WO2023159754A1 - 能力等级分析方法、装置、电子设备及存储介质 - Google Patents
能力等级分析方法、装置、电子设备及存储介质 Download PDFInfo
- Publication number
- WO2023159754A1 WO2023159754A1 PCT/CN2022/090430 CN2022090430W WO2023159754A1 WO 2023159754 A1 WO2023159754 A1 WO 2023159754A1 CN 2022090430 W CN2022090430 W CN 2022090430W WO 2023159754 A1 WO2023159754 A1 WO 2023159754A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- question
- subject
- preset
- value
- level
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Definitions
- the present application relates to the technical field of intelligent decision-making, and in particular to a capability level analysis method, device, electronic equipment and computer-readable storage medium.
- testees based on the preset question bank, and then to evaluate the relevant abilities of the testees according to the answers of the testees, especially in the field of language education.
- suitable courses can be selected, or corresponding learning products can be recommended.
- IRT Item Response Theory, one-dimensional item response theory
- setting test questions reflecting different ability levels and making an initial prediction of the ability level of the testee based on the collected basic information of the testee.
- the ability level is obtained to determine the corresponding test items, and the final test item set is obtained for the testee to perform the test.
- this evaluation method may have the situation that the test questions do not match the real ability level of the testee, especially for the testees with strong abilities, their real ability level has not been detected. At the same time, there will be too many test questions, and the repetition of test questions with the same ability level will cause the resentment of the testees and affect the real ability level of the testees.
- the above-mentioned evaluation method ignores the relationship between the ability reflected by the testee in the process of leveling in real time and the characteristics of the test topic, which may lead to a decline in the accuracy of the ability analysis of the testee.
- a capability level analysis method provided by this application includes:
- testee's answer score of the tested question When it is detected that the subject has completed a question, obtain the testee's answer score of the tested question, and update the testee's ability value according to the response level and answer score of each of the tested questions ;
- the latest updated capability value of the subject is taken as the final capability level of the subject.
- the present application also provides a capability level analysis device, which includes:
- Ability preliminary evaluation module used to obtain the information data of the subject, and calculate the ability value of the subject according to the information data
- the question bank topic selection module is used to obtain the response level of each question in the preset question bank, and select a question from the preset question bank that meets the first preset condition according to the reaction level and the ability value and send it to all Describe the subject;
- An ability update module configured to obtain the testee's answer scores of the tested questions when it is detected that the testee completes a question, and update the said testee according to the response level and answer score of each said tested question.
- a level determination module configured to calculate the absolute difference between the updated capability value and the pre-updated capability value, and if the absolute difference does not meet the second preset condition, return to the above-mentioned The ability value of the subject is selected, and a question satisfying the first preset condition is selected from the preset question bank and sent to the subject, if the absolute difference satisfies the second preset condition, Then, the latest updated capability value of the subject is taken as the final capability level of the subject.
- the present application also provides an electronic device, the electronic device comprising:
- a memory storing at least one computer program
- a processor executing the program stored in the memory to implement the capability level analysis method as follows:
- testee's answer score of the tested question When it is detected that the subject has completed a question, obtain the testee's answer score of the tested question, and update the testee's ability value according to the response level and answer score of each of the tested questions ;
- the latest updated capability value of the subject is taken as the final capability level of the subject.
- the present application also provides a computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement capability level analysis as described below method:
- testee's answer score of the tested question When it is detected that the subject has completed a question, obtain the testee's answer score of the tested question, and update the testee's ability value according to the response level and answer score of each of the tested questions ;
- the latest updated capability value of the subject is taken as the final capability level of the subject.
- FIG. 1 is a schematic flow diagram of a capability level analysis method provided by an embodiment of the present application
- FIG. 2 is a schematic diagram of a detailed implementation process of one of the steps in the capability level analysis method shown in FIG. 1;
- FIG. 3 is a functional block diagram of a capability level analysis device provided by an embodiment of the present application.
- Fig. 4 is a schematic structural diagram of an electronic device implementing the capability level analysis method provided by an embodiment of the present application.
- An embodiment of the present application provides a capability level analysis method.
- the subject of execution of the capability level analysis method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application.
- the capability level analysis method can be executed by software or hardware installed on the terminal device or server device, and the software can be a block chain platform.
- the server can be an independent server, or provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (ContentDeliveryNetwork , CDN), and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms.
- the capability level analysis method includes:
- the information data refers to information data that can directly or indirectly reflect the ability level of the subject in the field that needs to be evaluated.
- the information data includes but not limited to the testee's education background, major, age, job nature, whether he often browses English news or watches English programs, movies, etc.
- the ability value of the subject refers to a quantification of the skill level of the subject in the field that needs to be evaluated.
- the testee's ability value ranges from 1 to 6.
- the calculation of the ability value of the subject according to the information data includes: extracting the text features contained in the information data to obtain a text feature set; calculating the relationship between each of the text features in the text feature set and Relative probability values among preset multiple assessment levels; calculating the score of each assessment level according to the relative probability values, and determining the assessment level with the highest score as the ability value of the subject.
- Glove GlobalVectorsforWordRepresentation, global word vector
- EmbeddingLayer may be used to convert the information data into a text vector matrix.
- the text features include but not limited to text scenes, text topics , Text keywords.
- a pre-trained LSTM (LongShort-TermMemory, long-short-term memory network) model can be used to perform feature extraction on the text vector matrix of the information data, so as to obtain text features in the text vector matrix.
- LSTM LongShort-TermMemory, long-short-term memory network
- a preset activation function can be used to calculate each of the text features in the text feature set, so as to calculate the relative probability between each of the text features and a plurality of preset evaluation levels,
- the relative probability refers to the probability value that each text feature is a certain evaluation level.
- the text feature is used to express the evaluation level. The higher the probability of rank.
- the activation function includes, but is not limited to, a softmax activation function, a sigmoid activation function, and a relu activation function.
- the multiple preset evaluation levels include but are not limited to poor, average, proficient, and proficient.
- the preset question bank refers to a pre-designed set of questions for evaluating the ability level of the testee, which is usually set according to the difficulty level and knowledge composition of each question in the preset question bank.
- the evaluation level corresponding to each of the questions, that is, the reaction level, for example, the reaction level includes but not limited to level 1, level 2, level 3, etc.
- selecting a question from the preset question bank that satisfies the first preset condition and sending it to the subject includes: according to the reaction level and the Calculate the difficulty value of each of the questions based on the ability value; select a question whose difficulty value satisfies the first preset condition as an optional question; randomly select a question from the optional questions and send it to the tested subject By.
- the calculation of the difficulty value of each of the questions based on the reaction level of each of the questions and the ability value includes:
- p ui ( ⁇ ) represents the difficulty value corresponding to the i-th question in the preset question bank when the testee's ability value is equal to ⁇
- ui represents the response level corresponding to the i-th question in the preset question bank
- b ui represents the degree of difficulty for the subject to complete the i-th question in the preset question bank to reach the response level corresponding to ui
- D represents a constant
- a i represents the i-th question in the preset question bank distinction.
- the first preset condition may be a pre-designated maximum difficulty interval, for example, the maximum difficulty interval is 50% to 60%, and when the testee's ability value is ⁇ , question 1 is relatively The difficulty value of the subject being tested is 75%, the difficulty value of topic 2 is 52% relative to the subject being tested, and the difficulty value of topic 3 is 40% relative to the subject being tested, then the difficulty value of topic 2 is If the value is within the maximum difficulty range, the corresponding topic 2 can be included in the optional topics.
- a question that meets the first preset condition is selected from the preset question bank and sent to the testee.
- the degree of correlation between the test questions and the testee's ability value can be improved, so that each question sent to the testee can more effectively reflect the real ability level of the testee.
- each question in the preset question bank can be a binary question, and the binary question is mostly an objective question. Usually, the answer to the binary question is unique, and the corresponding question score is only 0 or full score in two cases.
- Each question can also be a multi-point system question. The multi-point system questions are mostly subjective questions. Usually, the answers to the multi-point system questions are not unique. According to the preset answer standard, the corresponding reaction levels of different scores are divided.
- updating the ability value of the subject according to the response level and answer score of each of the tested questions includes:
- the preset mapping relationship between the score of a question and the reaction level refers to a one-to-one correspondence between different scores of each question and the reaction level of the question. For example, if the testee's score for a certain binary question is full, then the testee's ability value conforms to the response level of the binary question, and the testee's score for a certain binary question is zero. points, the ability value of the subject does not meet the response level of the binary question.
- the relationship between the score of the multi-point system topic and the response level of the multi-point system topic is more complicated.
- the mapping relationship can define the response levels corresponding to different score intervals. For example, the score range of a certain multi-point system topic is 0 to 5 points, and the response level corresponding to the multi-point system topic is level 3. If the score of the above multi-point system is less than 3 points, the corresponding response level is 1, and the respondent's score is 3 to 4 points, and the corresponding response level is 2, and the respondent's score is 5 points, and the corresponding response The level is 3.
- the preset maximum likelihood function is as follows:
- V) represents the answering result of the testee when completing the V-th question
- ⁇ represents the corresponding predictive ability value of the testee when completing the V-th question
- ui represents the i-th question in the preset question bank.
- ki represents the testee’s score when answering the i-th question
- record uik represents the answer result of the i-th question in the preset question bank.
- the maximum likelihood function may be used to solve the corresponding predictive ability value of the subject when completing the V-th track question through the Newton-Raphson iterative method.
- the ability value of the subject can be updated in real time according to the reaction level and score of each tested question.
- the second preset condition may be a pre-specified maximum capability difference, for example, 0.2 or 0.3.
- the absolute difference between the updated capability value and the pre-updated capability value is relatively small, it means that the measured person's capability value is relatively stable during the pre- and post-evaluation processes. If the absolute difference between the ability value after the update and the ability value before the update is relatively large, it means that the response levels of the questions sent to the subject before and after the difference are relatively large, and the corresponding ability value of the subject is still relatively large. Unstable, it is necessary to continue to send questions to the subject for further evaluation until the ability value of the subject tends to be stable.
- the absolute difference if the absolute difference does not satisfy the second preset condition, it means that the ability value of the subject is in an unstable state, and further evaluation of the subject is required.
- the number of test questions can be controlled.
- the absolute difference does not meet the For the second preset condition, return to the above-mentioned step of selecting a question satisfying the first preset condition from the preset question bank and sending it to the subject according to the reaction level and the ability value, and replace it with: Judging whether the number of tested questions is greater than the preset threshold of evaluation questions; if the number of tested questions is not greater than the threshold of the number of evaluation questions, return to S2, if the number of tested questions is greater than the number of evaluation questions threshold value, the latest updated ability value of the person under test is used as the final ability level of the person under test;
- the preset threshold for the amount of evaluation questions may be set according to actual conditions.
- the testee's ability value tends to be stable, and the evaluation can be ended, and the testee's latest updated ability value is used as The testee's final ability level.
- This application adjusts the questions sent to the testee according to the ability value of the testee updated in real time during the testee's answering process, and strengthens the relationship between the questions and the testee's ability, so that the questions sent to the testee
- the tester's questions can more effectively reflect the real ability level of the testee, which improves the accuracy of ability level analysis.
- by controlling the absolute value between the ability values before and after the update it prevents the questions sent to the testee from appearing before and after Large jumps, thus ensuring the accuracy of ability level analysis.
- FIG. 3 it is a functional block diagram of a capability level analysis device provided by an embodiment of the present application.
- the capability level analysis device 100 described in this application can be installed in electronic equipment. According to the functions realized, the ability level analysis device 100 may include an ability preliminary evaluation module 101, a question bank topic selection module 102, an ability update module 103 and a level determination module 104.
- the module described in this application can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.
- each module/unit is as follows:
- the ability preliminary evaluation module 101 is used to obtain the information data of the subject, and calculate the ability value of the subject according to the information data;
- the question bank topic selection module 102 is used to obtain the response level of each topic in the preset question bank, and select one from the preset question bank that satisfies the first preset requirement according to the reaction level and the ability value of the subject. Conditional questions are sent to the subject;
- the ability update module 103 is used to obtain the answer score of the tested subject when it is detected that the subject has completed a question, and according to the response level and answer score of each of the tested questions, updating the ability value of the subject;
- the level determination module 104 is configured to calculate the absolute difference between the updated capability value and the pre-updated capability value, and if the absolute difference does not meet the second preset condition, return to the above-mentioned response based on the level and the ability value of the testee, select a question from the preset question bank that meets the first preset condition and send it to the testee, if the absolute difference satisfies the second preset If the condition is set, the latest updated capability value of the subject is taken as the final capability level of the subject.
- each module in the capability level analysis device 100 described in the embodiment of the present application adopts the same technical means as the capability level analysis method described in the above-mentioned Figures 1 to 2 when used, and can generate the same technical effect, which will not be repeated here.
- FIG. 4 it is a schematic structural diagram of an electronic device implementing a capability level analysis method provided by an embodiment of the present application.
- the electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and operable on the processor 10, such as a capability level analysis program.
- the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc.
- the storage 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 .
- the memory 11 can also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk equipped on the electronic device 1, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, flash memory card (FlashCard), etc.
- the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
- the memory 11 can not only be used to store application software and various data installed in the electronic device 1 , such as codes of capability level analysis programs, but also can be used to temporarily store outputted or to-be-outputted data.
- the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more A combination of central processing unit (Central Processing unit, CPU), microprocessor, digital processing chip, graphics processor and various control chips, etc.
- the processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and runs or executes programs or modules stored in the memory 11 (such as capability level analysis program, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
- the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like.
- PCI peripheral component interconnect
- EISA extended industry standard architecture
- the bus can be divided into address bus, data bus, control bus and so on.
- the bus is configured to realize connection and communication between the memory 11 and at least one processor 10 and the like.
- FIG. 4 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 4 does not constitute a limitation to the electronic device 1, and may include fewer or more components, or combinations of certain components, or different arrangements of components.
- the electronic device 1 can also include a power supply (such as a battery) for supplying power to various components.
- the power supply can be logically connected to the at least one processor 10 through a power management device, so that the power supply can be controlled by power management.
- the device implements functions such as charge management, discharge management, and power consumption management.
- the power supply may also include one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.
- the electronic device 1 may also include various sensors, bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
- the electronic device 1 may also include a network interface.
- the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which are usually used in the electronic device 1 Establish a communication connection with other electronic devices.
- the electronic device 1 may further include a user interface, which may be a display (Display) or an input unit (such as a keyboard (Keyboard)).
- the user interface may also be a standard wired interface or a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) touch device, and the like.
- the display may also be appropriately called a display screen or a display unit, and is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
- the capability level analysis program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can realize:
- testee's answer score of the tested question When it is detected that the subject has completed a question, obtain the testee's answer score of the tested question, and update the testee's ability value according to the response level and answer score of each of the tested questions ;
- the latest updated capability value of the subject is taken as the final capability level of the subject.
- the integrated modules/units of the electronic device 1 are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium.
- the computer-readable storage medium may be volatile or non-volatile.
- the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) ).
- the present application also provides a computer-readable storage medium, the readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, it can realize:
- testee's answer score of the tested question When it is detected that the subject has completed a question, obtain the testee's answer score of the tested question, and update the testee's ability value according to the response level and answer score of each of the tested questions ;
- the latest updated capability value of the subject is taken as the final capability level of the subject.
- modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
- each functional module in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
- the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software function modules.
- Blockchain essentially a decentralized database, is a series of data blocks associated with each other using cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify its Validity of information (anti-counterfeiting) and generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
- AI artificial intelligence
- the embodiments of the present application may acquire and process relevant data based on artificial intelligence technology.
- artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
本申请涉及智能决策技术,揭露一种能力等级分析方法,包括:监测到被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;判断更新前后能力值之间的绝对差值是否满足第二预设条件;若所述绝对差值不满足所述第二预设条件,则根据每道题目的反应等级及所述被测者的能力值,从预设题库中选取一道满足第一预设条件的题目发送给所述被测者;若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。本申请还提出一种能力等级分析装置、设备以及介质。本申请可以提升能力等级分析的准确率。
Description
本申请要求于2022年02月23日提交中国专利局、申请号为202210166713.X,发明名称为“能力等级分析方法、装置、电子设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及智能决策技术领域,尤其涉及一种能力等级分析方法、装置、电子设备及计算机可读存储介质。
基于预设的题库对被测者进行测试,进而根据被测者的答题情况,对被测者进行相关能力的评估在线上或线下教育领域中是非常普遍的一种做法,尤其是在语言类教育领域最为常见。例如,英语词汇量等级测评、英语口语能力等级测评。通常可以根据被测者的能力评级等级,选择适配相关的课程,或推荐相应的学习产品。
当前大多数能力测评基于IRT(ItemResponseTheory,单维项目反应理论),设置反映不同能力等级的测试题目,基于采集到的被测者的基本信息对被测者的能力水平进行初始预测,根据初始预测得到能力水平确定相应的测试题目,得到最终的测试题目集供所述被测者进行测试。
发明人意识到,通常测试题目集一次性确定后,在测评过程中不会根据被测者的实际答题情况进行测试题目范围和数量的调整。因此,这种测评方式可能存在测试题目与被测者的真实能力水平不符的情况,尤其针对能力较强的被测者而言,自己的真实能力水平并没有被检测出来。同时也会存在测试题目数量过多,放映相同能力水平的测试题目的重复,会引起被测者的反感,影响了被测者的真实能力水平的发挥。上述这种测评方式忽略了被测者在测平过程实时反映出的能力与测试题目的特性之间的关联,可能会导致对被测者能力分析准确性的下降。
发明内容
本申请提供的一种能力等级分析方法,包括:
获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
计算更新后的能力值与更新前的能力值之间的绝对差值;
若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;
若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
本申请还提供一种能力等级分析装置,所述装置包括:
能力初评模块,用于获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
题库选题模块,用于获取预设题库中每道题目的反应等级,根据所述反应等级及所述 能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
能力更新模块,用于监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
等级确定模块,用于计算更新后的能力值与更新前的能力值之间的绝对差值,若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述被测者的能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤,若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
本申请还提供一种电子设备,所述电子设备包括:
存储器,存储至少一个计算机程序;及
处理器,执行所述存储器中存储的程序以实现如下所述的能力等级分析方法:
获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
计算更新后的能力值与更新前的能力值之间的绝对差值;
若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;
若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有至少一个计算机程序,所述至少一个计算机程序被电子设备中的处理器执行以实现如下所述的能力等级分析方法:
获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
计算更新后的能力值与更新前的能力值之间的绝对差值;
若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;
若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
图1为本申请一实施例提供的能力等级分析方法的流程示意图;
图2为图1所示能力等级分析方法中其中一个步骤的详细实施流程示意图;
图3为本申请一实施例提供的能力等级分析装置的功能模块图;
图4为本申请一实施例提供的实现所述能力等级分析方法的电子设备的结构示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所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。
本申请实施例提供一种能力等级分析方法。所述能力等级分析方法的执行主体包括但 不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述能力等级分析方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端可以是独立的服务器,也可以是提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、内容分发网络(ContentDeliveryNetwork,CDN)、以及大数据和人工智能平台等基础云计算服务的云服务器。
参照图1所示,为本申请一实施例提供的能力等级分析方法的流程示意图。在本实施例中,所述能力等级分析方法包括:
S1、获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
本申请实施例中,所述信息数据是指能够直接地或间接地反映出所述被测者在需要评估的领域内的能力水平的信息数据。例如,在英语口语测评中,所述信息数据包括但不限于所述被测者的学历、专业、年龄、工作性质、是否经常浏览英语新闻或观看英语节目、电影等。
本申请实施例中,所述被测者的能力值是指对所述被测者在需要评估的领域内的技能水平的一种量化。例如,在英语口语测评中,所述被测者的能力值范围可以为1至6级。
详细地,所述根据所述信息数据计算所述被测者的能力值,包括:提取所述信息数据包含的文本特征,得到文本特征集;计算所述文本特征集中每个所述文本特征与预设的多个测评等级之间的相对概率值;根据所述相对概率值计算每个所述测评等级的得分,确定得分最高的测评等级为所述被测者的能力值。
本申请实施例中,可采用Glove(GlobalVectorsforWordRepresentation,全局词向量)、EmbeddingLayer等方法将所述信息数据转换为文本向量矩阵。
进一步地,在将所述信息数据转换为文本向量矩阵后,可对所述文本向量矩阵进行特征提取,以获取所述信息数据的文本特征,所述文本特征包括但不限于文本场景、文本主题、文本关键词。
本申请其中一个实施例中,可利用预先训练的LSTM(LongShort-TermMemory,长短期记忆网络)模型对所述信息数据的文本向量矩阵进行特征提取,以获取所述文本向量矩阵中的文本特征。
本申请实施例中,可利用预设的激活函数分别对所述文本特征集中每个所述文本特征进行计算,以计算每个所述文本特征与预设多个测评等级之间的相对概率,其中,所述相对概率是指每一个文本特征是某一种测评等级的概率值,当某一文本特征与某一测评等级之间的相对概率越高,则该文本特征是用于表达该测评等级的概率越高。
本申请实施例中,所述激活函数包括但不限于softmax激活函数、sigmoid激活函数、relu激活函数。
本申请实施例中,所述预设的多个测评等级包括但不限于较差、一般,熟练,精通。
S2、获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
本申请实施例中,所述预设题库是指预先设计的用于测评被测者能力水平的题目集,通常会根据所述预设题库中每道题目的难易程度、知识构成等信息设置每道所述题目对应的测评等级,即反应等级,例如,所述反应等级包括但不限于1级、2级、3级等。
详细地,所述根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者,包括:根据所述反应等级及所述能力值计算每道所述题目的难度值;选择所述难度值满足所述第一预设条件的题目作为可选题目;从所述可选题目中随机选择一道题目发送给所述被测者。
详细地,所述根据每道所述题目的反应等级及所述能力值计算每道所述题目的难度值,包括:
利用如下预设的难度评估函数,计算每道所述题目对应的难度值:
p
ui(θ)表示在被测者的能力值等于θ的情况下,所述预设题库中第i道题目对应的难度值,ui表示所述预设题库中第i道题目对应的反应等级,b
ui表示被测者完成所述预设题库中第i道题目达到ui对应的反应等级的难度等级,D表示一个常量,a
i表示所述第i道题目在所述预设题库中的区分度。
本申请实施例中,所述第一预设条件可以是预先指定的最大难度区间,例如,所述最大难度区间为50%至60%,当被测者的能力值为θ时,题目1相对于所述被测者的难度值为75%,题目2相对于所述被测者的难度值为52%,题目3相对于所述被测者的难度值为40%,则题目2的难度值在所述最大难度区间内,相应的题目2可以纳入到所述可选题目中。
本申请实施例中,根据每道所述题目的反应等级及所述被测者的能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者,可以提升测评题目与所述被测者能力值之间的关联度,使得每道发送给所述被测者的题目能更加有效地反应出所述被测者的真实能力水平。
S3、监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
本申请实施例中,在所述预设的题库中每道题目可以是二分制题目,所述二分制题目多为客观题,通常所述二分制题目的答案是唯一的,相应的题目得分只有0或满分两种情况。每到题目也可以是多分制题目,所述多分制题目多为主观题,通常所述多分制题目的答案是不唯一,根据预设的答案标准,划分不同的得分对应的反应等级。
详细地,参阅图2所示,所述S2中,所述根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值,包括:
S31、根据预设的题目得分与反应等级之间的映射关系,判断每道所述已测题目的答题得分与所述已测题目的反应等级是否匹配;
若每道所述已测题目的答题得分与所述已测题目的反应等级匹配,则执行S32、将所述已测题目的答题结果设置为1;
若每道所述已测题目的答题得分与所述已测题目的反应等级不匹配,则执行S33、将所述已测题目的答题结果设置为0;
S34、利用预设的极大似然函数,根据每道所述已测题目的答题结果,计算所述被测者的预测能力值,并将所述预测能力值作为所述被测者更新后的能力值。
本申请实施例中,所述预设的题目得分与反应等级之间的映射关系是指每道所述题目的不同得分与所述题目的反应等级之间的一一对应关系。例如,所述被测者针对某二分制题目的得分为满分,则所述被测者的能力值符合所述二分制题目的反应等级,所述被测者针对某二分制题目的得分为零分,则所述被测者的能力值不符合所述二分制题目的反应等级。
本申请实施例中,相较于二分制题目,所述多分制题目的得分与所述多分制题目的反应等级之间的关系较为复杂,通过所述预设的题目得分与反应等级之间的映射关系,可以定义不同得分区间对应的反应等级,例如,某一多分制题目的得分范围为0至5分,所述多分制题目对应的反应级别为3级,可以设置被测者针对所述多分制题目的得分低于3分,相应的反应等级为1级,被测者的得分为3至4分,相应的反应级别为2级,被测者的得分为5分,相应的反应级别为3级。
本申请实施例中,所述预设的极大似然函数如下所示:
其中,L(θ|V)表示被测者完成第V道题目时的答题结果,θ表示被测者在完成第V道题目时对应的预测能力值,ui表示所述预设题库中第i道题目的反应等级,ki表示被测者在答复第i道题目时的得分,record
uik表示所述预设题库中第i道题目的答题结果。
本申请实施例中,当题目的得分与所述题目的反应等级匹配时,record
uik=1,当题目的得分与所述题目的反应等级不匹配时,record
uik=0。
本申请实施例中,可以通过牛顿拉夫逊迭代法,利用所述极大似然函数求解所述被测者在完成第V道题目时对应的预测能力值。
本申请实施例中,所述被测者每完成一道题目,根据每道所述已测题目的反应等级及得分,可以实时更新所述被测者的能力值。
S4、计算更新后的能力值与更新前的能力值之间的绝对差值
本申请实施例中,所述第二预设条件可以是一个预先指定的最大能力差值,例如,0.2或0.3。
可以理解的是,如果更新后的能力值与更新前的能力值之间的绝对差值比较小,表示前后测评过程中所述被测者的能力值比较稳定。如果更新后的能力值与更新前的能力值之间的绝对差值比较大,表示前后发送给所述被测者的题目的反应等级差别比较大,相应的所述被测者的能力值还不稳定,需要继续向所述被测者发送题目进行进一步地测评,直到所述被测者的能力值趋于稳定。
若所述绝对差值不满足第二预设条件,则返回S2;
本申请实施例中,若所述绝对差值不满足所述第二预设条件,则表示所述被测者的能力值处于不稳定状态,需要进一步地对所述被测者进行测评。
本申请另一可选实施例中,为了防止被测者由于测评题量过大,导致测评准确率下降的情况,可以控制测评题目的数量,详细地,所述若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤替换为:判断已测题目的数量是否大于预设的测评题量阈值;若所述已测题目的数量不大于所述测评题量阈值,则返回S2,若所述已测题目的数量大于所述测评题量阈值,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级;
本申请实施例中,所述预设的测评题量阈值可以根据实际情况设置。
若所述绝对差值满足所述第二预设条件,则执行S5、将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
本申请实施例中,若所述绝对差值满足所述第二预设条件,表示所述被测者的能力值趋于稳定,可以结束测评,将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
本申请申请通过在被测者的答题过程中,根据实时更新的被测者的能力值调整发送给被测者的题目,加强了题目与被测者能力之间的关联关系,使得发送给被测者的题目更能有效的反应出被测者的真实能力水平,提升了能力等级分析的准确性,同时通过控制更新前后能力值之间的绝对值,防止发送给被测者的题目前后出现较大的跳跃性,从而保障了能力等级分析的准确性。
如图3所示,是本申请一实施例提供的能力等级分析装置的功能模块图。
本申请所述能力等级分析装置100可以安装于电子设备中。根据实现的功能,所述能 力等级分析装置100可以包括能力初评模块101、题库选题模块102、能力更新模块103及等级确定模块104。本申请所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述能力初评模块101,用于获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
所述题库选题模块102,用于获取预设题库中每道题目的反应等级,根据所述反应等级及所述被测者的能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
所述能力更新模块103,用于监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
所述等级确定模块104,用于计算更新后的能力值与更新前的能力值之间的绝对差值,若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述被测者的能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤,若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
详细地,本申请实施例中所述能力等级分析装置100中的各个模块在使用时采用与上述的图1至图2中所述的能力等级分析方法一样的技术手段,并能够产生相同的技术效果,这里不再赘述。
如图4所示,是本申请一实施例提供的实现能力等级分析方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如能力等级分析程序。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(SmartMediaCard,SMC)、安全数字(SecureDigital,SD)卡、闪存卡(FlashCard)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如能力等级分析程序的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(CentralProcessingunit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(ControlUnit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如能力等级分析程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheralcomponentinterconnect,简称PCI)总线或扩展工业标准结构(extendedindustrystandardarchitecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图4仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图4示出的结构 并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(OrganicLight-EmittingDiode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的能力等级分析程序是多个指令的组合,在所述处理器10中运行时,可以实现:
获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
计算更新后的能力值与更新前的能力值之间的绝对差值;
若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;
若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
具体地,所述处理器10对上述指令的具体实现方法可参考图1对应实施例中相关步骤的描述,在此不赘述。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读存储介质中。所述计算机可读存储介质可以是易失性的,也可以是非易失性的。例如,所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-OnlyMemory)。
本申请还提供一种计算机可读存储介质,所述可读存储介质存储有计算机程序,所述计算机程序在被电子设备的处理器所执行时,可以实现:
获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;
获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;
监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;
计算更新后的能力值与更新前的能力值之间的绝对差值
若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;
若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图标记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
本申请实施例可以基于人工智能技术对相关的数据进行获取和处理。其中,人工智能(ArtificialIntelligence,AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能,感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。
Claims (20)
- 一种能力等级分析方法,其中,所述方法包括:获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;计算更新后的能力值与更新前的能力值之间的绝对差值;若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
- 如权利要求1所述的能力等级分析方法,其中,所述根据所述信息数据计算所述被测者的能力值,包括:提取所述信息数据包含的文本特征,得到文本特征集;计算所述文本特征集中每个所述文本特征与预设的多个测评等级之间的相对概率值;根据所述相对概率值计算每个所述测评等级的得分,确定得分最高的测评等级为所述被测者的能力值。
- 如权利要求1所述的能力等级分析方法,其中,所述根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者,包括:根据所述反应等级及所述能力值计算每道所述题目的难度值;选择所述难度值满足所述第一预设条件的题目作为可选题目;从所述可选题目中随机选择一道题目发送给所述被测者。
- 如权利要求1所述的能力等级分析方法,其中,所述根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值,包括:根据预设的题目得分与反应等级之间的映射关系,判断每道所述已测题目的答题得分与所述已测题目的反应等级是否匹配;若每道所述已测题目的答题得分与所述已测题目的反应等级匹配,则将所述已测题目的答题结果设置为1;若每道所述已测题目的答题得分与所述已测题目的反应等级不匹配,则将所述已测题目的答题结果设置为0;利用预设的极大似然函数,根据每道所述已测题目的答题结果,计算所述被测者的预测能力值,并将所述预测能力值作为所述被测者更新后的能力值。
- 如权利要求1至6任一项所述的能力等级分析方法,其中,所述若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤替换为:判断已测题目的数量是否大于预设的测评题量阈值;若所述已测题目的数量不大于所述测评题量阈值,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;若所述已测题目的数量大于所述测评题量阈值,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
- 一种能力等级分析装置,其中,所述装置包括:能力初评模块,用于获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;题库选题模块,用于获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;能力更新模块,用于监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;等级确定模块,用于计算更新后的能力值与更新前的能力值之间的绝对差值,若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤,若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
- 一种电子设备,其中,所述电子设备包括:至少一个处理器;以及,与所述至少一个处理器通信连接的存储器;其中,所述存储器存储有可被所述至少一个处理器执行的计算机程序,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的能力等级分析方法:获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;计算更新后的能力值与更新前的能力值之间的绝对差值;若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
- 如权利要求9所述的电子设备,其中,所述根据所述信息数据计算所述被测者的能力值,包括:提取所述信息数据包含的文本特征,得到文本特征集;计算所述文本特征集中每个所述文本特征与预设的多个测评等级之间的相对概率值;根据所述相对概率值计算每个所述测评等级的得分,确定得分最高的测评等级为所述被测者的能力值。
- 如权利要求9所述的电子设备,其中,所述根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者,包括:根据所述反应等级及所述能力值计算每道所述题目的难度值;选择所述难度值满足所述第一预设条件的题目作为可选题目;从所述可选题目中随机选择一道题目发送给所述被测者。
- 如权利要求9所述的电子设备,其中,所述根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值,包括:根据预设的题目得分与反应等级之间的映射关系,判断每道所述已测题目的答题得分与所述已测题目的反应等级是否匹配;若每道所述已测题目的答题得分与所述已测题目的反应等级匹配,则将所述已测题目的答题结果设置为1;若每道所述已测题目的答题得分与所述已测题目的反应等级不匹配,则将所述已测题目的答题结果设置为0;利用预设的极大似然函数,根据每道所述已测题目的答题结果,计算所述被测者的预测能力值,并将所述预测能力值作为所述被测者更新后的能力值。
- 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下所述的能力等级分析方法:获取被测者的信息数据,根据所述信息数据计算所述被测者的能力值;获取预设题库中每道题目的反应等级,根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者;监测到所述被测者完成一道题目时,获取所述被测者的已测题目的答题得分,根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值;计算更新后的能力值与更新前的能力值之间的绝对差值;若所述绝对差值不满足第二预设条件,则返回上述的根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者的步骤;若所述绝对差值满足所述第二预设条件,则将所述被测者最近更新的能力值作为所述被测者的最终能力等级。
- 如权利要求15所述的计算机可读存储介质,其中,所述根据所述信息数据计算所述被测者的能力值,包括:提取所述信息数据包含的文本特征,得到文本特征集;计算所述文本特征集中每个所述文本特征与预设的多个测评等级之间的相对概率值;根据所述相对概率值计算每个所述测评等级的得分,确定得分最高的测评等级为所述被测者的能力值。
- 如权利要求15所述的计算机可读存储介质,其中,所述根据所述反应等级及所述能力值,从所述预设题库中选取一道满足第一预设条件的题目发送给所述被测者,包括:根据所述反应等级及所述能力值计算每道所述题目的难度值;选择所述难度值满足所述第一预设条件的题目作为可选题目;从所述可选题目中随机选择一道题目发送给所述被测者。
- 如权利要求15所述的计算机可读存储介质,其中,所述根据每道所述已测题目的反应等级及答题得分,更新所述被测者的能力值,包括:根据预设的题目得分与反应等级之间的映射关系,判断每道所述已测题目的答题得分与所述已测题目的反应等级是否匹配;若每道所述已测题目的答题得分与所述已测题目的反应等级匹配,则将所述已测题目的答题结果设置为1;若每道所述已测题目的答题得分与所述已测题目的反应等级不匹配,则将所述已测题目的答题结果设置为0;利用预设的极大似然函数,根据每道所述已测题目的答题结果,计算所述被测者的预测能力值,并将所述预测能力值作为所述被测者更新后的能力值。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210166713.X | 2022-02-23 | ||
| CN202210166713.XA CN114519534A (zh) | 2022-02-23 | 2022-02-23 | 能力等级分析方法、装置、电子设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023159754A1 true WO2023159754A1 (zh) | 2023-08-31 |
Family
ID=81598833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/090430 Ceased WO2023159754A1 (zh) | 2022-02-23 | 2022-04-29 | 能力等级分析方法、装置、电子设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114519534A (zh) |
| WO (1) | WO2023159754A1 (zh) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007271886A (ja) * | 2006-03-31 | 2007-10-18 | Nippon Tokei Jimu Center:Kk | 能力値推定方法、能力値推定装置、およびコンピュータプログラム |
| CN106981230A (zh) * | 2017-06-02 | 2017-07-25 | 广州星耀悦教育科技有限公司 | 一种阅读能力的测评方法及其存储介质、装置 |
| CN107657559A (zh) * | 2017-08-25 | 2018-02-02 | 北京享阅教育科技有限公司 | 一种中文阅读能力测评方法及系统 |
| CN111311055A (zh) * | 2019-12-26 | 2020-06-19 | 成都终身成长科技有限公司 | 一种用户能力的评估方法、装置及存储介质 |
| CN111507084A (zh) * | 2019-01-30 | 2020-08-07 | 沪江教育科技(上海)股份有限公司 | 一种语句难度确定方法及系统 |
| CN111507632A (zh) * | 2020-04-21 | 2020-08-07 | 北京一起教育信息咨询有限责任公司 | 一种发展性评测的方法、装置及电子设备 |
| CN111784553A (zh) * | 2020-07-07 | 2020-10-16 | 北京新唐思创教育科技有限公司 | 数据分析方法、装置、电子设备及存储介质 |
| CN113850512A (zh) * | 2021-09-27 | 2021-12-28 | 平安科技(深圳)有限公司 | 基于自适应测评的用户能力定级方法、装置、设备及介质 |
| CN113987328A (zh) * | 2020-12-30 | 2022-01-28 | 深圳平安智汇企业信息管理有限公司 | 一种题目推荐方法、设备、服务器及存储介质 |
| CN114049240A (zh) * | 2021-11-06 | 2022-02-15 | 北京乐学一百在线教育科技有限公司 | 基于学生在线学习数据智能推荐题目及学习路径的方法 |
-
2022
- 2022-02-23 CN CN202210166713.XA patent/CN114519534A/zh active Pending
- 2022-04-29 WO PCT/CN2022/090430 patent/WO2023159754A1/zh not_active Ceased
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007271886A (ja) * | 2006-03-31 | 2007-10-18 | Nippon Tokei Jimu Center:Kk | 能力値推定方法、能力値推定装置、およびコンピュータプログラム |
| CN106981230A (zh) * | 2017-06-02 | 2017-07-25 | 广州星耀悦教育科技有限公司 | 一种阅读能力的测评方法及其存储介质、装置 |
| CN107657559A (zh) * | 2017-08-25 | 2018-02-02 | 北京享阅教育科技有限公司 | 一种中文阅读能力测评方法及系统 |
| CN111507084A (zh) * | 2019-01-30 | 2020-08-07 | 沪江教育科技(上海)股份有限公司 | 一种语句难度确定方法及系统 |
| CN111311055A (zh) * | 2019-12-26 | 2020-06-19 | 成都终身成长科技有限公司 | 一种用户能力的评估方法、装置及存储介质 |
| CN111507632A (zh) * | 2020-04-21 | 2020-08-07 | 北京一起教育信息咨询有限责任公司 | 一种发展性评测的方法、装置及电子设备 |
| CN111784553A (zh) * | 2020-07-07 | 2020-10-16 | 北京新唐思创教育科技有限公司 | 数据分析方法、装置、电子设备及存储介质 |
| CN113987328A (zh) * | 2020-12-30 | 2022-01-28 | 深圳平安智汇企业信息管理有限公司 | 一种题目推荐方法、设备、服务器及存储介质 |
| CN113850512A (zh) * | 2021-09-27 | 2021-12-28 | 平安科技(深圳)有限公司 | 基于自适应测评的用户能力定级方法、装置、设备及介质 |
| CN114049240A (zh) * | 2021-11-06 | 2022-02-15 | 北京乐学一百在线教育科技有限公司 | 基于学生在线学习数据智能推荐题目及学习路径的方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114519534A (zh) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022141861A1 (zh) | 情感分类方法、装置、电子设备及存储介质 | |
| CN113887930B (zh) | 问答机器人健康度评估方法、装置、设备及存储介质 | |
| CN114913371B (zh) | 多任务学习模型训练方法、装置、电子设备及存储介质 | |
| CN112288337B (zh) | 行为推荐方法、装置、设备及介质 | |
| CN114781832A (zh) | 课程推荐方法、装置、电子设备及存储介质 | |
| CN113742069B (zh) | 基于人工智能的容量预测方法、装置及存储介质 | |
| CN113918704A (zh) | 基于机器学习的问答方法、装置、电子设备及介质 | |
| CN116645554A (zh) | 多模态医学报告检索方法、装置、电子设备及存储介质 | |
| CN113297371A (zh) | 推荐题目库的生成方法、装置、设备及存储介质 | |
| WO2021135322A1 (zh) | 一种自动出题方法、装置及系统 | |
| WO2023178979A1 (zh) | 问题标注方法、装置、电子设备及存储介质 | |
| CN116521867B (zh) | 文本聚类方法、装置、电子设备及存储介质 | |
| CN112269875B (zh) | 文本分类方法、装置、电子设备及存储介质 | |
| CN111784553B (zh) | 数据分析方法、装置、电子设备及存储介质 | |
| CN111930908A (zh) | 基于人工智能的答案识别方法及装置、介质、电子设备 | |
| CN116364300A (zh) | 中医体质辨识方法、装置、设备及存储介质 | |
| CN115952778A (zh) | 问卷问题权重自适应生成方法、装置、设备及存储介质 | |
| CN114722280A (zh) | 基于用户画像的课程推荐方法、装置、设备及存储介质 | |
| CN115048501A (zh) | 知识库的优化方法、装置、电子设备及存储介质 | |
| WO2023159754A1 (zh) | 能力等级分析方法、装置、电子设备及存储介质 | |
| JP6751955B1 (ja) | 学習方法、評価装置、及び評価システム | |
| CN115146622B (zh) | 数据标注纠错方法、装置、电子设备及存储介质 | |
| CN114723488B (zh) | 课程推荐方法、装置、电子设备及存储介质 | |
| CN116628162A (zh) | 语义问答方法、装置、设备及存储介质 | |
| CN116737946A (zh) | 实体信息图谱生成方法、装置、电子设备及存储介质 |
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: 22928026 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: 22928026 Country of ref document: EP Kind code of ref document: A1 |




