Method and system for generating MBTI psychological scale for specific scene

Abstract

The invention relates to the technical field of psychological assessment, and discloses a method and system for generating an MBTI psychological scale for a specific scene, and the method comprises the steps: constructing a scene knowledge network, a question bank comprising a plurality of question items; analyzing input specific scene description, querying the scene knowledge graph, and generating a multi-dimensional importance weight matrix for a specific scene through a large language model; screening out a candidate question set from the question bank based on the multi-dimensional importance weight; a comprehensive optimization score function is constructed and solved through an optimization algorithm, and an optimal question item combination is selected from the candidate question set; and arranging the selected optimal question item combination to generate a complete MBTI psychological scale. Through a specific scene knowledge network construction mechanism and scene scale generation, dynamic generation and real-time optimization of the MBTI psychological scale in a specific application scene are realized, and the situation adaptability and result stability of psychological assessment are improved.

Description

Technical Field

[0001] This invention relates to the field of psychological assessment technology, specifically to a method and system for generating the MBTI psychological scale for specific scenarios. Background Technology

[0002] In recent years, psychological assessment tools have been widely used in educational management, career planning, and personalized services. Among them, the Myers-Briggs Type Indicator (MBTI), a commonly used personality classification tool, characterizes an individual's cognitive and behavioral patterns by combining their preferences across four dimensions: extraversion / introversion, sensing / intuition, thinking / feeling, and judging / perceiving. However, existing MBTI administration methods often rely on fixed questionnaires or static scenario descriptions, lacking the ability to dynamically adapt to specific application scenarios. For example, in career counseling or personalized recommendation scenarios, an individual's psychological performance is often influenced by context, task load, and social setting, making it difficult for traditional static scales to effectively capture these contextual differences. Existing research has attempted to infer personality traits based on social media data, such as constructing low-dimensional representations using behavioral features like likes and text expressions, and then using logistic regression or support vector machines for personality prediction. Other methods utilize the Big Five personality theory as an intermediate layer, indirectly inferring MBTI-related types through linguistic or behavioral features. However, these methods mostly rely on general models and lack adaptive design for specific application tasks, making them prone to prediction bias in cross-contextual situations. Furthermore, existing questionnaire generation methods depend on fixed question banks, failing to dynamically generate test items according to scenario requirements, resulting in a semantic disconnect between the questionnaire and the target task. In summary, existing solutions still have shortcomings in combining personality assessment with application scenarios, mainly manifested in the lack of scenario-based feature constraints and the lack of responsiveness to dynamic changes in users' psychological states, thus limiting the accuracy and dynamic application of the MBTI scale in specific scenarios.

[0003] Current methods based on fixed questionnaires and generic personality modeling have significant shortcomings in terms of scenario adaptability and semantic accuracy. Specifically, these shortcomings manifest in the following aspects: 1. Lack of scenario adaptability and low content validity: In pursuit of universality, the traditional MBTI scale designs its items around general scenarios. When applied to a highly specific scenario, a significant content gap exists between the questionnaire and the actual assessment needs. The composition and proportion of its items fail to reflect the differentiated requirements of different psychological traits in a specific scenario, resulting in weak correlation between the assessment results and actual scenario performance, and insufficient content validity.

[0004] 2. Rigid scale combination and lack of optimization mechanism: The existing scales have fixed item combinations, and it is impossible to adjust the weight and ratio of items in each dimension according to the needs of the scenario. There is a lack of a scientific and quantifiable combination optimization mechanism to ensure that the whole questionnaire is the most efficient set for a specific goal.

[0005] 3. Customization is costly and inefficient: The only traditional way to solve the above problems is to hire psychometric experts to manually customize the scales. This process is not only extremely costly and time-consuming (usually taking weeks or even months), but also highly dependent on the expert's personal experience and lacks unified, reproducible scientific standards. This makes it almost impossible in practice to provide high-quality customized scales for diverse specific scenarios.

[0006] 4. Insufficient Discrimination of Key Traits: In specific scenarios, the accurate identification of certain key personality traits is crucial. Generalized scales are far from sufficient for in-depth and reliable assessment of individuals, lacking a mechanism to proactively identify and strengthen the examination of key traits in specific scenarios. Summary of the Invention

[0007] To address the core shortcomings of existing MBTI scales, such as rigid content structure, disconnect from application scenarios, and inefficient customization processes, this invention provides a method and system for generating MBTI psychological scales for specific scenarios. It aims to abandon fixed questionnaire models and, by establishing a quantitative correlation model between scenario requirements and psychometric indicators, automatically and scientifically generate an optimal complete scale from a massive, high-quality question bank for any specific scenario. Specifically, this invention focuses on solving the following two core technical problems: 1. Achieve deep coupling between scale content and scenario requirements. That is, establish a set of psychological needs that can quantify and analyze specific application scenarios, and use this as the core basis to intelligently guide the combination and construction of scales in terms of item selection, dimension ratio, and content emphasis, so as to ensure that the final scale has extremely high content validity and scenario relevance.

[0008] 2. Ensure the scientific rigor and optimality of the generated scale. That is, establish a multi-objective optimization framework that can simultaneously consider multiple key psychometric indicators such as scenario relevance, dimensional balance, information value (discrimination), and content non-redundancy during the decision-making process of combining and generating the scale. This will ensure that the final output is not only relevant, but also a scientific, efficient, and robust optimal questionnaire.

[0009] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for generating an MBTI psychological scale for a specific scenario, comprising: Construct a scene knowledge network that includes a scene knowledge graph and a vectorized question bank. It contains multiple items, each labeled with measurement dimensions, information value, scene relevance, and semantic vector; Parse the specific scenario description of the input The system queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model. A set of candidate questions is selected from the question bank based on multi-dimensional importance weights; Construct a comprehensive optimization scoring function, which includes at least scenario relevance, dimensional balance, information value, and semantic redundancy, and solve it through an optimization algorithm to select the optimal combination of items from the candidate item set; The selected optimal combination of items is arranged to generate a complete MBTI psychological scale.

[0010] In one embodiment, the parsed input is a specific scenario description. It queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model, specifically including: The user inputs a specific scenario description. The scenario description is parsed using a large language model, and a knowledge graph is queried to output an MBTI dimension importance weight matrix. : ; ; in, For dimension Importance weights This indicates an individual's primary tendency to obtain energy. It indicates an individual's tendency in acquiring information; It indicates an individual's tendency in decision-making; It indicates an individual's lifestyle preferences.

[0011] In one embodiment, the step of selecting a set of candidate questions from the question bank based on multi-dimensional importance weights specifically includes: Based on the importance weights of different dimensions, from the question bank Selecting candidate topics The higher the importance weight of a dimension, the more candidate topics there are, and the higher the quality requirements.

[0012] In one embodiment, the construction of a comprehensive optimization scoring function includes at least scene relevance, dimensional balance, information value, and semantic redundancy, specifically including: This will require selecting from the candidate topic set. The optimal problem is selected and modeled as a combinatorial optimization problem, and a comprehensive optimization score is defined. for: ; Scene relevance ; This represents the i-th item. express The degree of relevance to the scene; Dimensional balance ;in, For the question bank, it belongs to the dimension The number of questions This is the adjustment coefficient; Information value ; express Information value; semantic redundancy ; They are respectively semantic vectors, This represents the j-th item; in, These are the weight parameters.

[0013] In one embodiment, the step of selecting the optimal combination of questions from the candidate question set through an optimization algorithm specifically includes: By employing optimization algorithms such as genetic algorithms, beam search, or integer programming, the combinatorial optimization problem is solved to obtain the combination of question items with the highest total score. : .

[0014] Secondly, the present invention provides a system for generating an MBTI psychological scale for specific scenarios, comprising: The knowledge network construction module builds a scene knowledge network that includes a scene knowledge graph and a vectorized question bank. It contains multiple items, each labeled with measurement dimensions, information value, scene relevance, and semantic vector; The weight matrix generation module parses the input specific scene description. The system queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model. The question selection module filters a set of candidate questions from the question bank based on multi-dimensional importance weights; The optimal question selection module constructs a comprehensive optimization scoring function, which includes at least scenario relevance, dimensional balance, information value, and semantic redundancy, and solves it through an optimization algorithm to select the optimal combination of questions from the candidate question set. The scale generation module arranges the selected optimal combination of items to generate a complete MBTI psychological scale.

[0015] In one embodiment, the parsed input is a specific scenario description. It queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model, specifically including: The user inputs a specific scenario description. The scenario description is parsed using a large language model, and a knowledge graph is queried to output an MBTI dimension importance weight matrix. : ; ; in, For dimension Importance weights This indicates an individual's primary tendency to obtain energy. It indicates an individual's tendency in acquiring information; It indicates an individual's tendency in decision-making; It indicates an individual's lifestyle preferences.

[0016] In one embodiment, the step of selecting a set of candidate questions from the question bank based on multi-dimensional importance weights specifically includes: Based on the importance weights of different dimensions, from the question bank Selecting candidate topics The higher the importance weight of a dimension, the more candidate topics there are, and the higher the quality requirements.

[0017] In one embodiment, the construction of a comprehensive optimization scoring function includes at least scene relevance, dimensional balance, information value, and semantic redundancy, specifically including: The problem of selecting the optimal question from the candidate question set is modeled as a combinatorial optimization problem, and a comprehensive optimization score is defined. for: ; Scene relevance ; This represents the i-th item. express The degree of relevance to the scene; Dimensional balance ;in, For the question bank, it belongs to the dimension The number of questions This is the adjustment coefficient; Information value ; express Information value; semantic redundancy ; They are respectively semantic vectors, This represents the j-th item; in, These are the weight parameters.

[0018] In one embodiment, the step of selecting the optimal combination of questions from the candidate question set through an optimization algorithm specifically includes: By employing optimization algorithms such as genetic algorithms, beam search, or integer programming, the combinatorial optimization problem is solved to obtain the combination of question items with the highest total score. : .

[0019] Compared with the prior art, the beneficial technical effects of the present invention are: This invention, through a specific scenario knowledge network construction mechanism and a scenario-based scale generation method, achieves dynamic generation and real-time optimization of the MBTI psychological scale in specific application scenarios, significantly improving the contextual adaptability and result stability of psychological assessments. Specifically, it has the following main beneficial effects: First, it achieves deep coupling between scale content and application scenarios: each scale generated is customized for a specific application scenario, has extremely high content validity, and directly solves the problem of insufficient customization of general scales.

[0020] Second, it ensures the psychometric quality of the generated scale: through multi-objective optimization, the system not only considers the relevance of the scenario, but also takes into account core psychometric indicators such as dimensional balance, information value and non-redundancy, thus ensuring the scientific nature and robustness of the generated scale.

[0021] Third, extremely high flexibility and scalability: users can generate customized scales for any emerging and specific scenario at any time, as needed. Meanwhile, the system's capabilities can be continuously enhanced by expanding and optimizing the backend knowledge graph and question bank. Attached Figure Description

[0022] Figure 1 This is a flowchart of the method in an embodiment of the present invention; Figure 2 This is a schematic diagram of the overall technical framework in an embodiment of the present invention; Figure 3 This is a schematic diagram of the scene generation mechanism in an embodiment of the present invention. Detailed Implementation

[0023] A preferred embodiment of the present invention will now be described in detail with reference to the accompanying drawings.

[0024] like Figure 1As shown, a method for generating an MBTI psychological scale for a specific scenario according to the present invention includes the following steps: S1, construct a scene knowledge network that includes a scene knowledge graph and a vectorized question bank. It contains multiple items, each labeled with measurement dimensions, information value, scene relevance, and semantic vector; S2, Parsing the specific scenario description of the input. The system queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model. S3, based on multi-dimensional importance weights, selects a set of candidate questions from the question bank; S4. Construct a comprehensive optimization scoring function, which includes at least scene relevance, dimensional balance, information value, and semantic redundancy, and solve it through an optimization algorithm to select the optimal combination of items from the candidate item set; S5. Arrange the selected optimal combination of items to generate a complete MBTI psychological scale.

[0025] The overall technical framework of this invention is as follows: Figure 2 As shown. The core objective of this method is to automatically and instantly generate a psychometrically robust and complete MBTI questionnaire for any given application scenario. To achieve this goal, this framework introduces a psychological knowledge graph as its knowledge foundation and designs a multi-objective combined optimization function. Through this method, a directly usable, complete MBTI scale deeply optimized for a specific scenario is output, thus solving the fundamental problem of the disconnect between traditional general-purpose scales and application needs.

[0026] This invention is mainly achieved through two processes: the construction of a knowledge network for a specific scenario and the generation of a scenario-based scale.

[0027] 1. Construction of knowledge networks for specific scenarios.

[0028] First, a knowledge network is constructed that links "scene-dimension-question," including a scene knowledge graph and a vectorized question bank. The knowledge graph defines highly relevant dimensions for specific scenes. Next, a vectorized question bank is built, creating a massive question bank containing tens of thousands of standard MBTI questions, and each question undergoes rich metadata annotation and vectorization. .

[0029] Each question item It has the following attributes: (1) Dimension: ; (Extraversion–Introversion) indicates an individual's primary tendency to acquire energy; extraversion... Introversion refers to a preference for drawing energy from external activities and interpersonal interactions. It refers to a preference for drawing energy from internal reflection and solitude; (Sensing-intuition) refers to an individual's tendency in acquiring information; feeling This refers to a preference for perceiving the world through concrete facts and details; intuition. This refers to a preference for understanding the world through abstract patterns and holistic relationships; (Thinking–Feeling) represents an individual's tendency in decision-making; thinking... Preferences refer to decisions based on logic and objective criteria, rather than emotions. This refers to a preference for making decisions based on values ​​and interpersonal emotions. (Judging–Perceiving) represents an individual's lifestyle preferences, specifically judgment. This refers to a preference for a planned and structured lifestyle, and perception. It refers to a preference for a flexible, open, and adaptable lifestyle.

[0030] (2) Information value (discrimination): ; (3) Scene relevance: ; (4) Semantic vector: .

[0031] Questions semantic similarity between .

[0032] 2. Contextualized scale generation.

[0033] Contextualized generation mechanism, such as Figure 3 As shown.

[0034] The user inputs a specific scenario description. The scene description is parsed using a large language model, and a knowledge graph is queried to output an MBTI dimension importance weight matrix: ; .

[0035] in Dimensions in the Scene Importance weights Then, based on the importance weight of each dimension, in Selecting candidate topics Dimensions with higher importance weights have more candidate questions and higher quality requirements. The selection of the optimal question from the candidate question set is modeled as a combinatorial optimization problem, and a comprehensive optimization score is defined. for: .

[0036] The definitions of each part are as follows: (1) Scene relevance .

[0037] (2) Dimensional balance .in The question set belongs to the dimension The number of questions This is the adjustment coefficient.

[0038] (3) Information value .

[0039] (4) Semantic redundancy .

[0040] in, These are weighting parameters used to balance the importance of each optimization objective.

[0041] Then, optimization algorithms such as genetic algorithms, beam search, or integer programming are used to solve this combinatorial optimization problem, ultimately yielding the combination of questions with the highest total score. : .

[0042] Finally, the optimized combination of items is randomly sorted or arranged according to a specific logic and packaged into a complete MBTI scale that end users can directly answer (for example, by generating a PDF file or a web link).

[0043] This invention systematically solves the problems of insufficient scene adaptability, limited semantic alignment capability, and delayed result updates through the following key mechanisms: (1) A systematic method for structuring psychometric knowledge, scenario requirements, and question bank resources into a knowledge graph, and then performing scenario analysis, dimensional weighting, and candidate question selection based on this graph. This provides high-quality input and constraints for the combined optimization and generation of scales, and is the foundation for achieving high-precision scenario-based customization.

[0044] (2) Instead of directly generating text, the system uses a multi-objective optimization function to select and combine an optimal set of items from a large-scale question bank, taking into account factors such as scene relevance, dimensional balance, information value, and semantic redundancy, thus forming a complete scale. This is a key innovation that distinguishes it from traditional fixed scales and simple rule-based selection.

[0045] (3) The present invention integrates the above mechanisms into an end-to-end dynamic scale generation method, which can effectively cope with semantic differences, uneven distribution of psychological features and dynamic evolution of user status in different application scenarios, and significantly improve the adaptability, stability and interpretability of psychological assessment.

[0046] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0047] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple steps or stages, which are not necessarily completed at the same time, but may be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0048] Based on the description of the above method embodiments, the present invention also provides a system. The system may be a system that uses software (applications), modules, components, servers, clients, etc., using the methods described in the embodiments of this specification, combined with necessary implementation hardware. Based on the same innovative concept, the systems in one or more embodiments provided in this disclosure are as described in the following embodiments. Since the implementation schemes and methods for solving the problem are similar, the specific system implementations in the embodiments of this specification can refer to the implementations of the foregoing methods, and repeated details will not be repeated. As used below, the terms "module" or "module group" refer to a combination of software and / or hardware capable of implementing a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0049] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention, and no reference numerals in the claims should be construed as limiting the scope of the claims.

[0051] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A method for generating an MBTI psychological scale for a specific scenario, characterized in that, include: Construct a scene knowledge network that includes a scene knowledge graph and a vectorized question bank. It contains multiple items, each labeled with measurement dimensions, information value, scene relevance, and semantic vector; Parse the specific scenario description of the input The system queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model. A set of candidate questions is selected from the question bank based on multi-dimensional importance weights; Construct a comprehensive optimization scoring function, which includes at least scenario relevance, dimensional balance, information value, and semantic redundancy, and solve it through an optimization algorithm to select the optimal combination of items from the candidate item set; The selected optimal combination of items is arranged to generate a complete MBTI psychological scale.

2. The method for generating an MBTI psychological scale for a specific scenario according to claim 1, characterized in that, The specific scenario description of the parsed input It queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model, specifically including: The user inputs a specific scenario description. The scenario description is parsed using a large language model, and a knowledge graph is queried to output an MBTI dimension importance weight matrix. : ； ； in, For dimension Importance weight, This indicates an individual's primary tendency to obtain energy. It indicates an individual's tendency in acquiring information; It indicates an individual's tendency in decision-making; It indicates an individual's lifestyle preferences.

3. The method for generating an MBTI psychological scale for a specific scenario according to claim 1, characterized in that, The selection of candidate question sets from the question bank based on multi-dimensional importance weights specifically includes: Based on the importance weights of different dimensions, from the question bank Selecting candidate topics The higher the importance weight of a dimension, the more candidate topics there are, and the higher the quality requirements.

4. The method for generating an MBTI psychological scale for a specific scenario according to claim 2, characterized in that, The construction of a comprehensive optimization scoring function includes at least scene relevance, dimensional balance, information value, and semantic redundancy, specifically including: This will require selecting from the candidate topic set. The optimal problem is selected and modeled as a combinatorial optimization problem, and a comprehensive optimization score is defined. for: ； Scene relevance ; This represents the i-th item. express The degree of relevance to the scene; Dimensional balance ;in, For the question bank, it belongs to the dimension The number of questions This is the adjustment coefficient; Information value ; express Information value; semantic redundancy ; They are respectively semantic vectors, This represents the j-th item; in, These are the weight parameters.

5. The method for generating an MBTI psychological scale for a specific scenario according to claim 4, characterized in that, The step of selecting the optimal combination of questions from the candidate question set through optimization algorithms specifically includes: Solve the combinatorial optimization problem using genetic algorithms, beam search algorithms, or integer programming algorithms to obtain the combination of questions with the highest total score. : 。 6. A system for generating an MBTI psychological scale for a specific scenario, characterized in that, include: The knowledge network construction module builds a scene knowledge network that includes a scene knowledge graph and a vectorized question bank. It contains multiple items, each labeled with measurement dimensions, information value, scene relevance, and semantic vector; The weight matrix generation module parses the input specific scene description. The system queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model. The question selection module filters a set of candidate questions from the question bank based on multi-dimensional importance weights; The optimal question selection module constructs a comprehensive optimization scoring function, which includes at least scenario relevance, dimensional balance, information value, and semantic redundancy, and solves it through an optimization algorithm to select the optimal combination of questions from the candidate question set. The scale generation module arranges the selected optimal combination of items to generate a complete MBTI psychological scale.

7. The system for generating an MBTI psychological scale for a specific scenario according to claim 6, characterized in that, The specific scenario description of the parsed input It queries the scene knowledge graph and generates a multi-dimensional importance weight matrix for a specific scene using a large language model, specifically including: The user inputs a specific scenario description. The scenario description is parsed using a large language model, and a knowledge graph is queried to output an MBTI dimension importance weight matrix. : ； ； in, For dimension Importance weight, This indicates an individual's primary tendency to obtain energy. It indicates an individual's tendency in acquiring information; It indicates an individual's tendency in decision-making; It indicates an individual's lifestyle preferences.

8. The system for generating an MBTI psychological scale for a specific scenario according to claim 6, characterized in that, The selection of candidate question sets from the question bank based on multi-dimensional importance weights specifically includes: Based on the importance weights of different dimensions, from the question bank Selecting candidate topics The higher the importance weight of a dimension, the more candidate topics there are, and the higher the quality requirements.

9. A system for generating an MBTI psychological scale for a specific scenario according to claim 7, characterized in that, The construction of a comprehensive optimization scoring function includes at least scene relevance, dimensional balance, information value, and semantic redundancy, specifically including: The problem of selecting the optimal question from the candidate question set is modeled as a combinatorial optimization problem, and a comprehensive optimization score is defined. for: ； Scene relevance ; This represents the i-th item. express The degree of relevance to the scene; Dimensional balance ;in, For the question bank, it belongs to the dimension The number of questions This is the adjustment coefficient; Information value ; express Information value; semantic redundancy ; They are respectively semantic vectors, This represents the j-th item; in, These are the weight parameters.

10. A system for generating an MBTI psychological scale for a specific scenario according to claim 9, characterized in that, The step of selecting the optimal combination of questions from the candidate question set through optimization algorithms specifically includes: Solve the combinatorial optimization problem using genetic algorithms, beam search algorithms, or integer programming algorithms to obtain the combination of questions with the highest total score. : 。

Images