User capability evaluation method, medium and system

Abstract

The invention discloses a user ability evaluation method, medium and system, and the method comprises the steps: obtaining original answer data, calculating a corresponding score standard deviation, and generating standardized score data; obtaining a user answering behavior log, and calculating a redo rate corresponding to user evaluation based on the user answering behavior log; judging whether a fluctuation factor can be constructed or not; if yes, calculating a fluctuation factor, and generating a normalized vector according to the standardized score data and the fluctuation factor; constructing a fluctuation derivative based on a behavior fluctuation sequence generation mechanism of the sliding window; judging whether the fluctuation derivative meets a dynamic adjustment condition or not; if yes, performing dynamic weighted fusion based on the fluctuation derivative and the normalized vector to obtain a final risk score; and if not, performing static weighted fusion based on the normalized vector to obtain a final risk score. The user capability can be effectively evaluated, the volatility of the user in the evaluation process is effectively evaluated, and the accuracy of the evaluation result is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent assessment technology, and in particular to a user capability assessment method, medium, and system. Background Art

[0002] With the development of science and technology, more and more applications are being developed to serve user ability assessment scenarios (for example, on-the-job ability assessment, educational assessment, psychological assessment, etc.).

[0003] In related technologies, when assessing user capabilities, most methods use a weighted average based on user scores. In other words, a user's capabilities are directly evaluated based on the average of individual behavior or task scores. This approach is highly intuitive and computationally efficient. However, this approach completely ignores the volatility of the user assessment process over time or at the dimensional level. This can lead to potentially risky users not being identified, thus affecting the accuracy of the assessment results. Summary of the Invention

[0004] The present invention aims to solve, at least to a certain extent, one of the technical problems in the related art. To this end, one object of the present invention is to provide a user capability assessment method that can effectively assess user capabilities and effectively evaluate the volatility of users during the assessment process, thereby improving the accuracy of the assessment results.

[0005] In the first aspect, an embodiment of the present invention proposes a user capability assessment method, including: obtaining original answer data corresponding to the user assessment, and calculating the corresponding score standard deviation based on the original answer data, and generating standardized score data based on the score standard deviation; obtaining the user answer behavior log recorded during the user assessment, and calculating the redo rate corresponding to the user assessment based on the user answer behavior log; judging whether the fluctuation factor can be constructed based on the user answer behavior log, the score standard deviation and the redo rate; if so, calculating the fluctuation factor based on the standardized score data, and generating a normalized vector based on the standardized score data and the fluctuation factor; constructing a fluctuation derivative based on a behavioral fluctuation sequence generation mechanism of a sliding window; judging whether the fluctuation derivative meets the dynamic adjustment conditions; if so, performing dynamic weighted fusion based on the fluctuation derivative and the normalized vector to obtain a final risk score; if not, performing static weighted fusion based on the normalized vector to obtain a final risk score.

[0006] In some embodiments, the standardized score data is generated by the following formula: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

[0007] In some embodiments, the retry rate is calculated by the following formula: in, Represents the redo rate, Indicates the total number of redo events for all questions during the user evaluation process. Indicates the number of valid questions.

[0008] In some embodiments, whether the fluctuation factor is constructible is determined based on the user answer behavior log, the score standard deviation and the redo rate, including: determining whether the behavior log is missing; if so, determining that the fluctuation factor is not constructible; if not, determining whether the score standard deviation is greater than or equal to a lower limit value; if the score standard deviation is less than the lower limit value, determining that the fluctuation factor is not constructible; if the score standard deviation is greater than or equal to the lower limit value, determining whether the redo rate is greater than a redo rate threshold; if the redo rate is greater than the redo rate threshold, determining that the fluctuation factor is not constructible; if the redo rate is less than or equal to the redo rate threshold, determining that the fluctuation factor is constructible.

[0009] In some embodiments, if the volatility factor is not constructible, the standardized score data is directly normalized to obtain a corresponding normalized result, and a calculation is performed based on the normalized result to obtain a final risk score.

[0010] In some embodiments, static weighted fusion is performed based on the normalized vector to obtain a final risk score, including: Performing linear fusion based on the normalized vector to obtain a linear fusion result, and performing nonlinear enhancement on the linear fusion result to obtain a final risk score; The normalized vector is expressed by the following formula: in, represents the normalized vector, represents the normalized result of the standardized score, represents the normalized result of the volatility factor; in, represents the linear fusion result, represents the weight parameter; in, represents the final risk score obtained by nonlinear enhancement, parameter Indicates the steepness of the nonlinear function, represents the median risk.

[0011] In some embodiments, dynamic weighted fusion is performed based on the following formula to obtain a final risk score: in, represents the wave derivative, Indicates the timestamp corresponding to the last valid question. Indicates the timestamp corresponding to the first valid question. represents the last window number in the standard deviation sequence, represents the dynamic weight, represents the risk response slope mapping coefficient, represents the dynamic risk index, represents the final risk score obtained by dynamic fusion, parameter Indicates the steepness of the nonlinear function, represents the median risk.

[0012] In a second aspect, an embodiment of the present invention provides a computer-readable storage medium on which a user capability assessment program is stored. When the user capability assessment program is executed by a processor, the user capability assessment method described above is implemented.

[0013] In a third aspect, an embodiment of the present invention proposes a user ability assessment system, comprising: a preprocessing module, the preprocessing module is used to obtain original answer data corresponding to the user assessment, and calculate the corresponding score standard deviation based on the original answer data, and generate standardized score data based on the score standard deviation; a behavior assessment module, the behavior assessment module is used to obtain the user answer behavior log recorded during the user assessment, and calculate the redo rate corresponding to the user assessment based on the user answer behavior log; a judgment module, the judgment module is used to judge whether the fluctuation factor can be constructed based on the user answer behavior log, the score standard deviation and the redo rate; a calculation module, the calculation module is used to, when the fluctuation factor can be constructed, calculate the redo rate based on the user answer behavior log. The standardized score data calculates the volatility factor, and generates a normalized vector based on the standardized score data and the volatility factor; a construction module, the construction module is used to construct a volatility derivative based on a behavioral volatility sequence generation mechanism of a sliding window; the judgment module is also used to judge whether the volatility derivative meets the dynamic adjustment conditions; a dynamic weighting module, the dynamic weighting module is used to perform dynamic weighted fusion based on the volatility derivative and the normalized vector when the volatility derivative meets the dynamic adjustment conditions to obtain a final risk score; the static weighting module is used to perform static weighted fusion based on the normalized vector when the volatility derivative does not meet the dynamic adjustment conditions to obtain a final risk score.

[0014] In some embodiments, the standardized score data is generated by the following formula: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

[0015] The beneficial effect of the present invention is that: when conducting an ability assessment on a user, the user's answer behavior log is collected to evaluate the user's behavior. While effectively assessing the user, the user's behavior volatility can be effectively assessed, thereby improving the accuracy and reference value of the assessment results.

[0016] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a method for evaluating user capabilities according to an embodiment of the present invention; Figure 2 4 is a block diagram of a user capability assessment system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0019] The following describes a user capability assessment method according to an embodiment of the present invention with reference to the accompanying drawings.

[0020] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for evaluating user capabilities according to an embodiment of the present invention. Figure 1 As shown, the user capability assessment method includes the following steps: S101, obtaining original answer data corresponding to the user evaluation, calculating the corresponding score standard deviation based on the original answer data, and generating standardized score data based on the score standard deviation.

[0021] In some embodiments, the normalized score data is generated by the following formula: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

[0022] As an example, first, the user answer record (i.e., original answer data) of the user evaluation is imported from the database of the evaluation platform; preferably, each user answer record may include: user number u, question identifier q, original score , assessment session number, answer timestamp , the maximum score set for the question , the dimension label to which the question belongs Next, field integrity and boundary value checks are performed on each user answer record to ensure that all numeric fields are valid non-negative real numbers, all time fields conform to the complete time format, and all identification fields are present and unique. Any user answer record that does not meet the requirements will be automatically removed and will not be included in subsequent processing.

[0023] After completing the structured data, each raw score in the original answer data is standardized to eliminate the proportional differences introduced by different question score settings. The standardization process uses Z-score changes, and the calculation formula is as follows: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

[0024] It can be understood that, through the above formula, each raw score can be mapped to a standard control centered at zero and with a standard deviation of one, so as to be used for the subsequent construction of mean and variance indicators.

[0025] S102: Obtain a user answer behavior log recorded during the user evaluation, and calculate a redo rate corresponding to the user evaluation based on the user answer behavior log.

[0026] In some embodiments, the retry rate is calculated by the following formula: in, Represents the redo rate, Indicates the total number of redo events for all questions during the user evaluation process. Indicates the number of valid questions.

[0027] As an example, first, read the user answer behavior log from the behavior tracking system. Preferably, each user answer behavior log records all interactive events during the user's answer process, including page loading, answer start, submission action, redo action, etc. Each log record contains event type , event trigger timestamp , user number u, evaluation session number s, event-related topic identifier q. Then, the log sequence of the same user in a single session is arranged in ascending order of time to construct its behavior trajectory Then, the trajectory is analyzed for time difference to calculate the interval time between consecutive events. If a certain time interval is less than the minimum event valid threshold , the system determines it as repeated triggering and merges it; if it is greater than or equal to the maximum allowed stay time , it is split into independent sessions to prevent behavioral drift from interfering with the evaluation structure.

[0028] Next, to support explicit modeling of behavioral volatility, we first generate a volatility label field and a behavioral stability signal variable. The system then counts the number of behavioral events triggered by a single user on the same question, extracts the "repeated answer" count, and uses this to calculate the user session's behavioral redo rate indicator: in, Represents the redo rate, Indicates the total number of redo events for all questions during the user evaluation process. Indicates the number of valid questions.

[0029] As an example, a threshold determination mechanism can be introduced: if the session meets the following two conditions: (i.e. the global standard deviation exceeds the stability threshold); (i.e., the redo rate exceeds the abnormal behavior threshold), the session is labeled as unstable behavior, and the label field is set to .

[0030] Finally, the system normalizes the score sequence of each user in each session , mean session score , standard deviation , redo rate , Volatility Label , session identifier and timestamp index are uniformly encapsulated and written into the structured data table , serving as the only standard input source for the subsequent risk index modeling process.

[0031] S103: Determine whether the volatility factor can be constructed based on the user's answer behavior log, score standard deviation, and redo rate.

[0032] In some embodiments, whether the fluctuation factor is constructible is determined based on the user's answer behavior log, score standard deviation and redo rate, including: determining whether the behavior log is missing; if so, determining that the fluctuation factor is not constructible; if not, determining whether the score standard deviation is greater than or equal to the lower limit value; if the score standard deviation is less than the lower limit value, determining that the fluctuation factor is not constructible; if the score standard deviation is greater than or equal to the lower limit value, determining whether the redo rate is greater than the redo rate threshold; if the redo rate is greater than the redo rate threshold, determining that the fluctuation factor is not constructible; if the redo rate is less than or equal to the redo rate threshold, determining that the fluctuation factor is constructible.

[0033] In other words, to account for the possibility that user response logs may be missing or incomplete for some assessment tasks, the system incorporates a "behavior omission compensation mechanism" into the volatility tag generation process. Specifically, when a user's response log is missing or the number of events is insufficient to form a valid trajectory, the volatility index is no longer forcibly constructed. Furthermore, if a user's response standard deviation is at an extreme relative to the overall user distribution, the system determines that their volatility factor cannot be constructed.

[0034] S104: If yes, calculate the fluctuation factor based on the standardized score data, and generate a normalized vector according to the standardized score data and the fluctuation factor.

[0035] That is, in order to eliminate the scale deviation between users, the standardized score data and the fluctuation factor are normalized to obtain the corresponding normalized vector.

[0036] As an example, the mean index and fluctuation factor of the standardized score of each user in a single assessment session are calculated, and the two factors are uniformly normalized. Specifically, first, the score sequence of all questions completed by each user in a complete assessment session is calculated. Aggregate and calculate its standardized capability mean index The formula is defined as follows: in, represents the standardized capability mean index, represents the standardized score, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. This mean indicator is used to measure the user's overall ability performance under a unified standard and is one of the dominant factors in measuring performance in the risk index structure.

[0037] Next, the standard deviation of the answer score sequence of the same user in the session is calculated to obtain its behavior stability index (i.e., volatility factor). The formula is as follows: In this formula The variance of the standardized score sequence represents the degree of user behavior fluctuation in the current assessment. It is calculated by taking the average of the squared deviations between the standardized score of each question and the standardized mean of all questions. and The meaning of is as described above. This indicator is one of the core structural variables in the risk scoring logic of the present invention. The larger its value, the greater the fluctuations in the user's answering process, the worse the stability of the behavior performance, and the higher the risk value should be.

[0038] Then, to achieve comparability of risk input indicators between different users, the system normalizes the above two indicators. Normalization uses the maximum and minimum values ​​of all samples as reference intervals and uniformly maps the values ​​to the [0,1] interval. The normalization formula is as follows: in, represents the normalized result of the standardized score, represents the normalized result of the volatility factor; Represents the average ability set of all users in the evaluation system under the evaluation task, represents the set of volatility indicators for all users; and These represent the minimum and maximum values ​​in the set, respectively, and are used to construct the upper and lower bounds of the linear normalization mapping. This normalization mechanism ensures that the model maintains a uniform numerical scale when processing user data from different distributions, preventing bias in risk calculations caused by external factors such as test batches and question difficulty.

[0039] Finally, the system combines the two normalized indicators to construct the input vector: The vector It is the main input variable of the risk index model. Its first dimension represents the ability performance and the second dimension represents the degree of stability. This structured tensor is stored in the risk sample table , providing input for subsequent collaborative risk modeling steps.

[0040] In some embodiments, if the volatility factor is not constructible, the standardized score data is directly normalized to obtain a corresponding normalized result, and calculation is performed based on the normalized result to obtain the final risk score.

[0041] That is to say, if the volatility factor cannot be constructed, then we will completely fall back to the capacity factor path.

[0042] As an example, in order to ensure that the risk index model always has stable output capabilities under various input scenarios, the system first normalizes the input vector before executing the index construction. If the system detects that the user has structurally missing behavior indicators in the current evaluation session, specifically: the number of behavior log events is less than the behavior judgment threshold set by the system , or its score standard deviation Less than the lower limit of stability judgment , the system will determine the current user's behavioral volatility index No model applicability.

[0043] Specifically, the capability factor is constructed by the following formula: in, represents the final risk score when the volatility factor cannot be constructed, This represents the normalized result of the standardized score, which is scored separately using the capability factor. This mechanism ensures that the model does not break or trigger abnormal computing behavior when input conditions are incomplete, forming the fault-tolerant control loop in the exponential modeling chain of this invention.

[0044] S105, constructing the fluctuation derivative based on the behavior fluctuation sequence generation mechanism of the sliding window.

[0045] As an example, in order to ensure that the wave derivative structure has computability, stability and structural expression ability, the system adopts a sliding window behavior wave sequence generation mechanism to construct the wave derivative. Specifically, first, extract the user's continuous answer record sequence in the current session , combined with the timestamp of each question , build a window size of Sliding window set The system calculates the standard deviation over each window. , we get the trajectory of behavioral volatility over time series distribution .

[0046] Then, based on this sequence, the system calculates the overall trend of volatility, dividing the difference between the first and last standard deviations by the total time span of the user's answer to form a first-order derivative approximation (volatility derivative): This fluctuation derivative captures the evolving trend of behavioral stability. A positive value indicates increasing volatility in user behavior, while a negative value indicates stabilization. The system only activates dynamic adjustment mechanisms when the derivative is positive. If the derivative is negative or undefined (e.g., due to missing timestamps or too few response samples), the behavioral risk is deemed to be stable, and the system reverts to a static path (i.e., static weighted fusion).

[0047] It should be noted that when the system executes the fallback path, it will construct the source field for the risk score of the sample record and set the flag bit This mechanism is used by subsequent modules (including reporting systems, audit interfaces, or supervisory models) to track the actual path decision sources of the risk model. This mechanism ensures that the model does not break or trigger abnormal computational behavior when input conditions are incomplete, forming a fault-tolerant control loop within the exponential modeling chain.

[0048] S106, determining whether the fluctuation derivative meets the dynamic adjustment conditions.

[0049] S107: If yes, perform dynamic weighted fusion based on the fluctuation derivative and the normalized vector to obtain a final risk score.

[0050] S108: If not, perform static weighted fusion based on the normalized vector to obtain a final risk score.

[0051] In some embodiments, static weighted fusion is performed based on the normalized vector to obtain a final risk score, including: Perform linear fusion based on the normalized vector to obtain a linear fusion result, and perform nonlinear enhancement on the linear fusion result to obtain the final risk score; The normalized vector is expressed by the following formula: in, represents the normalized vector, represents the normalized result of the standardized score, represents the normalized result of the volatility factor; in, represents the linear fusion result, represents the weight parameter; in, represents the final risk score obtained by nonlinear enhancement, parameter Indicates the steepness of the nonlinear function, represents the median risk.

[0052] That is to say, when the volatility factor can be constructed and the volatility derivative cannot be constructed, static weighted fusion is performed based on the normalized vector to obtain the final risk score.

[0053] As an example, first, in order to regulate the influence of the two types of factors, the system introduces configurable weighting coefficients into the main structure of the risk index. , the linear fusion results of constructing the initial risk index are as follows: in, represents the linear fusion result, represents the weight parameter; represents the normalized result of the standardized score, Represents the normalized result of the fluctuation factor. In this expression, the inverse value of the capacity factor It is used to reflect the relationship of "the higher the ability, the lower the risk", and the volatility factor Directly represents its stability risk contribution. Parameters Control the relative weight of the two in the overall risk. When it approaches 0, the model focuses more on the ability factor; when When it approaches 1, behavioral volatility dominates the risk output. This weight parameter can be configured based on the sensitivity of different assessment tasks, and can be uniformly set or injected in real time through the backend policy system to support scenario adaptation.

[0054] Then, in order to enhance the model's ability to identify high-risk samples, a nonlinear risk response function is used to calculate the original risk index. Mapping to generate a risk index , which is calculated as follows: in, The final risk score obtained by nonlinear enhancement is still in the range of [0,1]. Indicates the steepness of the nonlinear function and controls the response strength of the model to samples near the threshold; is the median risk value. hour, When the original risk score exceeds After the output risk value increases, it will accelerate, thereby widening the distribution gap between high-risk samples and improving the model's recognition resolution in key risk segments. This Sigmoid gain function has the advantages of strong interpretability, stable gradients, and differentiability.

[0055] It should be noted that when the system executes the static scoring path, in order to enhance the clarity and interpretability of the scoring structure, it explicitly constructs a static fusion score variable. This variable retains the linear combination of the original capability factor and the volatility factor before the final score is generated. It is used for interpretation and analysis, parameter adjustment and visualization, model fusion and expansion, and path consistency design. Through this variable, the system can achieve unified modeling of static and dynamic path scoring structures, improving the stability and transparency of the overall model.

[0056] In some embodiments, dynamic weighted fusion is performed based on the following formula to obtain a final risk score: in, represents the wave derivative, Indicates the timestamp corresponding to the last valid question. Indicates the timestamp corresponding to the first valid question, that is, the starting time of the window in the behavior trajectory. represents the last window number in the standard deviation sequence, represents the dynamic weight, represents the risk response slope mapping coefficient, represents the dynamic risk index, represents the final risk score obtained by dynamic fusion, parameter Indicates the steepness of the nonlinear function, represents the median risk.

[0057] As an example, first, in order to enhance the dynamic expression ability of the risk model under the influence of behavioral fluctuations, the system first constructs a dynamic weight coefficient driven by the user behavior derivative (i.e., dynamic weight). It represents the intensity response of the user's behavior fluctuation trend in the evaluation session s. The specific construction is as follows: in, is the risk response slope mapping coefficient, It represents the fluctuation derivative, which is used to characterize the changing trend of user behavior volatility during the evaluation process and is the core indicator for building a dynamic weighting mechanism.

[0058] To ensure that the wave derivative structure has computability, stability and structural expression capabilities, the system adopts a behavior wave sequence generation mechanism based on a sliding window. The specific process is as follows: the system first extracts the user's continuous answer record sequence in the current session. , combined with the timestamp of each question , build a window size of Sliding window set The system calculates the standard deviation over each window. , we get the trajectory of behavioral volatility over time series distribution .

[0059] Based on this sequence, the system calculates the overall trend of volatility, dividing the difference between the first and last standard deviations by the total time span of the user's answer to form the volatility derivative: This fluctuation derivative captures the evolving trend of behavioral stability. A positive value indicates increasing volatility in user behavior, while a negative value indicates stabilization. The system only activates dynamic adjustment mechanisms when the derivative is positive. If the fluctuation derivative is negative or undefined (e.g., due to missing timestamps or too few response samples), the behavioral risk is considered to be stable, and the system will revert to a static path.

[0060] In order to avoid abnormal samples causing severe disturbances to the weights, the system sets a maximum derivative response threshold , when the calculated result of the wave derivative exceeds the upper limit, it is truncated to To ensure that the risk weight control mechanism is not activated by outlier behavior. The final generated dynamic weight Will be used to replace the static weights in step 3 , enter the dynamic fusion path.

[0061] Based on this dynamic weight, the system reconstructs the risk fusion structure as follows: In the above formula Represents a dynamic risk index that integrates the scoring contributions of both capability and volatility factors and adaptively adjusts their structural weights based on behavioral trends. This structure supports the risk index's sensitive response to behavioral fluctuations, enabling the model to identify and dynamically adjust to individual behavioral variations.

[0062] The system then feeds this dynamic fusion result into the risk enhancement function to generate the final risk score: in, is the risk slope control parameter, which is used to adjust the steepness of the function response; is the critical risk center point. , the output value will increase significantly, thereby enhancing the distinguishability between high-risk samples.

[0063] In some embodiments, the final risk score may be Design a piecewise level mapping function: The grade label This information is appended to the risk output record and serves as decision-making input for downstream recommendation, reporting, and matching strategy modules. The upper and lower thresholds and intervals can be set uniformly in the system deployment configuration, and can also be configured differently based on the assessment task type.

[0064] During the output result writing and storage phase, the system will record the following core fields to construct a structured output package (Risk Output Record): · : Final risk score value, normalized and enhanced; · : The pre-enhancement scoring result constructed in step 3 is used for subsequent interpretability display; · : The fusion weight value generated by the behavioral derivative represents the contribution ratio of the ability and volatility factors in the current session; · : Risk fusion path whether to use the static capability score fallback flag, 1 means the fallback path is enabled; · : Whether dynamic weight calculation is invalid and whether to use default static weight ; · : Risk level label, used to match recommended strategies with report presentation; · : The timestamp field of the score generation, used for system log recording and task chain tracing.

[0065] The system writes the structured output record into the cache database for the real-time recommendation module to pull and use, and simultaneously writes it into persistent storage (such as a relational database rating table or an object storage structure log) to support subsequent evaluation report generation, behavior trajectory visualization, model debugging, and user historical rating comparison.

[0066] When the risk index output module encounters one of the following abnormal situations during operation: The behavior derivative is not differentiable and the behavior sequence data is missing; Misconfiguration of nonlinear function parameters results in uncalculated scores; The level threshold interval configuration is missing or conflicting; The system will automatically call the fallback logic and set the risk score to: Also record the fallback path tag field , so as to quickly identify and locate the source of the problem in the log and anomaly detection module.

[0067] This step, as the final link in the risk index generation process of the present invention, not only ensures the normalization and interpretability of the scoring structure, but also realizes the complete encapsulation of task logic, scoring levels and structural fields, so that the system has high stability, accessibility and universal scoring expression capabilities for multi-module linkage.

[0068] In summary, according to the user ability assessment method of an embodiment of the present invention, the original answer data corresponding to the user assessment is obtained, and the corresponding score standard deviation is calculated based on the original answer data, and standardized score data is generated based on the score standard deviation; the user answer behavior log recorded during the user assessment is obtained, and the redo rate corresponding to the user assessment is calculated based on the user answer behavior log; whether the fluctuation factor can be constructed is judged according to the user answer behavior log, the score standard deviation and the redo rate; if so, the fluctuation factor is calculated based on the standardized score data, and a normalized vector is generated according to the standardized score data and the fluctuation factor; a fluctuation derivative is constructed based on the behavior fluctuation sequence generation mechanism of the sliding window; it is judged whether the fluctuation derivative meets the dynamic adjustment conditions; if so, dynamic weighted fusion is performed based on the fluctuation derivative and the normalized vector to obtain a final risk score; if not, static weighted fusion is performed based on the normalized vector to obtain a final risk score, thereby achieving effective assessment of user ability and effective evaluation of the user's volatility during the assessment process, thereby improving the accuracy of the assessment results.

[0069] In a second aspect, an embodiment of the present invention provides a computer-readable storage medium on which a user capability assessment program is stored. When the user capability assessment program is executed by a processor, the user capability assessment method described above is implemented.

[0070] In a third aspect, the embodiment of the present invention proposes a user capability assessment system, such as Figure 2 As shown, the user ability assessment system includes: a preprocessing module 10, a behavior assessment module 20, a judgment module 30, a calculation module 40, a construction module 50, a dynamic weighting module 60 and a static weighting module 70.

[0071] The pre-processing module 10 is used to obtain the original answer data corresponding to the user evaluation, calculate the corresponding score standard deviation based on the original answer data, and generate standardized score data based on the score standard deviation; The behavior evaluation module 20 is used to obtain the user's answer behavior log recorded during the user evaluation, and calculate the redo rate corresponding to the user evaluation based on the user's answer behavior log; The judgment module 30 is used to judge whether the fluctuation factor can be constructed based on the user's answer behavior log, score standard deviation and redo rate; The calculation module 40 is used to calculate the fluctuation factor based on the normalized score data when the fluctuation factor is constructible, and to generate a normalized vector based on the normalized score data and the fluctuation factor; The construction module 50 is used to construct the fluctuation derivative based on the behavior fluctuation sequence generation mechanism of the sliding window; The judgment module 30 is further used to judge whether the fluctuation derivative meets the dynamic adjustment conditions; The dynamic weighting module 60 is used to perform dynamic weighted fusion based on the fluctuation derivative and the normalized vector when the fluctuation derivative meets the dynamic adjustment conditions to obtain the final risk score; The static weighting module 70 is used to perform static weighted fusion based on the normalized vector when the fluctuation derivative does not meet the dynamic adjustment conditions to obtain a final risk score.

[0072] In some embodiments, the normalized score data is generated by the following formula: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

[0073] It should be noted that the above description of the user capability assessment method is also applicable to the user capability assessment system and will not be elaborated here.

[0074] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0075] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0076] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0077] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0078] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0079] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0080] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0081] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A user capability assessment method, characterized in that: The following steps are involved: Obtaining original answer data corresponding to the user evaluation, calculating the corresponding score standard deviation based on the original answer data, and generating standardized score data based on the score standard deviation; Obtaining a user's answer behavior log recorded during the user evaluation, and calculating a redo rate corresponding to the user evaluation based on the user's answer behavior log; Determining whether a fluctuation factor can be constructed based on the user's answer behavior log, the score standard deviation, and the redo rate; If yes, calculating the fluctuation factor based on the normalized score data, and generating a normalized vector according to the normalized score data and the fluctuation factor; Constructing the volatility derivative based on the behavior volatility sequence generation mechanism of sliding window; Determining whether the fluctuation derivative meets the dynamic adjustment conditions; If yes, performing dynamic weighted fusion based on the fluctuation derivative and the normalized vector to obtain a final risk score; If not, static weighted fusion is performed based on the normalized vector to obtain a final risk score.

2. The user capability assessment method according to claim 1, wherein: The standardized score data is generated by the following formula: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

3. The user capability assessment method according to claim 1, wherein: The rework rate is calculated by the following formula: in, Represents the redo rate, Indicates the total number of redo events for all questions during the user evaluation process. Indicates the number of valid questions.

4. The user capability assessment method according to claim 1, wherein: Determining whether a fluctuation factor is constructible based on the user answer behavior log, the score standard deviation, and the redo rate includes: Determining whether the behavior log is missing; If yes, determining that the volatility factor is not constructible; If not, determining whether the score standard deviation is greater than or equal to a lower limit; If the score standard deviation is less than a lower limit, it is determined that the volatility factor cannot be constructed; If the score standard deviation is greater than or equal to the lower limit, determining whether the redo rate is greater than a redo rate threshold; If the redo rate is greater than the redo rate threshold, determining that the fluctuation factor is not constructible; If the retry rate is less than or equal to the retry rate threshold, it is determined that the fluctuation factor is constructible.

5. The user capability assessment method according to claim 1, wherein: If the volatility factor is not constructible, the standardized score data is directly normalized to obtain a corresponding normalized result, and calculation is performed based on the normalized result to obtain a final risk score.

6. The user capability assessment method according to claim 1, wherein: Static weighted fusion is performed based on the normalized vector to obtain a final risk score, including: Performing linear fusion based on the normalized vector to obtain a linear fusion result, and performing nonlinear enhancement on the linear fusion result to obtain a final risk score; The normalized vector is expressed by the following formula: in, represents the normalized vector, represents the normalized result of the standardized score, represents the normalized result of the volatility factor; in, represents the linear fusion result, represents the weight parameter; in, represents the final risk score obtained by nonlinear enhancement, parameter Indicates the steepness of the nonlinear function, represents the median risk.

7. The user capability assessment method according to claim 1, wherein: Dynamic weighted fusion is performed based on the following formula to obtain the final risk score: in, represents the wave derivative, Indicates the timestamp corresponding to the last valid question. Indicates the timestamp corresponding to the first valid question. represents the last window number in the standard deviation sequence, represents the dynamic weight, represents the risk response slope mapping coefficient, represents the dynamic risk index, represents the final risk score obtained by dynamic fusion, parameter Indicates the steepness of the nonlinear function, represents the median risk.

8. A computer-readable storage medium, characterized in that A user capability assessment program is stored thereon, and when the user capability assessment program is executed by a processor, the user capability assessment method as described in any one of claims 1 to 7 is implemented.

9. A user capability assessment system, characterized in that: include: A preprocessing module, the preprocessing module is used to obtain original answer data corresponding to the user evaluation, calculate the corresponding score standard deviation based on the original answer data, and generate standardized score data based on the score standard deviation; A behavior evaluation module, which is used to obtain a user's answer behavior log recorded during the user evaluation and calculate a redo rate corresponding to the user evaluation based on the user's answer behavior log; a judgment module, configured to judge whether a fluctuation factor can be constructed based on the user's answer behavior log, the score standard deviation, and the redo rate; a calculation module, configured to calculate the fluctuation factor based on the standardized score data when the fluctuation factor is constructible, and generate a normalized vector according to the standardized score data and the fluctuation factor; A construction module, wherein the construction module is used to construct a fluctuation derivative based on a behavior fluctuation sequence generation mechanism of a sliding window; The judgment module is further used to judge whether the fluctuation derivative meets the dynamic adjustment conditions; a dynamic weighting module, configured to perform dynamic weighted fusion based on the fluctuation derivative and the normalized vector when the fluctuation derivative meets the dynamic adjustment condition, so as to obtain a final risk score; A static weighting module is used to perform static weighted fusion based on the normalized vector when the fluctuation derivative does not meet the dynamic adjustment conditions to obtain a final risk score.

10. The user capability assessment system according to claim 9, wherein: The standardized score data is generated by the following formula: in, Indicates the number of valid questions. Represents the set of questions completed during the user evaluation process. represents the standardized score, represents the original score, represents the mean of the original scores, Indicates the standard deviation of scores.

Images