Scientific research facility sharing management method and system based on artificial intelligence

Abstract

The invention provides a scientific research facility sharing management method and system based on artificial intelligence, and relates to the technical field of equipment sharing management, and the method comprises the steps: building a first facility information base maintaining all scientific research facility feature portraits according to the first facility renting information of a first lessor; the method comprises the following steps: firstly, generating a first renting party portrait for a plurality of scientific research facility renting parties belonging to a first area together with a first renting party, secondly, determining a plurality of target scientific research popularity information according to potential first renting party information and latest scientific research popularity information, and finally, determining a plurality of target scientific research popularity information according to the target scientific research popularity information. And formulating a first facility scheduling strategy according with the latest scientific research direction based on the matching degree between the multiple pieces of target scientific research popularity information and the first facility information base. Through the technical scheme of the invention, big data analysis can be carried out on scientific research themes and scientific research strength related to a scientific research facility lessor and a leasing party in the same area, and a first facility scheduling strategy meeting actual requirements is formulated in combination with latest scientific research popularity information.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment sharing management, and in particular, relates to a scientific research facility sharing management method and system based on artificial intelligence. Background Art

[0002] At present, in order to promote the development of science and technology, sharing resources through sharing scientific research facilities has become a mainstream trend in the field of scientific research. However, how to improve the matching degree between the lessors and lessees of scientific research facilities is still a technical problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a scientific research facility sharing management method and system based on artificial intelligence to solve the technical problem of low demand matching between lessors and borrowers of scientific research facilities in the prior art.

[0004] This application proposes a scientific research facility sharing management method based on artificial intelligence, which includes: S1: Establish a first facility information database based on the first facility rental information of the first lessor; the first lessor refers to any institution in the first area that is responsible for the shared management of scientific research facilities; the first facility rental information includes a plurality of first basic information and a plurality of first usage record information; wherein the first facility information database includes a plurality of first facility portraits and first lessor portraits; S2: establishing a first lessee information database according to the first lessee information in the first area; the first lessee information refers to information used to characterize scientific research direction and scientific research capability; wherein the first lessee information database includes a plurality of first lessee portraits; S3: Determine a first leased device profile according to the first scientific research popularity information and the first lessee information database; S4: Determine a first facility scheduling strategy according to the first facility information database and the first leased equipment portrait.

[0005] Preferably, S1 comprises the following sub-steps: S11: acquiring a plurality of first basic information and a plurality of first usage record information according to each first facility of the first lessor; S12: determining a plurality of first facility portraits according to a plurality of the first basic information and a plurality of the first usage record information; S13: Clustering the plurality of first facility portraits to determine a first lessor portrait; S14: Obtain the first facility information database according to the multiple first facility portraits and the first lessor portraits.

[0006] Preferably, S2 comprises the following sub-steps: S21: Acquire information of a first lessee in the first area; S22: inputting the information of the first renters into a first renter portrait determination model respectively to obtain a plurality of first renter portraits; S23: Obtaining the first lessee information database according to the plurality of the first lessee portraits.

[0007] Preferably, S3 includes the following sub-steps: S31: Classify the first crawled information by field, and obtain multiple first scientific research field information; S32: Analyze each of the first scientific research field information to obtain a plurality of first scientific research popularity information; S33: screening out the first scientific research popularity information that meets the first preset condition, thereby determining a plurality of target scientific research popularity information; S34: Determine the first rental equipment profile based on the multiple target scientific research popularity information.

[0008] Preferably, S4 includes the following sub-steps: S41: Calculate a first similarity between the first leased device portrait and the first lessor portrait, and when the first similarity is higher than a first preset value, proceed to S42, otherwise end; S42: calculating the second similarities between the first rental equipment portrait and the plurality of first facility portraits one by one, and determining the scientific research facility corresponding to the first facility portrait whose second similarity is higher than a second preset value as the target scientific research facility; S43: Determine a first facility scheduling strategy for the plurality of target scientific research facilities.

[0009] This application also proposes an artificial intelligence-based scientific research facility sharing management system, which is used to implement the above-mentioned artificial intelligence-based scientific research facility sharing management method.

[0010] The present application proposes a method and system for sharing and managing scientific research facilities based on artificial intelligence, which relates to the technical field of equipment sharing and management. First, based on the first facility leasing information of the first lessor, a first facility information database is established to maintain characteristic portraits of all scientific research facilities. Secondly, first lessee portraits are generated for multiple scientific research facility lessees belonging to the first area with the first lessor. Next, based on the potential first lessee information and the latest scientific research heat information, multiple target scientific research heat information is determined. Finally, based on the matching degree between the multiple target scientific research heat information and the first facility information database, a first facility scheduling strategy that conforms to the latest scientific research direction is formulated. Through the technical solution of the present application, big data analysis can be conducted on the scientific research topics and scientific research strengths involved in the lessors and lessees of scientific research facilities in the same area, and combined with the latest scientific research heat information, a first facility scheduling strategy that meets actual needs can be formulated. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0012] Figure 1 It is an execution flow chart of a scientific research facility sharing management method based on artificial intelligence in the present invention.

[0013] Figure 2 It is an execution flow chart of determining the first rental equipment portrait of the present invention. DETAILED DESCRIPTION

[0014] 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.

[0015] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0016] The following is a detailed description of an artificial intelligence-based scientific research facility sharing management method and system of the present invention.

[0017] This embodiment proposes a scientific research facility sharing management method based on artificial intelligence. The specific method flow is as follows: Figure 1As shown, the specific steps include: S1: Establish a first facility information database according to the first facility leasing information of the first lessor.

[0018] The first lessor refers to any institution responsible for the shared management of scientific research facilities in the first region. The first region may be a province, a city, or any other administrative division. For example, the first lessor may be a university, a scientific research institute, or other institution responsible for the management of scientific research facilities.

[0019] Through this step, the first facility information database can be established based on the historical scientific research facility rental information of the first lessor, the usage information of the scientific research facilities during the rental process, etc., so as to make good decisions for the subsequent more scientific and reasonable scheduling of scientific research facilities.

[0020] The S1 comprises the following sub-steps: S11: acquiring a plurality of first basic information and a plurality of first usage record information according to each first facility of the first lessor.

[0021] Each of the first lessors usually maintains several scientific research facilities for rent by the lessee. Therefore, in order to analyze the characteristics of the scientific research facilities maintained by the first lessor, it is necessary to obtain the basic information and usage record information of each scientific research facility, wherein each first facility corresponds to one piece of the first basic information and multiple pieces of the first usage record information.

[0022] The first basic information includes the type of the first facility, the main scientific research topics involved, service life and maintenance information, etc. The first basic information can be used to analyze the use type and use status of the first facility.

[0023] The first usage record information refers to the historical rental record of the first facility, mainly including the number of rentals, the average rental duration per rental, the renter information, etc. The renter information may involve the renter's scientific research theme, relevant scientific research facility rental information, and scientific research strength information. Specifically, the scientific research facility rental information may include the renter's historical scientific research facility rental information; the scientific research strength information may include the number of papers published by the historical renter, the number of patent applications, the number of marketed products, etc.

[0024] S12: Determine a plurality of first facility portraits according to a plurality of first basic information and a plurality of first usage record information.

[0025] In this step, for each of the first facilities, it is necessary to generate a corresponding first facility portrait using the first basic information and multiple first usage record information corresponding to the first facility.

[0026] Preferably, in the generation stage of the first facility portrait, relatively representative features can be selected from the first basic information and the first usage record information as labels for the first facility portrait. For example, the usage period indicated in the first basic information is 0, and the historical renter indicated in the first usage record information has strong scientific research capabilities.

[0027] Preferably, in the generation stage of the first facility portrait, the first basic information and the first plurality of usage record information may be input into the first facility portrait generation model, so as to output the first facility portrait through the machine learning model. In the training stage of the first facility portrait generation model, the rental information of historical scientific research facilities may be used as sample data, the basic information and usage record information of the scientific research facilities in the sample data may be used as input, and the portrait thereof may be used as output, so as to mine the association relationship between the basic information, usage record information and facility portrait through big data.

[0028] S13: Clustering the multiple first facility portraits to determine the first lessor portrait.

[0029] Generally speaking, if a scientific research facility lessor needs multiple types of scientific research facilities under the same scientific research theme during the process of conducting a scientific research, therefore, if a scientific research facility lessor has multiple types of scientific research facilities under one scientific research theme, it is more likely to be selected by the lessee to establish a leasing relationship.

[0030] In this step, clustering is mainly performed based on the labels such as scientific research theme, scientific research facility category, service life and maintenance information in the first facility portrait. Specifically, the above information can be extracted from each of the first facility portraits to form a four-dimensional vector, such as [integrated circuit image sensor, integrating sphere, 2 years, 4 times]. Of course, other dimensions can also be used to form a multi-dimensional vector to characterize the scientific research category and usage of the scientific research facility.

[0031] In the specific implementation process of clustering, the four-dimensional vectors corresponding to the multiple first facility portraits can be clustered using the K-MEANS algorithm, and a number of labels can be extracted from the obtained cluster centers to form the first lessor portrait.

[0032] S14: Obtain the first facility information database according to the multiple first facility portraits and the first lessor portraits.

[0033] The first facility information base is a database file, which includes multiple data items. Each data item corresponds to a first facility owned by the first lessor, and specifically may record the first facility portrait of the first facility and other related information.

[0034] The first facility information database also includes a portrait of the first lessor, which is used to characterize the characteristics of the first lessor.

[0035] S2: Establish a first lessee information database according to the first lessee information in the first area.

[0036] In S1, the first facility information database for characterizing the characteristics of its scientific research facilities has been established with the first lessor as the main body. In this step, a first lessee information database needs to be established based on the information of multiple potential first lessees in the same area as the first lessor to prepare for subsequent leasing matching.

[0037] The S2 comprises the following sub-steps: S21: Acquire information about a first lessee in the first area.

[0038] Generally speaking, scientific research facilities are valuable instruments, and there is a risk of damage if they are transported over long distances, so priority is given to matching lessors and lessees in the same region. Specifically, as long as they are recognized as having certain scientific research capabilities, they can be identified as the first lessee.

[0039] The first lessee information mainly includes information related to the first lessee's historical academic and scientific research achievements and the research and development direction in the future. Specifically, the first lessee information may include the first lessee's research and development personnel information, published academic achievement information and publicity and reporting information within a preset time range, and the above information may be presented in the form of text description.

[0040] S22: Inputting the first renter information into a first renter portrait determination model respectively to obtain a plurality of first renter portraits.

[0041] In this step, one or more pieces of the first renter information in the form of text description may be input into the first renter portrait determination model, so as to obtain the first renter portrait corresponding to each of the first renters.

[0042] The first tenant portrait determination model is preferably a large language model, which intervenes in the general large language model to define the requirements and standards for semantic extraction, thereby achieving semantic analysis and label extraction of the first tenant information, and finally combining the extracted multiple labels into the first tenant portrait. For example, the first tenant portrait may include the following three labels: the number of R&D personnel, the scientific research topics involved in academic achievements, and the scientific research topics involved in publicity reports.

[0043] S23: Obtaining the first lessee information database according to the plurality of the first lessee portraits.

[0044] The first facility information base is a database file, which includes a plurality of data items, each of which corresponds to a first lessee, and specifically may record a portrait of the first lessee and other relevant information of the first lessee.

[0045] S3: Determine a first leased device profile according to the first scientific research popularity information and the first lessee information database.

[0046] In order to enable the lessor of scientific research facilities to timely dispatch and purchase scientific research facilities according to the scientific research needs within a preset time period in the future, so as to meet the scientific research needs of the lessee to the greatest extent, it is necessary to analyze the scientific research popularity information within the preset time period in the future in this step, and combine the first lessee information database obtained in S3 to determine the first leased equipment portrait used to characterize the scientific research facility needs in the first area.

[0047] S3 includes the following sub-steps, see Figure 2 : S31: Classify the first crawled information by field to obtain multiple first scientific research field information.

[0048] In this step, scientific research hotspot information is obtained from various scientific research websites through a web crawler. The scientific research hotspot information is the first crawled information, and the scientific research hotspot information may include scientific research news and media news in a certain field. Next, the scientific research hotspot information is classified according to the scientific research field. Specifically, the acquired scientific research news and media news can be classified according to the scientific research field, such as integrated circuits, biomedicine and other fields. In the specific classification operation, the semantic classification model in the prior art can be adopted, that is, the scientific research hotspot information is semantically analyzed, and the scientific research hotspot information is classified according to the extracted field keywords. Therefore, each of the first scientific research field information includes multiple scientific research news information and media news information corresponding to a scientific research field.

[0049] S32: Analyze each of the first scientific research field information to obtain multiple first scientific research popularity information.

[0050] In this step, each of the first scientific research field information is analyzed from multiple dimensions to obtain the first scientific research heat information used to characterize the research heat of the scientific research field. For example, the first scientific research heat information may include the number of annual paper publications, the number of academic achievements cited, the number of fund projects, the media discussion heat value, etc.

[0051] In the first scientific research popularity information, the number of papers published, the number of citations of the academic achievements and the number of fund projects can be obtained through data statistical analysis, and the media discussion heat value can use the topic heat determination method in the existing technology, which is not specifically limited here.

[0052] S33: Filter out the first scientific research heat information that meets the first preset condition, thereby determining multiple target scientific research heat information.

[0053] Among them, when screening, various types of data in the first scientific research heat information can be integrated to obtain a comprehensive score, so as to sort the first scientific research heat information according to the comprehensive score. For example, the comprehensive score can be determined by weighted summation, such as giving a higher weight to the media discussion heat value and giving relatively lower weights to the other three indicators. The specific calculation method can be set as needed.

[0054] After calculating the comprehensive scores corresponding to the multiple first scientific research heat information, they can be sorted in descending order according to the comprehensive scores, so that the top several first scientific research heat information can be determined as the target scientific research heat information.

[0055] S34: Determine the first rental equipment profile based on the multiple target scientific research popularity information.

[0056] Since each target scientific research heat information corresponds to a specified scientific research field, multiple target scientific research fields can be determined based on multiple target scientific research heat information, and the first rental equipment portrait can be determined based on multiple target scientific research fields. For example, the first rental equipment portrait may include: integrated circuits; biomedicine. The above is only an illustrative example, and the granularity of the division of scientific research fields can be further refined.

[0057] S4: Determine a first facility scheduling strategy according to the first facility information database and the first leased equipment portrait.

[0058] In step S3, the characteristics of scientific research equipment with a higher possibility of being rented have been determined based on the target scientific research popularity information. In order to enable the lessor of scientific research facilities to meet the demand for scientific research equipment rental in a timely manner in the future, it is necessary to perform similarity matching between the first facility information database and the first rented equipment portrait, and to dispatch the scientific research equipment in a timely manner when the matching degree does not meet the preset requirements.

[0059] The S4 comprises the following sub-steps: S41: Calculate a first similarity between the first leased device portrait and the first lessor portrait. When the first similarity is higher than a first preset value, proceed to S41, otherwise end.

[0060] The first rental equipment portrait and the first lessor portrait respectively reflect the potential rented equipment and the scientific research fields involved by the first lessor. When the matching degree between the two meets the preset needs, the first lessor is required to carry out facility scheduling in the form of purchase or facility scheduling to meet the rental demand. When the matching degree between the two is too low, equipment scheduling may not be considered due to excessive cost.

[0061] S42: Calculate the second similarities between the first rental equipment portrait and the plurality of first facility portraits one by one, and determine the scientific research facilities corresponding to the first facility portraits whose second similarities are higher than a second preset value as target scientific research facilities.

[0062] Through this step, multiple target scientific research facilities with a high degree of matching with the first leased equipment profile can be obtained.

[0063] The first similarity and the second similarity are both obtained by calculating the Euclidean distance.

[0064] S43: Determine a first facility scheduling strategy for the plurality of target scientific research facilities.

[0065] The first facility scheduling strategy may specifically include the following aspects: for multiple target scientific research facilities, no leasing schedule may be made within a preset time period in the future to provide space for potential lessees to lease them; timely maintenance of multiple target scientific research facilities may be carried out to meet leasing needs; and other scientific research facilities belonging to the same scientific research theme as the multiple target scientific research facilities may be purchased to meet potential leasing needs.

[0066] This application also proposes an artificial intelligence-based scientific research facility sharing management system, which is used to execute the above-mentioned artificial intelligence-based scientific research facility sharing management method.

[0067] The application proposes a method and system for sharing and managing scientific research facilities based on artificial intelligence, which relates to the field of equipment sharing technology. First, based on the first facility leasing information of the first lessor, a first facility information database is established to maintain characteristic portraits of all scientific research facilities. Secondly, first lessee portraits are generated for multiple scientific research facility lessees belonging to the first area with the first lessor. Next, based on the potential first lessee information and the latest scientific research heat information, multiple target scientific research heat information is determined. Finally, based on the matching degree between the multiple target scientific research heat information and the first facility information database, a first facility scheduling strategy that conforms to the latest scientific research direction is formulated. Through the technical solution of the application, big data analysis can be conducted on the scientific research topics and scientific research strengths involved in the lessors and lessees of scientific research facilities in the same area, and combined with the latest scientific research heat information, a first facility scheduling strategy that meets actual needs can be formulated.

[0068] The above description is only a preferred embodiment of the present invention, so all equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A scientific research facility sharing management method based on artificial intelligence, characterized in that: The method includes: S1: Establish a first facility information database based on the first facility rental information of the first lessor; the first lessor refers to any institution in the first area that is responsible for the shared management of scientific research facilities; the first facility rental information includes a plurality of first basic information and a plurality of first usage record information; wherein the first facility information database includes a plurality of first facility portraits and first lessor portraits; S2: establishing a first lessee information database according to the first lessee information in the first area; the first lessee information refers to information used to characterize scientific research direction and scientific research capability; wherein the first lessee information database includes a plurality of first lessee portraits; S3: determining a first leased device portrait according to first scientific research popularity information and the first lessee information database; the first scientific research popularity information is used to characterize the research popularity of a specified scientific research field; S4: Determine a first facility scheduling strategy according to the first facility information database and the first leased equipment portrait.

2. According to the artificial intelligence-based scientific research facility sharing management method of claim 1, it is characterized in that: The S1 comprises the following sub-steps: S11: acquiring a plurality of first basic information and a plurality of first usage record information according to each first facility of the first lessor; S12: determining a plurality of first facility portraits according to a plurality of the first basic information and a plurality of the first usage record information; S13: Clustering the plurality of first facility portraits to determine a first lessor portrait; S14: Obtain the first facility information database according to the multiple first facility portraits and the first lessor portraits.

3. According to claim 2, a method for sharing and managing scientific research facilities based on artificial intelligence is characterized in that: The S2 comprises the following sub-steps: S21: Acquire information of a first lessee in the first area; S22: inputting the information of the first renters into a first renter portrait determination model respectively to obtain a plurality of first renter portraits; S23: Obtaining the first lessee information database according to the plurality of the first lessee portraits.

4. According to claim 3, a method for sharing and managing scientific research facilities based on artificial intelligence is characterized in that: The S3 comprises the following sub-steps: S31: Classifying the first crawled information by field to obtain a plurality of first scientific research field information; the first crawled information is scientific research hotspot information obtained from various scientific research websites; each of the first scientific research field information includes a plurality of scientific research news information and media news information corresponding to a scientific research field; S32: Analyze each of the first scientific research field information to obtain a plurality of first scientific research popularity information; S33: screening out the first scientific research popularity information that meets the first preset condition, thereby determining a plurality of target scientific research popularity information; S34: Determine the first rental equipment profile based on the multiple target scientific research popularity information.

5. According to claim 4, a method for sharing and managing scientific research facilities based on artificial intelligence is characterized in that: The S4 comprises the following sub-steps: S41: Calculate a first similarity between the first leased device portrait and the first lessor portrait, and when the first similarity is higher than a first preset value, proceed to S42, otherwise end; S42: calculating the second similarities between the first rental equipment portrait and the plurality of first facility portraits one by one, and determining the scientific research facility corresponding to the first facility portrait whose second similarity is higher than a second preset value as the target scientific research facility; S43: Determine a first facility scheduling strategy for the plurality of target scientific research facilities.

6. An artificial intelligence-based scientific research facility sharing management system, used to implement an artificial intelligence-based scientific research facility sharing management method as described in any one of claims 1 to 5.

Images