WO2021180249A1 - 职业推荐方法、装置、设备和介质 - Google Patents

职业推荐方法、装置、设备和介质 Download PDF

Info

Publication number
WO2021180249A1
WO2021180249A1 PCT/CN2021/087375 CN2021087375W WO2021180249A1 WO 2021180249 A1 WO2021180249 A1 WO 2021180249A1 CN 2021087375 W CN2021087375 W CN 2021087375W WO 2021180249 A1 WO2021180249 A1 WO 2021180249A1
Authority
WO
WIPO (PCT)
Prior art keywords
test
ability
label
occupation
target object
Prior art date
Application number
PCT/CN2021/087375
Other languages
English (en)
French (fr)
Inventor
栗浩洋
薛镇
Original Assignee
上海松鼠课堂人工智能科技有限公司
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 上海松鼠课堂人工智能科技有限公司 filed Critical 上海松鼠课堂人工智能科技有限公司
Priority to AU2021103999A priority Critical patent/AU2021103999A4/en
Publication of WO2021180249A1 publication Critical patent/WO2021180249A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q50/2057—Career enhancement or continuing education service

Definitions

  • This application relates to the technical field of data recommendation, for example, to a career recommendation method, device, device, and medium.
  • the traditional job recommendation method is to use a large number of test questions to test the user's hobbies, personality, etc., so as to recommend corresponding jobs for users with different hobbies or different personalities.
  • This application provides a career recommendation method, device, equipment, and medium that can improve accuracy.
  • This application provides a career recommendation method, which includes:
  • the initial test ability label in the test ability label is determined based on the ability label corresponding to each occupation in the occupation information database;
  • the target ability label is a test ability label for which the target object has the ability corresponding to the test ability label
  • the target occupation is selected from the candidate occupations, and the target occupation is recommended to the target object.
  • This application also provides a career recommendation device, which includes:
  • the push module is configured to push multiple occupational test questions corresponding to the test ability label to the target object; wherein, the initial test ability label in the test ability label is based on the ability corresponding to each occupation in the occupation information database Identified by the label;
  • the determining module is configured to determine the ability test result corresponding to the target object according to the answer results of the multiple occupation test questions for the target object;
  • a screening module configured to screen out the test ability label corresponding to the next ability to be tested from the ability label according to the ability test result;
  • the repeat module is configured to return the multiple professional test questions corresponding to the test ability label pushed to the target object until the test stop condition is met, and multiple ability test results corresponding to the target object are obtained;
  • the determining module is further configured to determine the candidate occupation corresponding to the target ability label according to the multiple ability test results, wherein the target ability label is a test ability label for which the target object has the ability corresponding to the test ability label;
  • the recommendation module is configured to screen a target occupation from the candidate occupations and recommend the target occupation to the target object.
  • the present application also provides a computer device, including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
  • the initial test ability label in the test ability label is determined based on the ability label corresponding to each occupation in the occupation information database;
  • the target ability label is a test ability label for which the target object has the ability corresponding to the test ability label
  • the target occupation is selected from the candidate occupations, and the target occupation is recommended to the target object.
  • This application also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
  • the initial test ability label in the test ability label is determined based on the ability label corresponding to each occupation in the occupation information database;
  • the target ability label is a test ability label for which the target object has the ability corresponding to the test ability label
  • the target occupation is selected from the candidate occupations, and the target occupation is recommended to the target object.
  • Figure 1 is an application environment diagram of a career recommendation method in an embodiment
  • Figure 2 is a schematic flowchart of a career recommendation method in an embodiment
  • FIG. 3 is a schematic diagram of the principle of the difficulty model in an embodiment
  • Figure 4 (a) is an interface diagram of a test version selection page in an embodiment
  • Figure 4(b) is an interface diagram of a test answer page in an embodiment
  • Fig. 5 is an interface diagram of a professional test report in an embodiment
  • Figure 6 is an interface diagram of the analysis of the thinking ability method in the career test report in an embodiment
  • Fig. 7 is a structural block diagram of a career recommendation device in an embodiment
  • Fig. 8 is an internal structure diagram of a computer device in an embodiment.
  • the career recommendation method provided in this application can be applied to the application environment as shown in FIG. 1.
  • the user terminal 110 communicates with the server 120 through the network. Both the user terminal 110 and the server 120 can be used independently to execute the career recommendation method provided in the embodiments of the present application.
  • the user terminal 110 and the server 120 may also be used in cooperation to execute the career recommendation method provided in the embodiment of the present application.
  • the user terminal 110 may be, but is not limited to, a personal computer, a notebook computer, a smart phone, a tablet computer, and a portable wearable device.
  • the server 120 may be implemented as an independent server or a server cluster composed of multiple servers.
  • the server 120 pushes multiple career test questions corresponding to the test ability label to the user terminal 110 where the target object is located; where , The initial test ability label in the test ability label is determined based on the ability label corresponding to each of the multiple occupations in the occupation information database.
  • the user terminal 110 collects the answer results of the target object's answers to multiple occupational test questions, and transmits them to the server 120.
  • the server 120 determines the ability test result corresponding to the target object according to the answer result.
  • the server 120 screens out the test ability label corresponding to the next ability to be tested from the ability label according to the ability test result, and pushes multiple professional test questions corresponding to the next test ability label to the user terminal 110 where the target object is located. To test the ability of the target object. This is repeated until the test stop condition is met, and the test is stopped, and multiple ability test results corresponding to the target object are obtained.
  • the server 120 determines the candidate occupation corresponding to the target ability label according to the multiple ability test results.
  • the target ability label is a test ability label for the target object to have the ability corresponding to the test ability label.
  • the server 120 selects the target occupation from the candidate occupations, and pushes the target occupation to the user terminal 110 where the target object is located.
  • the method provided in this application is based on the ability model for career recommendation.
  • the ability model is also called the Mode of Thinking Capacity Methodology (MCM) model, which splits the learning thinking into thinking and learning ability. (Capacity) and a strategy of learning method (Methodology).
  • MCM Mode of Thinking Capacity Methodology
  • Capacity and a strategy of learning method (Methodology).
  • the corresponding MCM label can be constructed through the MCM model, and the MCM label can also be called the ability label, which is used to distinguish different thinking modes, learning abilities, and learning methods.
  • a career recommendation method is provided.
  • the method is applied to a computer device as an example for description.
  • the computer device may be the user terminal 110 or the server 120 in FIG.
  • the recommended method includes the following steps:
  • S202 Push multiple occupation test questions corresponding to the test ability label to the target object; wherein the initial test ability label in the test ability label is determined based on the ability label corresponding to each occupation in the occupation information database.
  • the target object may be a user object, and the user object may be a natural person, such as a student; the user object may also be a data object that can be processed by a computer device, such as an object represented by a user account.
  • the ability label is the category label of the occupational test question, which can be used to characterize the attribute characteristics of the occupational test question.
  • Capability tags are also called MCM (Mode of thinking Capacity Methodology) tags.
  • Ability labels such as classifying and discussing ideas, communication ability, estimation ability, standard expression ability, planning ability, and law exploration ability, etc. ability labels.
  • a capability corresponds to a capability tag.
  • One ability label can correspond to multiple occupational test questions.
  • Each vocational test question corresponds to at least one ability label, and the at least one ability label corresponding to each vocational test question is determined by the MCM model. Occupation test questions are used to test whether the user has the ability corresponding to the ability label.
  • test capability tag is a capability tag filtered from multiple capability tags.
  • Test ability labels are usually ability labels that appear frequently in multiple occupations. For example, the ability label that appears most frequently in multiple occupations is used as the test ability label. For another example, sort the appearance frequency of multiple ability labels in multiple occupations from high to low, and randomly select one of the ability labels whose ranking is less than the preset rank as the test ability label. For example, when the preset rank is In the fourth place, the computer equipment randomly selects a capability tag from the capability tags corresponding to the top three ranked as the test capability tag.
  • the occupational test questions corresponding to the test ability label are used to test whether the target object has the ability corresponding to the test ability label.
  • the multiple professional test questions under the communication ability label are used to test whether the user has the communication ability corresponding to the communication ability label.
  • the computer device uses the ability label with the highest frequency as the test ability label, and based on the ability test result corresponding to the test ability label, quickly determines the occupation that matches the user's ability among multiple occupations. In other words, the user does not need to test the occupational test questions corresponding to each occupation one by one, thereby ensuring the efficiency of the occupational evaluation.
  • the computer device when the computer device pushes the professional test questions to the target object, it may push the questions one by one one by one.
  • the computer device can push one occupation test question corresponding to the test ability label to the target object each time, and then determine and push the next occupation test question according to the answer result of the target object's answer to the current occupation test question. Since each user's answer to each occupational test question may be different, the computer device will adjust the subsequent occupational test questions according to the user's answering result, so the occupational test questions that each user needs to answer will be different. In this way, according to the current ability of the target object, it can push the occupation test questions that match the target object, so that it can quickly locate the occupation that matches the ability of the target object in a variety of occupations. Occupation, and answer each test question corresponding to each occupation.
  • the computer device divides the difficulty level of each occupation test question corresponding to the test ability label, for example, divides the multiple occupation test questions corresponding to the test ability label into 1-9 different difficulty levels. Among them, the higher the value, the more difficult the corresponding occupational test questions.
  • Computer equipment can classify vocational test questions with intermediate difficulty levels into medium-difficulty vocational test questions, such as categorizing vocational test questions with difficulty levels of 4-6 as medium-difficulty, or vocational tests with difficulty levels of 3-7 The questions are classified as medium difficulty, which is not limited in the embodiments of this application.
  • the computer device regards the occupational test question whose difficulty level meets the medium difficulty condition as the first question corresponding to the test ability label, where the occupational test question whose difficulty level meets the medium difficulty condition is, for example, a difficulty level of 4- 6 occupational test questions.
  • the computer equipment randomly selects an occupation test question from the occupation test questions with a difficulty level of 4-6 corresponding to the test ability label.
  • the occupation test question is regarded as the first question corresponding to the test ability label, and it will be related to the test ability label.
  • the corresponding first question is pushed to the user.
  • Each occupation test question corresponds to at least one ability label. For each ability label corresponding to each occupation test question, each occupation test question has a difficulty level corresponding to each ability label, that is, for each ability label Each vocational test question in, each vocational test question has a corresponding difficulty level.
  • the computer device may first calculate the difficulty value of each occupation test question corresponding to the one ability label, and then calculate the difficulty value Mapped to the corresponding difficulty level. It can be understood that the greater the difficulty value, the higher the difficulty level mapped by the difficulty value; the smaller the difficulty value, the smaller the difficulty level mapped by the difficulty value.
  • the computer equipment can determine the difficulty value of each professional test question through the logistic regression algorithm and the Expectation Maximization (EM) algorithm. The logistic regression algorithm classifies the right and wrong answers of multiple users.
  • EM Expectation Maximization
  • the computer device may prepare training samples in advance, and these training samples include multiple user samples and some sample test questions with difficulty values.
  • the difficulty value of the sample test question (the difficulty value of the sample test question corresponding to the ability label of the sample test question) can be calculated by professionals through experience and set artificially.
  • the computer device can obtain occupational test questions for which the difficulty value needs to be determined, and test these occupational test questions separately through the multiple user samples to obtain corresponding responses.
  • the computer device may be based on the ability value of each user sample corresponding to an ability label of an occupation test question, the response to the occupation test question, and the value of the occupation test question to be calculated corresponding to the one ability label
  • the difficulty value constructs the corresponding logic function.
  • the logical function corresponding to each user sample is multiplied to construct an objective function, which can be regarded as a difficulty model.
  • the computer device may use the difficulty value when the value of the objective function is maximized as the difficulty value of the occupation test question corresponding to the one ability label.
  • the following is an example to illustrate the calculation method of the difficulty value of a professional test question corresponding to an ability label: the probability of the i-th user correctly answering a professional test question, following the logic function (Also called response function), where D is the constant 1.7, ⁇ i is the ability value of the i-th user corresponding to the one ability label, and b is the one of the occupation test question and the occupation test question
  • the probability of incorrectly answering a professional test question is (Can also be called response function).
  • FIG. 3 is a schematic diagram of the principle of the difficulty model in an embodiment.
  • the response functions of the second user and the third user are similar to the curves of P 2 and P 3 in Figure 3 under different difficulty values; when the user answers the professional test question incorrectly , Under different difficulty values, the response function of the first user is a curve similar to Q 1 in Figure 3.
  • the response function reflects the probability of answering right or wrong.
  • the computer equipment can multiply the response functions corresponding to a group of users to obtain That is, the L(b) curve in Figure 3.
  • the computer device may use the difficulty value corresponding to the peak value of the L(b) curve as the difficulty value of the occupation test question corresponding to the one ability label.
  • the computer device determines the difficulty level of each occupation test question corresponding to the one ability label according to the calculated difficulty value of each occupation test question corresponding to the one ability label.
  • the ability values of three test students selected by computer equipment corresponding to an ability label of a vocational test question are 0.07, 0.25, and 0.09 respectively, and the corresponding responses of the three test students are ⁇ 0,1,1>, so Available when When the maximum value is obtained, the corresponding difficulty value b is -0.27, and the difficulty value is standardized, and the standardized difficulty value can be obtained as 0.43.
  • the computer equipment can divide the difficulty level of the occupation test question with the standardized difficulty value of 0.43 corresponding to the one ability label into 4, of course, the computer equipment can also use other methods to classify the levels. This application implements The example does not limit this.
  • the user terminal After the user terminal collects the user's answer result, it sends the answer result to the server.
  • the server determines the second question corresponding to the test ability label according to the answering result of the user. For example, when the user's answer is correct, the server pushes the user a career test question with a difficulty level higher than the first question as the second question; when the user's answer result is an incorrect answer, the server pushes the user to the user with a difficulty level lower than The occupational test of the first question is regarded as the second question.
  • the second question corresponding to the test ability label is determined. For example, when the user's answer is correct, the computer device will push the user a career test with a higher level of difficulty than the first question as the second question; when the user's answer is an incorrect answer, the computer device will push the user's difficulty level Career test questions lower than the first question will be regarded as the second question.
  • the computer device sets a push rule for each test capability label. For example, at most 3 professional test questions can be pushed under each test ability label. It is understandable that in order to conduct a more accurate test of the user’s abilities, for each test ability label (MCM label), more professional test questions can be pushed, such as 5 questions or 7 questions, etc. The embodiment of the application does not limit this.
  • the target object can enter a career test page through an application or a web page, and the career test page displays the career test questions. It is understandable that before entering the professional test page, users can select the corresponding test version according to their personal needs. For example, there are three test versions of "fast version”, “deep version” and "deluxe version”. Different test versions have different test capability tags for testing. For example, the "fast version” can test up to 7 test ability tags; the “deep version” can test up to 10 test ability tags; the "luxury version” can test up to 15 test ability tags. The embodiment of the application does not limit this.
  • test time spent by the user and the accuracy of the test ability result corresponding to the user are accurate Sex may be different.
  • S204 Determine an ability test result corresponding to the target object according to the answer results of the target object in answering the multiple vocational test questions.
  • the ability test result is the result of testing the user's ability, and the ability test result can be the ability has been mastered or the ability has not been mastered.
  • the answer result is the result corresponding to the user's answer to the occupational test question, which can be information such as the correct rate of the answer and the answering time.
  • the answering time can be the time from when the computer device displays the first test question to the time when the target object selects or fills in the answer.
  • the answer correct rate can be the difference between the target object's choice or the filled-in answer and the standard answer.
  • the correct answer rate is 100%; when the target object chooses or fills in the answer completely different from the standard answer, the correct answer rate is 0%; when the target object fills in the correct answer If the answer is partially the same as the standard answer, the answer correct rate is determined based on the matching degree between the answer filled in by the target object and the standard answer.
  • the correct answer rate is 100%; when the answer option selected by the target object is the same as the standard answer option If it is a different option, the correct answer rate is 0%.
  • the computer device when the occupational test question is a fill-in-the-blank question or a short-answer question, the computer device performs word segmentation processing on the answer filled in by the user, such as a whole sentence, to obtain the corresponding word sequence. Furthermore, the computer equipment can remove the insubstantial function words or modal auxiliary words from the word sequence to obtain a keyword set.
  • the computer device can match multiple keywords in the extracted keyword set with keywords in the standard answer. When the keywords in the answer of the target object are the same as the keywords in the standard answer, the matching is considered successful.
  • the computer device can calculate the matching degree according to the number of successfully matched keywords among the keywords in the answers of the target object and the number of keywords in the keyword set. The matching degree can be regarded as the answer correct rate.
  • the answer correct rate is determined according to the number of matches between the keywords in the answer of the target object and the keywords in the standard answer. For example, there are a total of 4 keywords, and when the target object answers the three keywords correctly, the computer device judges that the correct answer rate of the current occupation test question is 75%.
  • the degree of matching between the answer filled in by the target object and the standard answer that is, the correct rate of the answer can be obtained according to manual correction.
  • the computer device After the computer device obtains the answer filled in by the target object, it can push it to the terminal where the teacher is located. The teacher can correct the answers filled in by the target object, and determine the degree of matching between the answers filled in by the target object and the standard answer, so as to give the correct answer rate and feed it back to the computer equipment.
  • the computer device may also use other methods to calculate the degree of matching between the answer filled in by the target object and the standard answer, which is not limited in the embodiment of the present application.
  • the user terminal after the user has answered the professional test question corresponding to the test ability label, that is, after the user terminal collects the user's answer result, the user terminal sends the answer result to the server. In other words, the computer device receives the user's answer result.
  • the computer device adjusts the difficulty of the next professional test question in real time or adjusts the next test ability label in real time according to the answering result of the user, such as the correct rate of the answer and the answering time.
  • the computer device automatically pushes a professional test question whose difficulty level is lower than the current difficulty level, which is used to test the user's ability corresponding to the current test ability label in a deeper level; or, when the user When answering the occupation test questions with lower difficulty level under the current test ability label, when the user also gets the wrong answer, it means that the user does not have the ability corresponding to the current test ability label, and the computer equipment can automatically push the occupation test under the next test ability label To test the user’s other abilities. Therefore, the computer device can automatically adjust the difficulty level and type of occupational test questions in subsequent tests according to the user's answer results, thereby ensuring the accuracy of matching occupations that meet their respective abilities for users.
  • the computer device determines the user's ability test result according to the received answer result.
  • the computer device determines the number of correct answers corresponding to the test ability label. When the number of correct answers is greater than or equal to the preset number of times, the computer device determines that the user’s ability test result corresponding to the test ability label is the ability has been mastered; when the number of correct answers is less than the preset number of times, the computer device judges the user’s ability to test the label
  • the corresponding ability test result is that the ability is not mastered.
  • the preset number of times may be the median of the number of occupational test questions under the test ability label, that is, when the number of correct answers corresponding to the test ability label exceeds half, the corresponding ability test result is that the ability has been mastered.
  • the corresponding preset number of times may be 2 times.
  • the computer device receives the user’s answer twice, that is, the correct answer corresponding to the test ability label is more than half, it can be determined that the user’s ability test result is that the user’s ability has been mastered; when the computer device receives the user’s correct answer
  • the number of times is 1, that is, when the number of wrong answers is 2 times, it is determined that the user's ability test result is not mastered.
  • step S206 that is, the step of screening the test ability label corresponding to the next ability to be tested from the ability label according to the ability test result, includes: when the ability test result corresponding to the target object is the ability already When mastering, compose all occupations corresponding to the test ability label into the first set, and determine the frequency of appearance of each ability label except the test ability label in the ability labels corresponding to all occupations in the first set, and change the frequency corresponding to the highest frequency.
  • the ability label is used as the test ability label corresponding to the next ability to be tested; when the ability test result corresponding to the target object is that the ability is not mastered, all occupations in the occupation information database except the first set form the second set, and Determine the frequency of appearance of each ability label in the ability labels corresponding to all occupations in the second set, and use the ability label corresponding to the highest frequency as the test ability label corresponding to the next ability to be tested.
  • the computer device when it is determined that the ability test result corresponding to the test ability label is that the ability has been mastered according to the answer result corresponding to the test ability label, the computer device composes all occupations corresponding to the test ability label into the first set.
  • the computer equipment counts the appearance frequency of each ability label except the test ability label among the ability labels corresponding to all occupations in the first set, so as to screen out the ability label corresponding to the highest frequency.
  • the computer equipment uses the ability label corresponding to the highest frequency selected as the test ability label corresponding to the next ability to be tested.
  • the computer device when it is determined that the ability test result corresponding to the test ability label is not mastered according to the answer result corresponding to the test ability label, the computer device composes all occupations in the occupation information database except for the first set into the first set. Two sets. The computer equipment counts the frequency of appearance of each ability label in the ability labels corresponding to all occupations in the second set, so as to filter out the ability label corresponding to the most frequent frequency. The computer equipment uses the ability label corresponding to the highest frequency selected as the test ability label corresponding to the next ability to be tested.
  • the computer device screens out the test capability tag corresponding to the next capability to be tested from the capability tag according to the capability test result.
  • the computer device can effectively filter out another occupation test label in the occupation corresponding to the ability of the target object, thereby further testing the user's other abilities.
  • the computer equipment progressively screens out occupations that match the user’s abilities. Users do not need to test the occupation test questions under all the ability labels corresponding to each occupation one by one, which ensures the efficiency of the occupation test and thus the occupation recommendation. Accuracy.
  • the test stop condition is the condition used to stop the current test.
  • the test stop condition can be that the number of test ability labels reaches the preset number of labels (such as 5 labels), or the number of all professional test questions reaches the preset number of questions (such as 15 question).
  • the steps from S202 to S206 are repeated.
  • the number of test ability labels reaches the preset number of labels or the number of all professional test questions reaches the preset number of questions, for example, when the number of test ability labels reaches 5 or the number of all professional test questions under all test ability labels
  • the test ability label corresponding to the next ability to be tested is no longer obtained.
  • the computer device determines the ability test result obtained before the test stop condition is satisfied. For example, the computer device provides a total of 5 professional test questions under the test ability label, so the computer device can obtain 5 ability test results corresponding to the target object, that is, whether the user has the 5 ability corresponding to the 5 test ability labels . Users can master one or more of these abilities.
  • Target ability label The target object has mastered the test ability label of the corresponding ability. For example, after a test of multiple occupational test questions, the user has mastered a total of 3 abilities, then the test ability labels corresponding to these 3 abilities are respectively regarded as 3 target ability labels.
  • Candidate occupations are occupations corresponding to target ability labels, where each occupation corresponds to one or more ability labels. When the occupation includes the target ability label, the occupation can be regarded as a candidate occupation.
  • the computer device uses the corresponding test ability label whose ability test result is mastered as the target ability label.
  • the computer device uses any occupation that contains any target ability tag in the occupation information database as a candidate occupation.
  • the computer device uses occupations that contain multiple target ability tags in the occupation information database as candidate occupations.
  • the candidate profession needs to include multiple test ability labels that the user has mastered the corresponding ability.
  • the computer device uses the corresponding test ability label whose ability test result is not mastered as the missing ability label.
  • the computer equipment regards the occupations that contain the target ability label in the occupation information database and do not contain the lack of ability notes as candidate occupations.
  • the ability label of the candidate occupation does not include the test ability label for which the user has not mastered the corresponding ability.
  • S212 Screen the target occupation from the candidate occupations, and recommend the target occupation to the target object.
  • the target occupation is the occupation selected by the computer equipment to be recommended to the user. According to the different screening conditions, the target occupation can be one or more. The embodiment of the application does not limit this.
  • the computer device can also calculate the ability value of the user's ability corresponding to each target ability tag, so as to calculate the user's ability value corresponding to each target ability tag and the weight of each target ability tag. Value to calculate the match between the user and each candidate occupation.
  • the computer device may calculate the user's ability value corresponding to each target ability tag in the following manner.
  • the occupational test questions corresponding to the target ability label include m occupational test questions
  • the user's ability value corresponding to the target ability label can be calculated by the following formula: in, P j represents the probability of the user correctly answering the jth professional test question, Where D is a constant 1.7, ⁇ is the user's ability value corresponding to the target ability label, and b j is the difficulty value of the jth professional test question corresponding to the target ability label.
  • the computer device uses the value of ⁇ when L( ⁇ ) is maximized as the ability value of the user corresponding to the target ability tag.
  • the computer equipment To find the user's ability value corresponding to the target ability label, specifically, ⁇ when L( ⁇ ) can take the maximum value is used as the user's ability value corresponding to the target ability label.
  • the corresponding standardized ability value is 0.75
  • the standardized ability value 0.75 is used as the user's ability value corresponding to the target ability tag.
  • the standardized ability value can be Get the derivative.
  • the range of the ability value may be 0 to 1, or other ranges, which are not limited in the embodiment of the present application.
  • the computer device obtains the total answer score corresponding to each target ability label according to the answer scores of the multiple occupation test questions under the target ability label with the corresponding ability of the target object. For example, if the multiple answer scores corresponding to the multiple professional test questions under the user and target ability label are 50, 60, and 70 points, respectively, the total score of the answer corresponding to the target ability label of the user can be accumulated and averaged. In other words, the total score for the answer is 60 points. This application does not limit the calculation method of the total score of the answer questions.
  • the computer device determines the weight value of each target ability label in the ability label corresponding to each candidate occupation.
  • the computer device calculates the degree of match between the user and each candidate occupation by the total answer score corresponding to each target ability label and the weight value of each target ability label. For example, for each candidate occupation, the computer device can perform a weighted summation operation on the total answer scores corresponding to multiple target ability labels corresponding to each candidate occupation and the weight values of the multiple target ability labels to obtain the target object and the The degree of match of candidate occupations.
  • the computer device selects the candidate occupation with the highest matching degree from a plurality of candidate occupations, and uses the candidate occupation with the highest matching degree as the target occupation, that is, the occupation recommended by the computer device to the user.
  • the computer device sorts the multiple candidate occupations according to the corresponding matching degree, and selects candidate occupations whose ranking rank is less than a preset rank as the target occupation. For example, the computer device may use the top three candidate occupations with the highest matching degree as the target occupation of the target object.
  • the computer device generates a corresponding occupation test report according to the target occupation and the total answer score or ability value corresponding to the target ability tag, and feeds back the occupation test report to the user.
  • the occupation test questions corresponding to multiple test ability labels are sequentially pushed to the target object, and the answer results corresponding to the target object are obtained according to the answer results of the target object when answering the multiple occupation test questions corresponding to the multiple test ability labels
  • the candidate occupation corresponding to the target ability label of the target object with the corresponding ability is determined, and the target occupation is obtained from the candidate occupations, so as to recommend the occupation to the target object.
  • the professional test questions corresponding to the test ability label are pushed to the target object to test the size of the user's corresponding ability, so that the target occupation matching the user's corresponding ability can be selected from a variety of occupations, and the user can be qualified after the screening.
  • the recommended target occupation thereby greatly improving the accuracy of occupation recommendation.
  • the corresponding target occupations can be accurately and progressively selected from multiple dimensions. Users do not need to test the occupation test questions corresponding to each occupation one by one, thus reducing The test time cost for users to answer a large number of tedious or irregular occupation test questions is improved, which not only improves the efficiency of occupation recommendation, but also ensures the accuracy of occupation recommendation.
  • the initial test ability label in the occupation recommendation method is determined by the following steps: determining the ability label corresponding to each occupation in the multiple occupations in the occupation information database; determining the ability label that each ability label appears in the multiple occupations Frequency, the ability label corresponding to the highest frequency is used as the initial test ability label.
  • the computer device pre-builds a set of ability label architecture, and each ability label has a corresponding question bank.
  • the questions in the question bank corresponding to the ability label can be used to measure whether the user has mastered or has the ability corresponding to the ability label.
  • According to the user's mastery of a capability tag it indicates whether the user has the corresponding capability.
  • the user's mastery of an ability label can be determined by the user's answer results on the corresponding test questions.
  • multiple professions in the profession information database may include: teachers, doctors, planners, product managers, programmers, singer-songwriters, legal practitioners, translators, administrative staff, reporters, teachers, finance Workers and other occupations.
  • the computer device assigns an ability label matching the ability required by each occupation to each of the multiple occupations in the occupation information database.
  • the ability labels assigned by computer equipment to the "doctor" profession include seven MCM labels: data analysis ability, communication ability, information screening ability, estimation ability, scientific knowledge reserve ability, deductive reasoning ability, and classified discussion thoughts.
  • the computer device assigns a corresponding ability label (MCM label) and a weight value corresponding to each ability label to each of the multiple occupations in the occupation information database.
  • MCM label a corresponding ability label
  • the ability labels assigned by computer equipment to the profession of "teacher” include communication ability, summary ability, logical analysis ability, scientific knowledge reserve ability, classified discussion ideas, situational imagination and simplification ability, and cultural cognition ability.
  • the weight values corresponding to the 7 MCM tags are 7, 6, 5, 4, 3, 2, and 1, respectively. Among them, the higher the weight value, the more necessary to have the corresponding ability in the occupation. That is to say, in the "teacher" profession, the ability that users most need to master is the communication ability corresponding to the communication ability label.
  • the ability labels assigned by the computer equipment to the "programmer" occupation include logical analysis ability, law exploration ability, data analysis ability, classification discussion thought, screening ability, overall planning thought, and planning ability, which are 7 ability labels, and The corresponding weight values of the 7 MCM tags are 7, 6, 5, 4, 3, 2, and 1, respectively.
  • the computer device counts the frequency of appearance of each ability label in multiple occupations. For example, communication ability appears 15 times in multiple occupations in the occupation information database, which is the ability label with the highest frequency.
  • the computer equipment uses the communication ability label as the initial test ability label.
  • the computer device counts the frequency of occurrence of each ability label in multiple occupations, takes the ability label condition that meets the high frequency of the corresponding frequency as a candidate ability label, and randomly selects a label from the candidate ability labels As the initial test capability label.
  • the high-frequency capability label conditions such as the number of occurrences, are the three at most. For example, communication ability has appeared 15 times in multiple occupations in the occupational information database, logical analysis ability has appeared 12 times, and information screening ability has appeared 14 times. Therefore, the computer equipment combines communication ability, logical analysis ability and information screening.
  • Ability is used as a candidate ability label, and a label is randomly selected from the candidate ability labels as the initial test ability label.
  • the computer device uses the ability label with the highest frequency as the initial test ability label. Therefore, the professional test questions under the initial test ability label pushed by the computer device can cover the widest range, and the user does not need to be one by one.
  • the occupational test questions corresponding to each occupation are tested. That is to say, the occupational test questions under the initial test ability label can test one of the multiple abilities required by the largest number of occupations, thus improving the occupational test Efficiency, thereby ensuring the accuracy of career recommendations.
  • step S202 that is, the step of pushing multiple occupational test questions corresponding to the test ability label to the target object, includes: determining each occupational test question of the multi-vocational test questions corresponding to the test ability label Difficulty level; take the occupational test question whose difficulty level meets the medium difficulty conditions as the first question corresponding to the test ability label, and push the first question corresponding to the test ability label to the target object; based on the first question corresponding to the test ability label The answer result of one question, determine the second question corresponding to the test ability label; according to the answer results of the first question and the second question corresponding to the test ability label, determine whether to push the third question corresponding to the test ability label to the target object .
  • the computer device divides the difficulty level of each occupation test question corresponding to the test ability label, for example, divides the multiple occupation test questions corresponding to the test ability label into 1-9 different difficulty levels. The higher the value, the more difficult the corresponding occupational test question.
  • Computer equipment can classify vocational test questions with intermediate values into medium-difficulty vocational test questions, for example, categorize vocational test questions with a difficulty level of 4-6 as medium-difficulty, or divide vocational test questions with a difficulty level of 3-7 For moderate difficulty, the embodiments of this application do not limit this.
  • the computer device regards the occupational test question whose difficulty level meets the medium difficulty condition as the first question corresponding to the test ability label, where the occupational test question whose difficulty level meets the medium difficulty condition is, for example, a difficulty level of 4- 6 occupational test questions.
  • the computer equipment randomly selects an occupation test question from the occupation test questions with a difficulty level of 4-6 corresponding to the test ability label.
  • the occupation test question is regarded as the first question corresponding to the test ability label, and it will be related to the test ability label.
  • the corresponding first question is pushed to the user.
  • the computer device collects the user's answer results.
  • the computer equipment determines the second question corresponding to the test ability label according to the answering result of the user. For example, when the user's answer is correct, the computer device will push the user a career test with a higher level of difficulty than the first question as the second question; when the user's answer is an incorrect answer, the computer device will push the user's difficulty level career test questions lower than the first question will be regarded as the second question.
  • the computer device sets a push rule for each test capability label. For example, at most 3 professional test questions can be pushed under each test ability label. It is understandable that in order to perform a more accurate test of the user’s abilities, for each test ability label (MCM label), more professional test questions can be pushed, such as 5 questions or 7 questions, etc. The embodiment of the application does not limit this.
  • the computer device when the computer device pushes a total of 3 professional test questions corresponding to the test ability label, the computer device receives the user’s answer and the result is that the user has answered the first two questions correctly, and the computer device determines that the user has mastered the test.
  • the ability corresponding to the ability label that is, the computer device does not need to push the third question under the test ability label.
  • the computer device when the computer device pushes a total of 3 occupational test questions corresponding to the test ability label, the computer device receives the user’s answer and the result is that the first two questions are answered incorrectly, and the computer device determines that the user has not mastered the test.
  • the ability corresponding to the ability label that is, the computer device does not need to push the third question under the test ability label.
  • the computer device when the computer device pushes a total of 3 professional test questions corresponding to the test ability label, the computer device receives the user’s answer as a result of one of the first two questions being answered correctly and one wrong answer, then the computer device pushes And the third question under the test ability label, so as to further test the user's ability.
  • the computer device pushes the occupation test questions corresponding to the test ability label to the target object. In this way, it can be tested whether the user has the ability corresponding to the test ability label. Since the abilities of each user may be different, the computer equipment can adjust the corresponding professional test questions in real time to achieve the effect of accurately testing the user's abilities with a small number of professional test questions, which saves the user's time cost and guarantees professional recommendation Accuracy.
  • the step of determining the second question corresponding to the test ability label includes: calculating the first question based on the answer result and difficulty level corresponding to the first question The answer score of a question; when the answer score is greater than or equal to the first threshold, the occupation test question with a higher difficulty level than the first question is regarded as the second question corresponding to the test ability label, and the test ability is pushed to the target object The second question corresponding to the label; when the answer score is less than the first threshold, the occupation test question with a lower level of difficulty than the first question is regarded as the second question corresponding to the test ability label, and the test ability label is pushed to the target object Corresponding to the second question.
  • the first threshold is the answer score threshold preset by the computer device, and is a numerical value, such as 60 points.
  • the computer device calculates the answer score of the first question according to the answer result and difficulty level corresponding to the first question, where the answer result includes the answer time and the answer correct rate.
  • the answer correct rate is positively correlated with the answer score.
  • the corresponding answer score is higher; the difference between the answer time and the preset standard time period is negatively correlated with the answer score.
  • the user’s answer time is The smaller the difference in the preset standard time period, the higher the corresponding answer score; the difficulty level of the professional test question is positively correlated with the answer score.
  • the difficulty level of the professional test question answered by the user is higher, the corresponding answer score is high.
  • the preset standard time range is, for example, 10-30 seconds after the computer device pushes the question.
  • the score of the answer corresponding to the user's correct answer in 20 seconds is higher than the score of the answer corresponding to the user's correct answer in 5 seconds.
  • the computer device calculates the answer score of the first question, and when the answer score is greater than or equal to the first threshold, the computer device regards the occupation test question with a higher difficulty level than the first question as corresponding to the test ability label And push the second question corresponding to the test ability label to the target object.
  • the first question under the test ability label pushed by the computer device is a professional test question with a difficulty level of 6, and the user's answer to the first question scores 80 points, and the computer device pushes the user to the user with the difficulty level under the test ability label. 7 professional test questions.
  • the computer device calculates the answer score of the first question, and when the answer score is less than the first threshold, the computer device regards the occupation test question with a lower difficulty level than the first question as the first question corresponding to the test ability label.
  • Two questions and push the second question corresponding to the test ability label to the target object.
  • the first question under the test ability label pushed by the computer device is a professional test question with a difficulty level of 4, and the user's answer to the first question scores 50 points, and the computer device pushes the user to the user with a difficulty level under the test ability label. 3 career test questions.
  • the computer device determines the second question corresponding to the test ability label based on the answer result and difficulty level of the first question corresponding to the test ability label.
  • the computer equipment can adjust the corresponding professional test questions in real time according to the user's answering situation, so as to achieve the effect of accurately testing the user's ability with a small number of professional test questions, which is to save the user's time cost and ensure Accuracy of career recommendations.
  • the ability test result includes the ability already mastered and the ability not mastered.
  • Step S204 that is, the step of determining the ability test result corresponding to the target object according to the answer result of the target object's answer to the occupational test question, includes: The answer result corresponding to the test ability label determines the number of correct answers corresponding to the test ability label; when the number of correct answers is greater than or equal to the second threshold, the ability test result corresponding to the target object is determined as the ability has been mastered; when the number of correct answers is less than At the second threshold, it is determined that the ability test result corresponding to the target object is that the ability is not mastered.
  • the second threshold is the preset number of times by the computer device, and is a numerical value, such as 2 times.
  • the computer device determines the number of correct answers corresponding to the test ability label according to the answer result corresponding to the test ability label. For example, the computer device has pushed a total of three occupational test questions corresponding to the test ability label, and the corresponding correct answers can be 0, 1, or 2 times.
  • the computer device pushes a total of 2 professional test questions corresponding to the test ability label, and the number of correct answers of the user is 2 times. Since the number of correct answers is equal to the second threshold, the computer device determines that the user has mastered the ability corresponding to the test ability label; when the computer device has pushed a total of 2 professional test questions corresponding to the test ability label, and the user’s The number of correct answers is 0. Since the number of correct answers is less than the second threshold, at this time, the computer device determines that the user has not mastered the ability corresponding to the test ability label.
  • the computer device pushes a total of 3 occupational test questions corresponding to the test ability label, and the user's answer is correct twice. Since the number of correct answers is equal to the second threshold, at this time, the computer device determines that the user has mastered the ability corresponding to the test ability label; when the computer device has pushed a total of 3 professional test questions corresponding to the test ability label, and the user’s The number of correct answers is 1 time. Since the number of correct answers is less than the second threshold, at this time, the computer device determines that the user has not mastered the ability corresponding to the test ability label.
  • the computer device indicates the user's ability mastery according to the user's ability value corresponding to the test ability tag. For example, when the user's ability value corresponding to the test ability label is greater than 0.7, it means that the user has a strong grasp of the ability corresponding to the test ability label; when the user's ability value corresponding to the test ability label is between 0.6 and 0.7, it means the user Has a strong grasp of the ability corresponding to the test ability label.
  • the computer device determines the number of correct answers corresponding to each test ability label, and determines the ability test result corresponding to the target object according to the number of correct answers. In this way, whether the user has the ability corresponding to the test ability label can be indicated according to the ability test result. Since the ability of each user may be different, the computer equipment can adjust the next test ability label in real time to achieve the effect of accurately testing the user’s ability with a small number of professional test questions under the test ability label, which saves the user’s time cost. And to ensure the accuracy of career recommendations.
  • step S212 that is, the step of screening the target occupation from the candidate occupations and recommending the target occupation to the target object, includes: calculating and obtaining the target object’s and each target’s corresponding answer results according to each target ability label.
  • the ability value corresponding to each target ability label based on the weight value of each target ability label in the ability label corresponding to each candidate occupation and the ability value of the target object corresponding to each target ability label, the target object and the said The matching degree corresponding to each candidate occupation; select at least one target occupation whose matching degree meets the high matching degree condition from multiple candidate occupations; generate a corresponding occupation test report according to the target occupation, and feed the occupation test report back to the target object.
  • the computer device obtains the total answer score corresponding to each target ability label according to the answer scores of the multiple occupation test questions under each target ability label.
  • the computer device can determine the weight value of each target ability label in the ability label corresponding to each candidate occupation.
  • the computer device may perform a weighted sum operation on the total answer score corresponding to the multiple target ability labels and the weight values of the multiple target ability labels to obtain the degree of matching between the target object and the candidate occupation.
  • the computer device may also calculate the degree of match between the target object and each candidate occupation according to the ability value corresponding to each target ability tag and the corresponding weight value.
  • the computer device can search for the target ability label corresponding to the candidate occupation and corresponding to the ability of the target object, and then determine the weight value of the searched target ability label in the ability label corresponding to the candidate occupation.
  • the computer device may perform a weighted sum operation on the ability value corresponding to the corresponding target ability label and the corresponding weight value to obtain the degree of matching between the candidate occupation and the target object.
  • the computer device selects the candidate occupation with the highest matching degree from a plurality of candidate occupations, and uses the candidate occupation with the highest matching degree as the target occupation, that is, the occupation recommended by the computer device to the user.
  • the computer device sorts the multiple candidate occupations according to the corresponding matching degree, and selects candidate occupations whose ranking rank is less than a preset rank as the target occupation. For example, the computer device may use the top three candidate occupations with the highest matching degree as the target occupation recommended to the target object.
  • the computer device generates a corresponding occupation test report according to the target occupation and the total answer score or ability value corresponding to the target ability label, and feeds the occupation test report back to the user.
  • the professional test report may also include the user's personal information, such as the user's WeChat name and WeChat avatar.
  • the computer device displays the recommended target occupations in the occupation test report in the order of matching degree, for example, the target occupation with the highest matching degree is displayed in the first row of the occupation test report. Or, the computer device displays the target occupation with the highest matching degree in the middle of the occupation test report, and magnifies and highlights the target occupation with the highest matching degree.
  • the computer device displays the reason for recommendation in the occupational test report.
  • the main reason for the recommendation is to analyze the user's ability test results corresponding to the test ability label.
  • the computer equipment is sorted according to the user's ability values corresponding to the multiple target ability labels from high to low, and displays the target ability label with the highest ranking ability value in the occupation test report. For example, if the target capability tag has 3 tags in total, the first 2 digits are taken; if the target capability tag has 2 tags, only the first digit is taken.
  • the recommended reason may be a preset speech technique.
  • the recommended reason may be: you have (extremely strong/strong) "target ability label 1" and (extremely strong/stronger). Strong) "Target Ability Label 2", has the potential to become an excellent “No. 1 Target Pro profession", and at the same time may become a "No. 2 Target Pro profession” and "No. 3 Target Pro profession”; for example;
  • the recommended reason can be: but you are slightly lacking in the "Lack of Ability Label 1" and "Lack of Ability Label 2", work hard to improve these abilities, and you will become even better.
  • the ability value can be used to distinguish between "extremely strong” and “strong”. For example, when the ability value is greater than 0.7, it means extremely strong, and when the ability value is less than 0.7, it means strong.
  • the career test report may also include a user radar chart.
  • Computer equipment selects 3 target ability labels. For example, when the vocational test report includes the recommended "extremely strong” or “strong” target ability labels, the recommended "extremely strong” or “strong” will be selected first Target ability label; when the number of recommended "extremely strong” or “strong” target ability labels is not enough, for example, less than 3, select the target ability label with the top ranking of the user's ability value, and then select a total of 3 Target ability label:
  • the computer device also selects 2 missing ability labels of the user or 2 target ability labels with the lower ranking of the user's ability value.
  • the computer equipment displays the radar chart of these 5 ability labels in the occupational test report according to the ability value.
  • the range of the ability value can be 0 to 1, or other ranges.
  • the computer device when the user and the corresponding ability test results under the multiple test ability labels are not mastered, the computer device will not match the user to any corresponding occupation, that is, in the occupation test report Unable to recommend target occupation.
  • the computer device is provided with a "click to view test record" control in the occupation test report to provide the function of viewing the test record.
  • a pop-up box for verifying the phone number will automatically pop up in the professional test report.
  • the interface jumps from the professional test report to the answer record page.
  • the computer device is provided with a "share" control in the occupational test report to provide the function of sharing the occupational test report.
  • the "Share” button When the user clicks the "Share” button, the corresponding sharing page is automatically generated. Therefore, other users can jump to the test homepage through the sharing page to perform the corresponding professional test.
  • each user can only conduct a career test once. When the user completes the test and clicks the "Enter Test” button again, the user will directly view his own professional test report.
  • the user when the user ends the test early during the occupation test, for example, when the user exits the test answer page during the answering process, when the user enters the test answer page again, it will automatically jump to the last time the user did not complete the test.
  • the test answer page corresponding to the occupation test questions, so that the user can continue to complete the remaining occupation test questions.
  • the computer device calculates the target object and each candidate occupation based on the weight value of each target ability label in the target ability labels corresponding to the multiple candidate occupations and the user's ability value corresponding to each target ability label. Corresponding matching degree, so as to filter out the target occupation to be recommended to the target object according to the matching degree.
  • the target occupation matching the user's corresponding ability is screened from a variety of occupations to ensure that the user is competent for the target occupation recommended after the screening, thereby greatly improving the accuracy of the occupation recommendation. This not only improves the efficiency of career recommendation, but also ensures the accuracy of career recommendation.
  • the user can enter the career test page by scanning the QR code to enter the application or web page, for example, enter the H5 test page of Smart Eyes.
  • the user clicks the "Start Test” button referring to Figure 4(a)
  • the test version selection page includes three different version selection controls and "enter test” controls. Version selection controls such as “fast version” control, "deep version” control and "deluxe version” control, users can choose different test versions according to personal needs.
  • different versions have different total number of ability labels tested in the occupational test, and different termination conditions. For example, in the "fast version", a maximum of 7 test ability tags are tested.
  • test ability results corresponding to the user including 3 abilities already mastered and 2 abilities not mastered
  • the test can be terminated; in the "in-depth version”
  • a maximum of 10 test ability labels can be tested.
  • test ability results corresponding to the user including 4 kinds of abilities have been mastered and 3 kinds of abilities have not been mastered
  • the test can be terminated; in the "Deluxe Edition", a maximum of 15 test ability labels can be tested .
  • the computer equipment tests the test ability results corresponding to the user including 5 kinds of ability has been mastered and 4 kinds of ability not mastered the test can be terminated.
  • the occupational test questions that appear on the test answer page are mainly multiple-choice questions, and sometimes they can also be fill-in-the-blank questions or answer questions.
  • the first question recommended to the user in the test answer page is the professional test question in the question bank corresponding to the initial test ability label.
  • the test answer page includes a question serial number 401, an answer timer 402, an occupation test question 403, a "skip” control 404, and a "submit” control 405.
  • the computer equipment is preset to push up to 3 questions under a single test ability label.
  • the computer equipment determines that the user’s ability test result corresponding to the test ability label is that the ability has been mastered, and switches to the next test ability label; when the user is on a single test ability label
  • the computer device determines that the user's ability test result corresponding to the test ability label is not mastered, and switches to the next test ability label.
  • the computer device determines the first set of all occupations that need to master the test ability label. According to the ability label corresponding to each occupation in the first set, the computer device screens and obtains the ability label corresponding to the highest frequency of occurrence as the next test ability label to be tested. Furthermore, the computer device can push the question in the next test ability label to be tested to the user.
  • the computer device determines the second set of occupations that do not need to master the test ability label.
  • the computer equipment screens and obtains the ability label corresponding to the highest frequency of occurrence according to the ability label corresponding to each occupation in the second set as the next test ability label to be tested. Furthermore, the computer device can push the question in the next test ability label to be tested to the user.
  • the occupation test report includes the user's personal information 501, the recommended target occupation 502, the reason for recommendation 503, the radar chart 504, and the "click to view the question record" control 505.
  • FIG. 6 is an interface diagram of the analysis of the thinking ability method in the career recommendation method in an embodiment.
  • the user clicks to view "Analysis of Thinking Method Ability"
  • the user can view the mastery of all abilities related to the method of thinking ability. For example, display communication ability, information screening ability, law exploration ability, word memorization ability, cultural memorization ability, data analysis ability, classification discussion thought, algorithm construction and realization ability and other test ability labels.
  • the higher the percentage value the higher the user's mastery of the corresponding ability. For example, when the percentage value is greater than 70%, it is considered to be excellent; when the percentage value is less than 20%, it is considered to be poor.
  • the embodiment of the application does not limit this.
  • a pop-up box for verifying the user's mobile phone number will automatically pop up in the professional test report.
  • the computer device verifies the user's mobile phone number to determine whether it is the user's own operation.
  • the computer equipment will jump the interface from the professional test report to the answer record page.
  • the answer record page includes professional test questions and corresponding multiple answer options.
  • a correct mark is added to the answer option selected by the user, such as a mark in the form of "tick”.
  • an error mark is added to the answer option selected by the user, such as a mark in the form of "cross", and a mark in the form of "check” after the correct option.
  • steps in the flowchart of FIG. 2 are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least part of the steps in FIG. 2 may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times, and the order of execution of these steps or stages is also It is not necessarily performed sequentially, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
  • a career recommendation device 700 including: a pushing module 701, a determining module 702, a screening module 703, a repeating module 704, and a recommendation module 705, wherein:
  • the push module 701 is configured to push multiple occupational test questions corresponding to the test ability label to the target object; wherein, the initial test ability label in the test ability label is based on the ability label corresponding to each occupation in the occupation information database Determined.
  • the determination module 702 is configured to determine the ability test result corresponding to the target object according to the answer results of the multiple occupation test questions for the target object.
  • the screening module 703 is configured to screen out the test ability label corresponding to the next ability to be tested from the ability label according to the ability test result.
  • the repetition module 704 is configured to push back multiple professional test questions corresponding to the test ability label to the target object until the test stop condition is met, and multiple ability test results corresponding to the target object are obtained.
  • the determining module 702 is further configured to determine a candidate occupation corresponding to a target ability label according to multiple ability test results, where the target ability label is a test ability label for the target object to have a corresponding ability.
  • the recommendation module 705 is configured to screen target occupations from candidate occupations and recommend the target occupations to target objects.
  • the determining module 702 is further configured to determine the ability label corresponding to each of the multiple occupations in the occupation information database; determine the frequency of each ability label in the multiple occupations, and set the most frequent The corresponding capability label is used as the initial test capability label.
  • the pushing module 701 is configured to push multiple occupational test questions corresponding to the test ability label to the target object in the following manner: determine each occupational test question in the multi-vocational test questions corresponding to the test ability label Difficulty level; take the occupational test question whose difficulty level meets the medium difficulty condition as the first question corresponding to the test ability label, and push the first question corresponding to the test ability label to the target object; based on the corresponding test ability label The answer result of the first question is to determine the second question corresponding to the test ability label; according to the answer results of the first question and the second question corresponding to the test ability label, determine whether to push the third question corresponding to the test ability label to the target object question.
  • the push module 701 is configured to determine the second question corresponding to the test ability label based on the answer result of the first question corresponding to the test ability label in the following manner: according to the answer result corresponding to the first question and Difficulty level, calculate the answer score of the first question; when the answer score is greater than or equal to the first threshold, take the occupation test question with a higher difficulty level than the first question as the second question corresponding to the test ability label, and send it to the target The object pushes the second question corresponding to the test ability label; when the answer score is less than the first threshold, the occupation test question with a lower level of difficulty than the first question is regarded as the second question corresponding to the test ability label and sent to the target object Push the second question corresponding to the test ability label.
  • the ability test result includes the ability already mastered and the ability not mastered; the determination module 702 is set to determine the ability test result corresponding to the target object according to the answer result of the professional test question of the target object in the following way:
  • the answer result corresponding to the test ability label determines the number of correct answers corresponding to the test ability label; when the number of correct answers is greater than or equal to the second threshold, the ability test result corresponding to the target object is determined as the ability has been mastered; when the number of correct answers is less than At the second threshold, it is determined that the ability test result corresponding to the target object is that the ability is not mastered.
  • the screening module 703 is configured to, when the ability test result corresponding to the target object is that the ability has been mastered, compose all occupations corresponding to the test ability label into the first set, and determine that all occupations in the first set correspond to The frequency of appearance of each ability label except the test ability label in the ability label, the ability label corresponding to the highest frequency is the test ability label corresponding to the next ability to be tested; when the ability test result corresponding to the target object is When the ability is not mastered, all the occupations in the occupation information database except the first set are formed into the second set, and the frequency of each ability label in the ability labels corresponding to all occupations in the second set is determined, and the highest frequency corresponds to The capability tag is used as the test capability tag corresponding to the next capability to be tested.
  • the recommendation module 705 is further configured to calculate the ability value of the target object corresponding to each target ability label according to the answer result corresponding to each target ability label; based on the ability value in the ability label corresponding to each candidate occupation The weight value of each target ability label and the ability value of the target object corresponding to each target ability label are calculated to obtain the matching degree between the target object and each candidate occupation; the matching degree is selected from multiple candidate occupations to meet the high matching degree At least one target occupation of the conditions; generate a corresponding occupation test report according to at least one target occupation, and feedback the occupation test report to the target object.
  • each occupational test question corresponds to at least one ability label
  • the at least one ability label corresponding to each occupational test question is determined according to the MCM model.
  • the above device for professional recommendation based on the ability model pushes the occupation test questions corresponding to multiple test ability labels to the target object in turn, and the answer results of the multiple occupation test questions corresponding to each test ability label are obtained according to the target object’s answer results.
  • Multiple ability test results corresponding to the target object thereby determining the candidate occupation corresponding to the target ability label of the target object with the corresponding ability, and selecting the target occupation from the candidate occupations to make a career recommendation to the target object.
  • the professional test questions corresponding to the test ability label are pushed to the target object to test the size of the user's corresponding ability, so that the target occupation matching the user's corresponding ability can be selected from a variety of occupations, and the user can be qualified after the screening.
  • the recommended target occupation thereby greatly improving the accuracy of occupation recommendation.
  • the corresponding target occupations can be accurately and progressively selected from multiple dimensions. Users do not need to test the occupation test questions corresponding to each occupation one by one, thus reducing The test time cost for users to answer a large number of tedious or irregular occupation test questions is improved, which not only improves the efficiency of occupation recommendation, but also ensures the accuracy of occupation recommendation.
  • the multiple modules in the above-mentioned career recommendation device can be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
  • a computer device is provided.
  • the computer device may be a terminal or a server, and its internal structure diagram may be as shown in FIG. 8.
  • the computer equipment includes a processor, a memory, and a communication interface connected through a system bus.
  • the processor of the computer device is configured to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system and a computer program.
  • the internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium.
  • the communication interface of the computer equipment is used for wired or wireless communication with external terminals.
  • the wireless way can be through WIFI (Wireless Fidelity, wireless local area network), operator network, NFC (Near Field Communication) or other technologies accomplish.
  • the computer program is executed by the processor to achieve a target classification method.
  • FIG. 8 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
  • a computer device including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the above-mentioned career recommendation method.
  • the career recommendation method here may be the career recommendation method of the multiple embodiments described above.
  • a computer-readable storage medium is provided, and a computer program is stored.
  • the computer program is executed by a processor, the processor executes the above-mentioned career recommendation method.
  • the career recommendation method here may be among the career recommendation methods in the multiple embodiments described above.
  • Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical storage.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM may be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Educational Administration (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Educational Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种职业推荐方法、装置、设备和介质。所述方法包括：向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定（S202）；根据目标对象解答多道职业测试题的答题结果，确定与目标对象对应的能力测试结果（S204）；根据能力测试结果从能力标签中筛选出下一个待测试的能力所对应的测试能力标签（S206）；返回向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与目标对象对应的多个能力测试结果（S208）；根据多个能力测试结果，确定目标能力标签所对应的候选职业（S210）；从候选职业中筛选目标职业，并将目标职业推荐给目标对象（S212）。

Description

职业推荐方法、装置、设备和介质
本申请要求在2020年06月09日提交中国专利局、申请号为202010516522.2的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据推荐技术领域，例如涉及一种职业推荐方法、装置、设备和介质。
背景技术
随着数据推荐技术的发展，出现了职业推荐技术。传统的职业推荐方法是用大量的测试题测试用户的兴趣爱好、以及性格等情况，从而为不同兴趣爱好或不同性格的用户推荐相应的职业。
然而，采用传统的职业推荐方法时，常常会碰到所推荐的职业与用户的能力不匹配的情况，导致用户无法胜任所推荐的职业，因而存在职业推荐的准确率低的问题。
发明内容
本申请提供一种能够提高准确性的职业推荐方法、装置、设备和介质。
本申请提供一种职业推荐方法，所述方法包括：
向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定；
根据目标对象解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果；
根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对应的测试能力标签；
返回所述向目标对象推送与测试能力标签相对应的多道职业测试题的步骤并继续执行，直至满足测试停止条件，得到与所述目标对象对应的多个能力测试结果；
根据所述多个能力测试结果，确定目标能力标签所对应的候选职业，其中，所述目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签；
从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象。
本申请还提供一种职业推荐装置，所述装置包括：
推送模块，设置为向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定；
确定模块，设置为根据目标对象解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果；
筛选模块，设置为根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对应的测试能力标签；
重复模块，设置为返回所述向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与所述目标对象对应的多个能力测试结果；
所述确定模块还设置为根据所述多个能力测试结果，确定目标能力标签所对应的候选职业，其中所述目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签；
推荐模块，设置为从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象。
本申请还提供一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现以下步骤：
向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定；
根据目标对象解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果；
根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对 应的测试能力标签；
返回所述向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与所述目标对象对应的多个能力测试结果；
根据所述多个能力测试结果，确定目标能力标签所对应的候选职业，其中所述目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签；
从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象。
本申请还提供一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现以下步骤：
向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定；
根据目标对象解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果；
根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对应的测试能力标签；
返回所述向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与所述目标对象对应的多个能力测试结果；
根据所述多个能力测试结果，确定目标能力标签所对应的候选职业，其中所述目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签；
从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象。
附图说明
图1为一个实施例中职业推荐方法的应用环境图；
图2为一个实施例中职业推荐方法的流程示意图；
图3为一个实施例中难度模型的原理示意图；
图4(a)为一个实施例中测试版本选择页的界面图；
图4(b)为一个实施例中测试答题页的界面图；
图5为一个实施例中职业测试报告的界面图；
图6为一个实施例中职业测试报告中思想能力方法分析的界面图；
图7为一个实施例中职业推荐装置的结构框图；
图8为一个实施例中计算机设备的内部结构图。
具体实施方式
以下结合附图及实施例，对本申请进行说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供的职业推荐方法，可以应用于如图1所示的应用环境中。用户终端110通过网络与服务器120进行通信。用户终端110和服务器120均可单独用于执行本申请实施例中提供的职业推荐方法。用户终端110和服务器120也可协同用于执行本申请实施例中提供的职业推荐方法。用户终端110可以但不限于是个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备。服务器120可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
比如，当用户终端110和服务器120协同用于执行本申请实施例所提供的职业推荐方法时，服务器120向目标对象所在的用户终端110推送与测试能力标签相对应的多道职业测试题；其中，测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定。用户终端110收集目标对象解答多道职业测试题的答题结果，并传输至服务器120。服务器120根据答题结果确定与目标对象对应的能力测试结果。服务器120根据能力测试结果从能力标签中筛选出下一个待测试的能力所对应的测试能力标签，并向目标对象所在的用户终端110推送与下一个测试能力标签相对应的多道职业测试题，以对目标对象的能力进行测试。这样重复执行，直至满足测试停止条件时停止测试，得到与目标对象对应的多个能力测试结果。服务器120根据多个能力测试结果，确定目标能力标签所对应的候选职业，目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签。服务器120从候选职业中筛选目标职业，并将目标职业推送至目标对象所在的用户终端110。
本申请提供的方法基于能力模型进行职业推荐，能力模型也称思维模式能力方法(Mode of thinking Capacity Methodology，MCM)模型，是将学习思维进行拆分，拆分出思维模式(thinking)、学习能力(Capacity)和学习方法(Methodology)的一种策略。通过MCM模型可构建对应的MCM标签，而MCM标签也可称作能力标签，用于区分不同的思维模式、学习能力和学习方法。
在一个实施例中，如图2所示，提供了一种职业推荐方法，以该方法应用于计算机设备为例进行说明，该计算机设备可以是图1中的用户终端110或服务器120，该职业推荐方法包括以下步骤：
S202，向目标对象推送与测试能力标签相对应的多道职业测试题；其中，测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定。
目标对象可以是用户对象，该用户对象可以是自然人，如学生；该用户对象也可以是计算机设备可处理的数据对象，比如用户账号所表示的对象。
能力标签是职业测试题的类别标签，可用于表征职业测试题的属性特征。能力标签也称作MCM(Mode of thinking Capacity Methodology)标签。能力标签比如分类讨论思想、沟通能力、估测能力、规范表达能力、规划能力以及规律探究能力等能力标签。一种能力对应一个能力标签。一个能力标签下可对应多道职业测试题。每道职业测试题对应至少一种能力标签，每道职业测试题对应的至少一种能力标签通过MCM模型确定。职业测试题用来测试用户是否掌握与能力标签对应的能力。
测试能力标签是从多个能力标签中筛选出的能力标签。测试能力标签通常是在多个职业中出现频率较高的能力标签。比如，将多个职业中出现频率最高的能力标签作为测试能力标签。还比如，将多个能力标签在多个职业中的出现频率按照从高到低进行排序，从排序名次小于预设名次的能力标签中随机选中一个作为测试能力标签，比如，当预设名次为第四名时，计算机设备从排序的前三名所对应的能力标签中随机挑选一个能力标签作为测试能力标签。当然，还可以有其他的挑选方式，本申请实施例对此不作限定。
测试能力标签下所对应的职业测试题用于测试目标对象是否具有与测试能力标签相应的能力。比如沟通能力标签下的多道职业测试题用于测试用户是否具有与沟通能力标签相应的沟通能力。
在一个实施例中，计算机设备将出现频率最高的能力标签作为测试能力标签，并根据与测试能力标签对应的能力测试结果，在多种职业中快速确定与用户所具备的能力相匹配的职业，也就是说，用户无需逐一对每个职业所对应的职业测试题进行测试，从而保证了职业测评的效率。
在一个实施例中，计算机设备在向目标对象推送职业测试题时，可一道题一道题的依次推送。计算机设备可每次向目标对象推送与测试能力标签相对应的一道职业测试题，再根据目标对象解答当前的职业测试题的答题结果，来确定并推送下一道职业测试题。由于每个用户对每道职业测试题的答题结果可能 不同，计算机设备根据用户的答题结果会相应调整后续的职业测试题，因而每个用户所需解答的职业测试题就会不同。这样，就可根据目标对象当前所具备的能力，推送与目标对象相匹配的职业测试题，从而可以实现在多种职业中快速定位到目标对象具备的能力匹配的职业，不需要逐一根据每一个职业，以及每个职业所对应的每道测试题作答。
在一个实施例中，计算机设备划分与测试能力标签对应的每道职业测试题的难易程度，比如将与测试能力标签对应的多道职业测试题分成1-9的不同难度级别。其中，数值越高表示对应的职业测试题越难。计算机设备可将难度级别处于中间级别的职业测试题划分为中等难度的职业测试题，比如将难度级别为4-6的职业测试题划分为中等难度，或者将难度级别为3-7的职业测试题划分为中等难度，本申请实施例对此不做限定。
在一个实施例中，计算机设备将难度级别满足中等难度条件的职业测试题，作为与测试能力标签对应的第一题，其中，难度级别满足中等难度条件的职业测试题比如是难度级别在4-6的职业测试题。计算机设备随机从与测试能力标签对应的难度级别在4-6的职业测试题中抽选一道职业测试题，将该职业测试题作为与测试能力标签对应的第一题，并将与测试能力标签对应的第一题推送给用户。
每道职业测试题对应至少一个能力标签，对于每道职业测试题对应的每个能力标签，每道职业测试题具有一个与所述每个能力标签对应的难度级别，即对于每个能力标签下的每道职业测试题，每道职业测试题具有对应的难度级别。
在一个实施例中，对于每道职业测试题的与一个能力标签对应的难度级别，计算机设备可先计算出每道职业测试题的与所述一个能力标签所对应的难度值，再将难度值映射成对应的难度级别。可以理解，难度值越大，难度值映射成的难度级别也相对越高；难度值越小，难度值映射成的难度级别也相对越小。计算机设备可以通过逻辑回归算法和最大期望(Expectation Maximization，EM)算法来确定每道职业测试题的难度值。逻辑回归算法是将多个用户的答案对错进行分类。
计算机设备可预先准备训练样本，这些训练样本包括多个用户样本、一些带有难度值的样本测试题。此处的样本测试题的难度值(样本测试题的与样本测试题的能力标签对应的难度值)可以由专业人员通过经验推算得到，并进行人为的设置。
接下来，可通过用户样本来对这些样本测试题进行测试，根据用户样本的响应(响应包括答对或答错)、以及这些样本测试题的难度值来计算得到每个用户样本的与能力标签对应的能力值。关于能力值的计算方式，可参考后面的实施 例中的相关内容。
计算机设备可获取需要确定难度值的职业测试题，通过这多个用户样本分别对这些职业测试题进行测试，得到对应的响应。计算机设备可基于每个用户样本的与一道职业测试题的一个能力标签对应的能力值、对该职业测试题的响应、以及待计算的所述一道职业测试题的与所述一个能力标签对应的难度值构建对应的逻辑函数。然后将每个用户样本所对应的逻辑函数进行连乘运算，以构建目标函数，该目标函数可认为是难度模型。计算机设备可将使得该目标函数的值最大化时的难度值，作为该职业测试题的与所述一个能力标签对应的难度值。
下面来举例说明一道职业测试题的与一个能力标签对应的难度值的计算方式：第i个用户正确回答一道职业测试题的概率，遵从逻辑函数
Figure PCTCN2021087375-appb-000001
(也可称作响应函数)，其中D为常量1.7，θ i是第i个用户的与所述一个能力标签对应的能力值，b是该职业测试题的与该职业测试题的所述一个能力标签对应的难度值。错误回答一道职业测试题的概率为
Figure PCTCN2021087375-appb-000002
(也可称作响应函数)。其中，第i个用户对该题目的响应记为u i。如果用户的响应是正确的，则u i＝1。如果用户的响应是错误的，则u i＝0。n个用户对该题目的响应矢量为u＝＜u 1,u 2,u 3...u n＞。计算机设备对该职业测试题的响应为u的概率为
Figure PCTCN2021087375-appb-000003
参考图3，图3为一个实施例中难度模型的原理示意图。当用户答对这个职业测试题时，在不同难度值下，第2个用户和第3个用户的响应函数分别为图3中P 2和P 3类似的曲线；当用户答错这个职业测试题时，在不同难度值下，第1个用户的响应函数为图3中Q 1类似的曲线。该响应函数反映了答对或答错的概率。计算机设备可将一组用户所对应的响应函数进行连乘运算，得到
Figure PCTCN2021087375-appb-000004
也就是图3中的L(b)曲线。计算机设备可将该L(b)曲线的峰值所对应的难度值作为该职业测试题的与所述一个能力标签对应的难度值。
在一个实施例中，计算机设备根据所计算得到的每道职业测试题的与一个能力标签对应的难度值，确定所述每道职业测试题的与所述一个能力标签对应的难度级别。比如计算机设备挑选的三个测试学生的与一道职业测试题的一个能力标签对应的能力值分别为0.07、0.25以及0.09，且三个测试学生对应的响应分别为<0,1,1>，因而可得到，当
Figure PCTCN2021087375-appb-000005
取得最大值时，对应的难度值b为-0.27，将该难度值进行标准化，可得到标准化后的难度值为0.43。比如，计算机设备可将此时标准化难度值为0.43的职业测试题的与所述一个能 力标签对应的难度级别划分为4，当然，计算机设备也可采用其他的方式进行级别的划分，本申请实施例对此不做限定。
在一个实施例中，用户终端采集到用户的答题结果后，将答题结果发送给服务器。服务器根据用户的答题结果，确定与测试能力标签对应的第二题。比如，当用户的答题结果是答题正确时，服务器向用户推送难度级别高于第一题的职业测试题作为第二题；当用户的答题结果是答题错误时，服务器向用户推送难度级别低于第一题的职业测试题作为第二题。
在一个实施例中，计算机设备采集到用户的答题结果后，根据用户的答题结果，确定与测试能力标签对应的第二题。比如，当用户的答题结果是答题正确时，计算机设备向用户推送难度级别高于第一题的职业测试题作为第二题；当用户的答题结果是答题错误时，计算机设备向用户推送难度级别低于第一题的职业测试题作为第二题。
在一个实施例中，计算机设备设置每个测试能力标签的推送规则。比如每个测试能力标签下最多推送3道职业测试题。可以理解，为了对用户所具备的能力进行一个更准确的测试，对于每个测试能力标签(MCM标签)，还可推送对应的更多的职业测试题，比如5道题或7道题等，本申请实施例对此不做限定。
在一个实施例中，目标对象可通过应用程序或网页进入职业测试页面，该职业测试页面中展示有职业测试题。可以理解，用户在进入职业测试页面之前，可以根据个人需求选择对应的测试版本，比如存在“快速版”、“深入版”和“豪华版”三个测试版本。不同的测试版本进行测试的测试能力标签数量不同。比如“快速版”最多测试7个测试能力标签；“深入版”最多测试10个测试能力标签；“豪华版”最多测试15个测试能力标签。本申请实施例对此不做限定。
在一个实施例中，由于不同的测试版本进行测试的测试能力标签数量不同，因而当用户选择不用的测试版本进行职业测试后，用户所花费的测试时长、以及与用户对应的测试能力结果的准确性可能不同。
S204，根据目标对象解答多道职业测试题的答题结果，确定与目标对象对应的能力测试结果。
能力测试结果是测试用户能力的结果，能力测试结果可以是能力已掌握和能力未掌握。答题结果是用户解答职业测试题所对应的结果，具体可以是答案正确率以及答题时间等信息。答题时间可以是从计算机设备展示第一道测试题开始记时，直至目标对象选择或者填写了答案时为止的时间。答案正确率可以是目标对象选择或者填写的答案与标准答案的差异情况。比如，当目标对象选择或者填写的答案与标准答案相同，则答案正确率为100％；当目标对象选择或者填写的答案与标准答案完全不同，则答案正确率为0％；当目标对象填写的答 案与标准答案有部分相同，则答案正确率根据目标对象填写的答案与标准答案的匹配度所确定。
在一个实施例中，当职业测试题为选择题时，当目标对象选择的答案选项与标准答案选项是同一个选项，则答案正确率为100％；当目标对象选择的答案选项与标准答案选项是不同的选项，则答案正确率为0％。
在一个实施例中，当职业测试题为填空题或简答题时，计算机设备将用户填写的答案，比如一个整句，进行分词处理，得到对应的词序列。进而计算机设备可从词序列中去除掉无实意的虚词或语气助词等，得到关键词集。计算机设备可将所提取的关键词集中的多个关键词与标准答案中的关键词进行匹配，当目标对象的答案中的关键词与标准答案中的关键词相同时，则认为匹配成功。计算机设备可根据目标对象的答案中的关键词中匹配成功的关键词的数量，与关键词集中的关键词的数量，计算匹配度，该匹配度即可认为是答案正确率。
举例说明，当目标对象的答案中的关键词与标准答案中的关键词有部分相同，则答案正确率根据目标对象的答案中的关键词与标准答案中的关键词的匹配数量来决定匹配度，比如一共有4个关键词，则目标对象答对三个关键词时，计算机设备判定当前的职业测试题的答案正确率为75％。
在一个实施例中，该目标对象填写的答案与标准答案的匹配度，也就是该答案正确率可根据人工批改得到。计算机设备在获取到目标对象填写的答案后，可推送至老师所在的终端。老师可对目标对象所填写的答案进行批改，确定目标对象填写的答案与标准答案的匹配度，从而给出答案正确率，并反馈至计算机设备。当然，计算机设备还可采用其他的方式计算目标对象填写的答案与标准答案的匹配度，本申请实施例对此不做限定。
在一个实施例中，当用户解答完与测试能力标签对应的职业测试题后，也就是用户终端采集到用户的答题结果后，用户终端将答题结果发送至服务器。也就是说，计算机设备接收到用户的答题结果。
在一个实施例中，计算机设备根据用户的答题结果，比如答案正确率和答题时间，实时调整下一道职业测试题的难度，或者实时调整下一个测试能力标签。当用户解答当前难度的职业测试题得到错误答案时，计算机设备自动推送一道难度级别低于当前难度的职业测试题，用于更深层的测试用户与当前测试能力标签相应的能力；或者，当用户解答当前测试能力标签下难度级别较低的职业测试题时，用户也得到错误答案时，表示用户不具备与当前测试能力标签相应的能力，计算机设备可自动推送下一个测试能力标签下的职业测试题，从而测试用户的其他能力。因此，计算机设备根据用户的答题结果可以自动调整后续测试的职业测试题的难度级别以及种类，从而保证了为用户匹配符合各自 能力的职业的准确性。
在一个实施例中，计算机设备根据接收到的答题结果，确定用户的能力测试结果。计算机设备确定与测试能力标签对应的答案正确次数。当答案正确次数大于或等于预设次数时，计算机设备判定用户的与测试能力标签对应的能力测试结果为能力已掌握；当答案正确次数小于预设次数时，计算机设备判定用户的与测试能力标签对应的能力测试结果为能力未掌握。预设次数可以是该测试能力标签下的职业测试题的数量的中位数，也就是当与测试能力标签对应的答案正确次数超过一半时，对应的能力测试结果为能力已掌握。
举例说明，当计算机设备向目标对象推送测试能力标签下的3道职业测试题，此时，对应的预设次数可以是2次。当计算机设备接收到用户的答案正确次数为2次时，也就是与测试能力标签对应的答案正确次数超过一半，则可判定用户的能力测试结果为能力已掌握；当计算机设备接收到用户答案正确次数为1次，也就是答案错误次数为2次时，判定用户的能力测试结果为能力未掌握。
S206，根据能力测试结果从能力标签中筛选出下一个待测试的能力所对应的测试能力标签。
在一个实施例中，步骤S206，也就是根据能力测试结果从能力标签中筛选出下一个待测试的能力所对应的测试能力标签的步骤，包括：当与目标对象对应的能力测试结果为能力已掌握时，将所有与测试能力标签对应的职业构成第一集合，并确定第一集合中所有职业对应的能力标签中除测试能力标签以外的每个能力标签出现的频次，将最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签；当与目标对象对应的能力测试结果为能力未掌握时，将职业信息库中除第一集合以外的所有职业构成第二集合，并确定第二集合中所有职业对应的能力标签中每个能力标签出现的频次，将最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签。
在一个实施例中，当根据与测试能力标签对应的答题结果，确定与测试能力标签对应的能力测试结果为能力已掌握时，计算机设备将所有与测试能力标签对应的职业构成第一集合。计算机设备统计第一集合中所有职业对应的能力标签中除去测试能力标签以外的每个能力标签出现的频次，从而筛选出最高频次对应的能力标签。计算机设备将筛选出的最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签。
在一个实施例中，当根据与测试能力标签对应的答题结果，确定与测试能力标签对应的能力测试结果为能力未掌握时，计算机设备将职业信息库中除第一集合以外的所有职业构成第二集合。计算机设备统计第二集合中所有职业对 应的能力标签中每个能力标签出现的频次，从而筛选出最高频次对应的能力标签。计算机设备将筛选出的最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签。
上述实施例中，计算机设备根据能力测试结果从能力标签中筛选出下一个待测试的能力所对应的测试能力标签。通过这样的方式，计算机设备可以有效的筛选出与目标对象的能力对应的职业中的另一个职业测试标签，从而更深层测试用户的其他能力。计算机设备层层递进地筛选出与用户能力相匹配的职业，用户无需逐一对每个职业所对应的所有能力标签下的职业测试题进行测试，保证了职业测试的效率，进而保证了职业推荐的准确性。
S208，返回向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与目标对象对应的多个能力测试结果。
测试停止条件是用于停止当前测试的条件，测试停止条件可以是测试能力标签的数量达到预设标签数量(比如5个标签)，或者所有的职业测试题的数量达到预设题目数量(比如15道题)。
在一个实施例中，当计算机设备从能力标签中筛选出下一个待测试的能力所对应的测试能力标签后，重复执行S202到S206的步骤。当测试能力标签的数量达到预设标签数量或者所有的职业测试题的数量达到预设题目数量时，比如当测试能力标签的数量达到5个或者所有测试能力标签下的所有的职业测试题的数量达到15道题时，不再获取下一个待测试的能力所对应的测试能力标签。
在一个实施例中，计算机设备确定满足测试停止条件之前所得到的能力测试结果。比如，计算机设备一共提供了5个测试能力标签下的职业测试题，因而计算机设备可得到目标对象对应的5个能力测试结果，也就是用户是否具备与这5个测试能力标签对应的5种能力。用户可以掌握其中的一种或者多种能力。
S210，根据多个能力测试结果，确定目标能力标签所对应的候选职业。
目标能力标签目标对象已掌握相应能力的测试能力标签。比如，经过多道职业测试题的测试，用户一共掌握3种能力，那么将这3种能力所对应的测试能力标签分别作为3个目标能力标签。
候选职业是与目标能力标签所对应的职业，其中，每个职业都对应一种或多种能力标签，当该职业中包括目标能力标签时，该职业就可作为候选职业。
在一个实施例中，计算机设备得到与目标对象对应的多个能力测试结果之后，计算机设备将能力测试结果为已掌握的相应测试能力标签作为目标能力标签。
在一个实施例中，当目标能力标签的数量大于一个时，计算机设备将职业信息库中包含任意一个目标能力标签的职业作为候选职业。
在一个实施例中，当目标能力标签的数量大于一个时，计算机设备将职业信息库中同时包含多个目标能力标签的职业作为候选职业。也就是说，候选职业需包含用户已掌握相应能力的多个测试能力标签。
在一个实施例中，计算机设备将能力测试结果为未掌握的相应测试能力标签作为缺失能力标签。计算机设备将职业信息库中包含目标能力标签、且不包含缺失能力便签的职业作为候选职业。也就是说，候选职业的能力标签不包含用户未掌握相应能力的测试能力标签。
S212，从候选职业中筛选目标职业，并将目标职业推荐给目标对象。
目标职业是计算机设备筛选出来要向用户推荐的职业。根据筛选条件的不同，目标职业可以是一个或者多个。本申请实施例对此不作限定。
在一个实施例中，计算机设备还可计算用户所具备的与每个目标能力标签对应的能力的能力值，从而将用户的与每个目标能力标签对应的能力值以及每个目标能力标签的权重值，计算出用户与每个候选职业的匹配度。
在一个实施例中，计算机设备可通过以下方式来计算用户的与每个目标能力标签对应的能力值。比如与该目标能力标签对应的职业测试题包括m道职业测试题，可通过以下公式计算用户的与该目标能力标签对应的能力值：
Figure PCTCN2021087375-appb-000006
其中，
Figure PCTCN2021087375-appb-000007
P j表示该用户正确回答第j道职业测试题的概率，
Figure PCTCN2021087375-appb-000008
其中D为常量1.7，θ是该用户的与该目标能力标签对应的能力值，b j是第j道职业测试题的与该目标能力标签对应的难度值。错误回答一道职业测试题的概率为
Figure PCTCN2021087375-appb-000009
其中，该用户对第j道题目的响应记为u j。如果用户的响应是正确的，则u j＝1。如果用户的响应是错误的，则u j＝0。计算机设备将使得L(θ)最大化时的θ的值作为该用户的与该目标能力标签对应的能力值。
比如，计算机设备挑选的一个目标能力标签下的5道职业测试题的难度值分别为0.95、0.77、0.83、0.89以及0.89，且用户对这5道职业测试题的响应分别为u＝<0,1,1,0,1>，表示用户的第2题、3题和5题回答正确，第1题和4题回答错误。此时，计算机设备根据
Figure PCTCN2021087375-appb-000010
求解用户的与目标能力 标签对应的能力值，具体可以是将L(θ)可以取到最大值时的θ作为用户的与该目标能力标签对应的能力值。比如，θ为1.11时，此时，对应的标准化后的能力值为0.75，并将标准化后的能力值0.75作为用户的与该目标能力标签对应的能力值。标准化的能力值可通过对
Figure PCTCN2021087375-appb-000011
求导得到。能力值的范围可以是0～1，或者其他范围，本申请实施例对此不做限定。
在另一个实施例中，计算机设备根据与目标对象具备相应能力的目标能力标签下的多道职业测试题的答题得分，得到与每个目标能力标签对应的答题总得分。比如，用户与目标能力标签下的多道职业测试题对应的多个答题得分分别为50分、60分和70分，则用户与该目标能力标签对应的答题总得分可以通过累加后求平均值得到，也就是说，答题总得分为60分。本申请对答题总得分的计算方式并不做限定。
在一个实施例中，计算机设备确定每个候选职业对应的能力标签中每个目标能力标签的权重值。计算机设备将与每个目标能力标签对应的答题总得分以及每个目标能力标签的权重值，计算出用户与每个候选职业的匹配度。比如，对于每个候选职业，计算机设备可对与每个候选职业对应的多个目标能力标签对应的答题总得分以及多个目标能力标签的权重值进行加权求和运算，得到出目标对象与该候选职业的匹配度。
在一个实施例中，计算机设备从多个候选职业中筛选出匹配度最高的候选职业，并将匹配度最高的候选职业作为目标职业，也就是计算机设备向用户所推荐的职业。
在一个实施例中，计算机设备将多个候选职业按照相应匹配度的高低进行排序，将排序名次小于预设名次的候选职业筛选为目标职业。比如，计算机设备可将匹配度最高的前三名的候选职业作为目标对象的目标职业。
在一个实施例中，计算机设备根据目标职业、以及与目标能力标签对应的答题总得分或能力值生成对应的职业测试报告，并将职业测试报告反馈给用户。
上述职业推荐方法中，依次向目标对象推送与多个测试能力标签对应的职业测试题，根据目标对象在解答多个测试能力标签对应的多道职业测试题时的答题结果，得到与目标对象对应的多个能力测试结果，从而确定目标对象具备相应能力的目标能力标签所对应的候选职业，并从候选职业中筛选得到目标职业，以向目标对象进行职业推荐。通过这样的方式，向目标对象推送与测试能力标签对应的职业测试题，来测试用户相应能力的大小，从而在多种职业中筛选得到与用户相应能力匹配的目标职业，保证用户能够胜任筛选后所推荐的目标职业，从而大大提高职业推荐的准确性。并且，通过对测试能力标签的层层 筛选，可从多个维度准确、且层层递进地筛选出相应的目标职业，用户无需逐一对每个职业所对应的职业测试题进行测试，因此减少了用户解答大量繁琐或无规律的职业测试题的测试时间成本，这不仅提高了职业推荐的效率，还保证了职业推荐的准确性。
在一个实施例中，该职业推荐方法中初始的测试能力标签通过以下步骤确定：确定职业信息库中多个职业中每个职业对应的能力标签；确定每个能力标签出现在多个职业中的频次，将最高频次所对应的能力标签作为初始的测试能力标签。
在一个实施例中，计算机设备预先构建一套能力标签的架构，每个能力标签都有相对应的题库。该能力标签相对应的题库中的题，可用于测量用户是掌握或具有与该能力标签对应的能力。根据用户对一个能力标签的掌握情况来说明用户是否具有对应的能力。用户对一个能力标签的掌握情况可通过用户在相应测试题的答题结果来确定。
在一个实施例中，职业信息库中的多个职业可包括：教师、医生、策划师、产品经理、程序员、创作型歌手、法律从业人员、翻译家、行政办公人员、记者、教师、金融工作者等职业。本申请对此不做限定。计算机设备为职业信息库中的多个职业中每个职业分配与所述每个职业所需的能力相匹配的能力标签。比如计算机设备为“医生”职业分配的能力标签有数据分析能力、沟通能力、信息筛选能力、估测能力、科学类知识储备能力、演绎推理能力以及分类讨论思想这7个MCM标签。
参考表1，在一个实施例中，计算机设备为职业信息库中的多个职业中每个职业分配对应的能力标签(MCM标签)以及与每个能力标签对应的权重值。比如计算机设备为“教师”职业分配的能力标签有沟通能力、总结概括能力、逻辑分析能力、科学类知识储备能力、分类讨论思想、情景想象与简化能力以及文化识记能力这7个MCM标签，且这7个MCM标签各自对应的权重值分别为7、6、5、4、3、2和1。其中，权重值越高，说明在该职业中更需要具备相应的能力。也就是说，在“教师”职业中，用户最需要掌握的能力是与沟通能力标签对应的沟通能力。
在一个实施例中，计算机设备为“程序员”职业分配的能力标签有逻辑分析能力、规律探究能力、数据分析能力、分类讨论思想、筛选能力、统筹思想以及规划能力这7个能力标签，且这7个MCM标签各自对应的权重值分别为7、6、5、4、3、2和1。
表1多个职业与对应的MCM标签和权重值
职业 MCM标签 权重值
教师 沟通能力 7
教师 总结概括能力 6
教师 逻辑分析能力 5
教师 科学类知识储备能力 4
教师 分类讨论思想 3
教师 情景想象与简化能力 2
教师 文化识记能力 1
程序员 逻辑分析能力 7
程序员 规律探究能力 6
程序员 数据分析能力 5
程序员 分类讨论思想 4
程序员 信息筛选能力 3
程序员 统筹思想 2
程序员 规划能力 1
医生 数据分析能力 7
医生 沟通能力 6
医生 信息筛选能力 5
医生 估测能力 4
医生 科学类知识储备能力 3
医生 演绎推理能力 2
医生 分类讨论思想 1
在一个实施例中，计算机设备统计每个能力标签出现在多个职业中的频次，比如沟通能力在职业信息库的多个职业中的一共出现了15次，是出现频次最高的能力标签。计算机设备将沟通能力标签作为初始的测试能力标签。
在一个实施例中，计算机设备统计每个能力标签出现在多个职业中的频次，将相应频次满足高频次的能力标签条件作为备选能力标签，并从备选能力标签中随机抽取一个标签作为初始的测试能力标签。高频次的能力标签条件比如所 出现的频次数量是最多的三个。比如沟通能力在职业信息库的多个职业中的一共出现了15次，逻辑分析能力一共出现了12次，信息筛选能力一共出现了14次，因而计算机设备将沟通能力、逻辑分析能力以及信息筛选能力作为备选能力标签，并从备选能力标签中随机抽取一个标签作为初始的测试能力标签。
上述实施例中，计算机设备将出现频次最高的能力标签作为初始的测试能力标签，因而计算机设备所推送的初始的测试能力标签下的职业测试题可以覆盖到最广的范围，用户无需逐一对每个职业所对应的职业测试题进行测试，也就是说，初始的测试能力标签下的职业测试题可以对最大数量的职业所需的多项能力中一项能力进行测试，因而提高了职业测试的效率，进而保证了职业推荐的准确性。
在一个实施例中，步骤S202，也就是向目标对象推送与测试能力标签相对应的多道职业测试题的步骤，包括：确定与测试能力标签对应的多道职业测试题中每道职业测试题的难度级别；将难度级别满足中等难度条件的职业测试题，作为与测试能力标签对应的第一题，并向目标对象推送与测试能力标签对应的第一题；基于与测试能力标签对应的第一题的答题结果，确定与测试能力标签对应的第二题；根据与测试能力标签对应的第一题和第二题的答题结果，确定是否向目标对象推送与测试能力标签对应的第三题。
在一个实施例中，计算机设备划分与测试能力标签对应的每道职业测试题的难易程度，比如将与测试能力标签对应的多道职业测试题分成1-9的不同难度级别。数值越高表示对应的职业测试题越难。计算机设备可将处于中间数值的职业测试题划分为中等难度的职业测试题，比如将难度级别为4-6的职业测试题划分为中等难度，或者将难度级别为3-7的职业测试题划分为中等难度，本申请实施例对此不做限定。
在一个实施例中，计算机设备将难度级别满足中等难度条件的职业测试题，作为与测试能力标签对应的第一题，其中，难度级别满足中等难度条件的职业测试题比如是难度级别在4-6的职业测试题。计算机设备随机从与测试能力标签对应的难度级别在4-6的职业测试题中抽选一道职业测试题，将该职业测试题作为与测试能力标签对应的第一题，并将与测试能力标签对应的第一题推送给用户。
在一个实施例中，计算机设备采集用户的答题结果。计算机设备根据用户的答题结果，确定与测试能力标签对应的第二题。比如，当用户的答题结果是答题正确时，计算机设备向用户推送难度级别高于第一题的职业测试题作为第二题；当用户的答题结果是答题错误时，计算机设备向用户推送难度级别低于第一题的职业测试题作为第二题。
在一个实施例中，计算机设备设置每个测试能力标签的推送规则。比如每个测试能力标签下最多推送3道职业测试题。可以理解，为了对用户所具备的能力进行一个更准确的测试，对于每种测试能力标签(MCM标签)，还可推送对应的更多的职业测试题，比如5道题或7道题等，本申请实施例对此不做限定。
在一个实施例中，当计算机设备一共推送与测试能力标签对应的3道职业测试题时，计算机设备接收到用户的答题结果是用户前两题都答对了，计算机设备判定用户已掌握与该测试能力标签对应的能力，也就是说计算机设备无需推送该测试能力标签下的第三题。
在一个实施例中，当计算机设备一共推送与测试能力标签对应的3道职业测试题时，计算机设备接收到用户的答题结果是前两题都答错了，计算机设备判定用户未掌握与该测试能力标签对应的能力，也就是说计算机设备无需推送该测试能力标签下的第三题。
在一个实施例中，当计算机设备一共推送与测试能力标签对应的3道职业测试题时，计算机设备接收到用户的答题结果是前两题中答对一题和答错一题，则计算机设备推送与该测试能力标签下的第三题，从而对用户的能力进一步地进行测试。
上述实施例中，计算机设备向目标对象推送与测试能力标签对应的职业测试题。通过这样的方式，可测试用户是否具备与该测试能力标签对应的能力。由于每个用户的能力可能不同，计算机设备可实时调整对应的职业测试题，以达到用少量的职业测试题来准确测试用户能力的效果，也就是节约了用户的时间成本，并保证了职业推荐的准确性。
在一个实施例中，基于与测试能力标签对应的第一题的答题结果，确定与测试能力标签对应的第二题的步骤，包括：根据与第一题对应的答题结果和难度级别，计算第一题的答题得分；当答题得分大于或等于第一阈值时，将比第一题的难度级别更高的职业测试题作为与测试能力标签对应的第二题，并向目标对象推送与测试能力标签对应的第二题；当答题得分小于第一阈值时，将比第一题的难度级别更低的职业测试题作为与测试能力标签对应的第二题，并向目标对象推送与测试能力标签对应的第二题。
第一阈值是计算机设备预设的答题得分阈值，是一个数值，比如60分。
在一个实施例中，计算机设备根据与第一题对应的答题结果和难度级别，计算第一题的答题得分，其中，答题结果包括答题时间以及答案正确率。答案正确率与答题得分呈正相关，当用户的答案正确率越高，所对应的答题得分越高；答题时间与预设标准时间段的差值与答题得分呈负相关，当用户的答题时 间与预设标准时间段的差值越小，所对应的答题得分越高；职业测试题的难度级别与答题得分呈正相关，当用户解答的职业测试题的难度级别越高，所对应的答题得分越高。
在一个实施例中，当一道职业测试题的解答时间是40秒时，预设标准时间范围比如是计算机设备推送题目后的10-30秒。用户在20秒时回答正确所对应的答题得分，要比用户在5秒时回答正确所对应的答题得分高。这样通过统计答题时间，可将偶然性因素考虑进答题得分中，因而可减少因用户不进行思考、或随机选择一个答案所得到的高答题得分对职业推荐的影响。从而提高职业推荐的准确性。
在一个实施例中，计算机设备计算得到第一题的答题得分，当答题得分大于或等于第一阈值时，计算机设备将比第一题的难度级别更高的职业测试题作为与测试能力标签对应的第二题，并向目标对象推送与测试能力标签对应的第二题。比如计算机设备推送的测试能力标签下的第一题是难别级别为6的职业测试题，且用户在第一题的答题得分为80分，计算机设备向用户推送测试能力标签下的难度级别为7的职业测试题。
在一个实施例中，计算机设备计算得到第一题的答题得分，当答题得分小于第一阈值时，计算机设备将比第一题的难度级别更低的职业测试题作为与测试能力标签对应的第二题，并向目标对象推送与测试能力标签对应的第二题。比如计算机设备推送的测试能力标签下的第一题是难别级别为4的职业测试题，且用户在第一题的答题得分为50分，计算机设备向用户推送测试能力标签下的难度级别为3的职业测试题。
上述实施例中，计算机设备根据基于与测试能力标签对应的第一题的答题结果和难度级别，确定与测试能力标签对应的第二题。通过这样的方式，计算机设备可根据用户的答题情况，实时调整对应的职业测试题，以达到用少量的职业测试题来准确测试用户能力的效果，也就是节约了用户的时间成本，并保证了职业推荐的准确性。
在一个实施例中，能力测试结果包括能力已掌握和能力未掌握，步骤S204，也就是根据目标对象解答职业测试题的答题结果，确定与目标对象对应的能力测试结果的步骤，包括：根据与测试能力标签对应的答题结果，确定与测试能力标签对应的答案正确次数；当答案正确次数大于或等于第二阈值时，确定与目标对象对应的能力测试结果为能力已掌握；当答案正确次数小于第二阈值时，确定与目标对象对应的能力测试结果为能力未掌握。
第二阈值是计算机设备预设的次数，是一个数值，比如2次。
在一个实施例中，计算机设备根据与测试能力标签对应的答题结果，确定与测试能力标签对应的答案正确次数。比如计算机设备一共推送了与测试能力标签对应的三道职业测试题，则对应的答案正确次数可以是0、1或2次。
在一个实施例中，计算机设备一共推送了与测试能力标签对应的2道职业测试题，且用户的答案正确次数为2次。由于答案正确次数和第二阈值相等，此时，计算机设备判定该用户已掌握与该测试能力标签对应的能力；当计算机设备一共推送了与测试能力标签对应的2道职业测试题，且用户的答案正确次数为0次。由于答案正确次数小于第二阈值，此时，计算机设备判定该用户未掌握与该测试能力标签对应的能力。
在一个实施例中，计算机设备一共推送了与测试能力标签对应的3道职业测试题，且用户的答案正确次数为2次。由于答案正确次数和第二阈值相等，此时，计算机设备判定该用户已掌握与该测试能力标签对应的能力；当计算机设备一共推送了与测试能力标签对应的3道职业测试题，且用户的答案正确次数为1次。由于答案正确次数小于第二阈值，此时，计算机设备判定该用户未掌握与该测试能力标签对应的能力。
在一个实施例中，计算机设备根据用户的与测试能力标签对应的能力值的高低，来表示用户的能力掌握情况。比如用户的与测试能力标签对应的能力值大于0.7时，表示用户已极强地掌握了与测试能力标签对应的能力；当用户的与测试能力标签对应的能力值在0.6～0.7时，表示用户已较强地掌握了与测试能力标签对应的能力。
上述实施例中，计算机设备确定与每个测试能力标签对应的答案正确次数，并根据答案正确次数来确定与目标对象对应的能力测试结果。通过这样的方式，可根据能力测试结果来表示用户是否具备与该测试能力标签对应的能力。由于每个用户的能力可能不同，计算机设备可实时调整下一个测试能力标签，以达到用少量的测试能力标签下的职业测试题来准确测试用户能力的效果，也就是节约了用户的时间成本，并保证了职业推荐的准确性。
在一个实施例中，步骤S212，也就是从候选职业中筛选目标职业，并将目标职业推荐给目标对象的步骤，包括：根据每个目标能力标签对应的答题结果，计算得到目标对象的与每个目标能力标签对应的能力值；基于每个候选职业对应的能力标签中的每个目标能力标签的权重值和目标对象的与每个目标能力标签对应的能力值，计算得到目标对象与所述每个候选职业对应的匹配度；从多个候选职业中筛选匹配度满足高匹配度条件的至少一个目标职业；根据目标职业生成对应的职业测试报告，并将职业测试报告反馈至目标对象。
在一个实施例中，计算机设备根据每个目标能力标签下的多道职业测试题 的答题得分，得到与所述每个目标能力标签对应的答题总得分。计算机设备可确定每个候选职业对应的能力标签中每个目标能力标签的权重值。对于每个候选职业，计算机设备可对与多个目标能力标签对应的答题总得分以及多个目标能力标签的权重值进行加权求和运算，得到出目标对象与该候选职业的匹配度。
在一个实施例中，计算机设备还可根据每个目标能力标签所对应的能力值，与相应的权重值，来计算目标对象与每个候选职业的匹配度。对于每个候选职业，计算机设备可查找与该候选职业对应，且对应目标对象所具有能力的目标能力标签，进而确定查找到的目标能力标签在该候选职业对应的能力标签中的权重值。对于该候选职业，计算机设备可对相应的目标能力标签对应的能力值与对应的权重值进行加权求和运算，得到该候选职业与目标对象的匹配度。
在一个实施例中，计算机设备从多个候选职业中筛选出匹配度最高的候选职业，并将匹配度最高的候选职业作为目标职业，也就是计算机设备向用户所推荐的职业。
在一个实施例中，计算机设备将多个候选职业按照相应匹配度的高低进行排序，将排序名次小于预设名次的候选职业筛选为目标职业。比如，计算机设备可将匹配度最高的前三名的候选职业作为向目标对象推荐的目标职业。
在一个实施例中，计算机设备根据目标职业、以及与目标能力标签对应的答题总得分或者能力值生成对应的职业测试报告，并将职业测试报告反馈给用户。职业测试报告还可包括用户的个人信息，比如用户的微信名和微信头像。
在一个实施例中，计算机设备在职业测试报告中按匹配度的大小顺序来展示所推荐的目标职业，比如将匹配度最高的目标职业展示在职业测试报告的第一排。或者，计算机设备将匹配度最高的目标职业显示在职业测试报告的正中间，并且将匹配度最高的目标职业放大突出。
在一个实施例中，计算机设备在职业测试报告中展示推荐理由。推荐理由主要是分析用户与测试能力标签对应的能力测试结果。计算机设备按照用户与多个目标能力标签对应的能力值从高到低排序，在职业测试报告中显示能力值排序靠前的目标能力标签。比如，若目标能力标签一共有3个标签，则取前2位；若目标能力标签一共有2个标签，则只取第1位。
在一个实施例中，推荐理由可以是预设话术，比如用户已掌握相应能力时，推荐理由可以是：你有(极强/较强)的“目标能力标签1”和(极强/较强)的“目标能力标签2”，具有成为一名优秀“排名第1的目标职业”的潜力，同时还有可能成为“排名第2的目标职业”和“排名第3的目标职业”；比如用户未掌握相应能力时，推荐理由可以是：但是你在“缺失能力标签1”和“缺失能力标签 2”上稍有欠缺，努力提升这些能力，你将变得更加优秀。可以用能力值来区分“极强”和“较强”，比如能力值大于0.7时，表示极强，能力值小于0.7时，表示较强。
在一个实施例中，职业测试报告还可包括用户雷达图。计算机设备选取3个目标能力标签，比如，当职业测试报告中包括所推荐的“极强”或“较强”的目标能力标签，则优先选取所推荐的“极强”或“较强”的目标能力标签；当所推荐的“极强”或“较强”的目标能力标签的个数不够，比如少于3个时，选取用户的能力值排名靠前的目标能力标签，从而一共选取3个目标能力标签；计算机设备另选取2个用户的缺失能力标签或者用户的能力值排名靠后的2个目标能力标签。计算机设备按照能力值在职业测试报告中展示这5个能力标签的雷达图。能力值的范围可以是0～1，或者其他范围。
在一个实施例中，当用户与多个测试能力标签下对应的能力测试结果都为能力未掌握时，计算机设备不会将该用户匹配到任何一个对应的职业，也就是说，职业测试报告中无法推荐目标职业。
在一个实施例中，计算机设备在职业测试报告中设置“点击查看做题记录”控件，用于提供查看做题记录的功能。当用户点击“点击查看做题记录”按钮，该职业测试报告中会自动弹出验证手机号的弹框。当用户验证通过后，界面从职业测试报告跳转到答题记录页。
在一个实施例中，计算机设备在职业测试报告中设置“分享”控件，用于提供分享职业测试报告的功能。当用户点击“分享”按钮后，自动生成对应的分享页面。因而其他用户可通过该分享页面跳转到测试首页，以进行相应的职业测试。
在一个实施例中，每个用户只能进行一次职业测试。当用户完成测试后，再次点击“进入测试”按钮时，用户会直接查看到自己的职业测试报告。
在一个实施例中，当用户在职业测试的过程中提前结束测试，比如用户在答题过程中退出测试答题页，则当用户再次进入测试答题页时，会自动跳转到用户上次未完成的职业测试题所对应的测试答题页，因而用户可以继续完成剩余的职业测试题。
上述实施例中，计算机设备基于多个候选职业对应的目标能力标签中的每个目标能力标签的权重值和用户的与每个目标能力标签对应的能力值，计算得到目标对象与每个候选职业对应的匹配度，从而根据匹配度筛选出所要推荐给目标对象的目标职业。通过这样的方式，在多种职业中筛选得到与用户相应能力匹配的目标职业，保证用户能够胜任筛选后所推荐的目标职业，从而大大提 高职业推荐的准确性。这不仅提高了职业推荐的效率，还保证了职业推荐的准确性。
在一个实施例中，用户可通过扫描二维码进入应用程序或网页进入职业测试页面，比如进入到慧眼识人的H5测试页面。当用户点击“开始测试”按钮后，参考图4(a)，用户进入到测试版本选择页。测试版本选择页包括三个不同的版本选择控件和“进入测试”控件。版本选择控件如“快速版”控件、“深入版”控件和“豪华版”控件，用户可根据个人的需求来选择不同的测试版本。并且，不同的版本在职业测试中所测试的能力标签总数量不同、且终止条件也不同。比如，“快速版”中最多测试7个测试能力标签，当计算机设备测试出与用户对应的测试能力结果包括3种能力已掌握以及2种能力未掌握时，可终止测试；“深入版”中最多测试10个测试能力标签，当计算机设备测试出与用户对应的测试能力结果包括4种能力已掌握以及3种能力未掌握时，可终止测试；“豪华版”中最多测试15个测试能力标签，当计算机设备测试出与用户对应的测试能力结果包括5种能力已掌握以及4种能力未掌握时，可终止测试。
当用户选择完版本之后，用户点击“进入测试”按钮，参考图4(b)，用户进入到测试答题页。测试答题页中出现的职业测试题主要是选择题，有时也可以是填空题或解答题。在测试答题页中给用户推荐第一题是与初始的测试能力标签所对应题库中的职业测试题。测试答题页中包括题目序号401、答题计时器402、职业测试题403、“跳过”控件404、以及“提交”控件405。当用户点击“跳过”按钮时，自动跳转到下一题，且未作答的职业测试题的答题结果判定为答案错误。
比如计算机设备预先设置在单个测试能力标签下最多推送3道题。当用户在单个测试能力标签下答错2道题时，计算机设备判定用户与该测试能力标签对应的能力测试结果为能力已掌握，并切换到下一测试能力标签；当用户在单个测试能力标签下答对2道题时，计算机设备判定用户与该测试能力标签对应的能力测试结果为能力未掌握，并切换到下一测试能力标签。
当计算机设备得到用户与测试能力标签对应的能力测试结果为能力已掌握时，计算机设备确定所有需要掌握该测试能力标签的职业所构成的第一集合。计算机设备根据第一集合中每个职业所对应的能力标签，筛选得到出现频次最高所对应的能力标签作为下一个待测试的测试能力标签。进而，计算机设备可向用户推送下一个待测试的测试能力标签中的题。
当计算机设备得到用户与测试能力标签对应的能力测试结果为能力未掌握时，计算机设备确定所有不需要掌握该测试能力标签的职业所构成的第二集合。计算机设备根据第二集合中每个职业所对应的能力标签，筛选得到出现频次最 高所对应的能力标签作为下一个待测试的测试能力标签。进而，计算机设备可向用户推送下一个待测试的测试能力标签中的题。
当用户测试完成后，用户可点击“查看测试结果”按钮，参考图5，从而查看相应的职业测试报告。职业测试报告包括用户的个人信息501、所推荐的目标职业502、推荐理由503、雷达图504以及“点击查看做题记录”控件505。
用户可以点击查看一种能力的具体分析。参考图6，图6为一个实施例中职业推荐方法中的思想能力方法分析的界面图。比如当用户点击查看“思想方法能力分析”时，用户可查看到所有与思想方法能力相关的能力的掌握情况。比如显示沟通能力、信息筛选能力、规律探究能力、字词识记能力、文化识记能力、数据分析能力、分类讨论思想以及算法构造与实现能力等测试能力标签的相应能力的掌握程度。百分比数值越高表示用户掌握相应能力的程度越高。比如当百分比数值大于70％时，属于能力掌握情况为优秀；当百分比数值小于20％时，属于能力掌握情况为较差。本申请实施例对此不做限定。
当用户点击“点击查看做题记录”按钮，该职业测试报告中会自动弹出验证用户手机号的弹框。计算机设备通过验证用户手机号来确定是否为用户本人操作。当用户验证通过后，计算机设备将界面从职业测试报告跳转到答题记录页。答题记录页包括职业测试题目以及对应的多个答案选项。当用户所选的答案选项为正确选项时，用户所选的答案选项后添加正确标记，如以“打钩”的形式进行标记。当用户所选的答案选项为错误选项时，用户所选的答案选项后添加错误标记，如以“打叉”的形式进行标记，并在正确选项后面以“打钩”的形式进行标记。
应该理解的是，虽然图2的流程图中的多个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。
在一个实施例中，如图7所示，提供了一种职业推荐装置700，包括：推送模块701、确定模块702、筛选模块703、重复模块704和推荐模块705，其中：
推送模块701，设置为向目标对象推送与测试能力标签相对应的多道职业测试题；其中，测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定。
确定模块702，设置为根据目标对象解答多道职业测试题的答题结果，确定与目标对象对应的能力测试结果。
筛选模块703，设置为根据能力测试结果从能力标签中筛选出下一个待测试的能力所对应的测试能力标签。
重复模块704，设置为返回向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与目标对象对应的多个能力测试结果。
确定模块702还设置为根据多个能力测试结果，确定目标能力标签所对应的候选职业，其中，所述目标能力标签是所述目标对象具备相应能力的测试能力标签。
推荐模块705，设置为从候选职业中筛选目标职业，并将目标职业推荐给目标对象。
在一个实施例中，确定模块702还设置为确定职业信息库中所述多个职业中每个职业对应的能力标签；确定每个能力标签出现在所述多个职业中的频次，将最高频次所对应的能力标签作为初始的测试能力标签。
在一个实施例中，推送模块701是设置为通过如下方式向目标对象推送与测试能力标签相对应的多道职业测试题：确定与测试能力标签对应的多道职业测试题中每道职业测试题的难度级别；将难度级别满足中等难度条件的职业测试题，作为与测试能力标签对应的第一题，并向目标对象进行推送与测试能力标签对应的第一题；基于与测试能力标签对应的第一题的答题结果，确定与测试能力标签对应的第二题；根据与测试能力标签对应的第一题和第二题的答题结果，确定是否向目标对象推送与测试能力标签对应的第三题。
在一个实施例中，推送模块701是设置为通过如下方式基于与测试能力标签对应的第一题的答题结果，确定与测试能力标签对应的第二题：根据与第一题对应的答题结果和难度级别，计算第一题的答题得分；当答题得分大于或等于第一阈值时，将比第一题的难度级别更高的职业测试题作为与测试能力标签对应的第二题，并向目标对象推送与测试能力标签对应的第二题；当答题得分小于第一阈值时，将比第一题的难度级别更低的职业测试题作为与测试能力标签对应的第二题，并向目标对象推送与测试能力标签对应的第二题。
在一个实施例中，能力测试结果包括能力已掌握和能力未掌握；确定模块702是设置为通过如下方式根据目标对象解答职业测试题的答题结果，确定与目标对象对应的能力测试结果：根据与测试能力标签对应的答题结果，确定与测试能力标签对应的答案正确次数；当答案正确次数大于或等于第二阈值时，确定与目标对象对应的能力测试结果为能力已掌握；当答案正确次数小于第二阈 值时，确定与目标对象对应的能力测试结果为能力未掌握。
在一个实施例中，筛选模块703是设置为当与目标对象对应的能力测试结果为能力已掌握时，将所有与测试能力标签对应的职业构成第一集合，并确定第一集合中所有职业对应的能力标签中除测试能力标签以外的每个能力标签出现的频次，将最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签；当与目标对象对应的能力测试结果为能力未掌握时，将职业信息库中除第一集合以外的所有职业构成第二集合，并确定第二集合中所有职业对应的能力标签中每个能力标签出现的频次，将最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签。
在一个实施例中，推荐模块705还设置为根据每个目标能力标签对应的答题结果，计算得到目标对象的与每个目标能力标签对应的能力值；基于每个候选职业对应的能力标签中的每个目标能力标签的权重值和目标对象的与每个目标能力标签对应的能力值，计算得到目标对象与每个候选职业对应的匹配度；从多个候选职业中筛选匹配度满足高匹配度条件的至少一个目标职业；根据至少一个目标职业生成对应的职业测试报告，并将职业测试报告反馈至目标对象。
在一实施例中，每道职业测试题对应至少一种能力标签，每道职业测试题对应的至少一种能力标签根据MCM模型确定。
上述基于能力模型进行职业推荐的装置，依次向目标对象推送与多个测试能力标签对应的职业测试题，根据目标对象解答每个测试能力标签对应的多道职业测试题时的答题结果，得到与目标对象对应的多个能力测试结果，从而确定目标对象具备相应能力的目标能力标签所对应的候选职业，并从候选职业中筛选得到目标职业，以向目标对象进行职业推荐。通过这样的方式，向目标对象推送与测试能力标签对应的职业测试题，来测试用户相应能力的大小，从而在多种职业中筛选得到与用户相应能力匹配的目标职业，保证用户能够胜任筛选后所推荐的目标职业，从而大大提高职业推荐的准确性。并且，通过对测试能力标签的层层筛选，可从多个维度准确、且层层递进地筛选出相应的目标职业，用户无需逐一对每个职业所对应的职业测试题进行测试，因此减少了用户解答大量繁琐或无规律的职业测试题的测试时间成本，这不仅提高了职业推荐的效率，还保证了职业推荐的准确性。
关于职业推荐装置的限定可以参见上文中对于职业推荐方法的限定，在此不再赘述。上述职业推荐装置中的多个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是终端或服务器，其内部结构图可以如图8所示。该计算机设备包括通过系统总线连接的处理器、存储器和通信接口。该计算机设备的处理器设置为提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统和计算机程序。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的通信接口用于与外部的终端进行有线或无线方式的通信，无线方式可通过WIFI(Wireless Fidelity，无线局域网)、运营商网络、NFC(Near Field Communication，近场通信)或其他技术实现。该计算机程序被处理器执行时以实现一种目标分类方法。
本领域技术人员可以理解，图8中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合一些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器存储有计算机程序，计算机程序被处理器执行时，使得处理器执行上述职业推荐方法。此处职业推荐方法可以是上述多个实施例的职业推荐方法。
在一个实施例中，提供了一种计算机可读存储介质，存储有计算机程序，计算机程序被处理器执行时，使得处理器执行上述职业推荐方法。此处职业推荐方法可以是上述多个实施例的职业推荐方法中。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。本申请所提供的实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-Only Memory，ROM)、磁带、软盘、闪存或光存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic Random Access Memory，DRAM)等。
以上实施例的多个技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的多个个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。

Claims (11)

  1. 一种职业推荐方法，包括：
    向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定；
    根据所述目标对象在解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果；
    根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对应的测试能力标签；
    返回所述向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与所述目标对象对应的多个能力测试结果；
    根据所述多个能力测试结果，确定目标能力标签所对应的候选职业，其中，所述目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签；
    从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象。
  2. 根据权利要求1所述的方法，其中，所述初始的测试能力标签通过以下步骤确定：
    确定所述职业信息库中所述多个职业中每个职业对应的能力标签；
    确定每个能力标签出现在所述多个职业中的频次，将最高频次所对应的能力标签作为初始的测试能力标签。
  3. 根据权利要求1所述的方法，其中，所述向目标对象推送与测试能力标签相对应的多道职业测试题，包括：
    确定与所述测试能力标签对应的多道职业测试题中每道职业测试题的难度级别；
    将难度级别满足中等难度条件的职业测试题，作为与所述测试能力标签对应的第一题，并向所述目标对象推送与所述测试能力标签对应的第一题；
    基于与所述测试能力标签对应的第一题的答题结果，确定与所述测试能力标签对应的第二题；
    根据与所述测试能力标签对应的第一题和第二题的答题结果，确定是否向所述目标对象推送与所述测试能力标签对应的第三题。
  4. 根据权利要求3所述的方法，其中，所述基于与所述测试能力标签对应的第一题的答题结果，确定与所述测试能力标签对应的第二题，包括：
    根据与所述第一题对应的答题结果和难度级别，计算所述第一题的答题得分；
    在所述答题得分大于或等于第一阈值的情况下，将比所述第一题的难度级别更高的职业测试题作为与所述测试能力标签对应的第二题，并向所述目标对象推送与所述测试能力标签对应的第二题；
    在所述答题得分小于所述第一阈值的情况下，将比所述第一题的难度级别更低的职业测试题作为与所述测试能力标签对应的第二题，并向所述目标对象推送与所述测试能力标签对应的第二题。
  5. 根据权利要求1所述的方法，其中，所述能力测试结果包括能力已掌握和能力未掌握；所述根据目标对象解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果，包括：
    根据与所述测试能力标签对应的答题结果，确定与所述测试能力标签对应的答案正确次数；
    在所述答案正确次数大于或等于第二阈值的情况下，确定与所述目标对象对应的能力测试结果为能力已掌握；
    在所述答案正确次数小于所述第二阈值的情况下，确定与所述目标对象对应的能力测试结果为能力未掌握。
  6. 根据权利要求5所述的方法，其中，所述根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对应的测试能力标签，包括：
    在与所述目标对象对应的能力测试结果为能力已掌握的情况下，将所有与所述测试能力标签对应的职业构成第一集合，并确定所述第一集合中所有职业对应的能力标签中除所述测试能力标签以外的每个能力标签出现的频次，将最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签；
    在与所述目标对象对应的能力测试结果为能力未掌握的情况下，将所述职业信息库中除所述第一集合以外的所有职业构成第二集合，并确定所述第二集合中所有职业对应的能力标签中每个能力标签出现的频次，将最高频次所对应的能力标签作为下一个待测试的能力所对应的测试能力标签。
  7. 根据权利要求1至6中任一项所述的方法，其中，所述目标能力标签的数量为多个，所述候选职业的数量为多个；
    所述从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象，包括：
    根据所述每个目标能力标签对应的答题结果，计算得到所述目标对象的与 所述每个目标能力标签对应的能力值；
    基于每个候选职业对应的能力标签中的每个目标能力标签的权重值和所述目标对象的与每个目标能力标签对应的能力值，计算得到所述目标对象与所述每个候选职业对应的匹配度；
    从所述候选职业中筛选所述匹配度满足高匹配度条件的至少一个目标职业；
    根据所述至少一个目标职业生成对应的职业测试报告，并将所述职业测试报告反馈至所述目标对象。
  8. 根据权利要求1所述的方法，其中，每道职业测试题对应至少一种能力标签，每道职业测试题对应的至少一种能力标签根据MCM模型确定。
  9. 一种职业推荐装置，包括：
    推送模块，设置为向目标对象推送与测试能力标签相对应的多道职业测试题；其中，所述测试能力标签中初始的测试能力标签基于职业信息库中多个职业中每个职业对应的能力标签所确定；
    确定模块，设置为根据所述目标对象解答所述多道职业测试题的答题结果，确定与所述目标对象对应的能力测试结果；
    筛选模块，设置为根据所述能力测试结果从所述能力标签中筛选出下一个待测试的能力所对应的测试能力标签；
    重复模块，设置为返回所述向目标对象推送与测试能力标签相对应的多道职业测试题，直至满足测试停止条件，得到与所述目标对象对应的多个能力测试结果；
    所述确定模块还设置为根据所述多个能力测试结果，确定目标能力标签所对应的候选职业，其中，所述目标能力标签是所述目标对象具备测试能力标签相应能力的测试能力标签；
    推荐模块，设置为从所述候选职业中筛选目标职业，并将所述目标职业推荐给所述目标对象。
  10. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现权利要求1至8中任一项所述的方法。
  11. 一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1至8中任一项所述的方法。
PCT/CN2021/087375 2020-06-09 2021-04-15 职业推荐方法、装置、设备和介质 WO2021180249A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2021103999A AU2021103999A4 (en) 2020-06-09 2021-07-09 Occupation recommendation method, apparatus, device and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010516522.2 2020-06-09
CN202010516522.2A CN111651676B (zh) 2020-06-09 2020-06-09 基于能力模型进行职业推荐的方法、装置、设备和介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
AU2021103999A Division AU2021103999A4 (en) 2020-06-09 2021-07-09 Occupation recommendation method, apparatus, device and medium

Publications (1)

Publication Number Publication Date
WO2021180249A1 true WO2021180249A1 (zh) 2021-09-16

Family

ID=72347421

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/087375 WO2021180249A1 (zh) 2020-06-09 2021-04-15 职业推荐方法、装置、设备和介质

Country Status (2)

Country Link
CN (1) CN111651676B (zh)
WO (1) WO2021180249A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115455200A (zh) * 2022-09-13 2022-12-09 九江职业技术学院 一种用于专业大类的技能测试技能树构建方法及系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111651676B (zh) * 2020-06-09 2021-03-05 上海松鼠课堂人工智能科技有限公司 基于能力模型进行职业推荐的方法、装置、设备和介质
CN112634099A (zh) * 2020-12-24 2021-04-09 成都存时科技有限公司 基于大数据的实践管理方法、装置、设备及可读存储介质
CN112651862A (zh) * 2020-12-24 2021-04-13 成都存时科技有限公司 学生学业发展方向规划方法、装置、设备及可读存储介质
CN113095732B (zh) * 2021-05-10 2024-06-11 广州宏途数字科技有限公司 一种现实场景职业测评方法
CN113570322A (zh) * 2021-05-14 2021-10-29 南京奥派信息产业股份公司 面向高职学生的职业测评方法及装置
CN114819898A (zh) * 2022-04-25 2022-07-29 平安科技（深圳）有限公司 职业答题数据的处理方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102509184A (zh) * 2011-10-24 2012-06-20 山东城通科技有限公司 企业经营管理人才综合素质与岗位胜任能力测评体系
CN103294816A (zh) * 2013-06-09 2013-09-11 广东倍智人才管理咨询有限公司 一种为求职者推荐职位的方法和职位推荐系统
US20150149378A1 (en) * 2013-11-26 2015-05-28 Chegg, Inc. Job recall services in online education platforms
CN108647294A (zh) * 2018-05-07 2018-10-12 韦玮 信息推荐系统
CN109857835A (zh) * 2018-12-28 2019-06-07 北京红山瑞达科技有限公司 一种基于认知诊断理论的自适应网络安全知识测评方法
CN111651676A (zh) * 2020-06-09 2020-09-11 上海乂学教育科技有限公司 基于能力模型进行职业推荐的方法、装置、设备和介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20180037936A (ko) * 2018-03-26 2018-04-13 박관영 국제 지역의 산업군별 직무 특화 분석개발을 위한 정보통신기술 기반 빅데이터 분산 ＆ 매칭 알고리즘 도출과 활용 시스템
CN109272247A (zh) * 2018-10-09 2019-01-25 常州信息职业技术学院 一种大学生就业方向综合指导系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102509184A (zh) * 2011-10-24 2012-06-20 山东城通科技有限公司 企业经营管理人才综合素质与岗位胜任能力测评体系
CN103294816A (zh) * 2013-06-09 2013-09-11 广东倍智人才管理咨询有限公司 一种为求职者推荐职位的方法和职位推荐系统
US20150149378A1 (en) * 2013-11-26 2015-05-28 Chegg, Inc. Job recall services in online education platforms
CN108647294A (zh) * 2018-05-07 2018-10-12 韦玮 信息推荐系统
CN109857835A (zh) * 2018-12-28 2019-06-07 北京红山瑞达科技有限公司 一种基于认知诊断理论的自适应网络安全知识测评方法
CN111651676A (zh) * 2020-06-09 2020-09-11 上海乂学教育科技有限公司 基于能力模型进行职业推荐的方法、装置、设备和介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115455200A (zh) * 2022-09-13 2022-12-09 九江职业技术学院 一种用于专业大类的技能测试技能树构建方法及系统

Also Published As

Publication number Publication date
CN111651676A (zh) 2020-09-11
CN111651676B (zh) 2021-03-05

Similar Documents

Publication Publication Date Title
WO2021180249A1 (zh) 职业推荐方法、装置、设备和介质
US11615341B2 (en) Customizable machine learning models
Zehlike et al. Fairness in ranking: A survey
KR102206256B1 (ko) 온라인 강의 시스템에서 강사를 추천하는 방법
US11734566B2 (en) Systems and processes for bias removal in a predictive performance model
CN107230174B (zh) 一种基于网络的在线互动学习系统和方法
CN109740048B (zh) 一种课程推荐方法及装置
KR20200135892A (ko) 사용자 맞춤형 학습 커리큘럼 추천 및 교육 컨텐츠 제공 시스템 및 방법
CN111090809A (zh) 题目推荐方法、装置、计算机设备和存储介质
Putpuek et al. Comparative study of prediction models for final GPA score: a case study of Rajabhat Rajanagarindra University
Henry et al. Quantifying fear of failure in STEM: Modifying and evaluating the Performance Failure Appraisal Inventory (PFAI) for use with STEM undergraduates
CN116263782A (zh) 一种基于题库的智能组卷方法、系统及存储介质
KR20190006409A (ko) 암기학습 데이터를 활용한 단어 인지상태 정량화와 스마트기기 학습 및 스케줄링 장치 및 방법
Chen et al. Online item calibration for Q-matrix in CD-CAT
WO2022005440A2 (en) A system and method for determining digital maturity level of organizations
Timmermans et al. In search of value added in the case of complex school effects
Costa et al. Automatic classification of computational thinking skills in elementary school math questions
CN113313470A (zh) 一种基于大数据的就业类型评估方法及系统
CN112365384A (zh) 目标事件结果指标权重、影响因素值确定方法及相关装置
Bao et al. Flexible computerized adaptive tests to detect misconceptions and estimate ability simultaneously
CN111553555A (zh) 培训方法、装置、计算机设备和存储介质
CN112598202B (zh) 试题难度评估方法、装置及存储介质、计算设备
CN114971962A (zh) 学生作业的评价方法、装置、电子设备及存储介质
AU2021103999A4 (en) Occupation recommendation method, apparatus, device and medium
CN112200474A (zh) 教学质量评价方法、终端设备及计算机可读存储介质

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: 21768551

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21768551

Country of ref document: EP

Kind code of ref document: A1

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 1205A DATED 300623)

122 Ep: pct application non-entry in european phase

Ref document number: 21768551

Country of ref document: EP

Kind code of ref document: A1