of the industrial chain to be invested in the designated area;

[0059] S2: obtaining enterprise data of all the enterprises to be selected in the enterprise set and a preset target indicator set, and when any target indicator in the enterprise data does not exist, converting all the target indicators into target indicator functions, and constructing an evaluation matrix of the enterprise set to be selected based on all the target indicator functions;

[0060] S3: using the entropy weight method and the CRITIC method to assign weights to the evaluation matrix, and obtaining the first weight and the second weight of each candidate enterprise in the evaluation matrix;

[0061] S4: Calculate the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function;

[0062] S5: Determine a list of target enterprises in the designated area according to the enterprise scores of all the selected enterprises.

[0063] In the specific implementation, the designated area is a designated specific spatial scope, such as a city, administrative district or industrial park, and relevant data of the industrial chain to be invested in the designated area is obtained. The data sources include but are not limited to enterprise databases, investment project databases, patent databases, customs import and export databases, investment and financing databases, policy databases and social media databases, etc. For the industrial chain to be invested, a pre-identified industrial chain map is obtained. The source of the map can be expert experience, preliminary industry research, etc. The industrial chain map must clarify the composition of the industrial chain links and the upstream and downstream relationships of the industrial chain links, and match the industrial chain links with relevant databases in advance to obtain the enterprise information, product information and invention patent information in the designated research area corresponding to each industrial chain link, and determine the set of enterprises to be selected based on the industrial chain link evaluation indicators and the investment needs of the industrial chain to be invested in the designated area.

[0064] It should be noted that the target indicator set includes enterprise recommended target indicators and enterprise constraint indicators.

[0065] Among them, the enterprise recommendation target indicators correspond to the enterprise recommendation targets. The optional enterprise recommendation targets include leading traction targets, potential cultivation targets, personal connection traction targets, business expansion targets and benefit balance targets; the leading traction target is to select industry leading enterprises or enterprises with a certain scale to give play to the upstream and downstream agglomeration effect of the leading industry chain. When the leading traction target is an industry leading target, such as a listed company, a top four enterprise, or a regional headquarters of an enterprise, the corresponding enterprise recommendation target indicators are whether it is a listed company, a top four enterprise, or a headquarters enterprise, all of which are 0-1 variables. If so, 1 is taken, otherwise 0 is taken; when the leading traction target is a high tax contribution target, such as a high tax amount For enterprises with high potential, the corresponding enterprise recommendation target indicator is the amount of enterprise tax paid; the potential cultivation target is to attract enterprises with development potential. When the potential cultivation target is a capital recognition target, that is, the recent investment and financing dynamics are active and recognized by the capital market, the corresponding enterprise recommendation target indicator is the investment amount obtained by the enterprise in the past year; when the potential cultivation target is a research and development innovation target, that is, the intellectual property rights are rich or growing rapidly, the corresponding enterprise recommendation target indicator is the number of invention patents applied for by the enterprise in the past year; the network traction target is that the main senior executives of the enterprise include industry leaders or high-level industry talent teams. After introduction, a large number of industrial and scientific research ecological resources can be brought in accordingly, thereby accelerating the construction of the industrial ecology, and the corresponding enterprise recommendation target indicator is The recommended target indicator is the number of academicians among corporate executives; the business expansion goal is to attract companies with market business expansion capabilities. When the business expansion goal is a scale expansion goal, that is, the staff scale expands rapidly, the corresponding recommended target indicator for the company is the growth rate of the number of employees in the company in the past year; when the business expansion goal is a business expansion goal, that is, the number and amount of biddings increase rapidly, the corresponding recommended target indicator for the company is the growth rate of the number of biddings in which the company participated in the past year; when the business expansion goal is a carrier expansion goal, that is, land bidding and auction are active and a lot of land has been acquired recently, the corresponding recommended target indicator for the company is the amount of land bidding and auction in the past year; when the business expansion goal is a market expansion goal, that is, product imports and exports increase rapidly, the corresponding recommended target indicator for the company is the growth rate of the number of biddings in which the company participated in the past year. The growth is fast, and the corresponding recommended target indicator for the enterprise is the export amount of the enterprise's products in the past year; the benefit balance target is to try to achieve better social benefits after introducing the enterprise, while minimizing negative externalities. When the benefit balance target is a green, environmentally friendly and low-pollution enterprise, the corresponding recommended target indicator for the enterprise is the pollution emissions of the enterprise in the past year; when the benefit balance target is a labor-intensive enterprise that solves a large number of employment problems, the corresponding recommended target indicator for the enterprise is the number of employees recruited by the enterprise in the past year; according to the actual investment promotion needs, one or more enterprise recommendation targets can be selected, and the corresponding enterprise recommended target indicators can be obtained. For example, for the convenience of solving the problem, the number of enterprise recommended target indicators can be limited to 3.

[0066] Furthermore, the enterprise constraint index corresponds to the enterprise investment promotion constraint. The optional enterprise investment promotion constraints include land use constraint, capital constraint and construction period constraint, etc. The land resources available for investment promotion in the study area are limited. It is necessary to reasonably plan investment promotion projects according to the land supply situation to avoid land waste and over-development. When the land use constraint is the area constraint of the land available for investment promotion, the corresponding enterprise constraint index is the required land area; the land use nature of different plots, such as industrial land, commercial land, residential land, etc., has clear regulations. Investment promotion enterprises must comply with the requirements of the plot nature and shall not change the use without authorization. When the land use constraint is the planned land use nature constraint of the land available for investment promotion, the corresponding enterprise constraint index is the required land use nature; some regions may set a minimum investment amount requirement. Only enterprises that reach this amount can participate in the investment promotion. When the capital constraint is the minimum investment amount specified in the study area, the corresponding enterprise constraint indicator is the estimated investment amount of the project; the enterprise may need to complete the capital investment within a specific time. When the capital constraint is the maximum period for the funds to be in place specified in the study area, the corresponding enterprise constraint indicator is the estimated period for the funds to be in place for the project; the enterprise needs to complete the project construction and put it into production within the specified time. When the construction period constraint is the longest project construction period specified in the study area, the corresponding enterprise constraint indicator is the estimated construction period of the project; the enterprise needs to commit to the long-term maintenance and renewal of the project. When the construction period constraint is the shortest project maintenance period specified in the study area, the corresponding enterprise constraint indicator is the estimated maintenance period of the project.

[0067] The enterprise data of all the candidates in the candidate enterprise set are obtained. When any target indicator in the enterprise data does not exist, the existing target indicator is converted into a target indicator function. Based on all the target indicator functions, an evaluation matrix of the candidate enterprise set is constructed, and all the target indicator functions are standardized according to the optimization target direction; wherein the optimization target direction includes forward and reverse directions; the entropy weight method and the CRITIC method are used to assign weights to the evaluation matrix to obtain a first weight and a second weight of each candidate enterprise in the evaluation matrix; according to the first weight, the second weight and the target indicator function, the enterprise score of each candidate enterprise is calculated; according to the enterprise scores of all the candidate enterprises, a list of target enterprises in the designated area is determined.

[0068] In summary, the present invention determines the set of selected enterprises according to the evaluation index of the industrial chain link and the investment demand of the industrial chain to be invested in the designated area; obtains the enterprise data and preset target indicator set of all the selected enterprises in the selected enterprise set, and when any target indicator in the enterprise data does not exist, converts all the target indicators into target indicator functions, and constructs the evaluation matrix of the selected enterprise set based on all the target indicator functions; adopts the entropy weight method and the CRITIC method to weight the evaluation matrix, and obtains the first weight and the second weight of each selected enterprise in the evaluation matrix; calculates the enterprise score of each selected enterprise according to the first weight, the second weight and the target indicator function; determines the list of target enterprises in the designated area according to the enterprise scores of all the selected enterprises. The present invention uses and covers various data dimensions, can output differentiated enterprise recommendation results for different investment targets, realizes more flexible and target-oriented investment recommendation, evaluates the development prospects of each link of the industrial chain, can realize more long-term investment decision-making, and can improve the accuracy and credibility of the target enterprise selection of investment projects.

[0069] In an optional implementation, determining the set of enterprises to be selected according to the evaluation index of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area includes:

[0070] Calculate the evaluation indicators of the industrial chain links; wherein the evaluation indicators of the industrial chain links include indicators related to industrial advantage, indicators related to industrial coreness and indicators related to policy fit;

[0071] Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area;

[0072] The calculation process of the policy fit index includes:

[0073] Obtaining the investment target text of the investment project in the designated area; wherein the investment target text includes an investment policy text and an investment planning text;

[0074] Performing data preprocessing on the investment promotion target text;

[0075] Use natural language processing (NLP) technology to extract keywords from the pre-processed investment target text;

[0076] According to the extracted keywords, the degree of fit of each industrial link of the industrial chain to be invested is calculated to obtain the policy fit index.

[0077] Specifically, according to the investment demand of the industrial chain to be invested in the designated area, the set of enterprises to be selected is determined, and the evaluation indicators of the industrial chain links are calculated first. The evaluation indicators of the industrial chain links include indicators related to industrial advantage, indicators related to industrial coreness, and policy fit indicators.

[0078] Among them, the industry advantage related indicators include the local supporting degree of the industrial chain, the enterprise scale advantage and the industry supply-demand ratio. The calculation method of each indicator is as follows:

[0079] The local matching degree of the industrial chain = procurement volume in this region / (procurement volume in other regions + procurement volume in this region) × 100%, where procurement volume in this region refers to the total amount of raw materials, parts and components purchased by the main products of this industrial link in the study area, and procurement volume in other regions refers to the total amount of raw materials, parts and components purchased by the main products of this industrial link from non-study areas. Optionally, in order to more accurately reflect the local matching degree of the industrial chain, the importance of different parts and components can be considered, such as demand scale, price, quality and technical content, and corresponding weight coefficients can be assigned. The local matching degree of the industrial chain can measure the proportion of local resources and local industries used in the product production process of a study area. This indicator is of great significance for evaluating the integrity of the local industrial chain, promoting local industrial development and reducing external dependence. The higher the local matching degree of the industrial chain, the higher the self-sufficiency of the industrial link in the study area, the higher the supply chain resilience, and the more prominent the advantages of the industrial link.

[0080] Enterprise scale advantage = (number of enterprises in this industry link / number of enterprises in the entire industrial chain) × (number of high-tech enterprises in this industry link / number of high-tech enterprises in the entire industrial chain) × (number of unicorn enterprises in this industry link / number of unicorn enterprises in the entire industrial chain) × 100%, where the number of enterprises in this industry link refers to the total number of registered enterprises in this industry link in the study area, the number of enterprises in the entire industrial chain refers to the sum of the total number of registered enterprises in all links of the industrial chain in the study area, the number of high-tech enterprises in this industry link refers to the total number of registered high-tech enterprises in this industry link in the study area, the number of high-tech enterprises in the entire industrial chain refers to the sum of the total number of registered high-tech enterprises in all links of the industrial chain in the study area, the number of unicorn enterprises in this industry link refers to the total number of registered unicorn enterprises in this industry link in the study area, and the number of unicorn enterprises in the entire industrial chain refers to the sum of the total number of registered unicorn enterprises in all links of the industrial chain in the study area. The enterprise scale advantage can measure and identify which industrial links occupy an important position in the entire industrial chain. These important industrial links often have a high number of enterprises, abundant high-tech enterprises and unicorn enterprises, and are the core driving force for the development of the industrial chain. The higher the enterprise scale advantage, the more important the industrial link is in the entire industrial chain.

[0081] Industry supply-demand ratio = (market supply / market demand) × (market supply growth rate / market demand growth rate) × 100%, where market supply refers to the market supply of products provided by local enterprises in the study area among the main output products of the industry link, and market demand refers to the demand in the local consumer market within the study area among the main output products of the link. Correspondingly, the market supply growth rate and the market demand growth rate refer to the increase in market supply and market demand in this statistical period compared with the previous statistical period. According to actual demand, the statistical period can be divided into different time granularities such as month, quarter, and year. The industry supply-demand ratio reflects the market supply and demand relationship of the industry in a specific period. When the supply-demand ratio is greater than 1, it means that the industry link is generally in a state of oversupply, then the industry link may be more advantageous. When the supply-demand ratio is less than 1, it means that the industry link is generally in a state of shortage of supply, then the industry link may be relatively weak.

[0082] The industry core indexes include technological competitiveness, output value contribution and industry segment profit margin. The calculation methods of each index are as follows:

[0083] Technological competitiveness = the number of invention patents in this link / the number of invention patents in the entire industrial chain × 100%, where the number of invention patents in this link refers to the number of invention patents applied for by enterprises in this industrial link in the research area, and the number of invention patents in the entire industrial chain refers to the sum of the number of invention patents applied for by enterprises in all links of the industrial chain in the research area. Technological competitiveness reflects the output results of intellectual property technology in this industrial link. The higher the value, the higher the technological barriers of this industrial link.

[0084] Output value contribution = output value of the link / output value of the entire industrial chain × 100%, where the output value of the link refers to the sum of the output value or revenue of enterprises in the industrial link within the study area, and the output value of the entire industrial chain refers to the sum of the output value or revenue of enterprises in all links of the industrial chain within the study area. The output value contribution reflects the role of the industrial link in promoting industrial and economic development. The higher the value, the greater the economic driving effect of the industrial link.

[0085] Profit margin of industrial link = profit of this link / profit of the whole industrial chain × 100%, where profit of this link refers to the sum of profits of enterprises in this industrial link within the study area, and profit of the whole industrial chain refers to the sum of profits of enterprises in all links of the industrial chain within the study area. Profit margin of industrial link is an important indicator reflecting the profitability of this industrial link. The higher the value, the greater the profitability of this industrial link, which plays a key role in enhancing the competitiveness of the industrial chain.

[0086] It should be noted that in the calculation process of the above-mentioned industry advantage related indicators and industry core degree related indicators, since division is involved, in order to avoid division by 0, the calculation formula of each indicator can be converted. The optional conversion methods include but are not limited to: logarithmic conversion, addend conversion, replacement of divisor and exponential conversion; for example, taking the calculation of technological competitiveness as an example, in order to avoid the division calculation error caused by the number of invention patents in the entire industrial chain being 0, the logarithmic conversion can be performed by logarithmically converting each variable in the formula, that is: technological competitiveness = ln (the number of invention patents in this link) / ln (the number of invention patents in the entire industrial chain) × 100%; the addend conversion can be performed by adding one to each variable in the formula. Pre-set parameters, namely: technological competitiveness = (the number of invention patents in this link + 1) / (the number of invention patents in the entire industry chain + 1) × 100%; the divisor can be replaced by manually replacing the divisor in the formula with a pre-set parameter, for example, replacing the number of invention patents in the entire industry chain with 1, namely: technological competitiveness = the number of invention patents in this link / 1 × 100%; exponential conversion can be performed by performing exponential conversion on each variable in the formula, namely: technological competitiveness = exp (the number of invention patents in this link) / exp (the number of invention patents in the entire industry chain) × 100%; in actual operation, the conversion method and corresponding indicator parameters can be selected according to the dimension of the variable, the difficulty of calculation and other actual needs.

[0087] To calculate the fit index, it is first necessary to obtain the investment promotion targets of the investment promotion projects in the specified area, that is, text information such as investment promotion policy texts and investment promotion planning texts. Natural language processing (NLP) technology is used to perform data preprocessing on the acquired text. Data preprocessing includes text cleaning, removal of punctuation marks, stop words and other irrelevant information, and word segmentation and part-of-speech tagging. Then, the keyword extraction algorithm in NLP is used, including but not limited to TF-IDF, TextRank, etc., to extract keywords related to each industrial link of the industrial chain to be invested from the text of the investment promotion targets, with special attention paid to those words closely related to policy orientations, support directions, development goals, etc. The keywords extracted from the text analysis are compared and matched with the characteristics of each link in the industrial chain, and each industrial link is scored to evaluate its fit with the text keywords. The score obtained is the fit index.

[0088] During the implementation process, according to the actual investment promotion needs, indicators are selected from the above-mentioned industrial chain link evaluation indicators, and different indicator selection ideas are determined according to different investment promotion needs. When the investment promotion needs need to focus on the weak or missing links in the industrial chain, consider the supporting needs of the industrial chain, and attract upstream and downstream enterprises that are compatible with the key links to improve the industrial chain structure, strengthen the security and resilience of the industrial chain, and improve the industrial synergy effect, the local supporting degree of the industrial chain, the enterprise scale advantage, and the balance of industrial supply and demand in the relevant indicators of industrial advantage can be selected for evaluation. By assigning a certain weight to each indicator and then taking the weighted sum, the evaluation results of the industrial chain links are calculated, and the link with the best evaluation result is selected as the industrial link that needs to be strengthened and supplemented; when the investment promotion needs need to focus on the key core links of the industrial chain, select the link that plays a key role in improving the overall competitiveness of the industrial chain as the focus of investment promotion. Some links generally have the characteristics of high technical barriers, large added value or strong market influence. The technical competitiveness, output value contribution and industrial link profit margin of the industry core degree related indicators can be selected for evaluation. By assigning a certain weight to each indicator and then taking the weighted sum, the evaluation results of the industrial chain links are calculated, and the links with the best evaluation results are selected as the industrial links that need to be strengthened and supplemented. When the investment demand needs to focus on the links that are consistent with the policy direction, according to the regional economic development plan and industrial policy, the short-term and long-term goals and directions of the industrial chain development are clarified, and enterprises in the corresponding industrial links and industrial tracks are attracted. The policy compatibility indicators can be selected for evaluation, and the links with the best evaluation results are selected as the industrial links that need to be strengthened and supplemented. After determining the links that need to be strengthened and supplemented, search the industrial database for the enterprises corresponding to the industrial link, extract these enterprises, and use them as the set of candidates for selection.

[0089] In an optional implementation manner, calculating the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function includes:

[0090] For each of the selected enterprises, a first enterprise score is calculated based on the first weight and the target indicator function, and a second enterprise score is calculated based on the second weight and the target indicator function.

[0091] Specifically, when each target indicator in the target indicator set exists, each target indicator is converted into a target indicator function, and based on all the target indicator functions, an evaluation matrix of the candidate enterprise set is constructed. Exemplarily, the evaluation matrix can be in the form of the following Table 1:

[0092] Table 1 Evaluation matrix

[0093]

[0094] Among them, f NIt represents the Nth target indicator function, which is a function of the selected target indicator in a linear or nonlinear form. The target indicator function can be set in advance according to the needs. N represents the number of determined target indicator functions. Indicates K max The value of the Nth target indicator function of the enterprise, where K max Represents the total number of enterprises in the candidate enterprise set.

[0095] For example, the construction of the target indicator function can be referred to as follows:

[0096] f1=ln(tax k (x))+pat k (x) 2 ;

[0097] f2=stf k (x)×bid k (x);

[0098] f3=pol k (x);

[0099] Among them, ln(tax k (x)) represents the natural logarithm of the tax amount of the kth candidate enterprise, pat k (x) 2 represents the square of the number of invention patents applied for by the kth candidate enterprise in the past year, stf k (x) represents the growth rate of the number of employees of the kth candidate enterprise in the past year, bid k (x) Table 1. The growth rate of the number of tenders and bids participated by the kth candidate enterprise in the past year, pol k (x) represents the pollution emission of the kth candidate enterprise in the past year, Inv k (x) represents the estimated investment amount of the project of the kth enterprise, InvLow k (x) represents the minimum investment amount specified in the study area, Lneedb k (x) represents the nature of the land required for the project of the kth candidate enterprise, Lplan k (x) represents the planned land use nature of the land available for investment promotion in the study area, where k = 1, ..., K max .

[0100] Furthermore, all target indicator functions are standardized according to the optimization target direction, wherein the optimization target direction includes positive and reverse directions. For example, the optimization target direction of target indicators such as the investment amount obtained by the enterprise in the past year and the number of invention patents applied for by the enterprise in the past year is positive, and generally the larger the better. The optimization target direction of the enterprise pollution emission indicator in the past year is reverse, and generally the smaller the better. For example, the formula for standardizing the positive indicator is as follows:

[0101]

[0102] Among them, r1 represents the standardized result of the positive indicator, t represents the variable value to be standardized, and t max is the maximum value of the variable t to be standardized, t min is the minimum value of the variable t to be standardized.

[0103] The formula for standardizing the reverse indicator is as follows:

[0104]

[0105] Among them, r2 represents the standardized result of the reverse indicator.

[0106] The entropy weight method and CRITIC method are used to assign weights to the standardized evaluation matrix. The entropy weight method is a commonly used objective weighting method. In the specific use process, the entropy weight of each indicator is calculated using information entropy according to the degree of dispersion of the data of each indicator, and then the entropy weight is corrected according to each indicator to obtain a more objective indicator weight. The CRITIC method is another commonly used objective weighting method. It comprehensively measures the objective weight of the indicator based on the comparative strength of the evaluation indicators and the conflict between the indicators. It considers the variability of the indicators while taking into account the correlation between the indicators, and scientifically evaluates the indicator weights. After weighting, the first weight w of each candidate enterprise in the evaluation matrix is ​​obtained. 1j and the second weight w 2j , where the first weight w 1j represents the weight of the jth target indicator function obtained by the entropy weight method, and the second weight w 2j It represents the weight of the jth objective indicator function obtained by the CRITIC method, j = 1, 2, ... N, N represents the number of objective indicator functions.

[0107] For each candidate enterprise, the first enterprise score is calculated based on the first weight and the target indicator function, and the second enterprise score is calculated based on the second weight and the target indicator function. For example, the calculation formula is as follows:

[0108]

[0109]

[0110] in, Indicates the first enterprise rating, represents the second enterprise score, t ij Represents the j-th target indicator function of the i-th enterprise.

[0111] In an optional implementation manner, determining the target enterprise list of the designated area according to the enterprise scores of all the selected enterprises includes:

[0112] All the enterprises to be selected are sorted in descending order according to the first enterprise scores, and starting from the enterprise with the highest first enterprise score, a preset number of enterprises to be selected are selected in turn to form a first enterprise list;

[0113] All the selected enterprises are sorted in descending order according to the second enterprise scores, and starting from the enterprise with the highest second enterprise score, a preset number of selected enterprises are selected in turn to form a second enterprise list;

[0114] Obtaining the number of repeated enterprises in the first enterprise list and the second enterprise list, and calculating a first repetition coefficient according to the number of repeated enterprises and a preset number of target enterprises;

[0115] Based on the first repetition coefficient, a list of target enterprises in the designated area is determined.

[0116] Specifically, after calculating the first enterprise score and the second enterprise score, all candidate enterprises are sorted in descending order according to the first enterprise score, and a preset number of candidate enterprises with the highest scores are selected in turn to form a first enterprise list. Then, all candidate enterprises are sorted in descending order according to the second enterprise score, and a preset number of candidate enterprises with the highest scores are selected in turn to form a second enterprise list. The preset number can range from 10 to 15, which is not specifically limited here.

[0117] Compare the two lists of enterprises, conduct consistency checks, count the number of duplicate enterprises in the two lists, and calculate the first duplication coefficient based on the number of duplicates and the preset number of target enterprises. The specific formula is as follows:

[0118]

[0119] Among them, RepR 12 Represents the first repetition coefficient, rep 12 represents the number of repeated enterprises in the two lists, and K represents the preset number of target enterprises.

[0120] In an optional implementation manner, determining the target enterprise list in the designated area based on the first repetition coefficient includes:

[0121] When the first repetition coefficient is greater than or equal to a preset first repetition coefficient threshold, merging the first enterprise list with the second enterprise list to obtain a target enterprise list of the designated area;

[0122] When the first repetition coefficient is less than the first repetition coefficient threshold, a comprehensive enterprise score is calculated according to the first enterprise score and the second enterprise score;

[0123] All the enterprises to be selected are sorted in descending order according to the comprehensive enterprise scores, and starting from the enterprise with the highest comprehensive enterprise score, a preset number of enterprises to be selected are selected in turn to form a list of target enterprises in the designated area.

[0124] Specifically, the first repetition coefficient threshold RepR′ is preset. For example, the first repetition coefficient threshold can be set to 80%, which is not specifically limited here. 12 When it is greater than or equal to the first repetition coefficient threshold RepR′, it means that the enterprise lists calculated by different weight measurement methods are highly similar and the results are relatively scientific and reliable. In this case, the first enterprise list and the second enterprise list are merged to obtain the target enterprise list for the specified area.

[0125] When the first repetition coefficient RepR 12 When it is less than the first repetition coefficient threshold RepR′, it means that the similarity of the enterprise recommendation lists calculated by different weight measurement methods is low. It is necessary to comprehensively consider the results of the two weight measurement methods to enhance the rationality of the results. Then, the comprehensive enterprise score is calculated based on the first enterprise score and the second enterprise score. The calculation method is as follows:

[0126]

[0127] in, Indicates the comprehensive enterprise rating. Indicates the first enterprise rating, Indicates the second enterprise rating.

[0128] All candidate enterprises are sorted in descending order according to their comprehensive enterprise scores, and a preset number of candidate enterprises with the highest scores are selected in turn to form a list of target enterprises in the designated area.

[0129] In an optional embodiment, the method further includes:

[0130] When all target indicators in the enterprise data exist, a multi-objective optimization model of the candidate enterprise set is constructed based on the target indicator set;

[0131] Using at least two optimization algorithms to solve the multi-objective optimization model to obtain multiple recommended enterprise lists;

[0132] Calculate the second repetition coefficient of each of the recommended enterprise lists and the remaining recommended enterprise lists;

[0133] A list of target enterprises in the designated area is determined according to all the second repetition coefficients and a preset second repetition coefficient threshold.

[0134] Specifically, when all target indicators in the target indicator set exist, the target enterprise list is determined through multi-objective optimization. First, a multi-objective optimization model is constructed for all enterprises in the candidate enterprise set. The multi-objective optimization model is referenced as follows:

[0135]

[0136] stG(x)∈H;

[0137] Among them, x represents the vector form of the target indicator in the target indicator set, max(min)f i (x) represents the i-th target indicator function, which is a function of the selected target indicators in linear or nonlinear form, i = 1, 2, ... n, N represents the number of target indicator functions, st represents the model constraint, G(x) represents the enterprise constraint indicator set, and H represents the selected enterprise constraint indicator range.

[0138] Exemplarily, an optional multi-objective optimization model is:

[0139]

[0140] stInv k (x)≥InvLow, k=1,...,K;

[0141] Lneedb k (x)∈Lplan, k=1,…,K;

[0142] Among them, ln(tax k (x)) represents the natural logarithm of the tax amount of the kth candidate enterprise, pat k (x) 2 represents the square of the number of invention patents applied for by the kth candidate enterprise in the past year, stf k (x) represents the growth rate of the number of employees of the kth candidate enterprise in the past year, bid k(x) Table 1. The growth rate of the number of tenders and bids participated by the kth candidate enterprise in the past year, pol k (x) represents the pollution emission of the kth candidate enterprise in the past year, Inv k (x) represents the estimated investment amount of the project of the kth enterprise, InvLow k (x) represents the minimum investment amount specified in the study area, Lneedb k (x) represents the nature of the land required for the project of the kth candidate enterprise, Lplan k (x) represents the planned land use nature of the land available for investment promotion in the study area, where k = 1, ..., K max .

[0143] It should be noted that at least two optimization algorithms are used to solve the multi-objective optimization model to obtain multiple recommended enterprise lists. The applicable solution algorithms include but are not limited to penalty function method, genetic algorithm, ant colony algorithm and simulated annealing algorithm, etc. For the recommended enterprise lists obtained by different algorithms, consistency checks are carried out pairwise, and the second repetition coefficient of each recommended enterprise list with the rest of the recommended enterprise lists is calculated; based on all the second repetition coefficients and a pre-set second repetition coefficient threshold, the target enterprise list of the designated area is determined.

[0144] In an optional implementation manner, determining the target enterprise list of the designated area according to all the second repetition coefficients and a preset second repetition coefficient threshold includes:

[0145] Counting the number of lists whose second repetition coefficient is greater than or equal to a preset second repetition coefficient threshold;

[0146] When the number of the lists is greater than or equal to two, two recommended enterprise lists with the largest second repetition coefficient are selected and merged to obtain a target enterprise list for the designated area;

[0147] When the number of the lists is less than two, all the recommended enterprise lists are merged, and the target enterprise list of the designated area is obtained based on the merged list.

[0148] Specifically, the second repetition coefficient threshold is set in advance. For example, the first repetition coefficient threshold can be set to 80%, which is not specifically limited here. The number of all lists whose second repetition coefficient is greater than or equal to the second repetition coefficient threshold is counted. When there are two or more lists whose second repetition coefficient is greater than or equal to the second repetition coefficient threshold, the two recommended enterprise lists with the largest second repetition coefficient are selected and merged to obtain the target enterprise list of the designated area.

[0149] When the number of lists whose second repetition coefficient is greater than or equal to the second repetition coefficient threshold is less than two, all recommended enterprise lists are merged, the frequency of appearance of each candidate enterprise in the merged list is counted, all candidate enterprises are arranged in order of frequency from large to small, and a preset number of candidate enterprises with the highest frequency are selected in turn to obtain a list of target enterprises in the designated area.

[0150] In a second aspect, an embodiment of the present invention provides a device for selecting a target enterprise for an investment project, see Figure 2 , which is a structural schematic diagram of an embodiment of a device for selecting a target enterprise for an investment promotion project provided by the present invention.

[0151] like Figure 2 As shown, the device comprises:

[0152] The data preparation module 21 is used to determine the set of enterprises to be selected according to the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area;

[0153] A matrix construction module 22 is used to obtain the enterprise data of all the enterprises to be selected in the enterprise set and a preset target indicator set, and when any target indicator in the enterprise data does not exist, convert all the target indicators into target indicator functions, and construct an evaluation matrix of the enterprise set to be selected based on all the target indicator functions;

[0154] A matrix weighting module 23 is used to weight the evaluation matrix using an entropy weight method and a CRITIC method to obtain a first weight and a second weight of each candidate enterprise in the evaluation matrix;

[0155] An enterprise score calculation module 24, configured to calculate an enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function;

[0156] The target enterprise selection module 25 is used to determine the target enterprise list of the designated area according to the enterprise scores of all the enterprises to be selected.

[0157] In an optional implementation, the data preparation module 21 is further used for:

[0158] Calculate the evaluation indicators of the industrial chain links; wherein the evaluation indicators of the industrial chain links include indicators related to industrial advantage, indicators related to industrial coreness and indicators related to policy fit;

[0159] Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area;

[0160] The calculation process of the policy fit index includes:

[0161] Obtaining the investment target text of the investment project in the designated area; wherein the investment target text includes an investment policy text and an investment planning text;

[0162] Performing data preprocessing on the investment promotion target text;

[0163] Use natural language processing (NLP) technology to extract keywords from the pre-processed investment target text;

[0164] According to the extracted keywords, the degree of fit of each industrial link of the industrial chain to be invested is calculated to obtain the policy fit index.

[0165] In an optional implementation, the enterprise rating calculation module 24 is further used to:

[0166] For each of the selected enterprises, a first enterprise score is calculated based on the first weight and the target indicator function, and a second enterprise score is calculated based on the second weight and the target indicator function.

[0167] In an optional implementation, the target enterprise selection module 25 is further used for:

[0168] All the enterprises to be selected are sorted in descending order according to the first enterprise scores, and starting from the enterprise with the highest first enterprise score, a preset number of enterprises to be selected are selected in turn to form a first enterprise list;

[0169] All the selected enterprises are sorted in descending order according to the second enterprise scores, and starting from the enterprise with the highest second enterprise score, a preset number of selected enterprises are selected in turn to form a second enterprise list;

[0170] Obtaining the number of repeated enterprises in the first enterprise list and the second enterprise list, and calculating a first repetition coefficient according to the number of repeated enterprises and a preset number of target enterprises;

[0171] Based on the first repetition coefficient, a list of target enterprises in the designated area is determined.

[0172] In an optional implementation, the target enterprise selection module 25 is further used for:

[0173] When the first repetition coefficient is greater than or equal to a preset first repetition coefficient threshold, merging the first enterprise list with the second enterprise list to obtain a target enterprise list of the designated area;

[0174] When the first repetition coefficient is less than the first repetition coefficient threshold, a comprehensive enterprise score is calculated according to the first enterprise score and the second enterprise score;

[0175] All the enterprises to be selected are sorted in descending order according to the comprehensive enterprise scores, and starting from the enterprise with the highest comprehensive enterprise score, a preset number of enterprises to be selected are selected in turn to form a list of target enterprises in the designated area.

[0176] In an optional implementation, the device further includes a multi-objective optimization module, and the multi-objective optimization module is used to:

[0177] When all target indicators in the enterprise data exist, a multi-objective optimization model of the candidate enterprise set is constructed based on the target indicator set;

[0178] Using at least two optimization algorithms to solve the multi-objective optimization model to obtain multiple recommended enterprise lists;

[0179] Calculate the second repetition coefficient of each of the recommended enterprise lists and the remaining recommended enterprise lists;

[0180] A list of target enterprises in the designated area is determined according to all the second repetition coefficients and a preset second repetition coefficient threshold.

[0181] In an optional implementation, the multi-objective optimization module is further used to:

[0182] Counting the number of lists whose second repetition coefficient is greater than or equal to a preset second repetition coefficient threshold;

[0183] When the number of the lists is greater than or equal to two, two recommended enterprise lists with the largest second repetition coefficient are selected and merged to obtain a target enterprise list for the designated area;

[0184] When the number of the lists is less than two, all the recommended enterprise lists are merged, and the target enterprise list of the designated area is obtained based on the merged list.

[0185] In a third aspect, an embodiment of the present invention provides an electronic device, see Figure 3 , which is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0186] like Figure 3 As shown, the device includes:

[0187] A memory 31, used for storing computer programs;

[0188] A processor 32, configured to execute the computer program;

[0189] Wherein, when the processor 32 executes the computer program, the method for selecting a target enterprise for an investment project as described in any of the above embodiments is implemented.

[0190] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 32 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0191] The processor 32 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0192] The memory 31 can be used to store the computer program and / or module, and the processor 32 realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory 31, and calling the data stored in the memory 31. The memory 31 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 31 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0193] It should be noted that the above electronic device includes, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 3 The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device, and may include more components than shown in the figure, or a combination of certain components, or different components.

[0194] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the method for selecting a target enterprise for an investment promotion project described in any of the above embodiments is implemented.

[0195] It should be understood that the present invention can implement all or part of the processes in the method for selecting the target enterprise of the above-mentioned investment promotion project, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the method for selecting the target enterprise of the above-mentioned investment promotion project can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0196] The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. It should be pointed out that for those skilled in the art, several equivalent obvious variations and / or equivalent substitutions can be made without departing from the technical principles of the present invention. These obvious variations and / or equivalent substitutions should also be regarded as the protection scope of the present invention.

Claims

1. A method for selecting target enterprises for investment projects, characterized in that: include: Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment needs of the industrial chain to be invested in the designated area; Acquire enterprise data and a preset target indicator set of all the enterprises to be selected in the enterprise set to be selected, and when any target indicator in the enterprise data does not exist, convert all the target indicators into target indicator functions, and construct an evaluation matrix of the enterprise set to be selected based on all the target indicator functions; The evaluation matrix is ​​weighted by using the entropy weight method and the CRITIC method to obtain the first weight and the second weight of each candidate enterprise in the evaluation matrix; Calculating the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function; A list of target enterprises in the designated area is determined based on the enterprise scores of all the selected enterprises.

2. The method for selecting target enterprises for investment promotion projects according to claim 1, characterized in that: The set of enterprises to be selected is determined according to the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area, including: Calculate the evaluation indicators of the industrial chain links; wherein the evaluation indicators of the industrial chain links include indicators related to industrial advantage, indicators related to industrial coreness and indicators related to policy fit; Determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment demand of the industrial chain to be invested in the designated area; The calculation process of the policy fit index includes: Obtaining the investment target text of the investment project in the designated area; wherein the investment target text includes an investment policy text and an investment planning text; Performing data preprocessing on the investment promotion target text; Use natural language processing (NLP) technology to extract keywords from the pre-processed investment target text; According to the extracted keywords, the degree of fit of each industrial link of the industrial chain to be invested is calculated to obtain the policy fit index.

3. The method for selecting target enterprises for investment promotion projects according to claim 1, characterized in that: The step of calculating the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function includes: For each of the selected enterprises, a first enterprise score is calculated based on the first weight and the target indicator function, and a second enterprise score is calculated based on the second weight and the target indicator function.

4. The method for selecting target enterprises for investment promotion projects as claimed in claim 3, characterized in that: Determining the list of target enterprises in the designated area according to the enterprise scores of all the selected enterprises includes: All the enterprises to be selected are sorted in descending order according to the first enterprise scores, and starting from the enterprise with the highest first enterprise score, a preset number of enterprises to be selected are selected in turn to form a first enterprise list; All the selected enterprises are sorted in descending order according to the second enterprise scores, and starting from the enterprise with the highest second enterprise score, a preset number of selected enterprises are selected in turn to form a second enterprise list; Obtaining the number of repeated enterprises in the first enterprise list and the second enterprise list, and calculating a first repetition coefficient according to the number of repeated enterprises and a preset number of target enterprises; Based on the first repetition coefficient, a list of target enterprises in the designated area is determined.

5. The method for selecting target enterprises for investment projects according to claim 4, characterized in that: Determining the list of target enterprises in the designated area based on the first repetition coefficient includes: When the first repetition coefficient is greater than or equal to a preset first repetition coefficient threshold, merging the first enterprise list with the second enterprise list to obtain a target enterprise list of the designated area; When the first repetition coefficient is less than the first repetition coefficient threshold, a comprehensive enterprise score is calculated according to the first enterprise score and the second enterprise score; All the enterprises to be selected are sorted in descending order according to the comprehensive enterprise scores, and starting from the enterprise with the highest comprehensive enterprise score, a preset number of enterprises to be selected are selected in turn to form a list of target enterprises in the designated area.

6. The method for selecting target enterprises for investment promotion projects according to claim 1, characterized in that: The method further comprises: When all target indicators in the enterprise data exist, a multi-objective optimization model of the candidate enterprise set is constructed based on the target indicator set; Using at least two optimization algorithms to solve the multi-objective optimization model to obtain multiple recommended enterprise lists; Calculate the second repetition coefficient of each of the recommended enterprise lists and the remaining recommended enterprise lists; A list of target enterprises in the designated area is determined according to all the second repetition coefficients and a preset second repetition coefficient threshold.

7. The method for selecting target enterprises for investment projects according to claim 6, characterized in that: Determining the target enterprise list of the designated area according to all the second repetition coefficients and a preset second repetition coefficient threshold comprises: Counting the number of lists whose second repetition coefficient is greater than or equal to a preset second repetition coefficient threshold; When the number of the lists is greater than or equal to two, two recommended enterprise lists with the largest second repetition coefficient are selected and merged to obtain a target enterprise list for the designated area; When the number of the lists is less than two, all the recommended enterprise lists are merged, and the target enterprise list of the designated area is obtained based on the merged list.

8. A device for selecting target enterprises for investment projects, characterized in that: include: The data preparation module is used to determine the set of enterprises to be selected based on the evaluation indicators of the industrial chain links and the investment needs of the industrial chain to be invested in the designated area; A matrix construction module, used to obtain enterprise data of all the enterprises to be selected in the enterprise set and a preset target indicator set, and when any target indicator in the enterprise data does not exist, convert all the target indicators into target indicator functions, and construct an evaluation matrix of the enterprise set to be selected based on all the target indicator functions; A matrix weighting module, used for weighting the evaluation matrix by using an entropy weight method and a CRITIC method, to obtain a first weight and a second weight of each candidate enterprise in the evaluation matrix; An enterprise score calculation module, used for calculating the enterprise score of each of the selected enterprises according to the first weight, the second weight and the target indicator function; The target enterprise selection module is used to determine the target enterprise list in the designated area according to the enterprise scores of all the enterprises to be selected.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program; Wherein, when the processor executes the computer program, the method for selecting a target enterprise for an investment promotion project as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for selecting a target enterprise for an investment promotion project according to any one of claims 1 to 7 is implemented.

Images