Incubation enterprise information recommendation method and device and electronic equipment

Abstract

The invention provides an incubation enterprise information recommendation method and device and electronic equipment, and belongs to the technical field of data processing, and the method comprises the steps: processing basic data of a target enterprise, and obtaining first data; matching the first data with information in an incubation platform resource database to generate a first recommendation scheme; optimizing the first recommendation scheme according to the influence factors to obtain a target recommendation scheme; the influence factors are parameters of which the demand relevancy with the target enterprise is greater than a preset threshold value; and recommending the target recommendation scheme to the target enterprise. According to the incubation enterprise information recommendation method and device and the electronic equipment provided by the invention, the multi-dimensional features of the enterprise are comprehensively considered, the matching degree of the recommended cooperative enterprise and the target enterprise is improved, and the diversified requirements of the enterprise in different development stages are effectively met.

Description

Technical Field

[0001] The present disclosure belongs to the field of data processing technology, and more specifically, relates to an incubation enterprise information recommendation method, device and electronic equipment. Background Art

[0002] In the current entrepreneurial incubation environment, many incubated enterprises face difficulties in obtaining resources and exploring cooperation opportunities during their development. The existing enterprise information recommendation model is often relatively simple, based on industry classification or keyword matching, lacking a comprehensive analysis of technical synergy and development stage adaptability, and cannot effectively combine user real-time behavior data to dynamically adjust the recommendation strategy. The recommendation results lack correlation evidence support, which affects the user's willingness to adopt. Newly settled enterprises are difficult to obtain effective recommendations due to insufficient data accumulation. The inability to fully consider the multi-dimensional characteristics of enterprises leads to a low match between the recommended cooperative enterprises and the target enterprises, and cannot effectively meet the diverse needs of enterprises at different stages of development. Summary of the invention

[0003] The purpose of the present disclosure is to provide a method and device for recommending incubation enterprise information, and electronic equipment, which comprehensively consider the multi-dimensional characteristics of enterprises, improve the matching degree between recommended cooperative enterprises and target enterprises, and effectively meet the diversified needs of enterprises at different development stages.

[0004] A first aspect of the embodiments of the present disclosure provides a method for recommending incubation enterprise information, comprising: Processing the basic data of the target enterprise to obtain first data; Matching the first data with the information in the incubation platform resource database to generate a first recommendation plan; optimizing the first recommendation plan according to the influencing factors to obtain a target recommendation plan; the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold; The target recommendation plan is recommended to the target enterprise.

[0005] Optionally, optimizing the first recommendation scheme according to the influencing factors to obtain a target recommendation scheme includes: Calculate the relevance between each enterprise in the first recommended solution and the target enterprise's needs based on the influencing factors; The enterprises in the first recommendation scheme are sorted according to the relevance between each enterprise and the needs of the target enterprise to obtain a target recommendation scheme.

[0006] Optionally, the calculating, based on the influencing factors, the relevance between each enterprise in the first recommendation scheme and the needs of the target enterprise includes: The correlation between each enterprise and the target enterprise's needs is calculated according to the first formula. The first formula is:

[0007] in, Indicates the first recommended solution i The relevance between the needs of individual enterprises and the target enterprise, i is a positive integer, N is the total number of enterprises in the first recommended solution, i = (1, 2, 3..., N ); is an adjustable parameter; n is the number of influencing factors; is an adjustable parameter used to control the logistic function The rate of change of The first recommended solution i The company in j The value of each influencing factor; For the target enterprises j The value of each influencing factor; For the j The threshold parameters corresponding to the influencing factors; is a natural constant.

[0008] Optionally, the incubation enterprise information recommendation method further includes: Determine the threshold parameter based on the basic threshold of the influencing factor, the similarity function and the data trend factor of the influencing factor; The similarity function is the first recommendation scheme. i The company in j The value of the influencing factor is related to the target enterprise in the j A function of the similarity between the values ​​of the influencing factors.

[0009] Optionally, recommending the target recommendation scheme to the target enterprise includes: Process the basic data of the target enterprise to obtain the characteristic value of the target enterprise; Determine the recommendation mode of the target recommendation plan according to the characteristic values ​​of the target enterprise; The target recommendation scheme is recommended to the target enterprise according to the recommendation mode.

[0010] Optionally, the recommendation mode includes a first recommendation mode and a second recommendation mode; the first recommendation mode and the second recommendation mode display data in different ways; The recommendation mode of determining the target recommendation scheme according to the characteristic value of the target enterprise includes: In response to the characteristic value of the target enterprise being less than a first threshold, determining the recommendation mode of the target recommendation scheme to be a first recommendation mode; In response to the characteristic value of the target enterprise being greater than or equal to the first threshold, determining the recommendation mode of the target recommendation solution as the second recommendation mode.

[0011] Optionally, it also includes: Process the feedback from the target enterprise and obtain the score value of the current recommended model; The recommendation mode is switched based on the current recommendation mode and the score value.

[0012] Optionally, switching the recommendation mode based on the current recommendation mode and the score value includes: If the current recommendation mode is the first recommendation mode and the score value is greater than the second threshold, the first recommendation mode is switched to the second recommendation mode; If the current recommendation mode is the second recommendation mode, and the score value is less than or equal to the second threshold, the second recommendation mode is switched to the first recommendation mode.

[0013] A second aspect of the embodiments of the present disclosure provides an incubation enterprise information recommendation device, characterized by comprising: A data processing unit, used for processing basic data of the target enterprise to obtain first data; A recommendation scheme generating unit is used to match the first data with the information in the incubation platform resource database to generate a first recommendation scheme; optimize the first recommendation scheme according to the influencing factors to obtain a target recommendation scheme; the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold; The recommendation unit is used to recommend the target recommendation plan to the target enterprise.

[0014] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned incubation enterprise information recommendation method when executing the computer program.

[0015] The beneficial effects of the incubation enterprise information recommendation method, device and electronic equipment provided by the embodiments of the present disclosure are: matching the first data with the information in the incubation platform resource database to generate a first recommendation plan; optimizing the first recommendation plan according to the influencing factors to obtain a target recommendation plan; the incubation enterprise information recommendation method, device and electronic equipment provided by the present disclosure comprehensively consider the multi-dimensional characteristics of the enterprise, improve the matching degree between the recommended cooperative enterprise and the target enterprise, and effectively meet the diversified needs of the enterprise at different development stages. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic diagram of a process for recommending incubation enterprise information provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of an incubation enterprise information recommendation device provided in an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0019] The incubation enterprise information recommendation method provided in the present disclosure is based on the research of the incubation platform. The incubation platform is an enterprise service platform integrating carrier management, carrier site management, carrier enterprise archive management, carrier cultivation management, performance evaluation management, enterprise service management, dual innovation map, and data large screen. The incubation platform adopts B / S architecture, and the display end uses personal computer (PC) end technology to realize interaction with users; the database uses MySQL (Structured Query Language, a management system for managing relational databases) or similar relational databases for data storage. The incubation platform is used to collect basic information of settled enterprises, including but not limited to the total output value and total tax payment of settled enterprises, incubation carrier data, enterprise intellectual property rights, enterprise qualifications, and enterprise category data. The incubation platform can also recommend enterprise information and policy and regulatory information according to the needs of enterprises. The incubation platform can also recommend financing according to the needs of enterprises; the financing enterprise list shows the name, financing amount, financing time, and financing source of the financing enterprise. The incubation platform can also view the site information of settled enterprises, including detailed floor and room, workstation information; the incubation platform can also view the detailed information of the contracted experts of the settled enterprises.

[0020] To make the purpose, technical solutions and advantages of the present disclosure clearer, the following will be combined with the attached Figure 1-3The following description will be given by way of specific examples.

[0021] Please refer to Figure 1 , Figure 1 A flowchart of a method for recommending incubation enterprise information provided by an embodiment of the present disclosure, the method comprising: S101: Process basic data of a target enterprise to obtain first data.

[0022] In this embodiment, before processing the basic data of the target enterprise, the basic data of the target enterprise is collected, the collected raw data is cleaned to remove duplicate, erroneous or incomplete data records, and the data is standardized to unify the data format to obtain the first data.

[0023] Among them, the target enterprise is the object of a certain enterprise in the incubation platform that hopes to establish a cooperative relationship with other enterprises; the basic data includes the enterprise's demand information, enterprise registration information, enterprise business information, enterprise financial information, enterprise technical information, etc. Registration information includes: enterprise name, registration address, establishment time, enterprise organizational structure information, such as department settings, staff size, management structure, etc.; enterprise business information includes core business scope, main product or service type, business development area, etc.; and enterprise financial information, such as registered capital, revenue, capital demand, etc.; enterprise technical information includes: intellectual property information, etc.; enterprise demand information includes technical demand information, financing demand information, policy demand information and office demand information, etc.

[0024] S102: Match the first data with the information in the incubation platform resource database to generate a first recommendation plan; optimize the first recommendation plan according to the influencing factors to obtain a target recommendation plan; the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold.

[0025] In this embodiment, the incubation platform resource database includes the basic information of the settled enterprises, the total output value and total tax paid by the settled enterprises, the incubation carrier data, the enterprise intellectual property rights, the enterprise qualifications, the enterprise category data, the policy and regulatory information, the name of the financing enterprise, the financing amount, the financing time, the financing source, the detailed information of the contracted experts of the settled enterprises, etc. The first recommendation plan is obtained by preliminarily screening out possible cooperation partners or resources based on the extensive matching of the target enterprise and other enterprises. The scope is relatively broad and the accuracy is limited. The target recommendation plan is obtained by adjusting the weights and re-screening the first recommendation plan based on more influencing factors, which is more in line with the actual needs of the target enterprise and has higher accuracy.

[0026] In this embodiment, the method for generating the first recommendation solution includes: The pre-processed first data is deeply matched with the information in the incubation platform resource database; in the matching process, advanced algorithm models, such as cosine similarity algorithm, Euclidean distance algorithm, etc., are used to compare the various attributes of the first data with the information in the incubation platform resource database one by one. Generate a first recommendation plan, obtain enterprise information that may have cooperation opportunities or resource complementarity with the target enterprise, and generate a recommended list of enterprise information. For example, use advanced algorithm models to compare the various attributes of the first data with the business information and financial information in the incubation platform resource database to determine the similarity and complementarity between the enterprise's business and the businesses of other enterprises in the database; analyze the matching degree between the capital demand and the capital support that can be provided by the enterprises on the platform, etc., and generate a recommended list of enterprise information sorted by matching degree.

[0027] In this embodiment, the first recommendation scheme is optimized according to the influencing factors to obtain the target recommendation scheme, where the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold.

[0028] Specifically, the influencing factors include: the development stage of the enterprise, industry trends, market competition situation, technology maturity, etc. The development stages of the enterprise include: start-up period, growth period, maturity period, etc. Different development stages have different resource requirements. The start-up period pays more attention to office space and start-up funds, the growth period focuses on market expansion and technology upgrade resources, and the maturity period focuses on industrial chain planning, etc.; industry trends include: emerging technology application trends and policy-oriented trends in the industry; market competition situation includes the competitive position of the target enterprise in the market, the business of the target enterprise competes with other enterprises, etc. This method optimizes the first recommendation plan according to the parameters whose relevance between the influencing factors and the needs of the target enterprise is greater than the preset threshold, and obtains the target recommendation plan; according to the relevance between the influencing factors and customer needs, the weights of the influencing factors can be generated, and according to the weights of the influencing factors, the enterprise information in the first plan is rearranged; and a recommendation table of enterprise information arranged according to the relevance to customer needs is obtained. This plan further considers the needs of enterprises, improves the matching degree between the recommended cooperative enterprises and the target enterprises, and effectively meets the diversified needs of enterprises at different development stages.

[0029] In this scheme, for each influencing factor, the weight of its influence on the target enterprise's needs is determined by combining quantitative analysis and expert evaluation, and then a weight of the influencing factor is generated according to the relevance between the influencing factor and customer needs. According to the weight of the influencing factor, the enterprise information in the first recommendation scheme is rearranged; and a recommendation table of enterprise information arranged according to the relevance to customer needs is obtained.

[0030] S103: Recommend the target recommendation plan to the target enterprise.

[0031] In this embodiment, the target recommendation plan is recommended to the target enterprise. The first recommendation mode is to directly view the target recommendation plan, and the second recommendation mode is not to directly view the target recommendation plan; directly viewing the target recommendation plan includes, the incubation platform pushes messages within the platform and displays on an exclusive recommendation page; not directly viewing the target recommendation plan includes: the incubation platform sends email notifications, sends links to the target recommendation plan, converts it into a document and directly pushes it, etc.; the carefully optimized recommendation plan is accurately presented to the target enterprise, making it convenient for the enterprise to obtain and view information about related enterprises. From the above, it can be concluded that the incubation enterprise information recommendation method provided by the present disclosure matches the first data with the information in the incubation platform resource database to generate a first recommendation plan; optimizes the first recommendation plan according to the influencing factors to obtain a target recommendation plan; comprehensively considers the multi-dimensional characteristics of the enterprise, improves the matching degree between the recommended cooperative enterprise and the target enterprise, and effectively meets the diversified needs of the enterprise at different development stages. The present disclosure also presents the optimized target recommendation plan to the target enterprise, making it convenient for the target enterprise to obtain and view the information of related enterprises.

[0032] In this embodiment, the first recommendation scheme is optimized according to the influencing factors to obtain a target recommendation scheme, including: Calculate the relevance between each enterprise in the first recommended solution and the target enterprise's needs based on the influencing factors; The enterprises in the first recommendation scheme are sorted according to the relevance between each enterprise and the needs of the target enterprise to obtain a target recommendation scheme.

[0033] Specifically, the correlation between each enterprise in the first recommended solution and the target enterprise's needs is calculated based on the influencing factors and the first formula; in the formula, in addition to considering the value of the influencing factor, the adjustable parameters and the threshold parameters corresponding to the influencing factors are also combined for comprehensive calculations. For industry trend influencing factors, by analyzing the technological innovation direction and policy support priorities of the industry in which the target enterprise is located, the performance of the enterprises in the first recommended solution in these aspects is scored and substituted into the first formula to calculate the correlation. For example, if the industry to which the target enterprise belongs is currently vigorously developing artificial intelligence technology, and a certain enterprise has outstanding performance in artificial intelligence R&D investment and achievement transformation, when calculating the correlation between a certain enterprise and the target enterprise's needs, the value of the influencing factor on technology is increased.

[0034] Each influencing factor is calculated according to the first formula to obtain the relevance between each enterprise in the first recommended solution and the target enterprise's needs. After obtaining the relevance between each enterprise and the target enterprise's needs, the enterprises in the first recommended solution are sorted in descending or ascending order according to the relevance value. In descending order, the enterprises with higher relevance values ​​are ranked higher, so that when the target enterprise views the recommended solution, the first thing it sees is the enterprise information that matches its needs the most.

[0035] During the sorting process, some special cases will also be considered. When the correlation values ​​of multiple enterprises are similar, their performance in terms of the needs of the target enterprise will be further compared, and enterprises with a high degree of match with the needs of the target enterprise will be prioritized. For example, for target enterprises that are in urgent need of funds, the performance of factors related to financial support of each enterprise will be prioritized, and the sorting order will be adjusted again to finally obtain the target recommendation plan. This disclosure is scientifically and orderly arranged according to the degree of closeness to the needs of the target enterprise, providing a more valuable reference for the target enterprise.

[0036] In this embodiment, the relevance between each enterprise in the first recommendation scheme and the target enterprise's needs is calculated based on the influencing factors, including: The correlation between each enterprise and the target enterprise's needs is calculated according to the first formula. The first formula is:

[0037] in, Indicates the first recommended solution i The relevance between the needs of individual enterprises and the target enterprise, i is a positive integer, N is the total number of enterprises in the first recommended solution, i = (1, 2, 3..., N ); is an adjustable parameter; n is the number of influencing factors, representing the total number of different factors considered to measure the relevance of the enterprise to the target enterprise's needs; is an adjustable parameter used to control the logistic function The rate of change, The larger the value, the steeper the logistic function curve, which means and The more sensitive the difference is to the function value; The first recommended solution i The company in j The value of each influencing factor; For the target enterprises j The value of each influencing factor; For the j The threshold parameters corresponding to the influencing factors; is a natural constant. The value range is [0, 1], which is used to balance the impact of the two parts of the calculation results in the formula on the final correlation; when When it approaches 1, the calculation results of the first part have a greater impact on the correlation; when When it approaches 0, the calculation results of the second part have a greater impact on the correlation.

[0038] In this embodiment, the incubation enterprise information recommendation method further includes: Determine the threshold parameter based on the basic threshold of the influencing factor, the similarity function and the data trend factor of the influencing factor; The similarity function is the first recommendation scheme. i The company in j The value of the influencing factor is related to the target enterprise in the j A function of the similarity between the values ​​of the influencing factors.

[0039] Specifically, the threshold corresponding to the influencing factor is determined according to the second formula; the second formula is:

[0040] in, For the j The threshold parameters corresponding to the influencing factors; For the j The initial basic threshold of each influencing factor can be set based on business experience or preliminary data analysis to provide a basic value for threshold adjustment; N is the total number of enterprises in the first recommended solution; To measure the first recommended solution i The company in j The value of the influencing factor With the target enterprise j The value of the influencing factor For example, cosine similarity, the inverse of the Euclidean distance, etc. can be used. If the inverse of the Euclidean distance is used, = ,in yes and The Euclidean distance of is an adjustable exponential parameter used to control the decay speed of the threshold adjustment by similarity. The larger it is, the more significant the effect of similarity on the threshold, that is, when the overall similarity is low, the threshold drops faster. For the j The data trend factor of an influencing factor can be calculated by time series analysis and other methods, such as using linear regression to fit the changing trend of the influencing factor over time (if the data has time attributes), which can be the absolute value of the regression coefficient. It reflects the intensity of the changing trend of the influencing factor. The stronger the trend, Specifically, the present disclosure comprehensively considers the basic thresholds of the above influencing factors, the total number of enterprises in the first recommended solution, the function for measuring similarity, the adjustable index parameters and the data trend factors of the influencing factors, and finally determines the accurate threshold parameters corresponding to each influencing factor, so as to provide a basis for more accurate calculation of the relevance between the enterprise and the target enterprise's needs in the future.

[0041] In this embodiment, recommending the target recommendation plan to the target enterprise includes: Process the basic data of the target enterprise to obtain the characteristic value of the target enterprise; Determine the recommendation mode of the target recommendation plan according to the characteristic values ​​of the target enterprise; Recommend the target recommendation plan to the target enterprise according to the recommendation model.

[0042] Specifically, the basic data of the target enterprise is processed to obtain the characteristic value of the target enterprise. Data dimensionality reduction and feature extraction techniques such as principal component analysis and factor analysis are used to convert the target enterprise's scale, reputation in the market and other data into characteristic values ​​of the target enterprise with the core characteristics of the enterprise.

[0043] Specifically, first, the collected raw data is standardized to eliminate the impact of different indicator dimensions and make all data on the same comparable scale; the third formula is used to calculate the enterprise characteristic value. The third calculation formula is E

[0044] in, E is the enterprise characteristic value, and its value range needs to be further mapped to the interval [0,1] through linear transformation; The principal component analysis obtained m principal component eigenvalues; M is the number of principal components involved in the calculation; In principal component analysis m Adaptive weights corresponding to the eigenvalues ​​of the principal components; The factor analysis results are t factor eigenvalues, T is the number of factors involved in the calculation; In factor analysis, t Adaptive weights corresponding to the eigenvalues ​​of each factor; It is a regularization coefficient used to prevent overfitting. Its value range is usually between (0, 1). The optimal value can be determined by cross-validation and other methods. is a regularization term, which is used to constrain the size of the eigenvalue and make the model more stable.

[0045] In this embodiment, the recommendation mode includes a first recommendation mode and a second recommendation mode; the first recommendation mode and the second recommendation mode display data in different ways; The recommendation model of the target recommendation scheme is determined according to the characteristic values ​​of the target enterprise, including: In response to the characteristic value of the target enterprise being less than a first threshold, determining the recommendation mode of the target recommendation scheme to be a first recommendation mode; In response to the characteristic value of the target enterprise being greater than or equal to the first threshold, determining the recommendation mode of the target recommendation solution as the second recommendation mode.

[0046] Specifically, the first recommendation mode is to recommend directly viewing the target recommendation plan, and the second recommendation mode is not to directly view the target recommendation plan; directly viewing the target recommendation plan includes that the incubation platform uses the incubation platform's online quick communication module to push recommendation information in the form of pop-up reminders and short message summaries through platform message push and exclusive recommendation page display, so that enterprises can quickly browse. Not directly viewing the target recommendation plan includes: the incubation platform sends email notifications, sends links to the target recommendation plan, converts it into a document and directly pushes it, etc.; it also includes organizing online one-on-one explanation meetings at the same time, and experts interpret the recommendation plan for the target enterprise to ensure that the target enterprise can fully and deeply understand the recommended content.

[0047] In this embodiment, the incubation enterprise information recommendation method further includes: Process the feedback from the target enterprise and obtain the score value of the current recommended model; Switch the recommendation mode based on the current recommendation mode and rating value; Switching the recommendation mode based on the current recommendation mode and rating value includes: If the current recommendation mode is the first recommendation mode and the score value is greater than the second threshold, the first recommendation mode is switched to the second recommendation mode; If the current recommendation mode is the second recommendation mode, and the score value is less than or equal to the second threshold, the second recommendation mode is switched to the first recommendation mode.

[0048] Specifically, the target enterprise's first feedback information on the target recommendation plan, the second feedback information on the recommendation model, and the target enterprise's behavior information in the process of using the recommendation service are collected; The first feedback information of the target recommendation plan includes the target enterprise's evaluation of the recommended content itself, such as the matching degree between the recommended enterprise and its own needs, the accuracy and completeness of the recommended information; the second feedback information of the recommendation mode includes whether the message push is timely, whether the display effect of the recommended target plan is good, etc.; the behavior information includes the number of clicks on the recommended enterprise details, the stay time on the recommendation page, etc.; The Analytic Hierarchy Process (AHP) was used to construct a comprehensive scoring system; A hierarchical model is established, with the target layer set as the recommendation model score, and the criterion layer including three dimensions: recommendation content matching, recommendation model satisfaction, and behavior data feedback; Construct a judgment matrix through expert scoring or target enterprise questionnaires; Calculate the eigenvector and maximum eigenvalue of the judgment matrix, normalize the eigenvector, and obtain the weight of each dimension; and calculate the score value based on the score and weight of each dimension.

[0049] If the current recommendation mode is the first recommendation mode and the score is greater than the second threshold, it means that the target enterprise has a high acceptance of the current intuitive recommendation mode and has a need for further in-depth understanding; the first recommendation mode is switched to the second recommendation mode to provide the target enterprise with more detailed and comprehensive recommendation content to meet the target enterprise's needs for in-depth exploration of potential partners.

[0050] Switching from the second recommendation mode: If the current recommendation mode is the second recommendation mode, and the score is less than or equal to the second threshold, it may indicate that the target enterprise is troubled by the overly detailed and complex recommendation content, or believes that the match between the recommendation content and its own needs does not meet expectations. At this time, switch the second recommendation mode to the first recommendation mode and use the intuitive recommendation mode.

[0051] The disclosed embodiment, through this dynamic recommendation mode switching mechanism, can continuously optimize the recommendation service according to the real-time feedback and demand changes of the target enterprise, and improve the recommendation effect and user satisfaction.

[0052] Corresponding to the incubation enterprise information recommendation method in the above embodiment, Figure 2 This is a structural block diagram of an incubation enterprise information recommendation device provided by an embodiment of the present disclosure. For the sake of convenience, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The incubation enterprise information recommendation device 20 includes: a data processing unit 21, a recommendation scheme generating unit 22 and a recommendation unit 23. Among them, the data processing unit 21 is used to process the basic data of the target enterprise to obtain the first data; the recommendation plan generation unit 22 is used to match the first data with the information in the incubation platform resource database to generate a first recommendation plan; the first recommendation plan is optimized according to the influencing factors to obtain the target recommendation plan; the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold; the recommendation unit 23 is used to recommend the target recommendation plan to the target enterprise.

[0053] In one embodiment of the present disclosure, the recommendation scheme generating unit 22 is specifically configured to: Calculate the relevance between each enterprise in the first recommended solution and the target enterprise's needs based on the influencing factors; The enterprises in the first recommendation scheme are sorted according to the relevance between each enterprise and the needs of the target enterprise to obtain a target recommendation scheme.

[0054] In one embodiment of the present disclosure, the recommendation scheme generating unit 22 is specifically configured to: The relevance between the needs of each enterprise and the target enterprise is calculated according to the first formula.

[0055] In this embodiment, the first formula is:

[0056] in, Indicates the first recommended solution i The relevance between the needs of individual enterprises and the target enterprise, i is a positive integer, N is the total number of enterprises in the first recommended solution, i = (1, 2, 3, ..., N ); is an adjustable parameter; n is the number of influencing factors; is an adjustable parameter used to control the logistic function The rate of change of The first recommended solution i The company in j The value of each influencing factor; For the target enterprises j The value of each influencing factor; For the j The threshold parameters corresponding to the influencing factors; is a natural constant.

[0057] In one embodiment of the present disclosure, the recommendation scheme generating unit 22 is specifically configured to: Determine the threshold parameter based on the basic threshold of the influencing factor, the similarity function and the data trend factor of the influencing factor; Among them, the similarity function is the first recommendation scheme i The company in j The value of the influencing factor is related to the target enterprise in the j A function of the similarity between the values ​​of the influencing factors.

[0058] In one embodiment of the present disclosure, the recommendation unit 23 is specifically used to: process the basic data of the target enterprise to obtain the characteristic value of the target enterprise; Determine the recommendation mode of the target recommendation plan according to the characteristic values ​​of the target enterprise; Recommend the target recommendation plan to the target enterprise according to the recommendation model.

[0059] In one embodiment of the present disclosure, the recommendation unit 23 is specifically configured to: In response to the characteristic value of the target enterprise being less than a first threshold, determining the recommendation mode of the target recommendation scheme to be a first recommendation mode; In response to the characteristic value of the target enterprise being greater than or equal to the first threshold, determining the recommendation mode of the target recommendation solution as the second recommendation mode.

[0060] The recommendation mode includes a first recommendation mode and a second recommendation mode; the first recommendation mode and the second recommendation mode display data in different ways; In one embodiment of the present disclosure, the recommendation unit 23 is specifically configured to: Process the feedback from the target enterprise and obtain the score value of the current recommended model; Switch the recommendation mode based on the current recommendation mode and rating value.

[0061] In one embodiment of the present disclosure, the recommendation unit 23 is specifically configured to: If the current recommendation mode is the first recommendation mode and the score value is greater than the second threshold, the first recommendation mode is switched to the second recommendation mode; If the current recommendation mode is the second recommendation mode, and the score value is less than or equal to the second threshold, the second recommendation mode is switched to the first recommendation mode.

[0062] The incubation enterprise information recommendation device 20 provided in the embodiment of the present disclosure matches the first data with the information in the incubation platform resource database to generate a first recommendation plan; optimizes the first recommendation plan according to the influencing factors to obtain a target recommendation plan; the incubation enterprise information recommendation method, device and electronic equipment provided by the present disclosure comprehensively consider the multi-dimensional characteristics of the enterprise, improve the matching degree between the recommended cooperative enterprise and the target enterprise, and effectively meet the diversified needs of the enterprise at different development stages.

[0063] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each unit in the above-mentioned device embodiments, such as Figure 2 The functions of units 21 to 23 are shown.

[0064] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be 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 the processor may also be any conventional processor, etc.

[0065] The input device 302 may include a touch panel, a fingerprint sensor (for collecting fingerprint information of the user and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0066] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0067] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the incubation enterprise information recommendation method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0068] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, wherein the program instructions are executed by a processor to implement all or part of the processes in the above-mentioned embodiment method, and may also be completed by instructing the relevant hardware through the computer program, wherein the computer program may be stored in a computer-readable storage medium, and wherein the computer program may be executed by the processor to implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the contents contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signal and telecommunication signal.

[0069] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0070] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0072] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0073] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0074] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0075] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for recommending incubation enterprise information, characterized in that: include: Processing the basic data of the target enterprise to obtain first data; Matching the first data with information in the incubation platform resource database to generate a first recommendation plan; Optimizing the first recommendation scheme according to the influencing factors to obtain a target recommendation scheme; the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold; The target recommendation plan is recommended to the target enterprise.

2. The incubation enterprise information recommendation method according to claim 1, characterized in that: The step of optimizing the first recommendation scheme according to the influencing factors to obtain the target recommendation scheme includes: Calculate the relevance between each enterprise in the first recommended solution and the target enterprise's needs based on the influencing factors; The enterprises in the first recommendation scheme are sorted according to the relevance between each enterprise and the needs of the target enterprise to obtain a target recommendation scheme.

3. The incubation enterprise information recommendation method according to claim 2, characterized in that: The calculating, based on the influencing factors, the relevance between each enterprise in the first recommendation scheme and the needs of the target enterprise includes: The correlation between each enterprise and the target enterprise's needs is calculated according to the first formula. The first formula is: in, Indicates the first recommended solution i The relevance between the needs of individual enterprises and the target enterprise, i is a positive integer, N is the total number of enterprises in the first recommended solution, i = (1, 2, 3, ..., N ); is an adjustable parameter; n is the number of influencing factors; is an adjustable parameter used to control the logistic function The rate of change of The first recommended solution i The company in j The value of each influencing factor; For the target enterprises j The value of each influencing factor; For the j The threshold parameters corresponding to the influencing factors; is a natural constant.

4. The incubation enterprise information recommendation method according to claim 3, characterized in that: Also includes: Determine the threshold parameter based on the basic threshold of the influencing factor, the similarity function and the data trend factor of the influencing factor; The similarity function is the first recommendation scheme. i The company in j The value of the influencing factor is related to the target enterprise in the j A function of the similarity between the values ​​of the influencing factors.

5. The incubation enterprise information recommendation method according to claim 1, characterized in that: The step of recommending the target recommendation scheme to the target enterprise comprises: Process the basic data of the target enterprise to obtain the characteristic value of the target enterprise; Determine the recommendation mode of the target recommendation plan according to the characteristic values ​​of the target enterprise; The target recommendation scheme is recommended to the target enterprise according to the recommendation mode.

6. The incubation enterprise information recommendation method according to claim 5, characterized in that: The recommendation mode includes a first recommendation mode and a second recommendation mode; The first recommendation mode and the second recommendation mode display data in different ways; The recommendation mode of determining the target recommendation scheme according to the characteristic value of the target enterprise includes: In response to the characteristic value of the target enterprise being less than a first threshold, determining the recommendation mode of the target recommendation scheme to be a first recommendation mode; In response to the characteristic value of the target enterprise being greater than or equal to the first threshold, determining the recommendation mode of the target recommendation solution as the second recommendation mode.

7. The incubation enterprise information recommendation method according to claim 6, characterized in that: Also includes: Process the feedback from the target enterprise and obtain the score value of the current recommended model; The recommendation mode is switched based on the current recommendation mode and the score value.

8. The incubation enterprise information recommendation method according to claim 7, characterized in that: Switching the recommendation mode based on the current recommendation mode and the score value includes: If the current recommendation mode is the first recommendation mode and the score value is greater than the second threshold, the first recommendation mode is switched to the second recommendation mode; If the current recommendation mode is the second recommendation mode, and the score value is less than or equal to the second threshold, the second recommendation mode is switched to the first recommendation mode.

9. An incubation enterprise information recommendation device, characterized in that: include: A data processing unit, used for processing basic data of the target enterprise to obtain first data; A recommendation scheme generating unit, used for matching the first data with the information in the incubation platform resource database to generate a first recommendation scheme; Optimizing the first recommendation scheme according to the influencing factors to obtain a target recommendation scheme; the influencing factors are parameters whose relevance to the needs of the target enterprise is greater than a preset threshold; The recommendation unit is used to recommend the target recommendation plan to the target enterprise.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images