WO2020001031A1 - 学校及专业推荐方法及系统 - Google Patents

学校及专业推荐方法及系统 Download PDF

Info

Publication number
WO2020001031A1
WO2020001031A1 PCT/CN2019/074360 CN2019074360W WO2020001031A1 WO 2020001031 A1 WO2020001031 A1 WO 2020001031A1 CN 2019074360 W CN2019074360 W CN 2019074360W WO 2020001031 A1 WO2020001031 A1 WO 2020001031A1
Authority
WO
WIPO (PCT)
Prior art keywords
school
applicant
application
information
target
Prior art date
Application number
PCT/CN2019/074360
Other languages
English (en)
French (fr)
Inventor
莫凌峰
Original Assignee
藕丝科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 藕丝科技（深圳）有限公司 filed Critical 藕丝科技（深圳）有限公司
Publication of WO2020001031A1 publication Critical patent/WO2020001031A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G06Q50/2053—Education institution selection, admissions, or financial aid

Definitions

  • the present invention relates to the field of information processing technology, and particularly to schools and professional recommendation methods and systems.
  • the main purpose of the present invention is to provide a school and professional recommendation method and system, which aims to solve the problem that it is difficult for the existing school selection consultation mode to comprehensively examine the applicant's own situation, school selection needs and school selection review indicators in order to provide a true A school / professional recommendation plan suitable for the applicant's own actual situation.
  • the present invention provides a school and professional recommendation method, which includes the following steps:
  • the application material information includes the application requirement information of the applicant
  • test paper includes a preset individual indicator test question associated with the applicant's application requirement information
  • Steps to force results including:
  • the applicant's school application competitiveness and professional application competitiveness are tested and scored, and the applicant's school application competitiveness results and professional application competitiveness results are output. .
  • the method further includes:
  • the method further includes:
  • the application material information of the applicant is analyzed , And generate an application competitiveness analysis and promotion plan corresponding to the selected school and major.
  • the method further includes:
  • the method further includes:
  • the application prompt message is generated and pushed to the applicant.
  • the method further includes:
  • the application prompt message is generated and pushed to the applicant.
  • the method further includes:
  • the application popularity value of the target major corresponding to the searched school is less than or equal to the application popularity value of the target major corresponding to the target school; a recommendation plan for the target specialty corresponding to the searched school is generated.
  • the method further includes:
  • the preset condition is that the application heat value of the target major of other schools is less than or equal to the application heat value of the target major corresponding to the target school.
  • the method further includes:
  • the number of admitted students of the corresponding school is updated.
  • the present invention also provides a school and professional recommendation system, including: the school and professional recommendation system includes a platform end and an applicant end; the platform end is communicatively connected with the applicant end; The platform includes acquisition unit, test unit, application competitiveness evaluation unit and recommendation unit;
  • the obtaining unit is configured to obtain information about the application materials of the applicant sent by the applicant; wherein the information about the application materials includes information about the application requirements of the applicant;
  • the test unit is configured to generate a corresponding test paper based on the application requirement information of the applicant; wherein the test paper includes a preset individual index test question associated with the application requirement information of the applicant;
  • the obtaining unit is further configured to receive an answer result of the applicant on the test paper;
  • the application competitiveness evaluation unit is configured to obtain the applicant's school application competitiveness according to the evaluation criteria in the preset application competitiveness model, the applicant's application material information, and the result of the applicant's response to the test paper. Results and professional application competitiveness results;
  • the recommendation unit is used to find schools and majors that match the applicant's school selection factor index, specialty selection factor index, school application competitiveness results, and professional application competitiveness results, and generate corresponding school and specialty recommendation solutions.
  • the applicant's answer result is input into the preset application competitiveness model; the applicant's application material information is input into the preset application competitiveness model. ; Based on the applicant's application material information and the applicant's response to the test paper, test and score the applicant's school application competitiveness and professional application competitiveness, and output the applicant's school application competitiveness results and professional application competitiveness result.
  • the obtaining unit is further configured to obtain the use feature information of the applicant, and send the use feature information to the recommendation unit;
  • the recommendation unit is further configured to determine the applicant's school selection preference characteristics and professional selection preference characteristics based on the applicant's use feature information; and to find the school selection preference characteristics and professional selection preferences of the applicant based on the preset matching rules. Feature matching schools.
  • the platform side further includes an application competitiveness analysis and promotion unit;
  • the obtaining unit is further configured to obtain information of a school selected by the applicant, obtain information of a specialty selected by the applicant, and send the information of the school and the specialty to the application competitiveness analysis and improvement unit;
  • the application competitiveness analysis and promotion unit is used to determine the strength level of the school selected by the applicant and the strength level of the major selected by the applicant; the strength level of the school selected by the applicant is greater than the strength level of the matching school, or The strength level of the major selected by the applicant is greater than the strength level of the matching major, then the application material information of the applicant is analyzed, and an application competitiveness analysis and improvement plan corresponding to the selected school and major is generated.
  • the application competitiveness evaluation unit is further configured to obtain first-class evaluation information of the current applicant's application for the competitiveness of the school and the professional application for the competition result; and obtain the second applicant's second-class evaluation result of the target school.
  • Type evaluation information obtain target school's third type evaluation information of the current applicant; adjust according to the first type evaluation information and / or the second type evaluation information and / or the third type evaluation information Relevant parameters in the preset application competitiveness model, and correspondingly adjust the preset application competitiveness model.
  • the school and professional recommendation system further includes an admissions terminal; the platform terminal is in communication connection with the admissions terminal;
  • the obtaining unit is further configured to send the pre-application information of the applicant to the admission end corresponding to the matched school; wherein the application information is generated based on the application material information of the applicant;
  • the obtaining unit is further configured to send pre-admission information to the applicant when receiving the application invitation request sent by the admissions end.
  • the recommendation unit is further configured to obtain information about the target school selected by the current applicant and target professional information corresponding to the target school, and obtain application data of each applicant corresponding to the target school and the target major corresponding to the target school; Determine the application popularity value of the target major corresponding to the target school according to the application data; determine whether to push the corresponding application reminder message to the applicant end according to the preset application reminder message push rule and the application popularity value; if yes, Generating and pushing the application prompt message to the applicant.
  • the recommendation unit is further used to obtain the strength level of the target school; according to the strength level of the target school, search for other schools with the same strength level as the target school; and according to the search result, obtain the target major corresponding to the school that is found Application enthusiasm value; if the application enthusiasm value of the target major corresponding to the searched school is less than or equal to the application enthusiasm value of the target major corresponding to the target school; a recommendation plan for the target major corresponding to the searched school is generated.
  • the recommendation unit is further configured to obtain the application popularity value of the target majors of other schools; search for target majors of other schools that meet the preset conditions, and generate schools and majors corresponding to the target majors of other schools that are searched out Recommended solution
  • the preset condition is that the application heat value of the target major of other schools is less than or equal to the application heat value of the target major corresponding to the target school.
  • the recommendation unit is further configured to update the number of admitted students of the corresponding school when receiving the preset admission confirmation information sent by the admissions end.
  • the present invention provides a school and professional recommendation method and system, which combines the applicant's application material information, application demand information, and preset individual indicators associated with it to comprehensively analyze the applicant's own situation, school selection needs, and school selection review indicators. Overall inspection, determine the applicant's application competitiveness results, find schools that match the applicant's application competitiveness results, and generate a corresponding school recommendation plan, so as to recommend to the applicant schools that are more in line with the actual situation of the applicant , Which helps improve the degree of matching between the applicant and the application school and application major, thereby effectively improving the applicant's application success rate.
  • the method of providing test applicants with test papers for evaluation is compared with the manual consultation method of consultants in the past, which saves manpower and material resources, helps to realize the electronicization, standardization and intelligence of the consultation process, thereby improving the applicant's evaluation Efficiency and improved user experience also enable a two-way choice between applicants and schools.
  • FIG. 1 is a schematic flowchart of a first embodiment of a school and professional recommendation method of the present invention
  • FIG. 2 is a schematic flowchart of a second embodiment of a school and professional recommendation method of the present invention
  • FIG. 3 is a schematic flowchart of a third embodiment of a school and specialty recommendation method of the present invention.
  • FIG. 4 is a schematic flowchart of a fourth embodiment of a school and specialty recommendation method of the present invention.
  • 5 is a schematic block diagram of each component of the school and the professional recommendation system of the present invention.
  • FIG. 6 is a schematic diagram of a two-way recommendation process for implementing a school and professional recommendation scheme by the school and professional recommendation system of the present invention
  • FIG. 7 is a function diagram of the school and professional recommendation system of the present invention.
  • FIG. 1 is a schematic flowchart of a first embodiment of a school and professional recommendation method of the present invention.
  • the method includes the following steps:
  • Step S10 Obtain application information of the applicant
  • Information on application materials can include various types of school selection review index data, including various types of structured data, semi-structured data, and unstructured data, such as 1 background information, including but not limited to: attended high school, university, Ranking of academic reputation of the colleges and universities attended; 2 Academic ability data, including but not limited to high school GPA, university GPA, university professional GPA, grade / class ranking, honors courses (AP / Honor), AG subjects (A is history, social science , B is English, C is mathematics, D is laboratory science, E is a language other than English, F is visual and performing arts, G is a preparatory elective course for a university), research experience, and published papers; 3 materials for extracurricular activities , Including community activities, sports activities, artistic talents, leadership activities, foundation studies, volunteer experience, work experience; 4 standardized test materials, including AP / Honor score, TOEFL score, IELTS score
  • the application material information includes application requirement information of the applicant
  • the applicant's application needs information can be specific to the school / professional preferences, including various application requirements, such as the country where the school is located, the school / professional to be admitted to, the school location (such as some applicants for science graduate applications If you prefer a quiet place of study, the corresponding school location is located in the suburbs or around the county seat, and the type of school (if some applicants prefer a liberal arts college, the corresponding school type is a liberal arts college).
  • the application requirements information of the applicant in the embodiment of the present invention may also include other various requirements of the applicant when applying, for example, in addition to the school / professional, it may also include scholarship funding, school running scale, school / professional ranking, and school environment. , Supporting facilities, male to female ratio, ethnic ratio, etc.
  • the method may further include the following steps: when the applicant successfully registers an account, the applicant is assigned a registration identification code; accordingly, the applicant uses the registration identification code to log in to the school And professional recommendation system.
  • the applicant if the applicant has already performed the evaluation of the competitive results of the application, the historical school / professional recommendation record will be directly fed back instead of performing the evaluation every time, thereby simplifying the school / professional recommendation process and improving the recommendation of the school to the applicant / Professional information efficiency.
  • Step S20 Generate a corresponding test paper based on the application requirement information of the applicant; wherein the test paper includes a preset individual indicator test question associated with the application requirement information of the applicant;
  • step S20 includes:
  • Step S21 Grab each application requirement item constituting the application requirement information according to the application material information of the applicant;
  • Step S22 Find a preset individual index item associated with the application requirement item
  • Step S23 Based on the preset individual index items, a corresponding test question is retrieved from a test database to generate the test paper.
  • the preset individual indicator items are used to measure the development level of the applicant's knowledge, ability, skills, psychology and other evaluation items.
  • the evaluation item is "personality adaptability", and the corresponding preset individual index items include: willpower, inward / outward orientation, and resilience; the evaluation item is "personal ability”, and the corresponding preset individual index item is specific Including: cooperation and coordination ability, analysis and evaluation, planning and execution ability, responsibility, innovation ability, resource allocation ability, project management ability, leadership organization ability, engineering technology ability. That is, for a specific school / professional, the admitted students have relatively stable group characteristics; and the preset individual index items can reflect the group characteristics of students admitted in a specific school / professional.
  • test database contains a large number of test questions, which correspond to the preset individual index items that need to be evaluated. Therefore, the generated test paper contains multi-dimension of different content formulated according to the applicant's application requirements information (such as the school to be admitted, the major to be admitted), the application material information, and the analysis of the specific school / professional. Test questions.
  • the preset individual indicator items associated with the "professionals wishing to study" application requirements include: the degree of preference in arts and sciences, the level of willpower, and the thinking mode. Understandably, there will be significant differences in the above-mentioned preset individual index items for applicants who choose the liberal arts major and those who choose the science major. Therefore, the above-mentioned preset individual indicator items of the applicant are evaluated by generating a test paper, so as to determine the degree of matching between the applicant and the "professionals to be admitted to” and the level of application competitiveness.
  • Step S30 Receive the answer result of the applicant on the test paper
  • test paper After the test paper is generated, the test paper is sent to the applicant's account, and the result of the applicant's response to the test paper is received.
  • Step S40 Determine an applicant's school selection factor index and a professional selection factor index according to the applicant's application material information and the applicant's answer result to the test paper;
  • the present invention is based on the two major dimensions of school selection and major selection to realize recommending schools and majors that are more suitable for the actual situation of the applicant.
  • the school selection element indicator refers to a series of element indicators determined based on the dimensions of school selection, such as the type of school the applicant wishes to attend, the school's strength level, and the country or region where the school is located.
  • Major selection factor indicators refer to a series of factor indicators determined based on the dimensions of major selection, such as the major the applicant wishes to study, personal employment propensity, and personal thinking mode.
  • the determination of school selection element indicators and professional selection element indicators can be specifically extracted from the applicant's application material information and the applicant's response to the test paper, and the corresponding data selection, cleaning and processing, Generate corresponding school selection factor indicators or major selection factor indicators.
  • step S50 according to the evaluation criteria in the preset application competitiveness model, the applicant's application material information, and the applicant's answer to the test paper, the applicant's school application competitiveness results and professional application competitiveness results are obtained. ;
  • Step S50 specifically includes:
  • Step S51 After receiving the applicant's answer result to the test paper, input the applicant's answer result into a preset application competitiveness model;
  • Step S52 input the information of the applicant's application materials into a preset application competitiveness model
  • Step S53 Based on the applicant's application information and the answer result of the test paper, test and score the applicant's school application competitiveness and professional application competitiveness, and output the applicant's school application competitiveness result and professional application Competitive results.
  • the preset application competitiveness model in the embodiment of the present invention refers to an analysis model that integrates various types of ability and condition characteristics required to apply for a certain school / major. Enter the applicant's application materials information and the applicant's answer to the test paper into the preset application competitiveness model, and calculate the applicant's school application competitiveness results and professional application competition based on the two different dimensions of the school and the major. Force results. That is, the applicant's school application competitiveness results are used to characterize the applicant's competitiveness level when applying for a school, and the applicant's professional application competitiveness results are used to characterize the applicant's competitiveness level when applying for a certain specialty. .
  • the module indicators related to the calculation of school application competitiveness results in the application competitiveness model include academic ability, extracurricular activities, school types, and other preset materials in Table 1.
  • the data of each sub-item corresponding to the module index is tested and calculated by the calculation model in the application competitiveness model (different module indicators correspond to different quantization and scoring rules), and finally the applicant's school application competitiveness is obtained. result.
  • the specific manifestation of the school's application for competitiveness can be written description, score, grade level, and percentage; for example, the school's application for competitiveness results in a total score.
  • P represents the total score of the school's application for competitive results
  • A, B, C, and D represent the applicant's academic ability, extra-curricular activities, school type, and other competitive results scores corresponding to the preset materials.
  • d indicates the weight coefficients corresponding to A, B, C, and D, respectively.
  • a and b can be larger, and c and d can be smaller to highlight the importance of academic ability and extracurricular activities for applicants to apply for schools.
  • the module indicators related to the calculation of school application competitiveness results in the application competitiveness model include academic ability, extracurricular activities, professional ability, personality adaptability, and individual in Table 1.
  • the specific manifestations of professional application competitive results can be written descriptions, scores, grade levels, percentages, etc. For example, the professional application competitiveness results in a total score or a certain level.
  • the calculation method of the applicant's school application competitiveness result is similar to the calculation method of the above school application competitiveness result, and is not repeated here.
  • Step S60 Find schools and majors that match the applicant's school selection factor index, major selection factor index, school application competitiveness results and major application competitiveness results, and generate corresponding school and major recommendation schemes.
  • a specific implementation includes: finding the first batch of schools matching the applicant's school application competitiveness results from a database storing various types of school information, and then screening the first batch of schools to match the applicant's school selection element indicators Second batch of schools. Based on the results of the screening, a third batch of schools matching the applicant's professional application competitiveness results were found in the second batch of schools, and a fourth batch of schools was selected from the third batch of schools that matched the applicant's professional selection factor indicators. Approve schools and corresponding majors. Among them, the majors screened out are those in the fourth batch of schools.
  • finding schools that match the applicant's school application competitiveness results include: based on the average school application competitiveness results of each school's past admission applicants, comparing the applicant's school application competitiveness results with the past history of each school Admission applicants ’average school application competitiveness results are compared separately; if the difference between the applicant's school application competitiveness results and the past admission applicant's average school application competitiveness results within a certain preset range, then It is determined that the school matches the applicant's school application competitiveness results.
  • the applicant's school selection factor index is used as a screening option for screening.
  • the average professional application competitiveness results of each major were obtained, and the results of the applicant's professional application competitiveness were compared with those of the majors.
  • the average professional application competitiveness results are compared separately; if the difference between the applicant's professional application competitiveness results and the average professional application competitiveness results of a specialty is within a certain preset range, the professional application of the specialty and the applicant is judged Competitive results match.
  • the applicant's major selection factor index is used as a screening option to screen. Finally, the matching school and corresponding applicable majors are obtained, and the matching school and corresponding majors that can be applied are generated. Recommended solution.
  • the generated school and professional recommendation plan specifically includes the above-mentioned calculated applicant's module index school / professional application competitiveness results, the schools and majors suitable for the applicant, and the applicant's knowledge, technology, and other advantages, disadvantages, and corresponding Suggestions for improving competitiveness.
  • the generated school and professional recommendation plan may also include: the probability of success of a certain specialty of the applicant's school, the school's / professional competitiveness ranking of the applicant, and so on.
  • the above school and professional recommendation schemes are provided to applicants, and the above school and professional recommendation schemes can be provided to the above applicants in at least one of the following ways: by webpage feedback results, by mobile communication, or by Push by email subscription, or push by instant messaging. That is to say, the school and professional recommendation system feedbacks the school / professional recommendation scheme to the applicant. It can borrow the existing network information transmission method to recommend the school / professional information to the applicant in a variety of feedback methods, improving the applicant's application efficiency.
  • the school and professional recommendation plan is sent to the applicant.
  • the applicant side may specifically include a web page side, a mobile application side, a WeChat mini-program, a public account, etc .; the applicant can conveniently and timely view the school recommendation scheme through the applicant side, which is helpful for the information reference of the applying school.
  • the school's admissions staff can obtain the applicant's application demand information and competitiveness results through the school, so as to select suitable students and send corresponding application invitations.
  • the school and professional recommendation method provided by this embodiment has the following beneficial effects: (1) The organic combination of the applicant's application material information, application demand information, and preset individual indicators associated with it to achieve the applicant's own situation A comprehensive and comprehensive inspection of school selection needs and school selection review indicators makes the applicant's application competitiveness results more in line with the applicant's own actual situation; based on the comprehensive evaluation of the school and major two dimensions, the generated school and major recommendation plan helps In order to improve the applicant's matching with the applicant school and application profession, thereby effectively improving the applicant's application success rate.
  • FIG. 2 is a schematic flowchart of a second embodiment of a school and professional recommendation method of the present invention.
  • step S20 the following steps are further included:
  • Step S70 Obtain application information and corresponding preset individual index items of historical applicants admitted by each school;
  • the method of acquisition can be crawled from various databases through automatic crawling robot crawling or search technology, and can also be shared through cooperative colleges or cooperative consulting organizations, as well as the behavior incident interview method, Delphi method, questionnaire described above.
  • Survey method, 360-degree assessment method, expert database system (Expert Database System) and observation methods, etc. to obtain application information and corresponding preset individual index items of historical applicants admitted by each school.
  • application material information and corresponding preset individual index items of historical applicants who have applied for school but have not been accepted can also be used as sample data.
  • Step S71 Determine application request information of the historical applicant according to the application material information of the historical applicant;
  • Step S72 Determine an application requirement item corresponding to the application requirement information according to the application requirement information of the historical applicant;
  • Step S73 Establish an association relationship between the application demand item and a preset individual index item
  • the specific association relationship can be determined based on actual experimental investigation data.
  • test database includes test questions corresponding to preset individual index items.
  • the test database contains a large number of test questions, which correspond to the preset individual index items that need to be evaluated. In this way, as long as the preset individual index items that need to be evaluated are determined, the corresponding test questions can be extracted for applicants to answer.
  • a test database based on a large number of multi-dimensional historical and effective data of historical applicants ensures that the group characteristics of students admitted in different majors of different schools are comprehensively and effectively reflected, thereby ensuring the accuracy of the applicant's application competitiveness evaluation results Effectiveness.
  • FIG. 3 is a schematic flowchart of a third embodiment of a method for recommending schools and majors according to the present invention.
  • the method further includes:
  • Step S80 Obtain information about the school selected by the applicant to determine the strength level of the school selected by the applicant;
  • Step S81 Obtain information about the profession selected by the applicant to determine the strength level of the profession selected by the applicant;
  • the school / professional selected by the applicant may be the recommended school / professional in the generated school and professional recommendation scheme, or the school / professional selected by the applicant.
  • the strength level of each school can be obtained by statistically averaging the application competitiveness results of applicants admitted by each school in the past, for example, averaging the application competitiveness results of applicants admitted by each school in the past. To obtain the average competitiveness results of applicants admitted by each school in the past; then, according to the average competitiveness results of applicants admitted by each school in the past, each school is divided into different strength levels.
  • the strength level of the same major in each school can be obtained by statistically averaging the application competitiveness results of applicants who have previously admitted to the same major in each school.
  • Step S82 if the strength level of the school selected by the applicant is greater than the strength level of the matching school, or the strength level of the profession selected by the applicant is greater than the strength level of the matched profession, the application materials of the applicant are The information is analyzed, and an application competitiveness analysis and promotion plan corresponding to the selected school and major is generated.
  • the strength level of the school selected by the applicant is greater than the strength level of the matching school, or the strength level of the specialty selected by the applicant is greater than the strength level of the matched specialty, indicating that the applicant's application material information has insufficient or weak items,
  • the applicant's application material information is analyzed accordingly, so as to analyze the applicant's shortcomings or weak items, that is, to generate an application competitiveness analysis and improvement plan corresponding to the selected school for the applicant's reference.
  • the school selected by the applicant is the second level
  • the school whose applicant's application competitiveness matches the strength level is the third level (smaller level numbers indicate higher levels, such as second level, first level) .
  • the application material information of the applicant is analyzed. Specifically, it can analyze the gaps and differences between the applicant's audit indicators and preset individual indicators in various types of school selections relative to the average statistical level of applicants who have been admitted to the corresponding school, so as to determine the shortcomings of the applicant when applying for the school or Disadvantaged projects and find improvement suggestions that match identified deficiencies or disadvantaged projects.
  • the applicant's application competitiveness analysis and promotion plan when applying for a certain specialty of the school includes analysis of the applicant's shortcomings or disadvantages when applying for a certain specialty of the school and corresponding improvement suggestions, and Correspondingly generate application competitiveness analysis and promotion plan.
  • the application competitiveness analysis and improvement plan is sent to the applicant.
  • Applicants can conveniently and timely review the application competitiveness analysis and improvement plan through the applicant's end, which helps applicants to understand the shortcomings and disadvantages of their own competitiveness before applying for schools / professions, and make corresponding improvements and improvements In order to improve your application competitiveness.
  • FIG. 4 is a schematic flowchart of a fourth embodiment of a school and professional recommendation method of the present invention.
  • the method further includes:
  • Step S90 Send the pre-application information of the applicant to the admissions end corresponding to the matching school; wherein the application information is generated based on the application material information of the applicant.
  • the pre-application information specifically includes the applicant's various school selection review index data, the applicant's application demand information, and can also include the applicant's application competitiveness results.
  • Step S91 When receiving the application invitation request sent by the admissions end, send pre-admission information to the applicant end.
  • the school's admissions staff sees the pre-application information of the applicant pushed by the platform, if they have the intention of admission, they can send an application invitation request to the platform through the admissions terminal.
  • the platform side sends pre-admission information to the applicant side of the corresponding applicant accordingly.
  • the embodiments of the present invention can also continuously collect the evaluation data of each applicant, and the success rate of the applicant's matching with the recommended school / professional, and use the regression method or other relevant verification methods to adjust various types of tests by adjusting the evaluation methods.
  • the content and quantity of the questions in order to improve the accuracy and effectiveness of the evaluation, and further analyze the data, adjust the index weights and index standard conversion rules, and even adjust the indicators of the application competitiveness model to make the application competitiveness model more Towards perfection.
  • the method further includes:
  • Step S100 Obtain the use characteristic information of the applicant
  • the application feature information of the applicant refers specifically to the use action characteristics of the applicant's mobile search, web terminal, public account and other terminals for school search, school information viewing, and browsing of web pages (such as posts and forums) applied by relevant schools. At least: the characteristics of the relevant school (such as school type, school strength level) browsed by the applicant, search keywords and search popularity.
  • Step S101 Determine a school selection preference characteristic and a professional selection preference characteristic of the applicant according to the use characteristic information of the applicant;
  • the application feature information of the applicant can be used for keyword statistics and correlation calculation to determine the preference characteristics of the applicant in terms of school selection (that is, the school selection preference characteristics), such as the type of school to be applied for and the country where the school is located Or subject areas or schools, and subject statistics; and keyword statistics and correlation calculations of the applicant's use characteristic information to determine the applicant's preference characteristics in selecting a specialty (ie, professional selection preference characteristics).
  • school selection preference characteristics such as the type of school to be applied for and the country where the school is located Or subject areas or schools, and subject statistics
  • keyword statistics and correlation calculations of the applicant's use characteristic information to determine the applicant's preference characteristics in selecting a specialty (ie, professional selection preference characteristics).
  • Step S102 Find schools that match the applicant's school selection preference characteristics and specialty selection preference characteristics according to the preset matching rules.
  • the preset matching rules include related rules that associate the database with school selection preference characteristics and professional selection preference characteristics. Therefore, based on the applicant's school selection preferences, a number of schools and corresponding majors that are of interest to the applicant are matched, and new schools and major recommendation schemes are generated for applicants' reference. In this way, based on the use characteristic information of the applicant, the schools and majors recommended to the applicant more accurately match the applicant's selection preferences, which helps to improve the accuracy of school and major recommendation.
  • the method further includes: Step S110: Obtaining a current applicant's competitiveness of the school application and the professional application competitiveness The first type of evaluation information of the result; step S111, obtaining the second type of evaluation information of the current applicant on the target school;
  • Step S112 Obtain the third type of evaluation information of the target applicant on the current applicant;
  • Step S113 Adjust relevant parameters in the preset application competitiveness model according to the first type of evaluation information and / or the second type of evaluation information and / or the third type of evaluation information and correspondingly Adjusting the preset application competitiveness model.
  • the first type of evaluation information refers to the current applicant's various evaluations of the recommended schools and professional recommendation schemes and the use of feedback information, such as whether the recommended schools and professional recommendation schemes truly match the personal situation;
  • the second type of evaluation Information refers to the current applicant's various evaluation information of the school / professor who has applied / interviewed, such as the degree of recognition of the school / professional;
  • the third type of evaluation information is the various evaluation information of the admissions school to the current applicant, such as admission The school's evaluation score for the current applicant during the interview process.
  • the preset application competitiveness model is dynamically maintained and adjusted; the adjusted related parameters can be the quantitative parameters or scoring parameters of the module indicators of the evaluation standard. Therefore, the application competitiveness measured by the preset application competitiveness model can better meet the actual ability of the applicant. For example, after recommending a school plan to an applicant, the applicant can make a real / anonymous comment on the recommendation result and the school, and can conduct a real / anonymous review after enrolling in the future. This review can help improve model accuracy and school selection experience.
  • the method further includes:
  • Step S120 Acquire the target school information selected by the current applicant and the target professional information corresponding to the target school, and obtain the application data of each applicant corresponding to the target school and the target major corresponding to the target school;
  • the target school is a certain school selected by the current applicant, and the target major corresponding to the target school is a certain specialty of a certain school selected by the current applicant.
  • Each applicant may be an applicant who applied for the target school within a certain period, for example, an applicant who has applied for the school within the past three years or within one year; in the embodiment of the present invention, each applicant refers to the school in the current year Applicants who have applied for the same major in the target school during the application cycle.
  • the application data may specifically include the total number of applicants of the same major who applied for the target school, and / or the results of application competitiveness of each applicant.
  • Step S121 Determine an application popularity value of a target major corresponding to the target school according to the application data
  • the application popularity value of the target school of the target school can reflect the popularity of the application of the target school, and the degree of attention and application difficulty of the target school can be predicted by calculating the application heat value of the target school.
  • the degree of interest in a major of a school at the same level of competence the more fierce the competition in applying for the major in that school, and the more difficult it is to apply.
  • the specific manner of determining the application heat value of the target school in this step is not limited.
  • Step S122 Determine whether to push the corresponding application reminder message to the applicant according to the preset application reminder message push rule and the application popularity value;
  • the preset application reminder message push rules can be set according to actual needs. For example, the target school's target major's application popularity value exceeds a certain threshold, and / or the target school's current number of applicants for the target major exceeds the planned enrollment difference. When a certain difference is reached, an application prompt message corresponding to the target school is pushed to the current applicant.
  • Step S123 if yes, generate and push the application prompt message to the current applicant.
  • the application reminder message may include the target school's application popularity value, the current number of applicants in the target school, the planned enrollment number of the target school, and the corresponding early-warning prompt information. That is, when the current number of applicants of the target school is too large, it is automatically implemented to send an application reminder message to applicants who have applied for the target school or applicants who have used the target school as an alternative application school.
  • This method of determining the popularity of the target major based on the application data of each applicant corresponding to the target major of the target school and sending an application reminder message to the applicant is helpful to improve the information symmetry between the applicant and the target school.
  • the target school's target professional application heat value, application difficulty, and relevant application risk prompt information can be known in time, so that the application decision is more rational; for the target school, too many applicants can be avoided Applying for the target major of the school will result in a heavier enrollment workload and is not conducive to careful selection of outstanding talents.
  • step S123 the method further includes:
  • Step S124 obtaining the strength level of the target school; step S125, searching for other schools with the same strength level as the target school according to the strength level of the target school; and step S126, obtaining an application for the target major corresponding to the school according to the search result Popularity value; step S117, if the popularization value of the target major corresponding to the searched school is less than or equal to the popularization value of the target major corresponding to the target school; a recommendation plan of the target major corresponding to the searched school is generated.
  • the strength level of the target school and other schools may be determined according to the method in the third embodiment. After searching for other schools with the same level of strength as the target school, continue to calculate the application heat value of the target major corresponding to the searched school according to the above method, and compare it with the application heat value of the target major corresponding to the target school. When the application popularity value of a certain major in a school of the same strength level is less than or equal to the application popularity value of the same major in the target school, it indicates that the popularity degree of the target major applying for the school is not higher than the target school.
  • the current applicant The degree of competition in the target majors applying for the school is relatively low, and the probability of success is high.
  • the invention is also applicable to another recommendation scheme for generating target majors based on the application heat value, specifically: obtaining the application heat values of the target majors of other schools; searching for target majors of other schools that meet the preset conditions, and generating and searching Schools and professional recommendation programs corresponding to the target majors of other schools; wherein the preset condition is that the application heat value of the target major of the other school is less than or equal to the application heat value of the target major corresponding to the target school.
  • generating and sending the corresponding school and major recommendation plan to the application side is also conducive to the applicant to make a more rational application decision with a higher probability of successful application, and also help the school's Talent recruitment.
  • the method further includes:
  • the number of admitted students of the corresponding school is updated.
  • the number of admissions within a school (professional) application cycle is generally rated, so the school (professional) needs to be updated in a timely manner based on the actual admissions of the school (professional) , So that applicants can obtain information on the number of students admitted to the school in a timely manner and make reasonable application decisions.
  • the situation where the admission end sends preset admission confirmation information may include but is not limited to the following cases: the applicant confirms the application for a certain school and completes the relevant application process; the school confirms the admission of the applicant, and the corresponding admissions end
  • the platform side sends preset admission confirmation information.
  • the platform side updates the number of admitted students of the school according to the preset admission confirmation information, for example, the number of admitted students is increased by one. Understandably, both the applicant side and the admissions side can obtain the number of students admitted to the updated school. In this way, it is helpful for the transparency of school admissions information, makes the information between the applicant and the school more symmetrical, and helps the applicant to make a more reasonable application decision.
  • FIG. 5 is a system block diagram of the first embodiment of the school and professional recommendation system of the present invention.
  • the school and professional recommendation system includes a platform end 10 and an applicant end 20; the platform end 10 is in communication with the applicant end 20; the platform end 10 includes an acquisition unit 110 and a test unit 120.
  • the obtaining unit 110 is configured to obtain application material information of the applicant sent by the applicant side, where the application material information includes the application requirement information of the applicant;
  • FIG. 6 is a schematic diagram of the school recommendation implementation of the school and the professional recommendation system of the present invention.
  • the applicant terminal 20 specifically, the web terminal or the application terminal
  • the applicant can enter his own application information.
  • the application material information includes the applicant's application requirements information;
  • the platform 10 referred to in the present invention may include various types of processors, servers, and other hardware and software architectures during specific deployment. Functional module or functional unit.
  • the information of the applicant's application requirements can be specific to the school / professional preferences, including various application requirements, such as the country where the school is located, the school / professional to be admitted to, the school location (such as some science graduate applicants prefer quiet The study location corresponds to the school location located in the suburbs or around the county seat, and the type of school (if some applicants prefer the liberal arts college, the corresponding school type is the liberal arts college).
  • the application requirements information of the applicant in the embodiment of the present invention may also include other various requirements of the applicant when applying, for example, in addition to the school / professional, it may also include scholarship funding, school running scale, school / professional ranking, and school environment. , Supporting facilities, male to female ratio, ethnic ratio, etc.
  • the school and the professional recommendation system when the applicant successfully registers an account, assigns a registration identity identification code to the applicant; accordingly, the applicant uses the registration identity identification code to log in to the system.
  • the applicant if the applicant has already performed the evaluation of the competitive results of the application, the historical school / professional recommendation record will be directly fed back instead of performing the evaluation every time, thereby simplifying the school / professional recommendation process and improving the recommendation of the school to the applicant / Professional information efficiency.
  • the test unit 120 is configured to generate a corresponding test paper based on the applicant's application requirement information; wherein the test paper includes a preset individual index test question associated with the applicant's application requirement information; the test The unit 120 is specifically configured to capture each application requirement item constituting the application requirement information according to the application material information of the applicant; that is, extract various types of application requirement items from the application material information of the applicant. Find a preset individual index item associated with the application requirement item; and based on the preset individual index item, retrieve a corresponding test question from a test database to generate the test paper.
  • the school's admissions staff can obtain the applicant's application demand information and competitiveness results through the school, so as to select suitable students and send corresponding application invitations.
  • the preset individual indicator items are used to measure the development level of the applicant's knowledge, ability, skills, psychology and other evaluation items.
  • the evaluation item is "personality adaptability", and the corresponding preset individual index items include: willpower, inward / outward orientation, and resilience; the evaluation item is "personal ability”, and the corresponding preset individual index item is specific Including: cooperation and coordination ability, analysis and evaluation, planning and execution ability, responsibility, innovation ability, resource allocation ability, project management ability, leadership organization ability, engineering technology ability. That is, for a specific school / professional, the admitted students have relatively stable group characteristics; and the preset individual index items can reflect the group characteristics of students admitted in a specific school / professional.
  • test database contains a large number of test questions, which correspond to the preset individual index items that need to be evaluated. Therefore, the generated test paper contains multi-dimension of different content formulated according to the applicant's application requirements information (such as the school to be admitted, the major to be admitted), the application material information, and the analysis of the specific school / professional. Test questions.
  • the preset individual indicator items associated with the "professionals wishing to study" application requirements include: the degree of preference in arts and sciences, the level of willpower, and the thinking mode. Understandably, there will be significant differences in the above-mentioned preset individual index items for applicants who choose the liberal arts major and those who choose the science major. Therefore, the above-mentioned preset individual indicator items of the applicant are evaluated by generating a test paper, so as to determine the degree of matching between the applicant and the "professionals to be admitted to” and the level of application competitiveness.
  • the obtaining unit 110 is further configured to receive an answer result of the applicant on the test paper;
  • test paper After the test paper is generated, the test paper is sent to the applicant 20 and the result of the applicant's response to the test paper is received.
  • the indicator determining unit 130 is configured to determine an applicant's school selection factor index and a professional selection factor index according to the applicant's application material information and the applicant's answer result to the test paper;
  • the present invention is based on the two major dimensions of school selection and major selection to realize recommending schools and majors that are more suitable for the actual situation of the applicant.
  • the school selection element indicator refers to a series of element indicators determined based on the dimensions of school selection, such as the type of school the applicant wishes to attend, the school's strength level, and the country or region where the school is located.
  • Major selection factor indicators refer to a series of factor indicators determined based on the dimensions of major selection, such as the major the applicant wishes to study, personal employment propensity, and personal thinking mode.
  • the determination of school selection element indicators and professional selection element indicators can be specifically extracted from the applicant's application material information and the applicant's response to the test paper, and the corresponding data selection, cleaning and processing, Generate corresponding school selection factor indicators or major selection factor indicators.
  • the application competitiveness evaluation unit 140 is configured to obtain the applicant's school application competition according to the evaluation criteria in the preset application competitiveness model, the applicant's application material information, and the applicant's response to the test paper. Force results and professional application competitiveness results;
  • the applicant's answer result is entered into the preset application competitiveness model; the applicant's application material information is entered into the preset application competitiveness model; based on the application
  • the applicant's application information and applicant's response to the test paper will test and score the applicant's school application competitiveness and professional application competitiveness, and output the applicant's school application competitiveness result and professional application competitiveness result.
  • the preset application competitiveness model in the embodiment of the present invention refers to an analysis model that integrates various types of ability and condition characteristics required to apply for a certain school / major.
  • the applicant's application material information and the applicant's response to the test paper are entered into the preset application competitiveness model, and the school's application competitiveness result and specialty are calculated based on the two different dimensions of school and specialty. Apply for competitive results. That is, the applicant's school application competitiveness results are used to characterize the applicant's competitiveness level when applying for a school, and the applicant's professional application competitiveness results are used to characterize the applicant's competitiveness level when applying for a certain specialty. .
  • the module indicators related to the calculation of school application competitiveness results in the application competitiveness model include academic ability, extracurricular activities, school types, and other preset materials in Table 1.
  • the data of each sub-item corresponding to the module index is tested and calculated by the calculation model (with different quantization and scoring rules) in the application competitiveness model, and the applicant's school application competitiveness result is finally obtained.
  • the specific manifestation of a school's application for competitiveness can be written descriptions, scores, grade levels, percentages, etc.
  • the school's application for competitiveness results is a total score.
  • P represents the total score of the school's application for competitive results
  • A, B, C, and D represent the applicant's academic ability, extra-curricular activities, school type, and other competitive results scores corresponding to the preset materials.
  • d indicates the weight coefficients corresponding to A, B, C, and D, respectively.
  • a and b can be larger, and c and d can be smaller to highlight the importance of academic ability and extracurricular activities for applicants to apply for schools.
  • the module indicators related to the calculation of school application competitiveness results in the application competitiveness model include academic ability, extracurricular activities, professional ability, personality adaptability, and individual in Table 1.
  • the specific manifestations of professional application competitive results can be written descriptions, scores, grade levels, percentages, etc. For example, the professional application competitiveness results in a total score or a certain level.
  • the calculation method of the applicant's school application competitiveness result is similar to the calculation method of the above school application competitiveness result, and is not repeated here.
  • the school recommendation unit 150 finds schools and majors that match the applicant's school selection factor index, major selection factor index, school application competitiveness result, and professional application competitiveness result, and generates a corresponding school and specialty recommendation plan.
  • a specific implementation includes: finding the first batch of schools matching the applicant's school application competitiveness results from a database storing various types of school information, and then screening the first batch of schools to match the applicant's school selection element indicators Second batch of schools. Based on the results of the screening, a third batch of schools matching the applicant's professional application competitiveness results were found in the second batch of schools, and a fourth batch of schools was selected from the third batch of schools that matched the applicant's professional selection factor indicators. Approve schools and corresponding majors. Among them, the majors screened out are those in the fourth batch of schools.
  • finding schools that match the applicant's school application competitiveness results include: based on the average school application competitiveness results of each school's past admission applicants, comparing the applicant's school application competitiveness results with the past history of each school Admission applicants ’average school application competitiveness results are compared separately; if the difference between the applicant's school application competitiveness results and the past admission applicant's average school application competitiveness results within a certain preset range, then It is determined that the school matches the applicant's school application competitiveness results.
  • the applicant's school selection factor index is used as a screening option for screening.
  • the average professional application competitiveness results of each major were obtained, and the results of the applicant's professional application competitiveness were compared with those of the majors.
  • the average professional application competitiveness results are compared separately; if the difference between the applicant's professional application competitiveness results and the average professional application competitiveness results of a specialty is within a certain preset range, the professional application of the specialty and the applicant is judged Competitive results match.
  • the applicant's major selection factor index is used as a screening option to screen. Finally, the matching school and corresponding applicable majors are obtained, and the matching school and corresponding majors that can be applied are generated. Recommended solution.
  • the generated school and professional recommendation plan specifically includes the above-mentioned calculated applicant's module index school / professional application competitiveness results, the schools and majors suitable for the applicant, and the applicant's knowledge, technology, and other advantages, disadvantages, and corresponding Suggestions for improving competitiveness.
  • the generated school and professional recommendation plan may also include: the probability of success of a certain specialty of the applicant's school, the school's / professional competitiveness ranking of the applicant, and so on.
  • the above school and professional recommendation schemes can be provided to the above applicants in at least one of the following ways: push through webpage feedback results, push through mobile communication, or subscribe by mail Push, or push by instant messaging. That is to say, the school and professional recommendation system feedbacks the school / professional recommendation scheme to the applicant. It can borrow the existing network information transmission method to recommend the school / professional information to the applicant in a variety of feedback methods, improving the applicant's application efficiency.
  • the school recommendation scheme is sent to the applicant.
  • the applicant side may specifically include a web page side, a mobile application side, a WeChat mini-program, a public account, etc .; the applicant can conveniently and timely view the school recommendation scheme through the applicant side, which is helpful for the information reference of the applying school.
  • the school and professional recommendation system provided in this embodiment has the following beneficial effects: (1) The organic combination of the applicant's application material information, application demand information, and preset individual indicators associated with it, realizes the applicant's own situation A comprehensive and comprehensive inspection of school selection needs and school selection review indicators makes the applicant's application competitiveness results more in line with the applicant's own actual situation; based on the comprehensive evaluation of the school and major two dimensions, the generated school and major recommendation plan helps In order to improve the applicant's matching with the applicant school and application profession, thereby effectively improving the applicant's application success rate.
  • the platform end 10 further includes a test database module 150;
  • the obtaining unit 110 is further configured to obtain application material information and corresponding preset individual index items of historical applicants admitted by each school;
  • the method of acquisition can be crawled from various databases through automatic crawling robot crawling or search technology, and can also be shared through cooperative colleges or cooperative consulting organizations, as well as the behavior incident interview method, Delphi method, questionnaire described above.
  • Survey method, 360-degree assessment method, expert database system (Expert Database System) and observation methods, etc. to obtain application information and corresponding preset individual index items of historical applicants admitted by each school.
  • application material information and corresponding preset individual index items of historical applicants who have applied for school but have not been accepted can also be used as sample data.
  • the test database module 150 is configured to determine the application requirement information of the historical applicant according to the application material information of the historical applicant; and determine the application corresponding to the application requirement information according to the application requirement information of the historical applicant.
  • a demand item establishing an association relationship between the application demand item and a preset individual index item; wherein the specific association relationship can be determined based on actual experimental investigation data.
  • test database includes test questions corresponding to preset individual index items.
  • the test database contains a large number of test questions, which correspond to the preset individual index items that need to be evaluated. In this way, as long as the preset individual index items that need to be evaluated are determined, the corresponding test questions can be extracted for applicants to answer.
  • a test database based on a large number of multi-dimensional historical and effective data of historical applicants ensures that the group characteristics of students admitted in different majors of different schools are comprehensively and effectively reflected, thereby ensuring the accuracy of the applicant's application competitiveness evaluation results Effectiveness.
  • the platform side further includes an application competitiveness analysis and promotion unit 160;
  • the obtaining unit 110 is further configured to obtain information of a school selected by the applicant, obtain information of a specialty selected by the applicant, and send the information of the school and the specialty to the application competitiveness analysis and improvement unit;
  • the school / major selected by the applicant may be the recommended school and major in the generated school and professional recommendation scheme, or the school and major selected by the applicant.
  • the strength level of each school can be obtained by statistically averaging the application competitiveness results of applicants admitted by each school in the past, for example, averaging the application competitiveness results of applicants admitted by each school in the past. To obtain the average competitiveness results of applicants admitted by each school in the past; then, according to the average competitiveness results of applicants admitted by each school in the past, each school is divided into different strength levels.
  • the strength level of the same major in each school can be obtained by statistically averaging the application competitiveness results of applicants who have previously admitted to the same major in each school.
  • the application competitiveness analysis and promotion unit 160 is configured to determine the strength level of the school selected by the applicant and the strength level of the major selected by the applicant; the strength level of the school selected by the applicant is greater than the strength level of the matching school, Or if the strength level of the major selected by the applicant is greater than the strength level of the matching major, the information of the application material of the applicant is analyzed, and an analysis and improvement plan for the competitiveness of the application corresponding to the selected school and major is generated.
  • the strength level of the school selected by the applicant is greater than the strength level of the matching school, or the strength level of the specialty selected by the applicant is greater than the strength level of the matched specialty, indicating that the applicant's application material information has insufficient or weak items,
  • the applicant's application material information is analyzed accordingly, so as to analyze the applicant's shortcomings or weak items, that is, to generate an application competitiveness analysis and improvement plan corresponding to the selected school for the applicant's reference.
  • the school selected by the applicant is the second level
  • the school whose applicant's application competitiveness matches the strength level is the third level (smaller level numbers indicate higher levels, such as second level, first level) .
  • the application material information of the applicant is analyzed.
  • the gaps and differences between the applicant's various school selection review indicators and preset individual indicator items relative to the average statistical level of applicants who have been accepted by the corresponding school can be analyzed to determine the existence of the applicant when applying for the school And find out the improvement suggestions that match the identified shortcomings or disadvantages.
  • the applicant's application competitiveness analysis and promotion plan when applying for a certain specialty of the school includes analysis of the applicant's shortcomings or disadvantages when applying for a certain specialty of the school and corresponding improvement suggestions, and Correspondingly generate application competitiveness analysis and promotion plan.
  • the application competitiveness analysis and improvement plan is sent to the applicant.
  • Applicants can conveniently and timely review the application competitiveness analysis and promotion plan through the applicant's end, which helps applicants to understand the shortcomings and disadvantages of their own competitiveness and apply corresponding improvements and improvements before applying for schools. Improve your own application competitiveness.
  • the school and professional recommendation system further includes an admissions terminal 30; the platform terminal 10 is communicatively connected with the admissions terminal 30;
  • the obtaining unit 110 is further configured to send pre-application information of the applicant to the admissions end 30 corresponding to the matching school; wherein the application information is generated based on the application material information of the applicant;
  • the pre-application information specifically includes the applicant's various school selection review index data, the applicant's application demand information, and can also include the applicant's application competitiveness results.
  • the obtaining unit 110 is further configured to send pre-admission information to the applicant 20 when receiving the application invitation request sent by the admissions terminal 30.
  • the school's admissions staff sees the pre-application information of the applicant pushed by the platform, if they have the intention of admission, they can send an application invitation request to the platform through the admissions terminal.
  • the platform side sends pre-admission information to the applicant side of the corresponding applicant accordingly.
  • the obtaining unit 110 is further configured to obtain the use feature information of the applicant, and send the use feature information to the school recommendation unit 150;
  • the application feature information of the applicant refers specifically to the use action characteristics of the applicant's mobile search, web terminal, public account and other terminals for school search, school information viewing, and browsing of web pages (such as posts and forums) applied by relevant schools. At least: the characteristics of the relevant school (such as school type, school strength level) browsed by the applicant, search keywords and search popularity.
  • the school recommendation unit 150 is further configured to determine the applicant's school selection preference characteristics and specialty selection preference characteristics based on the applicant's use characteristic information; and to find the school selection preference characteristics and specialty of the applicant based on the preset matching rules. Select schools with matching preference characteristics.
  • the application feature information of the applicant can be used for keyword statistics and correlation calculation to determine the preference characteristics of the applicant in terms of school selection (that is, the school selection preference characteristics), such as the type of school to be applied for and the country where the school is located Or subject areas or schools, and subject statistics; and keyword statistics and correlation calculations of the applicant's use characteristic information to determine the applicant's preference characteristics in selecting a specialty (ie, professional selection preference characteristics).
  • school selection preference characteristics such as the type of school to be applied for and the country where the school is located Or subject areas or schools, and subject statistics
  • keyword statistics and correlation calculations of the applicant's use characteristic information to determine the applicant's preference characteristics in selecting a specialty (ie, professional selection preference characteristics).
  • the preset matching rules include related rules that associate the database with school selection preference characteristics and professional selection preference characteristics. Therefore, based on the applicant's school selection preferences, a number of schools and corresponding majors that are of interest to the applicant are matched, and new schools and major recommendation schemes are generated for applicants' reference. In this way, based on the use characteristic information of the applicant, the schools and majors recommended to the applicant more accurately match the applicant's selection preferences, which helps to improve the accuracy of school and major recommendation.
  • the application competitiveness evaluation unit 140 is further configured to obtain the first type of evaluation information of the current applicant's competitiveness of the school application and the professional application's competitiveness results; and obtain the current applicant's ranking of the target school. Second-class evaluation information; obtaining third-class evaluation information of the target applicant from the current applicant; according to the first-class evaluation information and / or the second-class evaluation information and / or the third-class evaluation information, Relevant parameters in the preset application competitiveness model are adjusted, and the preset application competitiveness model is adjusted correspondingly.
  • the first type of evaluation information refers to the current applicant's various evaluations of the recommended schools and professional recommendation schemes and the use of feedback information, such as whether the recommended schools and professional recommendation schemes truly match the personal situation;
  • the second type of evaluation Information refers to the current applicant's various evaluation information of the school / professor who has applied / interviewed, such as the degree of recognition of the school / professional;
  • the third type of evaluation information is the various evaluation information of the admissions school to the current applicant, such as admissions The school's evaluation score for the current applicant during the interview process.
  • the preset application competitiveness model is dynamically maintained and adjusted; the adjusted related parameters can be the quantitative parameters or scoring parameters of the module indicators of the evaluation standard. Therefore, the application competitiveness measured by the preset application competitiveness model can better meet the actual ability of the applicant. For example, after recommending a school plan to an applicant, the applicant can make a real / anonymous comment on the recommendation result and the school, and can conduct a real / anonymous review after enrolling in the future. This review can help improve model accuracy and school selection experience.
  • the school recommendation unit 150 is further configured to obtain the target school information selected by the current applicant and the target major information corresponding to the target school, and obtain applications from each applicant corresponding to the target school and the target major corresponding to the target school. Data; determining an application popularity value of a target major corresponding to the target school according to the application data;
  • the target school is a certain school selected by the current applicant, and the target major corresponding to the target school is a certain specialty of a certain school selected by the current applicant.
  • Each applicant may be an applicant who applied for the target school within a certain period, for example, an applicant who has applied for the school within the past three years or within one year; in the embodiment of the present invention, each applicant refers to the school in the current year Applicants who have applied for the same major in the target school during the application cycle.
  • the application data may specifically include the total number of applicants of the same major who applied for the target school, and / or the results of application competitiveness of each applicant.
  • the application popularity value of the target school of the target school can reflect the popularity of the application for the target school.
  • the popularity degree and difficulty of the target school can be predicted by calculating the application heat value of the target school.
  • the greater the degree of interest in a major of a school at the same level of competence the more fierce the competition in applying for the major in that school, and the more difficult it is to apply.
  • the specific method of determining the application heat value of the target school is not limited.
  • the school recommendation unit 150 is further configured to determine whether to push a corresponding application notification message to the applicant according to a preset application notification message pushing rule and the application popularity value; if yes, generate and push the application notification to the applicant Application reminder message.
  • the preset application reminder message push rules can be set according to actual needs. For example, the target school's target major's application popularity value exceeds a certain threshold, and / or the target school's current number of applicants for the target major exceeds the planned enrollment difference. When a certain difference is reached, an application prompt message corresponding to the target school is pushed to the current applicant.
  • the application reminder message may include the target school's application popularity value, the current number of applicants in the target school, the planned enrollment number of the target school, and the corresponding early-warning prompt information. That is, when the current number of applicants of the target school is too large, it is automatically implemented to send an application reminder message to applicants who have applied for the target school or applicants who have used the target school as an alternative application school.
  • This method of determining the popularity of the target major based on the application data of each applicant corresponding to the target major of the target school and sending an application reminder message to the applicant is helpful to improve the information symmetry between the applicant and the target school.
  • the target school's target professional application heat value, application difficulty, and relevant application risk prompt information can be known in time, so that the application decision is more rational; for the target school, too many applicants can be avoided Applying for the target major of the school will result in a heavier enrollment workload and is not conducive to careful selection of outstanding talents.
  • the school recommendation unit 150 is also used to obtain the strength level of the target school; search for other schools with the same strength level as the target school according to the strength level of the target school; and obtain the target major corresponding to the school according to the search results If the application popularity value of the target major corresponding to the searched school is less than or equal to the application popularity value of the target major corresponding to the target school, a recommendation plan of the target specialty corresponding to the searched school is generated.
  • the strength level of the target school and other schools may be determined according to the method in the third embodiment. After searching for other schools with the same level of strength as the target school, continue to calculate the application heat value of the target major corresponding to the searched school according to the above method, and compare it with the application heat value of the target major corresponding to the target school. When the application popularity value of a certain major in a school of the same strength level is less than or equal to the application popularity value of the same major in the target school, it indicates that the popularity degree of the target major applying for the school is not higher than the target school.
  • the current applicant The degree of competition in the target majors applying for the school is relatively low, and the probability of success is high.
  • the school recommendation unit 150 is also used to obtain the application popularity value of the target majors of other schools; search for the target majors of other schools that meet the preset conditions, and generate schools and target schools Professional recommendation scheme; wherein the preset condition is that the application heat value of the target major of other schools is less than or equal to the application heat value of the target major corresponding to the target school.
  • generating and sending the corresponding school and major recommendation plan to the application side is also conducive to the applicant to make a more rational application decision with a higher probability of successful application, and also help the school's Talent recruitment.
  • the school recommendation unit 150 is further configured to update the number of admitted students of the corresponding school when receiving the preset admission confirmation information sent by the admissions end.
  • the number of admissions within a school (professional) application cycle is generally rated, so the school (professional) needs to be updated in a timely manner based on the actual admissions of the school (professional) , So that applicants can obtain information on the number of students admitted to the school in a timely manner and make reasonable application decisions.
  • the situation where the admission end sends preset admission confirmation information may include but is not limited to the following cases: the applicant confirms the application for a certain school and completes the relevant application process; the school confirms the admission of the applicant, and the corresponding admissions end
  • the platform side sends preset admission confirmation information.
  • the platform side updates the number of admitted students of the school according to the preset admission confirmation information, for example, the number of admitted students is increased by one. Understandably, both the applicant side and the admissions side can obtain the number of students admitted to the updated school. In this way, it is helpful for the transparency of school admissions information, makes the information between the applicant and the school more symmetrical, and helps the applicant to make a more reasonable application decision.
  • FIG. 7 is a functional schematic diagram of the school and professional recommendation system of the present invention, and the functions contained therein are various functions implemented by the functional units mentioned above.
  • sequence numbers of the foregoing embodiments of the present invention are merely for description, and do not represent the superiority or inferiority of the embodiments.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种学校及专业推荐方法，包括：获取申请者的申请材料信息(S10)；其中，所述申请材料信息包含申请者的申请需求信息；基于申请者的申请需求信息，生成对应的测试卷(S20)；接收申请者对所述测试卷的作答结果(S30)；根据申请者的所述申请材料及申请者对所述测试卷的作答结果，确定申请者的学校选择要素指标及专业选择要素指标(S40)；根据预设申请竞争力模型中的测评标准，申请者的所述申请材料、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果(S50)；查找与申请者的学校选择要素指标、专业选择要素指标、学校申请竞争力结果及专业申请竞争力结果匹配的学校及专业，并生成对应的学校及专业推荐方案(S60)。还提供了一种学校及专业推荐系统。解决了现有择校咨询模式难以将申请者自身情况、择校需求和择校审核指标全面整体考察的问题。

Description

学校及专业推荐方法及系统
技术领域
本发明涉及信息处理技术领域，尤其涉及学校及专业推荐方法及系统。
背景技术
随着生活水平的提高，除了进入国内学校学习以外，赴国外进行学习或者深造已经形成一种新风尚。而随着计算机网络技术的飞速发展，很多申请者在申请学校之前会通过互联网查询和了解不同学校/专业的相关录取信息，但是逐一的查询费时费力。
现有的信息整合网站能够将学校/专业录取信息整合，但是缺乏有效及针对性的推荐；申请者面对海量的信息同样会无所适从。而一些教育咨询机构的咨询顾问人员虽然可以依靠自身的从业经验及相关的信息查询匹配工具，根据申请者的个性化需求查找出部分与申请者择校审核指标（如高考成绩，平均绩点、TOEFL成绩（The Test of English as a Foreign Language，托福考试）、GRE成绩（Graduate Record Examination，美国研究生入学考试））较为吻合的部分学校/专业。但是，上述咨询顾问的服务模式同样存在以下突出的问题：
1、无法帮助申请者全面了解自身情况，例如兴趣、爱好、特长、性格，而咨询顾问人员也缺乏充分挖掘申请者自身状况的能力，难以对申请者自身情况、择校需求（如个人兴趣、学校/专业的选择偏好）和择校审核指标进行全面整体考察，寻找到真正适合申请者自身实际情况的学校/专业；
2、咨询顾问人员仅凭个人经验很难让咨询工作变得标准化，也难以提供透明、完整的学校/专业申请信息；同时咨询服务费用高昂，一般的申请者难以承受。
3、申请者与咨询顾问人员接洽及咨询的过程，同样会花费申请者大量的时间和金钱，申请者也难以直观准确地考察教育咨询机构和咨询顾问人员的服务水平。
上述内容仅用于辅助理解本发明的技术方案，并不代表承认上述内容是现有技术。
发明内容
本发明的主要目的在于提供一种学校及专业推荐方法及系统，旨在解决现有择校咨询模式难以将申请者自身情况、择校需求和择校审核指标全面整体考察的问题，以提供真正适合申请者自身实际情况的学校/专业推荐方案。
为实现上述目的，本发明提供一种学校及专业推荐方法，所述方法包括以下步骤：
获取申请者的申请材料信息；其中，所述申请材料信息包含申请者的申请需求信息；
基于申请者的申请需求信息，生成对应的测试卷；其中，所述测试卷包含与申请者的所述申请需求信息关联的预设个体指标测试题；
接收申请者对所述测试卷的作答结果；
根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果；
根据所述申请竞争力结果，查找与所述申请竞争力结果匹配的学校，并生成对应的学校推荐方案。
优选地，所述根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果的步骤，具体包括：
在接收到申请者对测试卷的所述作答结果之后，将申请者的作答结果输入至预设申请竞争力模型中；
将申请者的申请材料信息输入至预设申请竞争力模型中；
基于申请者的申请材料信息和申请者针对测试卷的作答结果对申请者的学校申请竞争力及专业申请竞争力进行测试和评分，并输出申请者的学校申请竞争力结果及专业申请竞争力结果。
优选地，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
获取申请者的使用特征信息；
根据申请者的所述使用特征信息，确定申请者的学校选择偏好特征及专业选择偏好特征；
根据预设匹配规则，查找与申请者的学校选择偏好特征及专业选择偏好特征匹配的学校。
优选地，所述查找匹配的学校的步骤之后，还包括：
获取申请者选择的学校的信息，以确定申请者选择的学校的实力等级；
获取申请者选择的专业的信息，以确定申请者选择的专业的实力等级；
确定与所述学校申请竞争力结果匹配的学校的实力等级；
若申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
优选地，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
获取当前申请者对所述学校申请竞争力结果及所述专业申请竞争力结果的第一类评价信息；
获取当前申请者对目标学校的第二类评价信息；
获取目标学校对当前申请者的第三类评价信息；
根据所述第一类评价信息、及/或所述第二类评价信息、及/或所述第三类评价信息，调整所述预设申请竞争力模型中的相关参数，并对应调整所述预设申请竞争力模型。
优选地，所述根据所述申请竞争力结果，匹配对应的学校，并生成对应的学校推荐方案的步骤之后，还包括：
获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；
根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；
根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；
若是，则生成并向申请者端推送所述申请提示消息。
优选地，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；
根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；
根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；
若是，则生成并向申请者端推送所述申请提示消息。
优选地，所述确定与目标学校对应的目标专业的申请热度值的步骤之后，还包括：
获取目标学校的实力等级；
根据目标学校的实力等级，搜寻与目标学校的实力等级相同的其它学校；
根据搜寻结果，获取搜寻出的学校对应的目标专业的申请热度值；
若搜寻出的学校对应的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值；则生成与搜寻出的学校对应的目标专业的推荐方案。
优选地，所述确定与目标学校对应的目标专业的申请热度值的步骤之后，还包括：
获取其它学校的目标专业的申请热度值；
搜寻出符合预设条件的其它学校的目标专业，并生成与搜寻出的其它学校的目标专业对应的学校及专业推荐方案；
其中，所述预设条件为：其它学校的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值。
优选地，所述向申请者端发送预录取信息的步骤之后，还包括：
在接收到所述招生端发送的预设录取确认信息时，更新对应学校的已录取人数。
此外，为实现上述目的，本发明还提供一种学校及专业推荐系统，包括：所述学校及专业推荐系统包括平台端、申请者端；所述平台端与所述申请者端通信连接；所述平台端包括获取单元、测试单元、申请竞争力测评单元及推荐单元；
所述获取单元，用于获取申请者端发送的申请者的申请材料信息；其中，所述申请材料信息包含申请者的申请需求信息；
所述测试单元，用于基于申请者的申请需求信息，生成对应的测试卷；其中，所述测试卷包含与申请者的所述申请需求信息关联的预设个体指标测试题；
所述获取单元，还用于接收申请者对所述测试卷的作答结果；
所述申请竞争力测评单元，用于根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果；
所述推荐单元，用于查找与申请者的学校选择要素指标、专业选择要素指标、学校申请竞争力结果及专业申请竞争力结果匹配的学校及专业，并生成对应的学校及专业推荐方案。
优选地，在接收到申请者对测试卷的所述作答结果之后，将申请者的作答结果输入至预设申请竞争力模型中；将申请者的申请材料信息输入至预设申请竞争力模型中；基于申请者的申请材料信息和申请者针对测试卷的作答结果对申请者的学校申请竞争力及专业申请竞争力进行测试和评分，并输出申请者的学校申请竞争力结果及专业申请竞争力结果。
优选地，所述获取单元还用于获取申请者的使用特征信息，并将所述使用特征信息发送至所述推荐单元；
所述推荐单元还用于根据申请者的所述使用特征信息，确定申请者的学校选择偏好特征及专业选择偏好特征；根据预设匹配规则，查找与申请者的学校选择偏好特征及专业选择偏好特征匹配的学校。
优选地，所述平台端还包括申请竞争力分析及提升单元；
所述获取单元，还用于获取申请者选择的学校的信息，以及获取申请者选择的专业的信息，并将学校及专业的信息发送至所述申请竞争力分析及提升单元；
所述申请竞争力分析及提升单元，用于确定申请者选择的学校的实力等级及申请者选择的专业的实力等级；申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
优选地，所述申请竞争力测评单元还用于获取当前申请者对所述学校申请竞争力结果及所述专业申请竞争力结果的第一类评价信息；获取当前申请者对目标学校的第二类评价信息；获取目标学校对当前申请者的第三类评价信息；根据所述第一类评价信息、及/或所述第二类评价信息、及/或所述第三类评价信息，调整所述预设申请竞争力模型中的相关参数，并对应调整所述预设申请竞争力模型。
优选地，所述学校及专业推荐系统还包括招生端；所述平台端与所述招生端通信连接；
所述获取单元，还用于向匹配的学校对应的招生端发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的；
所述获取单元，还用于当接收到所述招生端发送的申请邀请请求时，向申请者端发送预录取信息。
优选地，所述推荐单元还用于获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；若是，则生成并向申请者端推送所述申请提示消息。
优选地，所述推荐单元还用于获取目标学校的实力等级；根据目标学校的实力等级，搜寻与目标学校的实力等级相同的其它学校；根据搜寻结果，获取搜寻出的学校对应的目标专业的申请热度值；若搜寻出的学校对应的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值；则生成与搜寻出的学校对应的目标专业的推荐方案。
优选地，所述推荐单元还用于获取其它学校的目标专业的申请热度值；搜寻出符合预设条件的其它学校的目标专业，并生成与搜寻出的其它学校的目标专业对应的学校及专业推荐方案；
其中，所述预设条件为：其它学校的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值。
优选地，所述推荐单元还用于在接收到所述招生端发送的预设录取确认信息时，更新对应学校的已录取人数。
本发明提供的一种学校及专业推荐方法及系统，结合申请者的申请材料信息、申请需求信息及与其关联的预设个体指标，对申请者自身情况、择校需求和择校审核指标进行全面整体考察，确定出申请者的申请竞争力结果，查找出与申请者的申请竞争力结果匹配的学校，并生成对应的学校推荐方案，从而向申请者推荐更加符合申请者的自身实际情况的学校，有助于提高申请者与申请学校及申请专业的匹配度，从而有效地提升申请者的申请成功率。向申请者提供测试卷进行作答测评的方式相较于以往咨询顾问人员人工咨询的方式，节省了人力及物力，有助于实现咨询过程的电子化、标准化和智能化，从而提高申请者的测评效率和提升使用体验，也实现了申请者与学校之间的双向选择。
附图说明
图1为本发明学校及专业推荐方法第一实施例的流程示意图；
图2为本发明学校及专业推荐方法第二实施例的流程示意图；
图3为本发明学校及专业推荐方法第三实施例的流程示意图；
图4为本发明学校及专业推荐方法第四实施例的流程示意图；
图5为本发明学校及专业推荐系统的各组成部分的示意框图；
图6为本发明学校及专业推荐系统实现学校及专业推荐方案的双向推荐过程示意图；
图7为本发明学校及专业推荐系统的功能示意图。
本发明目的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
请参照图1，图1为本发明学校及专业推荐方法第一实施例的流程示意图。在本实施例中，所述方法包括以下步骤：
步骤S10，获取申请者的申请材料信息；
在本发明实施例中，申请者在登录实现本实施例的学校及专业推荐系统之后，申请者可以输入自己的申请材料信息。申请材料信息可以包括各类择校审核指标数据，具体包括各类结构化数据、半结构化数据、非结构化数据，例如①背景资料，包括但不限于：曾就读高中、曾就读大学、曾就读大学的院系学术声誉排名；②学术能力资料，包括但不限于高中GPA、大学GPA、大学专业GPA、年级/班级排名、荣誉课程(AP/Honor)、A-G科目（A为历史、社会科学，B为英语，C为数学，D为实验室科学，E为除英语之外的语言，F为视觉与表演艺术，G为大学预科选修课）、科研经历、发表论文情况；③课外活动资料，包括社团活动、体育活动、艺术才能、领导活动、预科情况、志愿者经历、工作经历；④标准化考试资料，包括AP/Honor成绩、TOEFL成绩、IELTS成绩、SAT成绩、SAT专业测试(SAT Subject)成绩、ACT成绩、GRE成绩、GRE专业测试成绩、GMAT成绩、LSAT成绩及其他语言和专业性测试成绩；⑤其他预设材料，包括但不限于：获奖情况、个人进步趋势、推荐信、自荐信。
此外，所述申请材料信息包含申请者的申请需求信息；
申请者的申请需求信息具体可以是对学校/专业的偏好情况，包括各类申请需求项，例如学校所在国家地区、希望入读的学校/专业、学校地点（如一些进行理科研究生申请的申请者偏好安静的学习地点，则对应学校地点为坐落在郊区或县城周边）、学校类型（如一些申请者偏好文理学院，则对应学校类型为文理学院）。另外本发明实施例中申请者的申请需求信息还可以包括申请者在申请时的其它各类需求，比如除了学校/专业之外还可以包括奖学金资助、学校办学规模、学校/专业排名、学校环境、配套设施、男女比例、种族比例等。
在本发明的一些实施例中，在步骤S10之前，还可以包括如下步骤：在申请者成功注册账号时，为申请者分配注册身份标识码；相应地，申请者使用该注册身份标识码登录学校及专业推荐系统。此外，若该申请者已经进行过申请竞争力结果的测评，则直接反馈历史学校/专业推荐记录，而不用每次都要进行测评，从而简化学校/专业推荐的流程，提高向申请者推荐学校/专业信息的效率。
步骤S20，基于申请者的申请需求信息，生成对应的测试卷；其中，所述测试卷包含与申请者的所述申请需求信息关联的预设个体指标测试题；
步骤S20具体实施包括：
步骤S21，根据申请者的所述申请材料信息，抓取组成所述申请需求信息的各申请需求项；
也即，从申请者的申请材料信息中利用数据挖掘相关算法提取出各类申请需求项。
步骤S22，查找与所述申请需求项关联的预设个体指标项；
步骤S23，基于所述预设个体指标项，从测试数据库中调取对应的测试题，以生成所述测试卷。
需要说明的是，预先将不同类型的申请需求项与若干个预设个体指标项建立关联关系。其中，预设个体指标项用于衡量申请者的知识、能力、技能、心理等评价项目的发展水平。例如，评价项目为“性格适应性”，其对应的预设个体指标项具体包括：意志力、内/外向性倾向、韧性；评价项目为“个人能力”，其对应的预设个体指标项具体包括：合作协调能力、分析与评估、计划与执行力、责任心、创新能力、资源分配能力、项目管理能力、领导组织能力、工程技术能力。也即，对于特定的学校/专业而言，录取的学生具有较为稳定的群体特征；而预设个体指标项可以反映特定的学校/专业录取的学生的群体特征。
测试数据库中涵盖有大量的测试题，这些测试题对应于需要测评的预设个体指标项。因此，生成的测试卷中包含有结合申请者的申请需求信息（如希望入读的学校、希望入读的专业）和申请材料信息、对特定学校/专业的分析而制定出的不同内容多维度的测试题。
例如，“希望入读的专业”申请需求项关联的预设个体指标项包括：文理偏好程度、意志力水平、思维模式。可理解地，选择文科专业与选择理科专业的申请者的上述预设个体指标项会存在明显的差异。因此，通过生成测试卷的方式对申请者的上述预设个体指标项进行测评，以此确定申请者与“希望入读的专业”的匹配度及申请竞争力水平。
步骤S30，接收申请者对所述测试卷的作答结果；
在生成测试卷后，将上述测试卷发送至申请者的账号，并接收申请者对测试卷的作答结果。
步骤S40，根据申请者的所述申请材料信息及申请者对所述测试卷的作答结果，确定申请者的学校选择要素指标及专业选择要素指标；
这里需要说明的是，对于申请者而言，选择合适的学校不仅仅需要考虑入读哪一间学校，一般还需要考虑是否入读该学校的某一专业。因此，本发明是基于学校选择、专业选择两个大维度实现向申请者推荐更加适合申请者自身实际情况的学校及专业。
其中，学校选择要素指标是指基于学校选择的维度确定的一系列要素指标，例如申请者希望入读的学校类型、学校实力等级、学校所处的国家或地区。专业选择要素指标是指基于专业选择的维度确定的一系列要素指标，例如申请者希望入读的专业、个人就业倾向、个人思维模式。学校选择要素指标及专业选择要素指标的确定，具体可以从申请者的申请材料信息及申请者对测试卷的作答结果中提取对应的指标/数据信息，并进行对应的数据筛选、清洗及处理，生成对应的学校选择要素指标或者专业选择要素指标。
步骤S50，根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果；
步骤S50具体包括：
步骤S51，在接收到申请者对测试卷的所述作答结果之后，将申请者的作答结果输入至预设申请竞争力模型中；
步骤S52，将申请者的申请材料信息输入至预设申请竞争力模型中；
步骤S53，基于申请者的申请材料信息和申请者针对测试卷的作答结果对申请者的学校申请竞争力及专业申请竞争力进行测试和评分，并输出申请者的学校申请竞争力结果及专业申请竞争力结果。
本发明实施例中的预设申请竞争力模型是指集成了申请某一学校/专业所需要具备的各类能力条件特征的分析模型。将申请者的申请材料信息和申请者针对测试卷的作答结果输入至预设申请竞争力模型中，基于学校、专业两个不同的维度分别计算得到申请者的学校申请竞争力结果、专业申请竞争力结果。也即，申请者的学校申请竞争力结果用于表征申请者在申请某一学校时的竞争力水平，申请者的专业申请竞争力结果用于表征申请者在申请某一专业时的竞争力水平。
举例来说，针对赴美国留学申请者（本科申请者、大学毕业生），采用行为事件访谈法、德尔菲法、问卷调查法、360度考核法、专家数据库系统(Expert Database System）和观察法等获取效标样本（即过往的赴美国留学申请者）的有关申请竞争力特征数据，再经过提炼和验证，以申请结果信息为导向，筛选出不同的学校及专业对于申请者的招录指标要求。一种招录指标如表1所示。其中，表1为美国研究生申请者对应于计算机软件工程专业的通用申请竞争力模型包含的招录指标。
表1
模块指标名称 指标分类 指标名称 指标分类
学术能力 曾就读大学排名 学校类型 学校全美综合排名
曾就读大学的院系学术声誉排名 学校全美专业排名
大学GPA 学校地理位置
专业GPA 专业能力 编程语言能力
年级/班级排名 数学能力
科研经历 逻辑推理能力
发表论文数量（第一作者） 计算机操作能力
发表论文数量（第二作者） 性格适应性 意志力
课外活动 社团活动 内/外向性
体育活动 韧性
艺术才能 个人能力 沟通能力
领导活动 合作协调能力
预科 分析与评估
志愿者（小时） 计划与执行力
工作经历 责任心
标准化考试 TOEFL成绩 创新能力
GRE成绩 资源分配能力
GRE Subject成绩 项目管理能力
其他预设 材料 获奖情况 领导组织能力
推荐信 工程技术能力
自荐信
个人进步趋势
例如，在计算申请者的学校申请竞争力结果时，申请竞争力模型中与学校申请竞争力结果计算相关的模块指标包括表1中的学术能力、课外活动、学校类型、其他预设材料；在具体计算时，将对应模块指标的各子项的数据通过申请竞争力模型中的计算模型（不同的模块指标对应不同的量化及评分规则）进行测试和计算，最终得到申请者的学校申请竞争力结果。学校申请竞争力结果的具体表现形式可以是文字描述、分数、等级级别、百分数；例如，学校申请竞争力结果为一总得分。
进一步举例说明：如表2所示，列举出某一申请者的四大模块指标的竞争力结果。
表2 某一申请者的模块指标的学校申请竞争力结果
模块指标 竞争力结果得分
学术能力 83分
课外活动 85分
学校类型 90分
其他预设材料 86分
一种学校申请竞争力结果的计算公式为：P=a*A+b*B+c*C+d*D
其中，P表示学校申请竞争力结果总分；A、B、C、D分别表示申请者的学术能力、课外活动、学校类型、其他预设材料对应的竞争力结果得分，a、b、c、d表示与A、B、C、D分别对应的权重系数。a、b可取较大值，c、d可取较小值，以突出学术能力、课外活动对于申请者申请学校的重要程度。申请竞争力结果总分越高，表明申请者在申请学校时的成功概率更高。
类似地，在计算申请者的专业申请竞争力结果时，申请竞争力模型中与学校申请竞争力结果计算相关的模块指标包括表1中的学术能力、课外活动、专业能力、性格适应性、个人能力；在具体计算时，将对应模块指标的各子项的数据通过申请竞争力模型中的计算模型（具有不同的量化及评分规则）进行测试和计算，最终得到申请者的专业申请竞争力结果。专业申请竞争力结果的具体表现形式可以是文字描述、分数、等级级别、百分数等。例如，专业申请竞争力结果为一总得分或者某一等级。计算申请者的学校申请竞争力结果与上述学校申请竞争力结果的计算方法类似，此处不再赘述。
步骤S60，查找与申请者的学校选择要素指标、专业选择要素指标、学校申请竞争力结果及专业申请竞争力结果匹配的学校及专业，并生成对应的学校及专业推荐方案。
一种具体实施包括：从存储学校各类信息的数据库中查找与申请者的学校申请竞争力结果匹配的第一批学校，再从第一批学校中筛选出与申请者的学校选择要素指标匹配的第二批学校。基于筛选的结果，在第二批学校中查找出与申请者的专业申请竞争力结果匹配的第三批学校，最后从第三批学校中筛选出与申请者的专业选择要素指标匹配的第四批学校及对应的专业。其中，最后筛选出的专业为第四批学校中的学校开设的专业。
更具体地，查找与申请者的学校申请竞争力结果匹配的学校，包括：基于各学校的过往录取申请者的平均学校申请竞争力结果，将申请者的学校申请竞争力结果与各学校的过往录取申请者的平均学校申请竞争力结果分别进行对比；若申请者的学校申请竞争力结果与某一学校的过往录取申请者的平均学校申请竞争力结果的差距在某一预设范围内，则判定该学校与申请者的学校申请竞争力结果匹配。
基于已匹配的学校，将申请者的学校选择要素指标作为筛选选项，进行筛选。
进一步地，基于某一筛选出的学校的各个专业的过往录取申请者的专业申请竞争力结果，得到各个专业的平均专业申请竞争力结果，并将申请者的专业申请竞争力结果与各个专业的平均专业申请竞争力结果分别进行对比；若申请者的专业申请竞争力结果与某一专业的平均专业申请竞争力结果的差距在某一预设范围内，则判定该专业与申请者的专业申请竞争力结果匹配。
基于已匹配的专业，将申请者的专业选择要素指标作为筛选选项，进行筛选，最终得到匹配的学校及对应的可进行申请的专业，并生成包含匹配的学校及对应的可进行申请的专业的推荐方案。
生成的学校及专业推荐方案具体包括上述计算出的申请者的模块指标的学校/专业申请竞争力结果、适合申请者的学校及专业、以及申请者的知识、技术等方面的优势、不足及对应的竞争力提升建议。此外，生成的学校及专业推荐方案还可以包括：申请者的某一学校的某一专业的成功概率、申请者的学校/专业竞争力排名等。将上述学校及专业推荐方案提供给申请者，可以通过以下的至少一种方式向上述申请者提供上述学校及专业推荐方案：以网页反馈结果的方式推送，或以移动通讯的方式推送，或以邮件订阅的方式推送，或以即时通讯的方式推送。也就是说，学校及专业推荐系统向申请者反馈学校/专业推荐方案可以借用现有的网络信息传递方式，以多种反馈方式向申请者推荐学校/专业信息，提高申请者的申请效率。
可理解地，在查找匹配的学校前，可以根据实际需要设置匹配度。例如设置匹配度较低时，相当于模糊匹配；然后在设置一较高的匹配度，在较低匹配度的查找结果中继续查找符合较高匹配度的学校，从而增加查找的适应范围，以及提高查找的效率。
可理解地，在生成对应的学校及专业推荐方案的步骤之后，向申请者端发送所述学校及专业推荐方案。其中，申请者端具体可包括网页端、移动应用程序端、微信小程序、公众号等；申请者可以通过申请者端方便且及时地查看该学校推荐方案，有助于申请学校的信息参考。
可选地，学校的招生人员可以通过学校端获取到申请者的申请需求信息及竞争力结果，从而挑选合适的学生并发送对应的申请邀请。
本实施例提供的一种学校及专业推荐方法，具有如下有益效果：(1)有机地结合申请者的申请材料信息、申请需求信息及与其关联的预设个体指标，实现了对申请者自身情况、择校需求和择校审核指标进行全面整体考察，使得申请者的申请竞争力结果更加符合申请者的自身实际情况；基于学校及专业两个维度综合评估，生成的学校及专业推荐方案有助于提高申请者与申请学校及申请专业的匹配度，从而有效地提升申请者的申请成功率。(2)向申请者提供测试卷进行作答测评的方式相较于以往咨询顾问人员人工咨询的方式，节省了人力及物力，有助于实现咨询过程的电子化、流程标准化和智能化，从而提高申请者的测评效率和提升使用体验。（3）实现了申请者与学校之间的双向选择，也即申请者可以选择学校进行申请，学校也可以挑选合适的学生并发送对应的申请邀请，相比以往学生申请、学校挑选的单向模式，提高了择校精准度，能够为学校输送更加优秀且适合的申请者。
请参照图2，图2为本发明学校及专业推荐方法第二实施例的流程示意图。在本实施例中，步骤S20之前还包括以下步骤：
步骤S70，获取各个学校录取的历史申请者的申请材料信息及对应的预设个体指标项；
获取的方式具体可以通过爬虫机器人自动抓取或者搜索技术从各类数据库中抓取，还可以通过合作院校或者合作咨询机构组织共享，以及上文所述行为事件访谈法、德尔菲法、问卷调查法、360度考核法、专家数据库系统(Expert Database System）和观察法等获取各个学校录取的历史申请者的申请材料信息及对应的预设个体指标项。此外，已进行学校申请但未被录取的历史申请者的申请材料信息及对应的预设个体指标项同样可以用作样本数据。
步骤S71，根据历史申请者的所述申请材料信息，确定历史申请者的申请需求信息；
步骤S72，根据历史申请者的所述申请需求信息，确定与所述申请需求信息对应的申请需求项；
步骤S73，将所述申请需求项与预设个体指标项建立关联关系；
具体的关联关系可以根据实际的实验考察数据确定。
步骤S74，建立测试数据库；其中，所述测试数据库包含与预设个体指标项对应的测试题。
测试数据库中涵盖有大量的测试题，这些测试题对应于需要测评的预设个体指标项。这样，只要确定需要测评的预设个体指标项，即可提取出相应的测试题，以供申请者作答。同时，基于历史申请者的大量、多维度的过往有效数据建立的测试数据库保证了全面且有效地反映不同学校的不同专业录取的学生的群体特征，进而确保申请者的申请竞争力测评结果的准确有效性。
进一步地，请参照图3，图3为本发明学校及专业推荐方法第三实施例的流程示意图。在本实施例中，所述根据所述申请竞争力结果，查找与所述申请竞争力结果匹配的学校，并生成对应的学校推荐方案的步骤之后，还包括：
步骤S80，获取申请者选择的学校的信息，以确定申请者选择的学校的实力等级；
步骤S81，获取申请者选择的专业的信息，以确定申请者选择的专业的实力等级；
其中，申请者选择的学校/专业可以是生成的学校及专业推荐方案中的推荐学校/专业，还可以是申请者自主选择的学校/专业。其中，各学校的实力等级可以是通过对各学校过往录取的申请者的申请竞争力结果进行数据统计、平均化后得到，例如对各学校过往录取的申请者的申请竞争力结果进行平均化处理，以得到各学校过往录取的申请者的平均竞争力结果；然后根据各学校过往录取的申请者的平均竞争力结果，将各学校划分成不同的实力等级。各学校同一专业的实力等级可以是通过对各学校同一专业的过往录取的申请者的申请竞争力结果进行数据统计、平均化后得到。
步骤S82，若申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，表明申请者的申请材料信息存在不足或者弱势项目，此时相应地对申请者的申请材料信息进行分析，从而分析出申请者的不足或者弱势项目，也即生成与选择的学校对应的申请竞争力分析及提升方案，以供申请者参考。
例如，申请者选择的学校是第二级别的，而申请者的申请竞争力结果匹配的学校的实力等级为第三级别（级别数字越小表示级别越高，如第二级别、第一级别）。此时，对申请者的所述申请材料信息进行分析。具体可以分析申请者在各类择校审核指标、预设个体指标项相对于对应学校已录取的申请者的平均统计水平的差距与差异度，从而确定申请者在申请该学校时存在的不足或者劣势项目，并查找出与已确定的不足或者劣势项目匹配的提升建议。也即，申请者在申请所述学校的某一专业时的申请竞争力分析及提升方案包括了申请者在申请该学校的某一专业时存在的不足或者劣势项目分析及对应的提升建议，并相应生成申请竞争力分析及提升方案。
可理解地，在生成所述申请竞争力分析及提升方案的步骤之后，向申请者端发送所述申请竞争力分析及提升方案。申请者可以通过申请者端方便且及时地查看所述申请竞争力分析及提升方案，有助于申请者在申请学校/专业之前，知悉自身竞争力的不足与劣势，并进行相应的提升和改进，以便提高自身的申请竞争力。
这样，申请者能够获知自身在申请该学校的某一专业时的不足或者弱势项目，并更有针对性进行提升，从而帮助申请者进行竞争力提升，提高申请学校的成功率。
请参照图4，图4为本发明学校及专业推荐方法第四实施例的流程示意图。在本实施例中，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
步骤S90，向匹配的学校对应的招生端发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的。
例如，所述预申请信息具体包括申请者的各类择校审核指标数据、申请者的申请需求信息，还可以包括申请者的申请竞争力结果。
步骤S91，当接收到所述招生端发送的申请邀请请求时，向申请者端发送预录取信息。
当学校的招生人员看到平台端推送的申请者的预申请信息时，若对申请者有录取的意向，则可以通过招生端向平台端发送申请邀请请求。平台端相应地向对应申请者的申请者端发送预录取信息。
这样，即实现了向学校精准地推荐较为符合学校录取条件及录取学生群体特征的申请者，提高学校的招生精准度，帮助学校录取到更合适的申请者。同时促进了申请者与学校的双向匹配与信息互动，摆脱了过往需要申请者与学习进行线下沟通的繁琐流程与时间耗费，提高了二者的沟通效率。
此外，本发明实施例还可以不断地收集各申请者测评数据，以及申请者与所推荐学校/专业的匹配成功率，以回归法或其它相关的验证方法，通过调整测评方式，调整各类测试题目的内容和数量，以便提升测评的准确度和有效性，并进一步通过数据分析，调整指标权重及指标标准分转换规则，甚至是调整申请竞争力模型的各个指标，以使申请竞争力模型更趋于完善。
此外，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
步骤S100，获取申请者的使用特征信息；
其中，申请者的使用特征信息具体是指申请者在移动终端、网页端、公众号等终端上进行学校搜索、学校信息查看、浏览相关学校申请的网页（如贴吧、论坛）的使用动作特征，至少包括：申请者浏览的相关学校的特征信息（如学校类型、学校实力等级）、搜索关键词及其搜索热度。
步骤S101，根据申请者的所述使用特征信息，确定申请者的学校选择偏好特征及专业选择偏好特征；
具体可以将申请者的使用特征信息进行关键词统计和相关度计算，从而确定出申请者的在选择学校方面的偏好特征（即学校选择偏好特征），如想要申请的学校类型、学校所在国家或地区、学校的优势学科；以及将申请者的使用特征信息进行关键词统计和相关度计算，从而确定出申请者的在选择专业方面的偏好特征（即专业选择偏好特征）。
步骤S102，根据预设匹配规则，查找与申请者的学校选择偏好特征及专业选择偏好特征匹配的学校。
其中，预设匹配规则包含了将数据库与学校选择偏好特征及专业选择偏好特征关联的相关规则。由此，基于申请者的择校偏好匹配出若干个申请者感兴趣的学校及对应的专业，并生成新的学校及专业推荐方案，以供申请者参考。这样，基于申请者的使用特征信息，向申请者推荐的学校及专业更加精准地匹配申请者的选择偏好，有助于提高学校及专业推荐的精准度。
此外，在本发明的一些实施例中，所述生成对应的学校及专业推荐方案的步骤之后，还包括：步骤S110，获取当前申请者对所述学校申请竞争力结果及所述专业申请竞争力结果的第一类评价信息；步骤S111，获取当前申请者对目标学校的第二类评价信息；
步骤S112，获取目标学校对当前申请者的第三类评价信息；
步骤S113，根据所述第一类评价信息、及/或所述第二类评价信息、及/或所述第三类评价信息，调整所述预设申请竞争力模型中的相关参数，并对应调整所述预设申请竞争力模型。
其中，第一类评价信息是指当前申请者对于所推荐的学校及专业推荐方案的各类评价以及使用效果反馈信息，如所推荐的学校及专业推荐方案是否真实匹配个人情况；第二类评价信息是指当前申请者对于进行申请/面试的学校/专业的各类评价信息，如对于学校/专业的认可程度；第三类评价信息是招生学校对于当前申请者的各类评价信息，如招生学校对当前申请者在面试过程中的评价分数。
基于上述各类评价信息，动态地维护及调整预设申请竞争力模型；调整的相关参数可以是测评标准的模块指标的量化参数或者评分参数。从而使得通过预设申请竞争力模型测评出的申请竞争力更能符合申请者的实际能力状况。例如，向申请者推荐学校方案后，申请者可以对推荐结果和学校进行实名/匿名评论，并可在日后入学之后进行实名/匿名追评。该评论可以帮助提升模型准确率和提升择校体验。
通过动态的申请竞争力模型评分体制，基于不同角度和维度建立多个测试题库，并结合学校/专业的分析，分别制订不同内容多维度的测试题目，申请者通过回答测试题展示出他实际的能力，学校及专业推荐系统自动根据测试者回答的内容做出动态评分，给申请者一个学校/专业申请竞争力的综合评分。根据不同的测评对象随机确定不同的测评题目，自动选择题目并且调整测评篇幅，自动确定不同对象的相应评分标准，并接受测试者的评价及效果反馈，动态调整申请竞争力模型，使得整个测评结果可信度提高。
此外，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
步骤S120，获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；
其中，目标学校是当前申请者端选择的某一学校，与目标学校对应的目标专业是当前申请者端选择的某一学校的某一专业。各申请者可以是某一时期内申请该目标学校的申请者，例如近三年内或者近一年内申请过该学校的申请者；在本发明实施例中，各申请者尤其是指在当年的学校申请周期内已申请该目标学校的同一专业的申请者。申请数据具体可以包括申请该目标学校的同一专业的申请者总数量，及/或各申请者的申请竞争力结果。
步骤S121，根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；
其中，目标学校的目标专业的申请热度值可以反映申请该目标学校的这一专业的热门程度，可以通过计算目标学校的目标专业的申请热度值预测该目标学校的受关注程度与申请难度。一般而言，处于同一实力水平等级的学校的某一专业的受关注程度越大，申请该学校的这一专业时竞争越激烈，申请难度也越大。
本步骤中确定目标学校的申请热度值的具体方式不作限定。
步骤S122，根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；
预设的申请提示消息推送规则可以根据实际需要进行设置，例如目标学校的目标专业的申请热度值超过某一阈值，及/或目标学校申请目标专业的当前申请人数超出计划招生人数的差值超过某一预设差值时，向当前申请者端推送与目标学校对应的申请提示消息。
步骤S123，若是，则生成并向当前申请者端推送所述申请提示消息。
申请提示消息可以包括目标学校的申请热度值、目标学校的当前申请人数、目标学校的计划招生人数及对应的预警提示信息。也即，当目标学校的当前申请人数过多时，自动实现向已申请该目标学校的申请者或者已将该目标学校作为备选的申请学校的申请者发送申请提示消息。
此类基于各申请者对应于目标学校的目标专业的申请数据确定目标专业的申请热度值、向申请者发送申请提示消息的方式，有助于提高申请者与目标学校之间的信息对称性。对于申请者而言，可以及时知道目标学校的目标专业申请热度值、申请难度和相关的申请风险提示信息，从而使得申请决策更为理性；对于目标学校而言，可以避免过多的申请者扎堆申请该学校的目标专业、导致招生工作量更加繁重，也不利于对优秀人才的仔细选拔。
更进一步地，在步骤S123之后，还包括：
步骤S124，获取目标学校的实力等级；步骤S125，根据目标学校的实力等级，搜寻与目标学校的实力等级相同的其它学校；步骤S126，根据搜寻结果，获取搜寻出的学校对应的目标专业的申请热度值；步骤S117，若搜寻出的学校对应的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值；则生成与搜寻出的学校对应的目标专业的推荐方案。
其中，目标学校及其它学校的实力等级可以根据上述第三实施例中的方法确定。在搜寻出与目标学校的实力等级相同的其它学校之后，继续按照以上方法计算搜寻出的学校对应的目标专业的申请热度值，并分别与目标学校对应的目标专业的申请热度值进行比较。当处于相同实力等级的某一学校的某一专业的申请热度值小于或者等于目标学校的同一专业的申请热度值时，表示申请该学校的目标专业的热门程度不高于目标学校，当前申请者申请该学校的目标专业的竞争程度相对较低，申请成功概率较高。
本发明还适用于另一种根据申请热度值生成目标专业的推荐方案，具体为：获取其它学校的目标专业的申请热度值；搜寻出符合预设条件的其它学校的目标专业，并生成与搜寻出的其它学校的目标专业对应的学校及专业推荐方案；其中，所述预设条件为：其它学校的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值。
也即，仅仅考察同一目标专业的申请热度值；当某一学校的同一目标专业的热度值小于或者等于上述已计算出的目标学校的该目标专业的申请热度值时，生成该学校及该目标专业的推荐方案。从而，向申请者提供另一种学校及专业的推荐方案，增加申请者的选择范围。
此外，针对选取的学校及对应的目标专业，生成并发送对应的学校及专业推荐方案至申请端，同样有利于申请者作出更为理性、申请成功概率更高的申请决策，也有助于学校的人才招录。
此外，所述向申请者端发送预录取信息的步骤之后，还包括：
在接收到所述招生端发送的预设录取确认信息时，更新对应学校的已录取人数。
对于某一学校（及其开设的专业）而言，在一个学校（专业）申请周期内的录取名额一般是额定的，因此需要根据该学校（专业）的实际录取情况及时更新该学校（专业）的已录取人数，以便于申请者及时地获取到该学校的已录取人数信息，并作出合理的申请决策。其中，招生端发送预设录取确认信息的情形可以包括但不限于以下情形：申请者确认申请某一学校，并完成相关的申请流程；该学校确认招录该申请者，通过对应对招生端向平台端发送预设录取确认信息，此时平台端根据该预设录取确认信息，更新该学校的已录取人数，例如将已录取人数增加一位。可理解地，申请者端及招生端均可以获取到更新后的学校的已录取人数。这样，有助于学校录取人数信息的透明化，使得申请者与学校之间的信息更加对称，帮助申请者进行更为合理的申请决策。
请参照图5，图5为本发明学校及专业推荐系统第一实施例的系统框图。在本实施例中，所述学校及专业推荐系统包括平台端10、申请者端20；所述平台端10与所述申请者端20通信连接；所述平台端10包括获取单元110、测试单元120、指标确定单元130、申请竞争力测评单元140及学校推荐单元150；
所述获取单元110，用于获取申请者端发送的申请者的申请材料信息；其中，所述申请材料信息包含申请者的申请需求信息；
请参照图6，图6为本发明学校及专业推荐系统的学校推荐实现示意图。申请者通过申请者端20（具体可以是网页端或者应用程序端）在登录实现本实施例的学校及专业推荐系统之后，申请者可以输入自己的申请材料信息。此外，所述申请材料信息包含申请者的申请需求信息；本发明中所指的平台端10在具体部署时，可包括各类处理器、服务器及其它硬件、软件搭建的架构，还包括各类功能模块或功能单元。
申请者的申请需求信息具体可以是对学校/专业的偏好情况，包括各类申请需求项，例如学校所在国家地区、希望入读的学校/专业、学校地点（如一些理科研究生申请者偏好安静的学习地点，则对应学校地点为坐落在郊区或县城周边）、学校类型（如一些申请者偏好文理学院，则对应学校类型为文理学院）。另外本发明实施例中申请者的申请需求信息还可以包括申请者在申请时的其它各类需求，比如除了学校/专业之外还可以包括奖学金资助、学校办学规模、学校/专业排名、学校环境、配套设施、男女比例、种族比例等。
在本发明的一些实施例中，在申请者成功注册账号时，学校及专业推荐系统为申请者分配注册身份标识码；相应地，申请者使用该注册身份标识码登录该系统。此外，若该申请者已经进行过申请竞争力结果的测评，则直接反馈历史学校/专业推荐记录，而不用每次都要进行测评，从而简化学校/专业推荐的流程，提高向申请者推荐学校/专业信息的效率。
所述测试单元120，用于基于申请者的申请需求信息，生成对应的测试卷；其中，所述测试卷包含与申请者的所述申请需求信息关联的预设个体指标测试题；所述测试单元120，具体用于根据申请者的所述申请材料信息，抓取组成所述申请需求信息的各申请需求项；也即，从申请者的申请材料信息中提取出各类申请需求项。查找与所述申请需求项关联的预设个体指标项；基于所述预设个体指标项，从测试数据库中调取对应的测试题，以生成所述测试卷。
可选地，学校的招生人员可以通过学校端获取到申请者的申请需求信息及竞争力结果，从而挑选合适的学生并发送对应的申请邀请。
需要说明的是，预先将不同类型的申请需求项与若干个预设个体指标项建立关联关系。其中，预设个体指标项用于衡量申请者的知识、能力、技能、心理等评价项目的发展水平。例如，评价项目为“性格适应性”，其对应的预设个体指标项具体包括：意志力、内/外向性倾向、韧性；评价项目为“个人能力”，其对应的预设个体指标项具体包括：合作协调能力、分析与评估、计划与执行力、责任心、创新能力、资源分配能力、项目管理能力、领导组织能力、工程技术能力。也即，对于特定的学校/专业而言，录取的学生具有较为稳定的群体特征；而预设个体指标项可以反映特定的学校/专业录取的学生的群体特征。
测试数据库中涵盖有大量的测试题，这些测试题对应于需要测评的预设个体指标项。因此，生成的测试卷中包含有结合申请者的申请需求信息（如希望入读的学校、希望入读的专业）和申请材料信息、对特定学校/专业的分析而制定出的不同内容多维度的测试题。
例如，“希望入读的专业”申请需求项关联的预设个体指标项包括：文理偏好程度、意志力水平、思维模式。可理解地，选择文科专业与选择理科专业的申请者的上述预设个体指标项会存在明显的差异。因此，通过生成测试卷的方式对申请者的上述预设个体指标项进行测评，以此确定申请者与“希望入读的专业”的匹配度及申请竞争力水平。
所述获取单元110，还用于接收申请者对所述测试卷的作答结果；
在生成测试卷后，将上述测试卷发送至申请者端20，并接收申请者对测试卷的作答结果。
所述指标确定单元130，用于根据申请者的所述申请材料信息及申请者对所述测试卷的作答结果，确定申请者的学校选择要素指标及专业选择要素指标；
这里需要说明的是，对于申请者而言，选择合适的学校不仅仅需要考虑入读哪一间学校，一般还需要考虑是否入读该学校的某一专业。因此，本发明是基于学校选择、专业选择两个大维度实现向申请者推荐更加适合申请者自身实际情况的学校及专业。
其中，学校选择要素指标是指基于学校选择的维度确定的一系列要素指标，例如申请者希望入读的学校类型、学校实力等级、学校所处的国家或地区。专业选择要素指标是指基于专业选择的维度确定的一系列要素指标，例如申请者希望入读的专业、个人就业倾向、个人思维模式。学校选择要素指标及专业选择要素指标的确定，具体可以从申请者的申请材料信息及申请者对测试卷的作答结果中提取对应的指标/数据信息，并进行对应的数据筛选、清洗及处理，生成对应的学校选择要素指标或者专业选择要素指标。
所述申请竞争力测评单元140，用于根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果；
具体包括：
在接收到申请者对测试卷的所述作答结果之后，将申请者的作答结果输入至预设申请竞争力模型中；将申请者的申请材料信息输入至预设申请竞争力模型中；基于申请者的申请材料信息和申请者针对测试卷的作答结果对申请者的学校申请竞争力及专业申请竞争力进行测试和评分，并输出申请者的学校申请竞争力结果及专业申请竞争力结果。
本发明实施例中的预设申请竞争力模型是指集成了申请某一学校/专业所需要具备的各类能力条件特征的分析模型。此外，将申请者的申请材料信息和申请者针对测试卷的作答结果输入至预设申请竞争力模型中，基于学校、专业两个不同的维度分别计算得到申请者的学校申请竞争力结果、专业申请竞争力结果。也即，申请者的学校申请竞争力结果用于表征申请者在申请某一学校时的竞争力水平，申请者的专业申请竞争力结果用于表征申请者在申请某一专业时的竞争力水平。
举例来说，针对赴美国留学申请者（本科申请者、大学毕业生），采用行为事件访谈法、德尔菲法、问卷调查法、360度考核法、专家数据库系统(Expert Database System）和观察法等获取效标样本（即过往的赴美国留学申请者）的有关申请竞争力特征数据，再经过提炼和验证，以申请结果信息为导向，筛选出不同的学校及专业对于申请者的招录指标要求。一种招录指标如表1所示。其中，表1为美国研究生申请者对应于计算机软件工程专业的通用申请竞争力模型包含的招录指标。
例如，在计算申请者的学校申请竞争力结果时，申请竞争力模型中与学校申请竞争力结果计算相关的模块指标包括表1中的学术能力、课外活动、学校类型、其他预设材料；在具体计算时，将对应模块指标的各子项的数据通过申请竞争力模型中的计算模型（具有不同的量化及评分规则）进行测试和计算，最终得到申请者的学校申请竞争力结果。学校申请竞争力结果的具体表现形式可以是文字描述、分数、等级级别、百分数等；例如，学校申请竞争力结果为一总得分。
进一步举例说明：如表2所示，列举出某一申请者的四大模块指标的竞争力结果。
一种学校申请竞争力结果的计算公式为：P=a*A+b*B+c*C+d*D
其中，P表示学校申请竞争力结果总分；A、B、C、D分别表示申请者的学术能力、课外活动、学校类型、其他预设材料对应的竞争力结果得分，a、b、c、d表示与A、B、C、D分别对应的权重系数。a、b可取较大值，c、d可取较小值，以突出学术能力、课外活动对于申请者申请学校的重要程度。申请竞争力结果总分越高，表明申请者在申请学校时的成功概率更高。
类似地，在计算申请者的专业申请竞争力结果时，申请竞争力模型中与学校申请竞争力结果计算相关的模块指标包括表1中的学术能力、课外活动、专业能力、性格适应性、个人能力；在具体计算时，将对应模块指标的各子项的数据通过申请竞争力模型中的计算模型（具有不同的量化及评分规则）进行测试和计算，最终得到申请者的专业申请竞争力结果。专业申请竞争力结果的具体表现形式可以是文字描述、分数、等级级别、百分数等。例如，专业申请竞争力结果为一总得分或者某一等级。计算申请者的学校申请竞争力结果与上述学校申请竞争力结果的计算方法类似，此处不再赘述。
所述学校推荐单元150，查找与申请者的学校选择要素指标、专业选择要素指标、学校申请竞争力结果及专业申请竞争力结果匹配的学校及专业，并生成对应的学校及专业推荐方案。
一种具体实施包括：从存储学校各类信息的数据库中查找与申请者的学校申请竞争力结果匹配的第一批学校，再从第一批学校中筛选出与申请者的学校选择要素指标匹配的第二批学校。基于筛选的结果，在第二批学校中查找出与申请者的专业申请竞争力结果匹配的第三批学校，最后从第三批学校中筛选出与申请者的专业选择要素指标匹配的第四批学校及对应的专业。其中，最后筛选出的专业为第四批学校中的学校开设的专业。
更具体地，查找与申请者的学校申请竞争力结果匹配的学校，包括：基于各学校的过往录取申请者的平均学校申请竞争力结果，将申请者的学校申请竞争力结果与各学校的过往录取申请者的平均学校申请竞争力结果分别进行对比；若申请者的学校申请竞争力结果与某一学校的过往录取申请者的平均学校申请竞争力结果的差距在某一预设范围内，则判定该学校与申请者的学校申请竞争力结果匹配。
基于已匹配的学校，将申请者的学校选择要素指标作为筛选选项，进行筛选。
进一步地，基于某一筛选出的学校的各个专业的过往录取申请者的专业申请竞争力结果，得到各个专业的平均专业申请竞争力结果，并将申请者的专业申请竞争力结果与各个专业的平均专业申请竞争力结果分别进行对比；若申请者的专业申请竞争力结果与某一专业的平均专业申请竞争力结果的差距在某一预设范围内，则判定该专业与申请者的专业申请竞争力结果匹配。
基于已匹配的专业，将申请者的专业选择要素指标作为筛选选项，进行筛选，最终得到匹配的学校及对应的可进行申请的专业，并生成包含匹配的学校及对应的可进行申请的专业的推荐方案。
生成的学校及专业推荐方案具体包括上述计算出的申请者的模块指标的学校/专业申请竞争力结果、适合申请者的学校及专业、以及申请者的知识、技术等方面的优势、不足及对应的竞争力提升建议。此外，生成的学校及专业推荐方案还可以包括：申请者的某一学校的某一专业的成功概率、申请者的学校/专业竞争力排名等。将上述学校推荐方案提供给申请者，可以通过以下的至少一种方式向上述申请者提供上述学校及专业推荐方案：以网页反馈结果的方式推送，或以移动通讯的方式推送，或以邮件订阅的方式推送，或以即时通讯的方式推送。也就是说，学校及专业推荐系统向申请者反馈学校/专业推荐方案可以借用现有的网络信息传递方式，以多种反馈方式向申请者推荐学校/专业信息，提高申请者的申请效率。
可理解地，在查找匹配的学校前，可以根据实际需要设置匹配度。例如设置匹配度较低时，相当于模糊匹配；然后在设置一较高的匹配度，在较低匹配度的查找结果中继续查找符合较高匹配度的学校，从而增加查找的适应范围，以及提高查找的效率。
需要说明的是，本发明各实施例中的学校及专业推荐系统同样适用于专业的推荐，这里就不再赘述专业推荐的具体实施方式。
可理解地，在生成对应的学校及专业推荐方案的步骤之后，向申请者端发送所述学校推荐方案。其中，申请者端具体可包括网页端、移动应用程序端、微信小程序、公众号等；申请者可以通过申请者端方便且及时地查看该学校推荐方案，有助于申请学校的信息参考。
本实施例提供的一种学校及专业推荐系统，具有如下有益效果：(1)有机地结合申请者的申请材料信息、申请需求信息及与其关联的预设个体指标，实现了对申请者自身情况、择校需求和择校审核指标进行全面整体考察，使得申请者的申请竞争力结果更加符合申请者的自身实际情况；基于学校及专业两个维度综合评估，生成的学校及专业推荐方案有助于提高申请者与申请学校及申请专业的匹配度，从而有效地提升申请者的申请成功率。(2)向申请者提供测试卷进行作答测评的方式相较于以往咨询顾问人员人工咨询的方式，节省了人力及物力，有助于实现咨询过程的电子化、流程标准化和智能化，从而提高申请者的测评效率和提升使用体验。（3）实现了申请者与学校之间的双向选择，也即申请者可以选择学校进行申请，学校也可以挑选合适的学生并发送对应的申请邀请，相比以往学生申请、学校挑选的单向模式，提高了择校精准度，能够为学校输送更加优秀且适合的申请者。
进一步地，如图5所示，所述平台端10还包括测试数据库模块150；
所述获取单元110，还用于获取各个学校录取的历史申请者的申请材料信息及对应的预设个体指标项；
获取的方式具体可以通过爬虫机器人自动抓取或者搜索技术从各类数据库中抓取，还可以通过合作院校或者合作咨询机构组织共享，以及上文所述行为事件访谈法、德尔菲法、问卷调查法、360度考核法、专家数据库系统(Expert Database System）和观察法等获取各个学校录取的历史申请者的申请材料信息及对应的预设个体指标项。此外，已进行学校申请但未被录取的历史申请者的申请材料信息及对应的预设个体指标项同样可以用作样本数据。
所述测试数据库模块150，用于根据历史申请者的所述申请材料信息，确定历史申请者的申请需求信息；根据历史申请者的所述申请需求信息，确定与所述申请需求信息对应的申请需求项；将所述申请需求项与预设个体指标项建立关联关系；其中，具体的关联关系可以根据实际的实验考察数据确定。
以及，建立测试数据库；其中，所述测试数据库包含与预设个体指标项对应的测试题。
测试数据库中涵盖有大量的测试题，这些测试题对应于需要测评的预设个体指标项。这样，只要确定需要测评的预设个体指标项，即可提取出相应的测试题，以供申请者作答。同时，基于历史申请者的大量、多维度的过往有效数据建立的测试数据库保证了全面且有效地反映不同学校的不同专业录取的学生的群体特征，进而确保申请者的申请竞争力测评结果的准确有效性。
请参照图5，所述平台端还包括申请竞争力分析及提升单元160；
所述获取单元110，还用于获取申请者选择的学校的信息，以及获取申请者选择的专业的信息，并将学校及专业的信息发送至所述申请竞争力分析及提升单元；
其中，申请者选择的学校/专业可以是生成的学校及专业推荐方案中的推荐学校及专业，还可以是申请者自主选择的学校及专业。其中，各学校的实力等级可以是通过对各学校过往录取的申请者的申请竞争力结果进行数据统计、平均化后得到，例如对各学校过往录取的申请者的申请竞争力结果进行平均化处理，以得到各学校过往录取的申请者的平均竞争力结果；然后根据各学校过往录取的申请者的平均竞争力结果，将各学校划分成不同的实力等级。各学校同一专业的实力等级可以是通过对各学校同一专业的过往录取的申请者的申请竞争力结果进行数据统计、平均化后得到。
所述申请竞争力分析及提升单元160，用于确定申请者选择的学校的实力等级及申请者选择的专业的实力等级；申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，表明申请者的申请材料信息存在不足或者弱势项目，此时相应地对申请者的申请材料信息进行分析，从而分析出申请者的不足或者弱势项目，也即生成与选择的学校对应的申请竞争力分析及提升方案，以供申请者参考。
例如，申请者选择的学校是第二级别的，而申请者的申请竞争力结果匹配的学校的实力等级为第三级别（级别数字越小表示级别越高，如第二级别、第一级别）。此时，对申请者的所述申请材料信息进行分析。具体实施时，可以分析申请者在各类择校审核指标、预设个体指标项相对于对应学校已录取的申请者的平均统计水平的差距与差异度，从而确定申请者在申请该学校时存在的不足或者劣势项目，并查找出与已确定的不足或者劣势项目匹配的提升建议。也即，申请者在申请所述学校的某一专业时的申请竞争力分析及提升方案包括了申请者在申请该学校的某一专业时存在的不足或者劣势项目分析及对应的提升建议，并相应生成申请竞争力分析及提升方案。
可理解地，在生成所述申请竞争力分析及提升方案的步骤之后，向申请者端发送所述申请竞争力分析及提升方案。申请者可以通过申请者端方便且及时地查看所述申请竞争力分析及提升方案，有助于申请者在申请学校之前，知悉自身竞争力的不足与劣势，并进行相应的提升和改进，以便提高自身的申请竞争力。
这样，申请者能够获知自身在申请该学校的某一专业时的不足或者弱势项目，并更有针对性进行提升，从而帮助申请者进行竞争力提升，提高申请学校的成功率。
进一步地，如图5所示，所述学校及专业推荐系统还包括招生端30；所述平台端10与所述招生端30通信连接；
所述获取单元110还用于向匹配的学校对应的招生端30发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的；
例如，所述预申请信息具体包括申请者的各类择校审核指标数据、申请者的申请需求信息，还可以包括申请者的申请竞争力结果。
所述获取单元110还用于当接收到所述招生端30发送的申请邀请请求时，向申请者端20发送预录取信息。
当学校的招生人员看到平台端推送的申请者的预申请信息时，若对申请者有录取的意向，则可以通过招生端向平台端发送申请邀请请求。平台端相应地向对应申请者的申请者端发送预录取信息。
这样，即实现了向学校精准地推荐较为符合学校录取条件及录取学生群体特征的申请者，提高学校的招生精准度，帮助学校录取到更合适的申请者。同时促进了申请者与学校的双向匹配与信息互动，摆脱了过往需要申请者与学习进行线下沟通的繁琐流程与时间耗费，提高了二者的沟通效率。
进一步地，所述获取单元110还用于获取申请者的使用特征信息，并将所述使用特征信息发送至所述学校推荐单元150；
其中，申请者的使用特征信息具体是指申请者在移动终端、网页端、公众号等终端上进行学校搜索、学校信息查看、浏览相关学校申请的网页（如贴吧、论坛）的使用动作特征，至少包括：申请者浏览的相关学校的特征信息（如学校类型、学校实力等级）、搜索关键词及其搜索热度。
所述学校推荐单元150还用于根据申请者的所述使用特征信息，确定申请者的学校选择偏好特征及专业选择偏好特征；根据预设匹配规则，查找与申请者的学校选择偏好特征及专业选择偏好特征匹配的学校。
具体可以将申请者的使用特征信息进行关键词统计和相关度计算，从而确定出申请者的在选择学校方面的偏好特征（即学校选择偏好特征），如想要申请的学校类型、学校所在国家或地区、学校的优势学科；以及将申请者的使用特征信息进行关键词统计和相关度计算，从而确定出申请者的在选择专业方面的偏好特征（即专业选择偏好特征）。
其中，预设匹配规则包含了将数据库与学校选择偏好特征及专业选择偏好特征关联的相关规则。由此，基于申请者的择校偏好匹配出若干个申请者感兴趣的学校及对应的专业，并生成新的学校及专业推荐方案，以供申请者参考。这样，基于申请者的使用特征信息，向申请者推荐的学校及专业更加精准地匹配申请者的选择偏好，有助于提高学校及专业推荐的精准度。
进一步地，所述申请竞争力测评单元140还用于获取当前申请者对所述学校申请竞争力结果及所述专业申请竞争力结果的第一类评价信息；获取当前申请者对目标学校的第二类评价信息；获取目标学校对当前申请者的第三类评价信息；根据所述第一类评价信息、及/或所述第二类评价信息、及/或所述第三类评价信息，调整所述预设申请竞争力模型中的相关参数，并对应调整所述预设申请竞争力模型。
其中，第一类评价信息是指当前申请者对于所推荐的学校及专业推荐方案的各类评价以及使用效果反馈信息，如所推荐的学校及专业推荐方案是否真实匹配个人情况；第二类评价信息是指当前申请者对于进行申请/面试的学校/专业的各类评价信息，如对于学校/专业的认可程度；第三类评价信息是招生学校对于当前申请者的各类评价信息，如招生学校对当前申请者在面试过程中的评价分数。
基于上述各类评价信息，动态地维护及调整预设申请竞争力模型；调整的相关参数可以是测评标准的模块指标的量化参数或者评分参数。从而使得通过预设申请竞争力模型测评出的申请竞争力更能符合申请者的实际能力状况。例如，向申请者推荐学校方案后，申请者可以对推荐结果和学校进行实名/匿名评论，并可在日后入学之后进行实名/匿名追评。该评论可以帮助提升模型准确率和提升择校体验。
通过动态的申请竞争力模型评分体制，基于不同角度和维度建立多个测试题库，并结合学校/专业的分析，分别制订不同内容多维度的测试题目，申请者通过回答测试题展示出他实际的能力，学校及专业推荐系统自动根据测试者回答的内容做出动态评分，给申请者一个学校/专业申请竞争力的综合评分。根据不同的测评对象随机确定不同的测评题目，自动选择题目并且调整测评篇幅，自动确定不同对象的相应评分标准，并接受测试者的评价及效果反馈，动态调整申请竞争力模型，使得整个测评结果可信度提高。
进一步地，所述学校推荐单元150还用于获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；
其中，目标学校是当前申请者端选择的某一学校，与目标学校对应的目标专业是当前申请者端选择的某一学校的某一专业。各申请者可以是某一时期内申请该目标学校的申请者，例如近三年内或者近一年内申请过该学校的申请者；在本发明实施例中，各申请者尤其是指在当年的学校申请周期内已申请该目标学校的同一专业的申请者。申请数据具体可以包括申请该目标学校的同一专业的申请者总数量，及/或各申请者的申请竞争力结果。
目标学校的目标专业的申请热度值可以反映申请该目标学校的这一专业的热门程度，可以通过计算目标学校的目标专业的申请热度值预测该目标学校的受关注程度与申请难度。一般而言，处于同一实力水平等级的学校的某一专业的受关注程度越大，申请该学校的这一专业时竞争越激烈，申请难度也越大。
确定目标学校的申请热度值的具体方式不作限定。
所述学校推荐单元150还用于根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；若是，则生成并向申请者端推送所述申请提示消息。
预设的申请提示消息推送规则可以根据实际需要进行设置，例如目标学校的目标专业的申请热度值超过某一阈值，及/或目标学校申请目标专业的当前申请人数超出计划招生人数的差值超过某一预设差值时，向当前申请者端推送与目标学校对应的申请提示消息。
申请提示消息可以包括目标学校的申请热度值、目标学校的当前申请人数、目标学校的计划招生人数及对应的预警提示信息。也即，当目标学校的当前申请人数过多时，自动实现向已申请该目标学校的申请者或者已将该目标学校作为备选的申请学校的申请者发送申请提示消息。
此类基于各申请者对应于目标学校的目标专业的申请数据确定目标专业的申请热度值、向申请者发送申请提示消息的方式，有助于提高申请者与目标学校之间的信息对称性。对于申请者而言，可以及时知道目标学校的目标专业申请热度值、申请难度和相关的申请风险提示信息，从而使得申请决策更为理性；对于目标学校而言，可以避免过多的申请者扎堆申请该学校的目标专业、导致招生工作量更加繁重，也不利于对优秀人才的仔细选拔。
此外，所述学校推荐单元150还用于获取目标学校的实力等级；根据目标学校的实力等级，搜寻与目标学校的实力等级相同的其它学校；根据搜寻结果，获取搜寻出的学校对应的目标专业的申请热度值；若搜寻出的学校对应的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值；则生成与搜寻出的学校对应的目标专业的推荐方案。
其中，目标学校及其它学校的实力等级可以根据上述第三实施例中的方法确定。在搜寻出与目标学校的实力等级相同的其它学校之后，继续按照以上方法计算搜寻出的学校对应的目标专业的申请热度值，并分别与目标学校对应的目标专业的申请热度值进行比较。当处于相同实力等级的某一学校的某一专业的申请热度值小于或者等于目标学校的同一专业的申请热度值时，表示申请该学校的目标专业的热门程度不高于目标学校，当前申请者申请该学校的目标专业的竞争程度相对较低，申请成功概率较高。
此外，所述学校推荐单元150还用于获取其它学校的目标专业的申请热度值；搜寻出符合预设条件的其它学校的目标专业，并生成与搜寻出的其它学校的目标专业对应的学校及专业推荐方案；其中，所述预设条件为：其它学校的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值。
也即，仅仅考察同一目标专业的申请热度值；当某一学校的同一目标专业的热度值小于或者等于上述已计算出的目标学校的该目标专业的申请热度值时，生成该学校及该目标专业的推荐方案。从而，向申请者提供另一种学校及专业的推荐方案，增加申请者的选择范围。
此外，针对选取的学校及对应的目标专业，生成并发送对应的学校及专业推荐方案至申请端，同样有利于申请者作出更为理性、申请成功概率更高的申请决策，也有助于学校的人才招录。
此外，所述学校推荐单元150还用于在接收到所述招生端发送的预设录取确认信息时，更新对应学校的已录取人数。
对于某一学校（及其开设的专业）而言，在一个学校（专业）申请周期内的录取名额一般是额定的，因此需要根据该学校（专业）的实际录取情况及时更新该学校（专业）的已录取人数，以便于申请者及时地获取到该学校的已录取人数信息，并作出合理的申请决策。其中，招生端发送预设录取确认信息的情形可以包括但不限于以下情形：申请者确认申请某一学校，并完成相关的申请流程；该学校确认招录该申请者，通过对应对招生端向平台端发送预设录取确认信息，此时平台端根据该预设录取确认信息，更新该学校的已录取人数，例如将已录取人数增加一位。可理解地，申请者端及招生端均可以获取到更新后的学校的已录取人数。这样，有助于学校录取人数信息的透明化，使得申请者与学校之间的信息更加对称，帮助申请者进行更为合理的申请决策。
如图7所示，图7为本发明学校及专业推荐系统的功能示意图，其中包含的功能为上文提及的各功能单元实现的各项功能。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品；或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质（如ROM/RAM、磁碟、光盘）中，包括若干指令用以使得一台终端设备执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。

Claims (24)

  1. 一种学校及专业推荐方法，其特征在于，所述方法包括以下步骤：
    获取申请者的申请材料信息；其中，所述申请材料信息包含申请者的申请需求信息；
    基于申请者的申请需求信息，生成对应的测试卷；其中，所述测试卷包含与申请者的所述申请需求信息关联的预设个体指标测试题；
    接收申请者对所述测试卷的作答结果；
    根据申请者的所述申请材料信息及申请者对所述测试卷的作答结果，确定申请者的学校选择要素指标及专业选择要素指标；
    根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果；
    查找与申请者的学校选择要素指标、专业选择要素指标、学校申请竞争力结果及专业申请竞争力结果匹配的学校及专业，并生成对应的学校及专业推荐方案。
  2. 如权利要求1所述的学校及专业推荐方法，其特征在于，所述根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果的步骤，具体包括：
    在接收到申请者对测试卷的所述作答结果之后，将申请者的作答结果输入至预设申请竞争力模型中；
    将申请者的申请材料信息输入至预设申请竞争力模型中；
    基于申请者的申请材料信息和申请者针对测试卷的作答结果对申请者的学校申请竞争力及专业申请竞争力进行测试和评分，并输出申请者的学校申请竞争力结果及专业申请竞争力结果。
  3. 如权利要求1所述的学校及专业推荐方法，其特征在于，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
    获取申请者的使用特征信息；
    根据申请者的所述使用特征信息，确定申请者的学校选择偏好特征及专业选择偏好特征；
    根据预设匹配规则，查找与申请者的学校选择偏好特征及专业选择偏好特征匹配的学校。
  4. 如权利要求1所述的学校及专业推荐方法，其特征在于，所述查找匹配的学校的步骤之后，还包括：
    获取申请者选择的学校的信息，以确定申请者选择的学校的实力等级；
    获取申请者选择的专业的信息，以确定申请者选择的专业的实力等级；
    若申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
  5. 如权利要求3所述的学校及专业推荐方法，其特征在于，所述查找匹配的学校的步骤之后，还包括：
    获取申请者选择的学校的信息，以确定申请者选择的学校的实力等级；
    获取申请者选择的专业的信息，以确定申请者选择的专业的实力等级；
    若申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
  6. 如权利要求1所述的学校及专业推荐方法，其特征在于，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
    获取当前申请者对所述学校申请竞争力结果及所述专业申请竞争力结果的第一类评价信息；
    获取当前申请者对目标学校的第二类评价信息；
    获取目标学校对当前申请者的第三类评价信息；
    根据所述第一类评价信息、及/或所述第二类评价信息、及/或所述第三类评价信息，调整所述预设申请竞争力模型中的相关参数，并对应调整所述预设申请竞争力模型。
  7. 如权利要求1所述的学校及专业推荐方法，其特征在于，所述查找匹配的学校的步骤之后，还包括：
    向匹配的学校对应的招生端发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的；
    以及，当接收到所述招生端发送的申请邀请请求时，向申请者端发送预录取信息。
  8. 如权利要求3所述的学校及专业推荐方法，其特征在于，所述查找匹配的学校的步骤之后，还包括：
    向匹配的学校对应的招生端发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的；
    以及，当接收到所述招生端发送的申请邀请请求时，向申请者端发送预录取信息。
  9. 如权利要求1所述的学校及专业推荐方法，其特征在于，所述生成对应的学校及专业推荐方案的步骤之后，还包括：
    获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；
    根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；
    根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；
    若是，则生成并向申请者端推送所述申请提示消息。
  10. 如权利要求7所述的学校及专业推荐方法，其特征在于，所述确定与目标学校对应的目标专业的申请热度值的步骤之后，还包括：
    获取目标学校的实力等级；
    根据目标学校的实力等级，搜寻与目标学校的实力等级相同的其它学校；
    根据搜寻结果，获取搜寻出的学校对应的目标专业的申请热度值；
    若搜寻出的学校对应的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值；则生成与搜寻出的学校对应的目标专业的推荐方案。
  11. 如权利要求7所述的学校及专业推荐方法，其特征在于，所述确定与目标学校对应的目标专业的申请热度值的步骤之后，还包括：
    获取其它学校的目标专业的申请热度值；
    搜寻出符合预设条件的其它学校的目标专业，并生成与搜寻出的其它学校的目标专业对应的学校及专业推荐方案；
    其中，所述预设条件为：其它学校的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值。
  12. 如权利要求6所述的学校及专业推荐方法，其特征在于，所述向申请者端发送预录取信息的步骤之后，还包括：
    在接收到所述招生端发送的录取确认信息时，更新对应学校的已录取人数。
  13. 一种学校及专业推荐系统，其特征在于，所述学校及专业推荐系统包括平台端、申请者端；所述平台端与所述申请者端通信连接；所述平台端包括获取单元、测试单元、指标确定单元、申请竞争力测评单元及推荐单元；
    所述获取单元，用于获取申请者端发送的申请者的申请材料信息；其中，所述申请材料信息包含申请者的申请需求信息；
    所述测试单元，用于基于申请者的申请需求信息，生成对应的测试卷；其中，所述测试卷包含与申请者的所述申请需求信息关联的预设个体指标测试题；
    所述获取单元，还用于接收申请者对所述测试卷的作答结果；
    所述指标确定单元，用于根据申请者的所述申请材料信息及申请者对所述测试卷的作答结果，确定申请者的学校选择要素指标及专业选择要素指标；
    所述申请竞争力测评单元，用于根据预设申请竞争力模型中的测评标准、申请者的所述申请材料信息、申请者对所述测试卷的作答结果，得到申请者的学校申请竞争力结果及专业申请竞争力结果；
    所述推荐单元，用于查找与申请者的学校选择要素指标、专业选择要素指标、学校申请竞争力结果及专业申请竞争力结果匹配的学校及专业，并生成对应的学校及专业推荐方案。
  14. 如权利要求11所述的学校及专业推荐系统，其特征在于，所述申请竞争力测评单元具体用于：在接收到申请者对测试卷的所述作答结果之后，将申请者的作答结果输入至预设申请竞争力模型中；将申请者的申请材料信息输入至预设申请竞争力模型中；基于申请者的申请材料信息和申请者针对测试卷的作答结果对申请者的学校申请竞争力及专业申请竞争力进行测试和评分，并输出申请者的学校申请竞争力结果及专业申请竞争力结果。
  15. 如权利要求11所述的学校及专业推荐系统，其特征在于，所述获取单元还用于获取申请者的使用特征信息，并将所述使用特征信息发送至所述推荐单元；
    所述推荐单元还用于根据申请者的所述使用特征信息，确定申请者的学校选择偏好特征及专业选择偏好特征；根据预设匹配规则，查找与申请者的学校选择偏好特征及专业选择偏好特征匹配的学校。
  16. 如权利要求11所述的学校及专业推荐系统，其特征在于，所述平台端还包括申请竞争力分析及提升单元；
    所述获取单元，还用于获取申请者选择的学校的信息，以及获取申请者选择的专业的信息，并将学校及专业的信息发送至所述申请竞争力分析及提升单元；
    所述申请竞争力分析及提升单元，用于确定申请者选择的学校的实力等级及申请者选择的专业的实力等级；申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
  17. 如权利要求13所述的学校及专业推荐系统，其特征在于，所述平台端还包括申请竞争力分析及提升单元；
    所述获取单元，还用于获取申请者选择的学校的信息，以及获取申请者选择的专业的信息，并将学校及专业的信息发送至所述申请竞争力分析及提升单元；
    所述申请竞争力分析及提升单元，用于确定申请者选择的学校的实力等级及申请者选择的专业的实力等级；申请者选择的学校的实力等级大于所述匹配的学校的实力等级，或者申请者选择的专业的实力等级大于所述匹配的专业的实力等级，则对申请者的所述申请材料信息进行分析，并生成与选择的学校及专业对应的申请竞争力分析及提升方案。
  18. 如权利要求11所述的学校及专业推荐系统，其特征在于，所述申请竞争力测评单元还用于获取当前申请者对所述学校申请竞争力结果及所述专业申请竞争力结果的第一类评价信息；获取当前申请者对目标学校的第二类评价信息；获取目标学校对当前申请者的第三类评价信息；根据所述第一类评价信息、及/或所述第二类评价信息、及/或所述第三类评价信息，调整所述预设申请竞争力模型中的相关参数，并对应调整所述预设申请竞争力模型。
  19. 如权利要求11所述的学校及专业推荐系统，其特征在于，所述学校及专业推荐系统还包括招生端；所述平台端与所述招生端通信连接；
    所述获取单元，还用于向匹配的学校对应的招生端发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的；
    所述获取单元，还用于当接收到所述招生端发送申请邀请请求时，向申请者端发送预录取信息。
  20. 如权利要求13所述的学校及专业推荐系统，其特征在于，所述学校及专业推荐系统还包括招生端；所述平台端与所述招生端通信连接；
    所述获取单元，还用于向匹配的学校对应的招生端发送申请者的预申请信息；其中，所述申请信息是基于申请者的所述申请材料信息生成的；
    所述获取单元，还用于当接收到所述招生端发送申请邀请请求时，向申请者端发送预录取信息。
  21. 如权利要求11所述的学校及专业推荐系统，其特征在于，所述推荐单元还用于获取当前申请者选择的目标学校信息及与目标学校对应的目标专业信息，并获取各申请者对应于目标学校及与目标学校对应的目标专业的申请数据；根据所述申请数据，确定与目标学校对应的目标专业的申请热度值；根据预设的申请提示消息推送规则及所述申请热度值，判断是否向申请者端推送对应的申请提示消息；若是，则生成并向申请者端推送所述申请提示消息。
  22. 如权利要求17所述的学校及专业推荐系统，其特征在于，所述推荐单元还用于获取目标学校的实力等级；根据目标学校的实力等级，搜寻与目标学校的实力等级相同的其它学校；根据搜寻结果，获取搜寻出的学校对应的目标专业的申请热度值；若搜寻出的学校对应的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值；则生成与搜寻出的学校对应的目标专业的推荐方案。
  23. 如权利要求17所述的学校及专业推荐系统，其特征在于，所述推荐单元还用于获取其它学校的目标专业的申请热度值；搜寻出符合预设条件的其它学校的目标专业，并生成与搜寻出的其它学校的目标专业对应的学校及专业推荐方案；
    其中，所述预设条件为：其它学校的目标专业的申请热度值小于或者等于与目标学校对应的目标专业的申请热度值。
  24. 如权利要求16所述的学校及专业推荐系统，其特征在于，所述推荐单元还用于在接收到所述招生端发送的预设录取确认信息时，更新对应学校的已录取人数。
PCT/CN2019/074360 2018-06-29 2019-02-01 学校及专业推荐方法及系统 WO2020001031A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810703303.8 2018-06-29
CN201810703303.8A CN108550095A (zh) 2018-06-29 2018-06-29 学校及专业推荐方法及系统

Publications (1)

Publication Number Publication Date
WO2020001031A1 true WO2020001031A1 (zh) 2020-01-02

Family

ID=63494202

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/074360 WO2020001031A1 (zh) 2018-06-29 2019-02-01 学校及专业推荐方法及系统

Country Status (2)

Country Link
CN (1) CN108550095A (zh)
WO (1) WO2020001031A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111639256A (zh) * 2020-04-20 2020-09-08 广东德诚科教有限公司 基于学科的专业推荐方法、装置、计算机设备和存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108550095A (zh) * 2018-06-29 2018-09-18 藕丝科技（深圳）有限公司 学校及专业推荐方法及系统
CN111191914A (zh) * 2019-12-27 2020-05-22 广东德诚科教有限公司 专业推荐方法、装置、计算机设备和计算机可读存储介质
CN113516372A (zh) * 2021-06-18 2021-10-19 广州启德教育科技有限公司 辅助留学选校的信息匹配方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105069606A (zh) * 2015-07-30 2015-11-18 深圳市软维科技有限公司 一种获取求职者对所申请职位胜任力的方法及装置
CN106168952A (zh) * 2015-05-18 2016-11-30 睿智顾问公司 学系选择系统及其方法
CN106875028A (zh) * 2016-06-17 2017-06-20 江婕 一种辅助择校的信息筛选方法和系统
CN107169899A (zh) * 2017-05-12 2017-09-15 广州阿基德米科技有限公司 留学智能匹配与推荐方法及系统
CN108550095A (zh) * 2018-06-29 2018-09-18 藕丝科技（深圳）有限公司 学校及专业推荐方法及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008515B (zh) * 2014-06-04 2017-11-03 江苏金智教育信息股份有限公司 一种智能选课推荐的方法
CN104182920A (zh) * 2014-08-26 2014-12-03 天脉聚源（北京）教育科技有限公司 测试方法、测试发起端、被测试端和测试系统
CN104658359A (zh) * 2015-03-23 2015-05-27 黄河科技学院 一种英语学习机系统及其数据处理方法
CN105335915A (zh) * 2015-09-11 2016-02-17 西安汇科网络技术有限公司 学生体测考试系统及方法
CN107169058A (zh) * 2017-04-27 2017-09-15 深圳市海云天科技股份有限公司 一种试题打乱顺序方法和系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106168952A (zh) * 2015-05-18 2016-11-30 睿智顾问公司 学系选择系统及其方法
CN105069606A (zh) * 2015-07-30 2015-11-18 深圳市软维科技有限公司 一种获取求职者对所申请职位胜任力的方法及装置
CN106875028A (zh) * 2016-06-17 2017-06-20 江婕 一种辅助择校的信息筛选方法和系统
CN107169899A (zh) * 2017-05-12 2017-09-15 广州阿基德米科技有限公司 留学智能匹配与推荐方法及系统
CN108550095A (zh) * 2018-06-29 2018-09-18 藕丝科技（深圳）有限公司 学校及专业推荐方法及系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111639256A (zh) * 2020-04-20 2020-09-08 广东德诚科教有限公司 基于学科的专业推荐方法、装置、计算机设备和存储介质
CN111639256B (zh) * 2020-04-20 2024-06-04 广东德诚科教有限公司 基于学科的专业推荐方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN108550095A (zh) 2018-09-18

Similar Documents

Publication Publication Date Title
WO2020001031A1 (zh) 学校及专业推荐方法及系统
WO2018205544A1 (zh) 软件项目管理方法、装置、终端及计算机存储介质
WO2019177182A1 (ko) 속성 정보 분석을 통한 멀티미디어 컨텐츠 검색장치 및 검색방법
WO2011083924A2 (ko) 온라인 소셜 네트워크에서 개인의 네트워크 경쟁력과 네트워크 효과를 측정하는 방법
WO2012060532A1 (ko) 특허 평가 모델 생성 방법, 특허 평가 방법, 특허 분쟁 예측 모델 생성 방법, 특허 분쟁 예측 정보 생성 방법, 특허 라이센싱 예측 정보 생성 방법, 특허 리스크 헤징 정보 생성 방법 및 시스템
WO2014115963A1 (ko) 재능경력중심학점 인정 학사관리시스템 및 학사관리방법
WO2021006505A1 (ko) 전문가 경력 관리 방법, 장치 및 프로그램
WO2014084498A2 (ko) 웹사이트와 어플에서의 회원 간 만남주선 시스템
WO2022010255A1 (ko) 기계학습모델을 이용하여 면접영상에 대한 자동화된 평가를 위한 심층질문을 도출하는 방법, 시스템 및 컴퓨터-판독가능 매체
WO2020022611A1 (ko) 재능경력중심 학점인정 학사관리 시스템 및 방법과 이를 이용하는 재능기부은행 서비스 제공 시스템
WO2019154305A1 (zh) 进行学校申请的个人竞争力智能评估系统及方法
WO2021027158A1 (zh) 车辆信息的推送方法、装置、设备及计算机可读存储介质
WO2011007935A1 (ko) 홈페이지 통합 서비스 제공 시스템 및 방법
WO2010090445A2 (ko) 자동 의사 수집 시스템 및 방법
WO2015174743A1 (en) Display apparatus, server, system and information-providing methods thereof
WO2017116215A1 (ko) 평가지표 자율제안에 의한 연구개발과제 선정 시스템 및 방법
WO2020040482A2 (ko) 전문가 플랫폼의 제어 방법, 장치 및 프로그램
WO2020145571A2 (ko) 면접영상 자동평가모델을 관리하는 방법, 시스템 및 컴퓨터-판독가능 매체
WO2020253115A1 (zh) 基于语音识别的产品推荐方法、装置、设备和存储介质
WO2020022819A1 (en) Communication via simulated user
WO2024005329A1 (ko) 인공지능 기반 구성원 평가 피드백 서비스 제공 방법, 장치 및 시스템
WO2024029922A1 (ko) 소프트웨어 기반 기업 esg 경영 관리 장치 및 그 수행 방법
WO2024005330A1 (ko) 인공지능 기반 업무 몰입 상태 판단 및 관리 서비스 제공 방법, 장치 및 시스템
WO2022265127A1 (ko) 인공 지능 학습 기반의 사용자 이탈율 예측 및 사용자 지식 추적 시스템 및 그것의 동작 방법
Isac et al. Enhancing Students’ Entrepreneurial Competencies through Extracurricular Activities—A Pragmatic Approach to Sustainability-Oriented Higher Education

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19825572

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 12/05/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19825572

Country of ref document: EP

Kind code of ref document: A1