Resource push method, system, terminal device and readable storage medium

Abstract

The embodiment of the present application provides a resource push method, system, terminal device and readable storage medium, the method comprising: respectively obtaining the R&D needs of the enterprise and the teacher information of the college, the information of each teacher includes at least four resource objects; according to each demand keyword in the R&D needs and each resource object of each teacher, obtaining the matching score of each resource object of each teacher; assigning weights to each resource object and using the weight value of each resource object and the matching score to calculate the total matching score of the corresponding teacher; sorting the total matching scores of all teachers and pushing the information of the first preset number of teachers with the highest matching degree to the enterprise. This method can quickly extract suitable teacher resources from the huge teaching staff of colleges and universities and push them to enterprises, so that matching teachers can participate in the production and R&D of the enterprise. Compared with manual resource screening, it can greatly improve the efficiency of teacher resource search.

Description

Technical Field

[0001] The present application relates to the field of database technology, and in particular to a resource push method, system, terminal device and readable storage medium. Background Art

[0002] In the institutions that connect with enterprises or other similar enterprise service centers and research institutions, there are often enterprises that want university teachers to participate in production and research and development to empower the enterprise. The reason is that enterprises focus on production and have good implementation capabilities, but lack R&D strength. Enterprises often encounter various technical problems that need to be solved in production, especially when developing new products and expanding new businesses. They urgently need university teachers to use their cutting-edge research results to provide guidance or cooperate in R&D in various ways.

[0003] Colleges and universities have abundant teacher resources. According to statistics in 2020, there are 1.602 million full-time teachers in colleges and universities across the country. However, it is not easy to obtain teacher resources in a narrow production field from this huge amount of teacher resources, because some university teachers / professors tend to focus on basic research or cutting-edge technologies, and there is a disconnection between the technology research and development for corporate production. Summary of the invention

[0004] In view of this, embodiments of the present application provide a resource push method, system, terminal device, and readable storage medium.

[0005] In a first aspect, an embodiment of the present application provides a resource push method, including:

[0006] Respectively obtain the R&D needs of the enterprise and the teacher information of the university, wherein the R&D needs include at least one demand keyword, and the teacher information of each teacher includes at least four resource objects;

[0007] According to each demand keyword in the R&D demand and each resource object of each teacher, a matching score of each resource object of each teacher is obtained;

[0008] Assigning a weight to each resource object of the corresponding teacher, and calculating the total matching score of the corresponding teacher using the weight value of each resource object and the matching score;

[0009] The total matching scores of all teachers are sorted, and information of a preset number of teachers with the highest matching degree is pushed to the enterprise.

[0010] In some embodiments, the at least four resource objects include the teacher's project, paper, research field and title, and the resource objects of the project, paper and research field are described by corresponding keyword lists;

[0011] The matching score of each resource object of each teacher is obtained according to each demand keyword in the R&D demand and each resource object of each teacher, including:

[0012] Match each demand keyword in the R&D demand with the keyword list of the current teacher's project, the paper, and the research field to calculate the corresponding matching score;

[0013] According to the respective matching scores of the current teacher's projects, papers and research fields, the matching score of the current teacher's professional title is calculated according to a preset formula.

[0014] In some embodiments, the keyword list includes at least one keyword sublist; matching each requirement keyword in the R&D requirement with the respective keyword lists of the current teacher's project, the paper, and the research field to calculate the corresponding matching score includes:

[0015] Traverse each of the keyword sublists of the current item resource object of the current teacher to search for each requirement keyword in the research and development requirement;

[0016] If all the required keywords are found in the same keyword sublist, the traversal is stopped, and the matching score of the current resource object is set to a first preset value;

[0017] If all the required keywords are found in different keyword sublists, the matching score of the current resource object is set to a second preset value, which is smaller than the first preset value;

[0018] If some of the required keywords are found in all the keyword sublists, the matching score of the current resource object is calculated according to the number of found keywords and the total number of the required keywords;

[0019] If any required keyword is not found in all the keyword sublists, each of the keyword sublists is expanded with similar words to obtain a corresponding extended keyword sublist, and the search continues from each extended keyword sublist;

[0020] If all the required keywords are found in the same extended keyword sublist, a matching score of the current resource object is calculated according to the first approximation coefficient and the first preset value;

[0021] If all the required keywords are found in different extended keyword sublists, the matching score of the current resource object is calculated according to the first approximation coefficient and the second preset value;

[0022] If some of the required keywords are found in all the extended keyword sublists, the matching score of the current resource object is calculated according to the number of found keywords, the total number of the required keywords and the first approximation coefficient.

[0023] In some embodiments, the resource push method further includes:

[0024] If any demand keyword is still not found in all the extended keyword sublists, then each demand keyword in the R&D demand is expanded with similar words to obtain at least one demand similar word for each demand keyword;

[0025] If any one of the demand approximate words corresponding to all the demand keywords is found in the same extended keyword sublist, the traversal is stopped, and the matching score of the current resource object is calculated according to the second approximate coefficient, the first approximate coefficient and the first preset value;

[0026] If any one of the demand approximation words corresponding to all the demand keywords is found in different extended keyword sublists, the matching score of the current resource object is calculated according to the second approximation coefficient, the first approximation coefficient and the second preset value;

[0027] If any demand approximate word corresponding to each of the partial demand approximate words is found in all the extended keyword sublists, the matching score of the current item resource object is calculated based on the number of found words, the total number of the demand keywords, the first approximate coefficient and the second approximate coefficient.

[0028] In some embodiments, the first approximation coefficient has a value range of 0.6 to 0.8, the second approximation coefficient has a value range of 0.7 to 0.9, and the second approximation coefficient is greater than the first approximation coefficient.

[0029] In some embodiments, the matching score of the job title is calculated according to the following formula:

[0030] ;

[0031] in, Respectively represent the matching scores of the title, the project, the paper and the research field; It is the preset job title coefficient.

[0032] In some embodiments, the weight values ​​of the project, the paper, the research field, and the title satisfy the following relationship:

[0033] The weight value of the adjacent item resource object is not less than a first preset multiple, and the ratio of the weight value of the project to the weight value of the title is not less than a second preset multiple, wherein the second preset multiple is greater than the first preset multiple.

[0034] In a second aspect, an embodiment of the present application provides a resource push system, including:

[0035] A resource acquisition module, used to respectively acquire the R&D needs of enterprises and the teacher information of colleges and universities, wherein the R&D needs include at least one demand keyword, and the teacher information of each teacher includes at least four resource objects;

[0036] A resource matching module, used to obtain a matching score for each resource object of each teacher according to each demand keyword in the R&D demand and each resource object of each teacher;

[0037] A matching scoring module is used to assign a weight to each resource object of the corresponding teacher, and calculate the total matching score of the corresponding teacher using the weight value of each resource object and the matching score;

[0038] The resource push module is used to sort the total matching scores of all teachers and push the information of the first preset number of teachers with the highest matching degree to the enterprise.

[0039] In a third aspect, an embodiment of the present application provides a terminal device, the terminal device comprising a processor and a memory, the memory storing a computer program, and the processor being used to execute the computer program to implement the above-mentioned resource push method.

[0040] In a fourth aspect, an embodiment of the present application provides a readable storage medium storing a computer program, which implements the above-mentioned resource push method when executed on a processor.

[0041] The embodiments of the present application have the following beneficial effects:

[0042] The resource push method of the embodiment of the present application obtains the R&D needs of the enterprise and the teacher information of the university respectively, and constructs a data list of multiple different resources of each teacher, and then matches the R&D needs with the different resource objects of the teacher and assigns different weights to the importance of different resource objects, and then calculates the total matching score of each teacher, and selects the appropriate teacher information to recommend to the enterprise. This method uses keyword extraction and weight assignment, automatic matching and other technologies to quickly find suitable teacher resources from the huge teaching staff of the university and push them to the enterprise. Compared with the solution of manually searching and screening suitable resources from the huge teaching staff, it can greatly improve the efficiency of resource search, save labor and time costs, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A first flow chart of the resource push method according to an embodiment of the present application is shown;

[0045] Figure 2 A second flow chart of the resource push method according to an embodiment of the present application is shown;

[0046] Figure 3 A third flow chart of the resource push method according to an embodiment of the present application is shown;

[0047] Figure 4 A fourth flow chart of the resource push method according to an embodiment of the present application is shown;

[0048] Figure 5 A schematic diagram of the structure of a resource push system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0050] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0051] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0052] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0053] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0054] Example 1

[0055] Figure 1 The first flow chart of the resource push method of the embodiment of the present application is shown. Exemplarily, the resource push method includes:

[0056] Step S100, respectively obtaining the R&D needs of the enterprise and the teacher information of the university.

[0057] Generally speaking, enterprises often encounter various technical problems that need to be solved during production, such as the research and development of new products, solving technical troubleshooting on actual production lines, performance optimization, etc. The solution to these technical problems is the corresponding R&D needs of the enterprise.

[0058] In one embodiment, for the R&D needs of an enterprise, corresponding scientific and technological terms can be extracted from the actual needs and stored in the form of a list or array, such as list1{keyword1, keyword2, ...}, so that the computer can recognize it. For example, assuming that the enterprise's needs are to optimize the performance of a fluff pulp crusher, the needs are input into the corresponding scientific and technological term library for scientific and technological term extraction, and the specific R&D needs that can be extracted are: list1{'fluff pulp', 'crusher'}, etc.

[0059] In this embodiment, the scientific and technological terms may be databases of standardized terms covering different technical fields published by authoritative organizations or platforms. The selection of specific databases is not limited here, and users can choose according to actual conditions.

[0060] As for the information of college teachers, for example, it can be automatically captured from the corresponding web pages through tools such as crawlers, etc., which is not limited here. Among them, the name of each teacher is used as a label to collect data such as the projects, papers, patents, teaching subjects, research fields and titles that the teacher participates in, and then the teacher information is divided according to different resource objects.

[0061] In this embodiment, the resource objects of the teacher include at least four items, namely, professional title, research field, project, and paper. Among them, for resource objects such as research field, project, and paper, the scientific and technological terminology segmentation and keyword extraction can be performed on the corresponding projects, papers, and the specific contents involved in the research field, and stored in the form of corresponding arrays or lists. Among them, if a teacher participates in many projects or publishes many papers, different projects and papers can be further distinguished and stored in the form of sub-arrays or sub-lists. It should be understood that in actual operation, if there are other information such as patents and teaching subjects, they can be further classified into these four items. For example, the name of the patent can be put into the project array, and the teaching subject can be included in the research field array.

[0062] For example, a teacher has three projects, namely: a. A natural science foundation project: "The ability, representation and stability of EEG and eye movement signals in multimodal emotion recognition"; b. A project topic "Research on visual cognitive coding and brain information fusion mechanism"; c. A foundation project "Research on key technologies for fatigue monitoring based on frontal electrooculography". Then the resource object projects[] about the teacher's project can include three projects {project[0], project[1], project[2]}. Furthermore, each project contains its own scientific and technological terms. For example, project[0] can be described as {'EEG', 'Eye movement signal', 'multimodal', 'emotion recognition'}, which can be obtained from the scientific and technological term corpus through word segmentation and keyword extraction. It can be understood that for the huge teacher resources, by using computers with the help of corresponding data processing technologies such as word segmentation and keyword extraction to automatically obtain, not only can the time cost of manual extraction be greatly reduced, but also the error rate and partial data omission can be reduced.

[0063] It is worth noting that for these resource objects, if there are some missing contents, when filling the missing data, the data can be filled in according to the importance of these resource objects. For example, the experience of the projects undertaken by the teacher is the most important, so only a smaller value can be used to fill in the gap. The papers are generally more theoretical, which is less important than the projects undertaken, but higher than the macro "research field", so an intermediate value can be taken.

[0064] Step S200, obtaining a matching score for each resource object of each teacher according to each demand keyword in the R&D demand and each resource object of each teacher.

[0065] For each teacher, this embodiment calculates the matching score of each resource object according to each demand keyword in the R&D demand. Taking the above four resource objects as an example, in one embodiment, Figure 2As shown, the above step S200 includes sub-steps S201 and S202:

[0066] Sub-step S201, matches each demand keyword in the R&D demand with the respective keyword lists of the current teacher's projects, papers, and research fields to calculate the corresponding matching scores.

[0067] For the three resource objects of project, paper, and research field, a keyword search method will be used to determine the matching degree between each teacher's resource information and the R&D demand, and obtain the matching score of each resource object of each teacher. For the resource object of professional title, in addition to considering the importance of the professional title itself, this embodiment will also calculate its matching score in combination with the matching of the first three items, as shown in sub-step S202.

[0068] like Figure 3 As shown, the above step S201 includes sub-steps S2011 to S2014:

[0069] Sub-step S2011, traverse each keyword sub-list of the current item resource object of the current teacher to search for each requirement keyword in the R&D requirement.

[0070] The following uses the project as the current resource object as an example to illustrate the determination of its matching score. It can be understood that for papers, research fields, etc., the principle types are different, so the description is not repeated.

[0071] Exemplarily, when the teacher is involved in multiple projects, the keyword list corresponding to the project will contain multiple keyword sub-lists, such as {project[0], project[1], project[2], ...}, etc. Then, each keyword sub-list in the project projects[] can be searched to see whether the various demand keywords in the R&D demand exist. If so, it means that the demand keyword is matched successfully.

[0072] Sub-step S2012: If all the required keywords are found in the same keyword sub-list, the traversal is stopped and the matching score of the current resource object is set to a first preset value.

[0073] For example, if all the keywords in the R&D requirement are found in a certain project[i], it means that the project in which the teacher is involved is very consistent with the R&D requirement. At this time, the traversal of other sub-projects will be stopped, and the matching score of the teacher's project resource object will be directly set to the first preset value, which can improve the efficiency of the entire search. For example, if the highest score is 1, the first preset value can be assigned to 1, and of course it can be set to other values, as long as it is higher than the scores of other subsequent matching situations, which is not limited here.

[0074] Sub-step S2013: if all the required keywords are found in different keyword sub-lists, the matching score of the current resource object is set to a second preset value, which is smaller than the first preset value.

[0075] For example, if keyword1 and keyword2 are found in project[0], and keyword3, keyword4, etc. are found in project[3], that is, all the required keywords are found in different sub-projects, then the matching score of the teacher's project resource object can be set to a second preset value, for example, it can be set to 0.9, etc., and can be adjusted accordingly according to the first matching situation mentioned above.

[0076] Sub-step S2014: if some of the required keywords are found in all the keyword sub-lists, the matching score of the current resource object is calculated according to the number of found keywords and the total number of required keywords.

[0077] If some of the required keywords are found in all sub-projects, the matching score of the project can be calculated according to the following formula : =(m) / n; where m is the number of demand keywords found and n is the total number of demand keywords.

[0078] The above cases are all situations where all or part of the required keywords are found. If any required keyword is not found in all keyword sublists, this embodiment will expand the words in these keyword sublists according to the corresponding scientific and technological terminology library and then search again. This can avoid missing some useful teacher resources due to inconsistent term descriptions, especially for some less popular technical fields.

[0079] Sub-step S2015, if any required keyword is not found in all keyword sub-lists, each keyword sub-list is expanded with similar words to obtain a corresponding expanded keyword sub-list, and the search is continued from each expanded keyword sub-list.

[0080] Sub-step S2016: If all the required keywords are found in the same extended keyword sub-list, the matching score of the current resource object is calculated according to the first approximation coefficient and the first preset value.

[0081] Sub-step S2017: if all the required keywords are found in different extended keyword sub-lists, the matching score of the current resource object is calculated according to the first approximation coefficient and the second preset value.

[0082] Sub-step S2018, if some of the required keywords are found in all the extended keyword sub-lists, the matching score of the current resource object is calculated according to the number of found keywords, the total number of required keywords and the first approximation coefficient.

[0083] For example, we can expand all keywords in projects[] to get Lprojects[], and then search for keywords in list1 in Lprojects[]. Similarly, if all keywords are found in a certain Lproject[i], the matching score of the project is =a* ,in is the first approximate coefficient, and a is the first preset value. For example, The value range of can be 0.6~0.8. Alternatively, if all keywords are found in Lprojects[], the matching score of the project is =b* , where b is the second preset value. Alternatively, if only some of the required keywords are found in all the extended keyword sublists, the matching score of the item may be: =(m) / n* .

[0084] As an optional solution, if no required keywords are found after similar expansion of the teacher's resource object, this embodiment will further expand the required keywords and use the expanded required keywords for matching. It can be understood that for some Chinese keywords obtained by including English translation, the problem of failure to match can be avoided by similar word expansion.

[0085] like Figure 4 As shown, for sub-step S2015, sub-steps S2019 to S2022 may also be included:

[0086] Sub-step S2019, if any demand keyword is still not found in all the extended keyword sub-lists, then each demand keyword in the R&D demand is expanded with similar words to obtain at least one demand similar word for each demand keyword.

[0087] It can be understood that during the search process, for a demand keyword, there are usually one or more similar words. When there are multiple similar words, during the matching process, as long as any one of these similar words can be found, it is considered to match the demand keyword.

[0088] Sub-step S2020, if any demand approximate word corresponding to all demand keywords is found in the same extended keyword sub-list, stop traversal and calculate the matching score of the current resource object according to the second approximate coefficient, the first approximate coefficient and the first preset value.

[0089] Sub-step S2021, if any one of the demand approximate words corresponding to all the demand keywords is found in different extended keyword sub-lists, then the matching score of the current resource object is calculated according to the second approximate coefficient, the first approximate coefficient and the second preset value.

[0090] Sub-step S2022, if any demand approximate word corresponding to each of the partial demand approximate words is found in all the extended keyword sub-lists, the matching score of the current item resource object is calculated according to the number of found words, the total number of demand keywords, the first approximate coefficient and the second approximate coefficient.

[0091] For example, if all are found in a certain Lproject[i], then the matching score is =a* * ,in, is the second approximation coefficient. In one embodiment, The value range of can be 0.7~0.9, and there are > Alternatively, if all are found in different Lproject[i], the match can be =b* * For other cases, if some keywords are found in all Lprojects, if only m are found, the matching score is =m / n* * .

[0092] It can be understood that for thesis[] and research field[], similar calculation processes as above can be performed to obtain the matching scores of the paper and the matching scores of the research field respectively. It should be understood that thesis[] often has an English title, which can be converted into Chinese by machine translation before the above processing.

[0093] Sub-step S202, based on the matching scores of the current teacher's projects, papers and research fields, the matching score of the current teacher's professional title is calculated according to a preset formula.

[0094] In one implementation, the teacher's professional title matching score may be calculated according to the following formula:

[0095] ;

[0096] in, is the preset job title coefficient, , , and Represent the matching scores of title, project, paper and research field respectively.

[0097] Generally, the professional titles of college teachers can be divided into four levels: professor, associate professor, lecturer and teaching assistant, or they can also be senior, associate senior, intermediate, junior, etc. The professional title coefficients of different levels of professional titles are different, for example, they can be taken in the range of 0.1~0.9. Generally, the higher the level, the larger the corresponding professional title coefficient. It can be understood that if the matching scores of the previous projects, papers, etc. are high, the score of the professional title will be relatively high, which can make the teacher higher in the ranking. Conversely, if the matching scores of the previous items are low, the score of the professional title will be affected and the ranking will be lowered accordingly, so as to avoid the ranking of teachers with high professional titles who are actually unmatched.

[0098] Step S300, weights are assigned to each resource object of the corresponding teacher, and the total matching score of the corresponding teacher is calculated using the weight value and matching score of each resource object.

[0099] In this embodiment, by assigning weights to the various resource objects of the teacher and adding influence constraints between the various parameters to highlight the importance of the projects undertaken by the teacher, and taking into account factors such as papers, research fields and professional titles for comprehensive evaluation, more suitable teacher resources can be obtained.

[0100] In one embodiment, the weight values ​​of the above-mentioned projects, papers, research fields and titles may satisfy the following relationship: the weight ratio between adjacent resource objects is not less than a first preset multiple, and the ratio of the weight of the project to the weight of the title is not less than a second preset multiple, wherein the second preset multiple is greater than the first preset multiple. For example, the first preset multiple may be 1.25, and the second preset multiple may be 2.5, etc. Specifically, if the ten-point system is taken as an example, the allocation method is: projects are 10, papers are 8, research fields are 6, and titles are 4. Other allocation methods may also be used, such as 9, 7, 5, 3, etc. It can be understood that in addition to the above-mentioned ten-point allocation method, percentage system and other methods may also be used, which are not limited here.

[0101] Furthermore, the following formula can be used to calculate the teacher's total matching score:

[0102] Y= * + * + * + * ;

[0103] Among them, Y represents the total matching score of the teacher, are the weights of projects, papers, research fields and titles respectively. , , and They are the matching scores for projects, papers, research fields and professional titles respectively.

[0104] Step S400, after sorting the total matching scores of all teachers from large to small, the information of the first preset number of teachers is pushed to the enterprise.

[0105] For each teacher, the above processing steps are used to obtain their respective total matching scores. Exemplarily, the total matching scores of all teachers can be sorted from large to small or from small to large. If they are arranged from small to large, the information of the last few teachers with the highest matching scores in the sequence will be fed back to the enterprise; if they are arranged from large to small, the information of the top few teachers will be fed back to the enterprise, so as to further solve the problem that the enterprise cannot accurately and quickly search for matching teacher resources.

[0106] The resource push method proposed in this embodiment can help enterprises or university-enterprise docking departments or project undertaking departments to quickly find matching teachers so that they can participate in actual R&D and production, thereby opening up the key links of industry-university-research cooperation and achieving teacher resource matching. Compared with manual resource search and further screening and matching solutions, this method can greatly improve resource search efficiency and save a lot of labor costs and time.

[0107] Example 2

[0108] Please refer to Figure 5 Based on the method of the above embodiment 1, this embodiment proposes a resource push system 100. By way of example, the resource push system 100 includes the following modules:

[0109] The resource acquisition module 110 is used to respectively acquire the R&D needs of the enterprise and the teacher information of the university, where the R&D needs include at least one demand keyword, and the teacher information of each teacher includes at least four resource objects;

[0110] The resource matching module 120 is used to obtain a matching score for each resource object of each teacher according to each demand keyword in the R&D demand and each resource object of each teacher;

[0111] The matching scoring module 130 is used to assign weights to each resource object of the corresponding teacher, and calculate the total matching score of the corresponding teacher using the weight value of each resource object and the matching score;

[0112] The resource push module 140 is used to sort the total matching scores of all teachers and push the information of the first preset number of teachers with the highest matching degree to the enterprise.

[0113] It can be understood that the device of this embodiment corresponds to the method of the above-mentioned embodiment 1, and the options in the above-mentioned embodiment 1 are also applicable to this embodiment, so they are not described repeatedly here.

[0114] The present application also provides a terminal device, which may be, for example, a computer, etc. Exemplarily, the terminal device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program, so that the terminal device executes the functions of each module in the resource push method or the resource push device.

[0115] The present application also provides a readable storage medium for storing the computer program used in the above-mentioned terminal device.

[0116] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0118] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0119] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A resource push method, characterized in that: include: Respectively obtain the R&D needs of enterprises and the teacher information of colleges and universities, wherein the R&D needs include at least one demand keyword, and the teacher information of each teacher includes at least four resource objects; the at least four resource objects include the teacher's project, paper, research field and title, and the resource objects of the project, paper and research field are all described by corresponding keyword lists; Match each demand keyword in the R&D demand with the respective keyword lists of the current teacher's project, the paper, and the research field to calculate the corresponding matching score; calculate the matching score of the current teacher's professional title according to a preset formula based on the respective matching scores of the current teacher's project, the paper, and the research field; Assigning a weight to each resource object of the corresponding teacher, and calculating the total matching score of the corresponding teacher using the weight value of each resource object and the matching score; Sorting the total matching scores of all teachers, and pushing information of a preset number of teachers with the highest matching scores to the enterprise; The keyword list includes at least one keyword sublist; and each requirement keyword in the R&D requirement is matched with the respective keyword lists of the current teacher's project, the paper, and the research field to calculate the corresponding matching score, including: Traverse each of the keyword sublists of the current item resource object of the current teacher to search for each requirement keyword in the research and development requirement; If all the required keywords are found in the same keyword sublist, the traversal is stopped, and the matching score of the current resource object is set to a first preset value; If all the required keywords are found in different keyword sublists, the matching score of the current resource object is set to a second preset value, which is smaller than the first preset value; If some of the required keywords are found in all the keyword sublists, the matching score of the current resource object is calculated according to the number of found keywords and the total number of the required keywords; If any required keyword is not found in all the keyword sublists, each of the keyword sublists is expanded with similar words to obtain a corresponding extended keyword sublist, and the search continues from each extended keyword sublist; If all the required keywords are found in the same extended keyword sublist, a matching score of the current resource object is calculated according to the first approximation coefficient and the first preset value; If all the required keywords are found in different extended keyword sublists, the matching score of the current resource object is calculated according to the first approximation coefficient and the second preset value; If some of the required keywords are found in all the extended keyword sublists, the matching score of the current resource object is calculated according to the number of the found keywords, the total number of the required keywords and the first approximation coefficient; If any demand keyword is still not found in all the extended keyword sublists, then each demand keyword in the R&D demand is expanded with similar words to obtain at least one demand similar word for each demand keyword; If any one of the demand approximate words corresponding to all the demand keywords is found in the same extended keyword sublist, the traversal is stopped, and the matching score of the current resource object is calculated according to the second approximate coefficient, the first approximate coefficient and the first preset value; If any one of the demand approximation words corresponding to all the demand keywords is found in different extended keyword sublists, the matching score of the current resource object is calculated according to the second approximation coefficient, the first approximation coefficient and the second preset value; If any demand approximate word corresponding to each of the partial demand approximate words is found in all the extended keyword sublists, the matching score of the current item resource object is calculated based on the number of found words, the total number of the demand keywords, the first approximate coefficient and the second approximate coefficient.

2. The resource push method according to claim 1, characterized in that: The value range of the first approximation coefficient is 0.6~0.8, the value range of the second approximation coefficient is 0.7~0.9, and the second approximation coefficient is greater than the first approximation coefficient.

3. The resource push method according to claim 1, characterized in that: The matching score of the job title is calculated according to the following formula; ； in, , , and Respectively represent the matching scores of the title, the project, the paper and the research field; It is the preset job title coefficient.

4. The resource push method according to any one of claims 1 to 3, characterized in that: The weight values ​​of the project, the paper, the research field and the title satisfy the following relationship: The weight value of the adjacent item resource object is not less than a first preset multiple, and the ratio of the weight value of the project to the weight value of the title is not less than a second preset multiple, wherein the second preset multiple is greater than the first preset multiple.

5. A resource push system, characterized in that: include: A resource acquisition module is used to respectively acquire the R&D needs of enterprises and the teacher information of colleges and universities, wherein the R&D needs include at least one demand keyword, and the teacher information of each teacher includes at least four resource objects; the at least four resource objects include the teacher's project, paper, research field and title, and the resource objects of the project, paper and research field are all described by corresponding keyword lists; A resource matching module is used to match each demand keyword in the R&D demand with the respective keyword lists of the current teacher's project, the paper, and the research field to calculate the corresponding matching score; according to the respective matching scores of the current teacher's project, the paper, and the research field, the matching score of the current teacher's professional title is calculated according to a preset formula; A matching scoring module is used to assign a weight to each resource object of the corresponding teacher, and calculate the total matching score of the corresponding teacher using the weight value of each resource object and the matching score; A resource push module, used to sort the total matching scores of all teachers, and push information of a preset number of teachers with the highest matching degree to the enterprise; The keyword list includes at least one keyword sublist; the resource matching module is used to match each demand keyword in the R&D demand with the respective keyword lists of the current teacher's project, the paper, and the research field to calculate the corresponding matching score, specifically including: Traverse each of the keyword sublists of the current item resource object of the current teacher to search for each requirement keyword in the research and development requirement; If all the required keywords are found in the same keyword sublist, the traversal is stopped, and the matching score of the current resource object is set to a first preset value; If all the required keywords are found in different keyword sublists, the matching score of the current resource object is set to a second preset value, which is smaller than the first preset value; If some of the required keywords are found in all the keyword sublists, the matching score of the current resource object is calculated according to the number of found keywords and the total number of the required keywords; If any required keyword is not found in all the keyword sublists, each of the keyword sublists is expanded with similar words to obtain a corresponding extended keyword sublist, and the search continues from each extended keyword sublist; If all the required keywords are found in the same extended keyword sublist, a matching score of the current resource object is calculated according to the first approximation coefficient and the first preset value; If all the required keywords are found in different extended keyword sublists, the matching score of the current resource object is calculated according to the first approximation coefficient and the second preset value; If some of the required keywords are found in all the extended keyword sublists, the matching score of the current resource object is calculated according to the number of the found keywords, the total number of the required keywords and the first approximation coefficient; If any demand keyword is still not found in all the extended keyword sublists, then each demand keyword in the R&D demand is expanded with similar words to obtain at least one demand similar word for each demand keyword; If any one of the demand approximate words corresponding to all the demand keywords is found in the same extended keyword sublist, the traversal is stopped, and the matching score of the current resource object is calculated according to the second approximate coefficient, the first approximate coefficient and the first preset value; If any one of the demand approximation words corresponding to all the demand keywords is found in different extended keyword sublists, the matching score of the current resource object is calculated according to the second approximation coefficient, the first approximation coefficient and the second preset value; If any demand approximate word corresponding to each of the partial demand approximate words is found in all the extended keyword sublists, the matching score of the current item resource object is calculated based on the number of found words, the total number of the demand keywords, the first approximate coefficient and the second approximate coefficient.

6. A terminal device, characterized in that: The terminal device comprises a processor and a memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the resource pushing method according to any one of claims 1 to 4.

7. A readable storage medium, characterized in that: The computer program is stored therein, and when the computer program is executed on a processor, the resource pushing method according to any one of claims 1 to 4 is implemented.

Images