Dynamic psychological assessment question selection method and system based on factor integrity principle

Abstract

The invention relates to the technical field of psychological assessment, and particularly discloses a dynamic psychological assessment question selection method and system based on a factor integrity principle, and the method comprises the steps: creating a session, collecting the psychological attention field of a user, mapping the psychological attention field of the user into a corresponding psychological factor, carrying out the duplicate removal, and generating a target psychological factor set; all questions corresponding to each psychological factor are retrieved and loaded from the database, preset answering time and actual answering time are obtained according to the number of the questions and preset average answering time of each question, psychological credibility indexes of the user are analyzed, answers to each question of the user and question fields are obtained, and an answering data set is generated; whether the user completes all target questions or not is verified through the score integrity verification module, score calculation is performed after integrity verification is passed, and the priority of the psychological attention field of the user is determined in combination with the psychological credibility index, so that the reliability of the evaluation data is ensured, and the user experience and the practical value of the evaluation result are also improved.

Description

Technical Field

[0001] This invention relates to the field of psychological assessment technology, and more specifically, to a method and system for selecting dynamic psychological assessment items based on the principle of factor integrity. Background Technology

[0002] Traditional psychological assessments, such as the SCL-90 and MMPI, use a fixed scale model. Users are required to answer all questions on the scale, regardless of their focus or actual needs. This results in a large number of redundant questions, which seriously reduces assessment efficiency and user experience. For example, with a scale containing 90 questions, a user may only need to focus on 20 questions, but still has to complete all of them, which is time-consuming and can easily lead to fatigue.

[0003] While Computer Adaptive Testing (CAT) can dynamically select items based on users' real-time performance, thus reducing the number of items, CAT's item selection strategy is primarily based on item difficulty and discrimination, with its core objective being to efficiently estimate users' latent trait levels. This approach, while pursuing efficiency, often fails to guarantee the completeness of factors in psychometrics. According to fundamental principles of psychometrics, a psychological factor's score must be based on the complete item set of the original scale to ensure its construct validity and reliability. Existing dynamic testing models may only select a subset of items, resulting in compromised psychometric construct integrity of the final score and significantly reducing the scientific rigor and professionalism of the assessment. Current systems lack effective mechanisms to accurately identify users' core concerns before the assessment begins; even simple screening often remains at the scale level. Furthermore, the item selection logic of dynamic tests like CAT is opaque to users, making it difficult for them to predict the number of items and completion time, leading to a poor user experience.

[0004] Therefore, it is necessary to provide a dynamic psychological assessment item selection method based on the principle of factor integrity and a system to solve the above-mentioned technical problems. In order to solve the above problems, a technical solution is provided. Summary of the Invention

[0005] To overcome the aforementioned shortcomings of existing technologies, this invention provides a dynamic psychological assessment item selection method and system based on the principle of factor integrity. This method addresses the problems of existing psychological assessment methods, such as redundancy and inefficiency in item selection, lack of specificity, and the fact that while they possess adaptive capabilities, they compromise factor integrity and measurement scientific rigor, making it difficult to balance assessment efficiency, result reliability, and user experience.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The method for selecting items in dynamic psychological assessments based on the principle of factor integrity includes the following steps: Users initiate the assessment on the client, create a session, and collect data on their areas of psychological concern. The data is then mapped to corresponding psychological factors and deduplicated to generate a set of target psychological factors. Based on the target set of psychological factors, retrieve and load all questions corresponding to each psychological factor from the MySQL database, extract question fields and merge them to generate a list of question fields; By statistically analyzing the number of questions in the question field list and the preset average answering time per question, the preset answering time and the actual answering time are obtained, the user's psychological credibility index is analyzed, and feedback is given to the user in real time. The system obtains users' answers to each question and generates a response dataset based on the question fields. It then verifies whether users have completed all target questions through a scoring integrity verification module. After the integrity verification is passed, the system calculates the score and determines the priority of users' psychological concern areas by combining psychological credibility indicators.

[0007] As a further aspect of the present invention, the user initiates the assessment on the client, creates a session, and collects data on the user's areas of psychological concern. The specific steps are as follows: When a user takes an assessment on the client side, the client sends an API request to the assessment service module on the server side to create an assessment session. After receiving the request, the server creates a new pending session record in the evaluation session table and generates a unique session field to return to the client. The client requests the initial question configuration from the server, and the server returns JSON data containing eight psychological concern areas options; Users can choose their psychological focus area on the client interface, and the client submits the user's selection to the assessment service module on the server via API.

[0008] As a further aspect of the present invention, based on the target psychological factor set, all questions corresponding to each psychological factor are retrieved and loaded from the MySQL database, question fields are extracted and merged to generate a question field list. The specific steps are as follows: Based on the target set of psychological factors, the question selection module is triggered. For each psychological factor in the target set of psychological factors, the question selection module performs a query on the question table in the MySQL database. By merging all the query question fields, a complete list of question fields is formed and stored in the question selection field of the corresponding session in the assessment session table.

[0009] As a further aspect of the present invention, by statistically analyzing the number of questions in the question field list and the preset average answering time per question, the preset answering time and the actual answering time are obtained. The user's psychological credibility index is then analyzed and fed back to the user in real time. The specific steps are as follows: The server counts the total number of questions in the question field list, calculates the preset answer time based on the preset average answer time per question, and returns the calculated total number of questions and the preset answer time to the client via API response. A user psychological analysis model is constructed based on the preset response time and the actual response time to obtain the uncertain factors in the user's psychological attention areas. The psychological credibility index is obtained by summarizing the uncertain factors in all the user's psychological attention areas.

[0010] As a further aspect of the present invention, a response dataset is generated by obtaining the user's answers to each question and the question fields. The scoring integrity verification module then verifies whether the user has completed all questions. The specific steps are as follows: After the user confirms that they have started answering the questions, the client requests the question data from the server based on the session fields. Users answer questions one by one on the client interface. After completing each question, the client submits the question field and answer to the server via API. The server stores the received answers in an answer table and associates them with the current session field. After the user completes all the questions and clicks "Submit", the client sends a request to the server to complete the assessment. The assessment service module triggers the scoring integrity verification module, which retrieves the previously stored question selection field from the assessment meeting table based on the session field. From the answer table, retrieve a list of all questions that the user actually answered, based on the conversation field. By comparing the evaluation meeting form and the answer sheet, it is verified whether the user has answered all the questions for each target factor. If all questions have been answered, the integrity verification is passed; if not all questions have been answered, the integrity verification is failed.

[0011] As a further aspect of the present invention, a score calculation is performed after the integrity verification is passed, and the specific steps are as follows: When a user passes the integrity verification, the server-side scoring calculation module is triggered. According to the preset scoring rules in the selection mapping table, all answers for each factor are scored, the first-level answer score corresponding to each psychological concern area is calculated, the average answer score is obtained after summarizing, and the average answer score is stored in the answer table and the score mapping table. If the integrity verification fails, the server will refuse to score and return an error message to the client, indicating that the user's answer is incomplete and a scientific report cannot be generated.

[0012] As a further aspect of the present invention, the priority of users' psychological concern areas is determined by combining psychological credibility indicators, and the specific steps are as follows: Obtain psychological credibility sub-indicators for each area of ​​user psychological interest, among which... For the b-th psychological concern area, the psychological credibility sub-index is used. Based on the psychological credibility sub-indicator and the first-level answer score for each psychological concern area, the psychological factor attention level corresponding to each psychological concern area is obtained, and the priority of the user's psychological concern area is determined according to the psychological factor attention level.

[0013] As a further aspect of the present invention, the priority of users' psychological attention areas is determined based on the degree of attention to psychological factors, and the specific steps are as follows: Obtain the attention level of psychological factors corresponding to each area of ​​psychological concern, and arrange them in descending order of value to form an attention level sequence. , For the psychological factors of the b-th psychological concern area, Given the total number of psychological attention areas, the attention levels of psychological factors are compared with the preset attention ranges in order. If the attention given to psychological factors exceeds the upper limit of the preset attention range, the psychological attention area is at the first-level psychological attention target; if the attention given to psychological factors is within the preset attention range, the psychological attention area is at the second-level psychological attention target; if the attention given to psychological factors is below the lower limit of the preset attention range, the psychological attention area is at the third-level psychological attention target.

[0014] A dynamic psychological assessment item selection system based on the factor integrity principle, including a client, an application server, and a data storage layer; The client is used to provide the front-end interface for user interaction, including WeChat mini programs, web applications or mobile apps. It is responsible for presenting initial question options to users, collecting user choices, displaying assessment questions, and sending user answer data to the server. The application server adopts a modular architecture and is responsible for handling client requests, including factor mapping, question selection, dynamic calculation, data storage, and scoring verification. The data storage layer is responsible for persistently storing the data required by the system, including a MySQL (relational) database and a cache database; the MySQL database is used to store core business data; and the cache database is used to cache frequently accessed data.

[0015] The technical effects and advantages of this invention's dynamic psychological assessment question selection method and system based on the factor integrity principle are as follows: This invention creates a session and collects the user's psychological focus areas. It maps these areas to corresponding psychological factors and removes duplicates, generating a target psychological factor set. This accurately identifies the psychological dimensions the user needs to assess, avoids question redundancy, and improves assessment efficiency. Retrieving and loading all questions corresponding to each psychological factor from the database standardizes the assessment process, ensuring consistency and comparability across different users. By using the number of questions and a preset average answer time per question, the invention obtains the preset answer time and actual answer time, analyzes the user's psychological credibility index, and generates a response dataset based on the user's answers and question fields. This dataset not only reflects the stability and focus of the user's responses but also provides real-time feedback during the assessment process, helping users self-monitor and maintain focus, thus improving the quality of their responses. The scoring integrity verification module verifies whether users have completed all target questions, ensuring that the calculation of each psychological factor score is based on the complete item set of the original scale for that factor. This guarantees the psychometric scientific rigor and professionalism of the assessment results, mitigating the risk of compromised scoring structure integrity that may exist in existing dynamic assessments, and maximizing the accuracy and reliability of the scores. Scoring is calculated after integrity verification is passed, and the priority of users' psychological focus areas is determined in conjunction with psychological reliability indicators, ensuring the reliability of the assessment data. The questions answered by users are all core questions in their focus areas, improving user engagement and satisfaction. Attached Figure Description

[0016] Figure 1 A flowchart illustrating a dynamic psychological assessment item selection method based on the factor integrity principle provided in this embodiment of the invention; Figure 2 The system block diagram of the dynamic psychological assessment item selection system based on the factor integrity principle provided in the embodiments of the present invention. Detailed Implementation

[0017] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described technical solutions are only a part of this invention, and not all of it. All other technical solutions obtained by those skilled in the art based on the technical solutions of this invention without inventive effort are within the scope of protection of this invention.

[0018] like Figure 1 The diagram shown is a flowchart of a dynamic psychological assessment item selection method based on the factor integrity principle provided in an embodiment of the present invention. Figure 1The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S4 are detailed as follows: Step S1: The user starts the assessment on the client, creates a session and collects the user's psychological focus areas, maps the user's psychological focus areas to corresponding psychological factors and removes duplicates, and generates a target psychological factor set; In this embodiment of the invention, when a user initiates an assessment on the client side of the psychological testing system, the system automatically creates a unique session to record the user's entire response process. At the beginning of the assessment, the user selects or the system collects their areas of psychological concern; for example, the user may be particularly interested in "stress management" and "emotion regulation." The system then maps these areas of concern to corresponding psychological factors. For example, "stress management" may correspond to psychological factors such as "anxiety level" and "stress response," while "emotion regulation" may correspond to psychological factors such as "emotional control ability" and "emotional fluctuation." To avoid repeatedly assessing the same psychological dimensions, the system deduplicates the mapped psychological factors, ultimately generating a set of target psychological factors for the user. This set is used for subsequent question selection and assessment design, ensuring that the assessment questions comprehensively cover the user's areas of concern while avoiding redundancy, thus improving assessment efficiency and relevance. For example, anxiety and stress factors that the user is concerned about will only appear once after the target set is generated; the system will automatically select relevant questions based on this set, ensuring accurate and efficient assessment content.

[0019] Step S2: Based on the target psychological factor set, retrieve and load all questions corresponding to each psychological factor from the MySQL database, extract question fields and merge them to generate a question field list; In this embodiment of the invention, once the system has generated a set of target psychological factors for the user, such as "anxiety level," "stress response," and "emotional control ability," the system automatically sends a query request to the MySQL database to retrieve all assessment questions corresponding to each psychological factor. Each psychological factor in the database is associated with several questions, which are scientifically designed to comprehensively assess the relevant psychological characteristics of that factor. The retrieved question information is extracted to extract question fields, such as question ID, question stem, and options. All question fields corresponding to the target psychological factors are merged to generate a complete list of question fields, forming a question set covering all the psychological factors the user is concerned with. This provides the user with a complete and structured question list for assessment. In practice, this automated retrieval and integration method not only improves assessment efficiency but also ensures that each psychological factor is fully evaluated, avoiding omissions or duplicate questions, and laying a data foundation for subsequent answering, scoring, and psychological analysis.

[0020] Step S3: By statistically analyzing the number of questions in the question field list and the preset average answering time per question, obtain the preset answering time and the actual answering time, analyze the user's psychological credibility index, and provide real-time feedback to the user. In this embodiment of the invention, after the system has generated a complete list of question fields for the user, the system first counts the total number of questions in the list and, combined with the preset average answering time for each question, calculates the preset total answering time for the entire assessment. For example, if there are 40 questions in total and the preset average answering time for each question is 1.5 minutes, then the preset answering time for the entire assessment is 60 minutes. As the user answers each question on the client, the system records the actual answering time for each question in real time and accumulates the user's actual total completion time. By comparing the actual answering time with the preset answering time, and considering the stability and consistency during the answering process, the system can calculate the user's psychological credibility index. This index reflects the user's level of seriousness in answering and the reliability of the data. To improve the user experience, the system can provide real-time feedback on the psychological credibility analysis results to the user, such as displaying prompts like "Current answering stability is good" or "Answering time for some questions is too short; it is recommended to answer carefully," guiding the user to maintain focus and improve the quality of their answers, thereby ensuring the scientific validity of subsequent scoring and psychological analysis.

[0021] Step S4: Obtain the user's answers to each question and generate an answer dataset from the question fields. Verify whether the user has completed all target questions through the scoring integrity verification module. After the integrity verification is passed, calculate the score and determine the priority of the user's psychological concern areas by combining the psychological credibility index.

[0022] In this embodiment of the invention, after a user completes answering each question, the system collects the question fields and corresponding answers for each question and generates a complete answer dataset. This dataset records the user's specific answers for each psychological factor. Subsequently, the system checks the dataset through a scoring integrity verification module to verify whether the user has completed all questions for the target psychological factor. For example, if the user misses some questions under the "stress management" factor, the module will detect the omissions and indicate that the integrity verification has failed. Only when the user has completed all questions and the integrity verification passes will the system trigger the scoring calculation module to score the answers for each psychological factor. The scoring results are then weighted and combined with previously collected psychological credibility indicators to reflect the reliability of the user's answers. Finally, based on psychological credibility and answer scores, the system generates a priority ranking for each psychological concern area. For example, "stress management" is classified as a first-level concern, "emotion regulation" as a second-level concern, and "attention concentration" as a third-level concern, thus providing a scientific basis for psychological counseling, personalized intervention, or report generation. This process ensures the completeness and reliability of the assessment data, and, combined with answer stability, provides users with accurate psychological concern analysis.

[0023] Preferably, the user initiates the assessment on the client, creates a session, and collects data on the user's areas of psychological concern. The specific steps are as follows: When a user takes an assessment on the client side, the client sends an API request to the assessment service module on the server side to create an assessment session. After receiving the request, the server creates a new pending session record in the evaluation session table and generates a unique session field to return to the client. The client requests the initial question configuration from the server, and the server returns JSON data containing eight psychological concern areas options; Users can choose their psychological focus area on the client interface, and the client submits the user's selection to the assessment service module on the server via API.

[0024] In this embodiment, the user initiates the psychological assessment process through a mobile application or web client, and the system automatically enters the session creation and psychological attention domain collection stage. First, after the user clicks the "Start Assessment" button on the client, the client sends an API request to the assessment service module on the server via the HTTPS protocol to create an assessment session. The request message contains basic data such as the user account identifier, device information, and the current timestamp.

[0025] Upon receiving the request, the server-side assessment service module automatically creates a new pending session record in the "Assessment Session Table" in the background. The system generates a unique session field for this session, which serves as the primary key identifier for all subsequent assessment data interactions, and returns the session field to the client via API response. At this point, the client caches this session identifier locally for association with subsequent user response data and time records.

[0026] After successfully creating a session, the client immediately requests initial question configuration data from the server. The assessment service module, based on the preset assessment initialization logic, reads a JSON data packet containing eight psychological concern areas from the configuration database and returns it to the client. This JSON data includes the number and name of each psychological concern area, such as "emotion regulation," "anxiety state," and "depressive tendency," as well as descriptive information and visualization parameters.

[0027] After receiving the JSON data, the client dynamically loads eight areas of psychological concern into the user interface as buttons or cards. Users can choose one or more areas of interest based on their own situation or current psychological state. For example, a user who has recently been experiencing low mood and poor sleep might select "Depressive Tendencies," "Anxiety," and "Sleep Quality" as areas of concern in the interface.

[0028] After the user completes their selection, the client submits the list of selected psychological concern areas to the server-side assessment service module via a POST request. The submitted data includes the user identifier, session fields, and an array of selected area fields. Upon receiving the data, the server writes the user's selections into the "Psychological Concern Areas Table" and associates it with the current session record for subsequent steps to perform psychological factor mapping and item retrieval operations.

[0029] Through the above interactive process, a complete workflow is achieved from user-initiated assessment to server-side session establishment and psychological focus area data collection. This ensures a smooth user experience and provides basic data support for subsequent personalized question generation and psychological factor analysis.

[0030] Preferably, the target psychological factor set is generated by mapping the user's psychological focus area to corresponding psychological factors and removing duplicates. The specific steps are as follows: After receiving the user's selection, the assessment service module calls the factor mapping module in the algorithm service module to map the user's selected psychological concern area into psychological factors according to the selection mapping table preset in memory. By deduplicating the psychological factors, the final set of target psychological factors is obtained and updated to the graph matching field of the corresponding session record in the assessment session table.

[0031] In this embodiment of the invention, after the server-side assessment service module receives the user's selected psychological focus areas submitted by the client, it enters the psychological factor mapping stage. The assessment service module first calls the "factor mapping module" in the algorithm service module to perform the correspondence conversion between focus areas and psychological factors. A "selection mapping table" is pre-loaded in the server-side memory. This mapping table is defined by psychometric experts according to the standard scale structure and theoretical model, and is used to identify the correspondence between each psychological focus area and its corresponding one or more psychological factors.

[0032] If a user selects "anxiety state," "depressive tendency," and "sleep quality" as their psychological concern areas on the client side, the algorithm service module will retrieve the selection mapping table for each area when invoking the mapping logic: The psychological factors corresponding to "anxiety state" include generalized anxiety factor. With stress response factors ; The psychological factors corresponding to "depressive tendencies" include depressive mood factors. With self-evaluation factors ; The psychological factors corresponding to "sleep quality" include somatization factors. With fatigue factors .

[0033] Because overlapping psychological factors may occur in the mapping relationship—for example, "stress response factor" belongs to both anxiety state and sleep quality—the system automatically performs deduplication on the resulting set of psychological factors after the initial mapping. The algorithm service module iterates through the mapping results, removes duplicates, and reconstructs the set, ultimately generating a target set containing all independent psychological factors. Based on the above example, the final target set of psychological factors is: ; After generating the target psychological factor set, the assessment service module writes the results of this set into the corresponding session record in the "Assessment Session Table" of the database. The unique code storing the target psychological factor set is updated in the "Graph Theory Matching Field" of this record, used for subsequent question retrieval and question graph matching processes. This field can be used for fast retrieval during subsequent question loading and also provides a data association index for the backend analysis module.

[0034] Through the above steps, intelligent mapping and deduplication integration from the user's psychological focus areas to specific psychological factors are achieved, ensuring that the subsequent generation of assessment questions maintains the structural integrity of the psychological factor level while taking into account the individualized focus needs of users, thus laying a data foundation for accurate dynamic assessment.

[0035] Preferably, based on the target psychological factor set, all questions corresponding to each psychological factor are retrieved and loaded from the MySQL database, question fields are extracted and merged to generate a question field list. The specific steps are as follows: Based on the target set of psychological factors, the question selection module is triggered. For each psychological factor in the target set of psychological factors, the question selection module performs a query on the question table in the MySQL database. By merging all the query question fields, a complete list of question fields is formed and stored in the question selection field of the corresponding session in the assessment session table.

[0036] In this embodiment of the invention, after the system completes the psychological factor mapping and deduplication operations, the assessment service module will initiate the question retrieval process based on the generated target psychological factor set. The server-side assessment service module first calls the "question selection module" in the algorithm service module to trigger the question retrieval task with the MySQL database. The question selection module performs a factor-by-factor query operation on the question table of the MySQL database according to each factor identifier in the target psychological factor set to obtain all question information related to that psychological factor.

[0037] The existing set of target psychological factors is as follows: Through multiple rounds of queries, the question selection module retrieves the complete question set corresponding to each psychological factor, including the following: The generalized anxiety factor corresponds to the item IDs {Q01, Q02, Q03, Q04}. The stress response factors correspond to question IDs {Q05, Q06, Q07}. The question IDs corresponding to the depressive mood factor are {Q08, Q09, Q10, Q11, Q12}. The self-evaluation factors correspond to the question IDs {Q13, Q14, Q15}. The somatization factor corresponds to the question IDs {Q16,Q17,Q18,Q19}.

[0038] After completing all queries, the question selection module deduplicates and sorts the retrieved question IDs to prevent the same question from appearing repeatedly due to belonging to multiple factors. After deduplication, all question IDs are merged to form a complete question ID list. For example, in the above case, the final merged question ID list is: {Q01, Q02, Q03, Q04, Q05, Q06, Q07, Q08, Q09, Q10, Q11, Q12, Q13, Q14, Q15, Q16, Q17, Q18, Q19}.

[0039] Subsequently, the question selection module stores the generated list of question IDs in the assessment session table of the MySQL database, corresponding one-to-one with the current session record. Specifically, this list is written to the "question selection field" in the session record, used for loading and sequential presentation of questions in the subsequent answering stage.

[0040] The above ensures that the complete set of questions for each psychological factor is loaded, guaranteeing the integrity of the factor structure in a psychometric sense. Unlike traditional fixed scales, this embodiment of the invention can dynamically generate the assessment question set based on the user's areas of interest, reducing the time wasted on irrelevant questions while preserving the measurement integrity of core factor dimensions, thus achieving a balance between personalization and scientific rigor.

[0041] Preferably, by statistically analyzing the number of questions in the question field list and the preset average answering time per question, the preset answering time and the actual answering time are obtained. The user's psychological credibility index is then analyzed and fed back to the user in real time. The specific steps are as follows: The server counts the total number of questions in the question field list, calculates the preset answer time based on the preset average answer time per question, and returns the calculated total number of questions and the preset answer time to the client via API response. A user psychological analysis model is constructed based on the preset response time and the actual response time to obtain uncertainties in the user's psychological focus areas. The psychological credibility index is obtained by summarizing all uncertainties in the user's psychological focus areas. The formula for calculating the psychological credibility index is as follows: ; In the formula: As an indicator of user psychological credibility, This represents the total number of areas of psychological concern. This represents the total number of question fields corresponding to the psychological concern area. The preset response time is set for the a-th question field within the b-th psychological concern area. This represents the actual time spent answering the question in the a-th question field within the b-th psychological concern area. The preset average response time is the time for the a-th question field in the b-th psychological concern area.

[0042] In this embodiment of the invention, after the question selection module on the server side completes the retrieval and merging of questions corresponding to the target psychological factor, it enters the stage of answer time analysis and psychological credibility index calculation. The assessment service module first counts the total number of questions in the generated question field list on the server side. For example, assuming that the question field list generated in the current assessment session contains 19 questions, the system obtains a total of 19 questions.

[0043] Then, the system calculates the total preset time for this assessment based on the preset average time for each question. This average time is set by the system in the configuration file. For example, if the average time for each question is 12 seconds, then the preset time for this assessment is 229 seconds. The assessment service module encapsulates the total number of questions and the preset answering time into API response data and returns it to the client for user reference. The client interface can simultaneously display prompts, such as: "This assessment is expected to take about 3 minutes and 48 seconds, with a total of 19 questions."

[0044] Once the user enters the formal answering stage, the client records the start and submission times of each question in real time and automatically calculates the actual answering time. After the user completes all the questions, the client uploads the actual answering time data for each question to the server, where the algorithm service module receives it and initiates the psychological credibility index analysis process.

[0045] The algorithm service module invokes a psychological analysis model, using the preset response time and actual response time as core inputs. It calculates a psychological credibility index for users across different psychological focus areas. By comparing the preset and actual response times for each question, it reflects the stability of the user's responses and fluctuations in their psychological state during the assessment process. When the actual response time is significantly shorter than the preset time, it may indicate that the user is skipping questions, avoiding questions, or experiencing distraction. When the response time is significantly longer, it may mean that the question triggered mental stagnation, hesitation, or emotional interference. The model uses a weighted average to synthesize the performance across all psychological focus areas, generating a psychological credibility index that reflects the overall stability of the user's responses.

[0046] After calculating the psychological credibility index, the system provides real-time feedback to the user as a quantitative result. For example, when the psychological credibility index is higher than 0.8, the client can prompt "The test answers are stable and the results are credible"; when the psychological credibility index is between 0.5 and 0.8, it can prompt "The test answers fluctuate moderately, and it is recommended to retest some questions"; if the psychological credibility index is lower than 0.5, it can prompt "The test answers are unstable and the results are less credible".

[0047] Through the above steps, a dynamic credibility assessment mechanism based on response time-series data is realized, which not only improves the scientificity and interpretability of psychological test results, but also enhances the user participation experience through real-time feedback, enabling users to understand their own state changes and receive timely guidance during the response process.

[0048] Preferably, the user's answers to each question and the question fields are obtained to generate an answer dataset. The scoring integrity verification module verifies whether the user has completed all questions. The specific steps are as follows: After the user confirms that they have started answering the questions, the client requests the question data from the server based on the session fields. Users answer questions one by one on the client interface. After completing each question, the client submits the question field and answer to the server via API. The server stores the received answers in an answer table and associates them with the current session field. After the user completes all the questions and clicks "Submit", the client sends a request to the server to complete the assessment. The assessment service module triggers the scoring integrity verification module, which retrieves the previously stored question selection field from the assessment meeting table based on the session field. From the answer table, retrieve a list of all questions that the user actually answered, based on the conversation field. By comparing the evaluation meeting form and the answer sheet, it is verified whether the user has answered all the questions for each target factor. If all questions have been answered, the integrity verification is passed; if not all questions have been answered, the integrity verification is failed.

[0049] In this embodiment of the invention, a psychological assessment platform provides a user with a questionnaire containing three psychological factors: attention, emotion regulation, and stress tolerance. After the user confirms the start of the test in the system, the client requests question data from the server based on the current session identifier. The server returns a list of questions corresponding to the user based on the target psychological factor set. The user answers each question on the client interface. After completing each question, the client submits the question fields and corresponding answers to the server in real time via API. The server stores this information in the answer table and associates it with the current session identifier to ensure data integrity and traceability. After the user completes the entire questionnaire and clicks "Submit," the client sends a completion request, triggering the scoring integrity verification module in the assessment service. This module retrieves the list of questions selected for this assessment from the assessment meeting table based on the session identifier, and simultaneously retrieves the list of questions actually answered by the user from the answer table, comparing each question with the target psychological factor to ensure that all questions have been answered. If the user completes all the questions for each psychological factor, the verification passes, and the system marks the assessment result as complete. Conversely, if any questions are left unanswered, the completeness verification fails, and the system will notify the user of the incomplete questions and guide them to return and complete the answers. This process ensures the completeness and reliability of the psychological assessment results, providing an accurate data foundation for subsequent psychological evaluations and report generation.

[0050] Preferably, the score is calculated after the integrity verification is passed, and the specific steps are as follows: When a user passes the integrity verification, the server-side scoring calculation module is triggered. According to the preset scoring rules in the selection mapping table, all answers for each factor are scored, the first-level answer score corresponding to each psychological concern area is calculated, the average answer score is obtained after summarizing, and the average answer score is stored in the answer table and the score mapping table. If the integrity verification fails, the server will refuse to score and return an error message to the client, indicating that "the answer is incomplete and a scientific report cannot be generated".

[0051] Preferably, the priority of users' psychological concerns is determined by combining psychological credibility indicators. The specific steps are as follows: Obtain psychological credibility sub-indicators for each area of ​​user psychological concern. ,in, For the b-th psychological concern area, the psychological credibility sub-index is used. Based on the psychological credibility sub-index and the first-level answer score, a domain priority analysis model is constructed to output the priority of the domains that users are psychologically concerned about.

[0052] In this embodiment of the invention, the scoring calculation stage begins after the integrity verification is passed. If a user completes a questionnaire containing three psychological factors—attention, emotion regulation, and stress tolerance—and it is detected that the user has answered all questions, the server triggers the scoring calculation module. Based on the pre-set scoring rules in the selection mapping table, all answers for each psychological factor are scored. For example, for the "attention" factor, the system maps each answer selected by the user to a corresponding score and summarizes the results to obtain the first-level answer score for that factor. Similarly, the answers for the "emotion regulation" and "stress tolerance" factors are also scored separately. Subsequently, the system calculates the average score for all factors to reflect the user's overall performance in each psychological attention area and stores this average score in both the answer table and the score mapping table for use in generating a subsequent psychological assessment report. Conversely, if the user fails the integrity verification, for example, by omitting some questions in the "stress tolerance" factor, the server will refuse to perform the scoring calculation and return an error message to the client, informing the user that "the answers are incomplete and a scientific report cannot be generated." This mechanism ensures the scientific rigor of the scoring process and the integrity of the data, avoiding distortion of assessment results due to missing data.

[0053] Preferably, the steps for constructing the domain priority analysis model are as follows: Obtain the psychological credibility sub-indicator and first-level answer score for each psychological concern area. Calculate the psychological factor attention level for each psychological concern area. Determine the priority of user psychological concern areas based on the psychological factor attention level. The formula for calculating the psychological factor attention level is: ; In the formula: For the psychological factors of the b-th psychological concern area, For the b-th psychological concern area, the psychological credibility sub-index is... Rate the Level 1 answer for the b-th psychological concern area. This represents the total number of areas of psychological concern. For error factor; Obtain the attention level of psychological factors corresponding to each area of ​​psychological concern, and arrange them in descending order of value to form an attention level sequence. The attention levels of psychological factors were compared with the preset attention ranges in sequence. If the attention given to psychological factors exceeds the upper limit of the preset attention range, the psychological attention area is at the first-level psychological attention target; if the attention given to psychological factors is within the preset attention range, the psychological attention area is at the second-level psychological attention target; if the attention given to psychological factors is below the lower limit of the preset attention range, the psychological attention area is at the third-level psychological attention target.

[0054] In this embodiment of the invention, after obtaining the answer scores for each psychological concern domain of the user, the system can further combine psychological credibility indicators to determine the user's psychological concern priority. If a user completes a questionnaire covering three psychological concern domains—attention, emotion regulation, and stress tolerance—the system first calculates the psychological credibility sub-indicator for each domain. This indicator is obtained by comparing the consistency of answers to different questions within the same domain, reflecting the stability and reliability of the user's responses. Next, the system combines the psychological credibility sub-indicator with the primary answer scores for the corresponding domain to construct a domain priority analysis model, calculating the psychological factor concern level for each psychological concern domain. Specifically, the psychological factor concern level is calculated using a formula, where an error factor is used to correct calculation bias. The system arranges the calculated concern level sequence from high to low and compares it with a preset concern level range. For example, if the psychological factor concern level for "stress tolerance" exceeds the preset upper limit, it is determined to be a primary psychological concern target; if the concern level for "emotion regulation" is within the range, it is a secondary psychological concern target; and if the concern level for "attention" is below the lower limit, it is a tertiary psychological concern target.

[0055] In one embodiment of the present invention, a user's attention scores in three psychological attention areas—"stress management," "emotion regulation," and "attention concentration"—are 0.85, 0.65, and 0.40, respectively. The system first sorts them as {0.85, 0.65, 0.40}. Then, the system compares the attention score of each psychological factor with a preset attention range. For example, the preset range is: upper limit 0.8, lower limit 0.5. Since the attention score of "stress management" (0.85) exceeds the upper limit of 0.8, it is determined to be a first-level psychological attention target, indicating that the user has a high need for attention in this area and requires priority attention and intervention. The attention score of "emotion regulation" (0.65) is between the upper and lower limits, so it is determined to be a second-level psychological attention target, indicating that the user's attention level in this area is moderate and can be considered as secondary attention. The attention score of "attention concentration" (0.40) is below the lower limit of 0.5, so it is determined to be a third-level psychological attention target, indicating that the user's relative attention level in this area is low and can be temporarily left unaddressed. This sorting and grading method can scientifically identify users' priorities in different psychological areas, providing a basis for the development of psychological counseling, personalized reports, or intervention programs.

[0056] Based on the above, the embodiments of the present invention can comprehensively consider the reliability and scoring level of user responses, and specifically identify the psychological areas that users need to pay the most attention to, thereby providing a scientific basis for subsequent psychological intervention or personalized reports.

[0057] A dynamic psychological assessment item selection system based on the factor integrity principle, including a client, an application server, and a data storage layer; The client is used to provide the front-end interface for user interaction, including WeChat mini programs, web applications, or mobile apps. It is responsible for presenting initial question options to users, collecting user choices, displaying assessment questions, and sending user answer data to the server.

[0058] The application server adopts a modular architecture and is responsible for handling client requests and executing the core methods of this invention, including factor mapping, question selection, dynamic calculation, data storage, and scoring verification.

[0059] The data storage layer is responsible for persistently storing the data required by the system, including a MySQL (relational) database and a cache database. The MySQL database is used to store core business data, such as user information, scales, factors, questions, assessment sessions, and results. The cache database is used to cache frequently accessed data, such as scale configurations and factor mapping relationships, to improve response speed.

[0060] The application server includes a user service module, an evaluation service module, and an algorithm service module; The user service module is used for user interaction, assessment session creation, and personalized needs collection. The assessment service module is used for loading questions, recording data, and verifying the completeness of answers. The algorithm service module is used to calculate psychological credibility indicators and determine the priority of psychological factors.

[0061] like Figure 2 The diagram shown is a system block diagram of a dynamic psychological assessment item selection system based on the factor integrity principle according to an embodiment of the present invention, which can be used to execute... Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0062] Through the above embodiments, this invention, by initiating the assessment and creating a session on the client side, can generate independent and traceable answer records for each user, ensuring data integrity and security while avoiding data confusion between different users. Mapping user psychological focus areas to specific psychological factors and removing duplicates generates a target psychological factor set, accurately identifying the psychological dimensions the user needs to assess, avoiding redundant questions, and improving assessment efficiency. By precisely matching target psychological factors to 1-3 focus areas selected by the user, it avoids users answering a large number of irrelevant questions. Compared to traditional fixed-scale models, such as the SCL-90 which requires completing all 90 questions, this invention can significantly reduce the number of questions. For example, if the user only selects two factors, "depressive mood" and "anxiety mood," the total number of questions is only 23 (13 for depression and 10 for anxiety), improving assessment efficiency by over 74%.

[0063] The system retrieves all questions for each psychological factor from the database and generates a list of question fields, automatically creating an assessment question bank tailored to user needs. This ensures comprehensive coverage of each psychological factor, standardizes the assessment process, and guarantees consistency and comparability across different users. User-answered questions are core topics within their areas of interest, enhancing user engagement and satisfaction. The total number of questions and estimated completion time are dynamically calculated and provided in real-time based on user selections, increasing transparency and user control. By statistically analyzing the number of questions and preset response times, the system calculates actual response time and combines this with psychological credibility indicators. This not only reflects the stability and focus of user responses but also provides real-time feedback during the assessment, helping users self-monitor, maintain focus, and improve the quality of their responses.

[0064] After obtaining users' answers to each question and generating a response dataset, the scoring integrity verification module ensures that users have completed all target questions, avoiding scoring distortion due to missing data. Strictly adhering to the factor integrity principle, it ensures that the calculation of each psychological factor score is based on the complete item set of that factor in the original scale, fundamentally guaranteeing the psychometric scientific rigor and professionalism of the assessment results. This addresses the risk of compromised scoring structure integrity that may exist in existing dynamic assessments, maximizing the accuracy and reliability of the scores. Scoring is only performed after integrity verification is passed. The module combines psychological credibility indicators to determine the priority of psychological concern areas, ensuring the scientific reliability of the scoring results. Furthermore, personalized analysis is conducted based on the actual responses of users, providing precise evidence for psychological intervention, counseling, or reporting.

[0065] The scientific validity of the scoring in this invention is guaranteed, and the generated assessment reports and risk assessment results have higher credibility and clinical reference value, which is beneficial to subsequent psychological intervention and treatment. It realizes closed-loop management from question generation, answer monitoring, data integrity verification to personalized priority analysis, which not only ensures the reliability of assessment data, but also improves user experience and the practical value of assessment results.

[0066] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

[0067] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A dynamic psychological assessment item selection method based on the principle of factor integrity, characterized in that, Includes the following steps: Users initiate the assessment on the client, create a session, and collect data on their areas of psychological concern. The data is then mapped to corresponding psychological factors and deduplicated to generate a set of target psychological factors. Based on the target set of psychological factors, retrieve and load all questions corresponding to each psychological factor from the MySQL database, extract question fields and merge them to generate a list of question fields; By statistically analyzing the number of questions in the question field list and the preset average answering time per question, the preset answering time and the actual answering time are obtained, the user's psychological credibility index is analyzed, and feedback is given to the user in real time. The system obtains users' answers to each question and generates a response dataset based on the question fields. It then verifies whether users have completed all target questions through a scoring integrity verification module. After the integrity verification is passed, the system calculates the score and determines the priority of users' psychological concern areas by combining psychological credibility indicators.

2. The method for selecting dynamic psychological assessment items based on the factor integrity principle according to claim 1, characterized in that, Users initiate the assessment on the client, create a session, and collect data on their areas of psychological concern. The specific steps are as follows: When a user takes an assessment on the client side, the client sends an API request to the assessment service module on the server side to create an assessment session. After receiving the request, the server creates a new pending session record in the evaluation session table and generates a unique session field to return to the client. The client requests the initial question configuration from the server, and the server returns JSON data containing eight psychological concern areas options; Users can choose their psychological focus area on the client interface, and the client submits the user's selection to the assessment service module on the server via API.

3. The method for selecting dynamic psychological assessment items based on the principle of factor integrity as described in claim 1, characterized in that, The target psychological factor set is generated by mapping users' areas of psychological interest to corresponding psychological factors and removing duplicates. The specific steps are as follows: After receiving the user's selection, the assessment service module calls the factor mapping module in the algorithm service module to map the user's selected psychological concern area into psychological factors according to the selection mapping table preset in memory. By deduplicating the psychological factors, the final set of target psychological factors is obtained and updated to the graph matching field of the corresponding session record in the assessment session table.

4. The method for selecting dynamic psychological assessment items based on the factor integrity principle according to claim 1, characterized in that, Based on the target psychological factor set, all questions corresponding to each psychological factor are retrieved and loaded from the MySQL database. Question fields are extracted and merged to generate a question field list. The specific steps are as follows: Based on the target set of psychological factors, the question selection module is triggered. For each psychological factor in the target set of psychological factors, the question selection module performs a query on the question table in the MySQL database. By merging all the query question fields, a complete list of question fields is formed and stored in the question selection field of the corresponding session in the assessment session table.

5. The method for selecting dynamic psychological assessment items based on the factor integrity principle according to claim 1, characterized in that, By statistically analyzing the number of questions in the question field list and the preset average answering time per question, the preset answering time and the actual answering time are obtained. This analysis assesses the user's perceived credibility and provides real-time feedback to the user. The specific steps are as follows: The server counts the total number of questions in the question field list, calculates the preset answer time based on the preset average answer time per question, and returns the calculated total number of questions and the preset answer time to the client via API response. A user psychological analysis model is constructed based on the preset response time and the actual response time to obtain the uncertain factors in the user's psychological attention areas. The psychological credibility index is obtained by summarizing the uncertain factors in all the user's psychological attention areas.

6. The method for selecting dynamic psychological assessment items based on the factor integrity principle according to claim 1, characterized in that, The system retrieves the user's answers to each question and generates a response dataset based on the question fields. The scoring integrity verification module then verifies whether the user has completed all questions. The specific steps are as follows: After the user confirms that they have started answering the questions, the client requests the question data from the server based on the session fields. Users answer questions one by one on the client interface. After completing each question, the client submits the question field and answer to the server via API. The server stores the received answers in an answer table and associates them with the current session field. After the user completes all the questions and clicks "Submit", the client sends a request to the server to complete the assessment. The assessment service module triggers the scoring integrity verification module, which retrieves the previously stored question selection field from the assessment meeting table based on the session field. From the answer table, retrieve a list of all questions that the user actually answered, based on the conversation field. Compare and evaluate the meeting form and the answer sheet to verify whether the user has answered all questions for each target factor; if all questions have been answered, the completeness verification is passed. If not all answers are provided, the integrity verification fails.

7. The method for selecting dynamic psychological assessment items based on the factor integrity principle according to claim 6, characterized in that, After the integrity verification is passed, the score is calculated. The specific steps are as follows: When a user passes the integrity verification, the server-side scoring calculation module is triggered. According to the preset scoring rules in the selection mapping table, all answers for each factor are scored, the first-level answer score corresponding to each psychological concern area is calculated, the average answer score is obtained after summarizing, and the average answer score is stored in the answer table and the score mapping table. If the integrity verification fails, the server will refuse to score and return an error message to the client, indicating that the user's answer is incomplete and a scientific report cannot be generated.

8. The method for selecting dynamic psychological assessment items based on the factor integrity principle according to claim 1, characterized in that, The following steps are taken to prioritize user psychological concerns by combining psychological credibility indicators: Obtain psychological credibility sub-indicators for each area of ​​user psychological interest, among which... For the b-th psychological concern area, the psychological credibility sub-index is used. Based on the psychological credibility sub-indicator and the first-level answer score for each psychological concern area, the psychological factor attention level corresponding to each psychological concern area is obtained, and the priority of the user's psychological concern area is determined according to the psychological factor attention level.

9. The method for selecting dynamic psychological assessment items based on the principle of factor integrity as described in claim 8, characterized in that, The priority of users' psychological concerns is determined based on the level of attention given to psychological factors. The specific steps are as follows: Obtain the attention level of psychological factors corresponding to each area of ​​psychological concern, and arrange them in descending order of value to form an attention level sequence. ,in, For the psychological factors of the b-th psychological concern area, Given the total number of psychological attention areas, the attention levels of psychological factors are compared with the preset attention ranges in order. If the attention given to psychological factors exceeds the upper limit of the preset attention range, the psychological attention area is at the first-level psychological attention target; if the attention given to psychological factors is within the preset attention range, the psychological attention area is at the second-level psychological attention target; if the attention given to psychological factors is below the lower limit of the preset attention range, the psychological attention area is at the third-level psychological attention target.

10. A dynamic psychological assessment item selection system based on the factor integrity principle, applied to the dynamic psychological assessment item selection method based on the factor integrity principle as described in any one of claims 1-9, characterized in that, The system includes a client, an application server, and a data storage layer; The client is used to provide the front-end interface for user interaction, including WeChat mini programs, web applications or mobile apps. It is responsible for presenting initial question options to users, collecting user choices, displaying assessment questions, and sending user answer data to the server. The application server adopts a modular architecture and is responsible for handling client requests, including factor mapping, question selection, dynamic calculation, data storage, and scoring verification. The data storage layer is responsible for persistently storing the data required by the system, including MySQL databases and cache databases; The MySQL database is used to store core business data; the cache database is used to cache frequently accessed data.

Images