Psychological assessment method and device, electronic equipment and product
By automating scale question modification and psychological analysis, the problems of low efficiency and poor user experience in traditional psychological assessments have been solved, achieving efficient and user-friendly automated psychological assessments.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- IFLYTEK SOUTH CHINA ARTIFICIAL INTELLIGENCE RES INST GUANGZHOU CO LTD
- Filing Date
- 2025-12-31
- Publication Date
- 2026-05-29
Smart Images
Figure CN122117255A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of psychological testing technology, and in particular to a psychological testing method, device, electronic device and product. Background Technology
[0002] With increasing life and work pressures in modern society, more and more people are suffering from mental illnesses or experiencing varying degrees of depression, which seriously affects their quality of life. Psychological testing, as a core tool for assessing individual psychological traits, states, and behaviors, occupies an important position in the mental health service system.
[0003] Traditional offline psychological assessments rely on on-site guidance from professionals. During the assessment process, professionals need to provide guidance to each test taker individually, which not only consumes a lot of time but also increases labor costs, thus affecting the efficiency of psychological assessments. Moreover, the collection and processing of assessment data also need to be done manually, which is prone to problems such as data entry errors or untimely processing, further affecting the efficiency of the assessment. Summary of the Invention
[0004] Based on the above needs, this application proposes a psychological assessment method, device, electronic device, and product that can improve the efficiency of psychological assessment and enhance the user experience of psychological assessment.
[0005] To achieve the above objectives, this application proposes the following technical solution: According to a first aspect of the embodiments of this application, a psychological testing method is provided, comprising: Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the questions in the pre-determined scale corpus are modified to obtain an updated scale corpus, and the scale questions for the next question-and-answer round are determined from the updated scale corpus. Repeat the above steps to output scale questions in each round of question-and-answer sessions and obtain corresponding user feedback; After the Q&A session concludes, psychological analysis is conducted based on the scale questions from each round of Q&A, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions from each round of Q&A, to obtain the user's psychological assessment results.
[0006] Optionally, based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the questions in the pre-determined scale corpus are modified to obtain an updated scale corpus, including: Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, determine the user's current emotional information and the user's level of acceptance of the scale questions in the current question-and-answer round. Based on the user's current emotional information and the user's acceptance of the scale questions in the current question-and-answer round, questions not raised in the pre-determined scale corpus are modified to obtain an updated scale corpus.
[0007] Optionally, before modifying the questions in a pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round to obtain an updated scale corpus, the following steps are also included: Based on pre-built user status data and current user feedback, the current scheduling strategy is determined; wherein, the user status data includes the user's current emotional information determined based on current user feedback, the user profile determined based on historical interaction data, and the user's current state time period; If the current scheduling strategy is an assessment workflow strategy, then a pre-determined scale question is output to obtain user feedback corresponding to the scale question; the assessment workflow strategy indicates entering the psychological assessment process or continuing the psychological assessment process.
[0008] Optional psychological assessment methods also include: If the current scheduling strategy is an empathic interaction workflow strategy, then based on the user status data and the current user feedback, a psychological empathic response is determined and output; wherein, the empathic interaction workflow strategy indicates exiting the psychological assessment process and performing psychological empathic interaction.
[0009] Optionally, based on pre-built user state data and current user feedback, the current scheduling strategy is determined, including: Based on pre-built user status data and current user feedback, the user's psychological state and assessment status are determined; wherein, the psychological state is used to indicate whether the user is in a psychological crisis state, and the assessment status indicates whether the user has withdrawn from the assessment. The current scheduling strategy is determined based on the user's psychological state and assessment status.
[0010] Optionally, based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the questions in the pre-determined scale corpus are modified to obtain an updated scale corpus, and the scale questions for the next question-and-answer round are determined from the updated scale corpus, including: Historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round are input into a pre-trained scale question generation model, so that the scale question generation model modifies the questions according to the pre-built prompts, resulting in an updated scale corpus and scale questions for the next question-and-answer round. The scale item generation model is a large language model.
[0011] Optional psychological assessment methods also include: Check whether the user feedback corresponding to the scale question in the current question-and-answer round matches the pre-built user status data; If the user feedback does not match the user status data, the user status data is updated based on the user feedback to obtain updated user status data. The prompt instructions are modified based on the updated user status data.
[0012] According to a second aspect of the embodiments of this application, a psychological testing device is provided, comprising: The scale question determination module is used to modify the questions in a pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, to obtain an updated scale corpus, and to determine the scale questions for the next question-and-answer round from the updated scale corpus. The questionnaire module is used to repeat the above operations to output questionnaire questions in each round of questioning and to obtain corresponding user feedback. The psychological analysis module is used to conduct psychological analysis after the question-and-answer session ends, based on the scale questions from each round of question-and-answer, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions from each round of question-and-answer, to obtain the user's psychological assessment results.
[0013] According to a third aspect of the embodiments of this application, an electronic device is provided, including: a memory and a processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the above-mentioned psychological assessment method by running the program in the memory.
[0014] According to a fourth aspect of the embodiments of this application, a computer program product is provided, including computer program instructions, which, when executed by a processor, cause the processor to implement the above-described psychological assessment method.
[0015] The psychological assessment method proposed in this application modifies a pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, resulting in an updated scale corpus. The scale questions for the next question-and-answer round are then determined from this updated corpus. After the question-and-answer session concludes, psychological analysis is performed based on the scale questions from each question-and-answer round, the original scale questions corresponding to each scale question, and the user feedback corresponding to each scale question, to obtain the user's psychological assessment results. Using the technical solution of this application, the scale questions can be automatically determined, and psychological analysis can be automatically performed, achieving automated psychological assessment and improving the efficiency of psychological assessment. Furthermore, modifying the scale questions based on historical interaction data and current user feedback makes the scale questions more suitable for users, thereby improving the user experience of the psychological assessment. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating a psychological assessment method provided in an embodiment of this application.
[0018] Figure 2 This is a flowchart illustrating another psychological assessment method provided in an embodiment of this application.
[0019] Figure 3 This is a flowchart illustrating another psychological assessment method provided in an embodiment of this application.
[0020] Figure 4 This is a flowchart illustrating another psychological assessment method provided in an embodiment of this application.
[0021] Figure 5 This is a schematic diagram of the structure of a psychological testing device provided in an embodiment of this application.
[0022] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0023] The technical solutions of this application are applicable to psychological testing scenarios. By employing the technical solutions of this application, the efficiency of psychological testing can be improved, as well as the user experience of psychological testing can be enhanced.
[0024] With increasing life and work pressures in modern society, more and more people are suffering from mental illnesses or experiencing varying degrees of depression. They may frequently feel down, lose interest, and feel lost and helpless about the future; they may become withdrawn and indifferent in interpersonal interactions, finding it difficult to build close relationships with others. These psychological problems are seriously eroding their physical and mental health.
[0025] Psychological testing, as a core tool for assessing an individual's psychological traits, state, and behavior, can provide in-depth understanding of an individual's psychological condition through scientific and systematic assessment methods, offering crucial evidence for the early detection, diagnosis, and intervention of psychological problems. Whether for maintaining mental health or treating mental illnesses, psychological testing plays an irreplaceable role. For example, in school mental health education, psychological testing can help teachers identify students' psychological problems in a timely manner, such as learning anxiety and social phobia, thereby taking targeted counseling measures to promote students' healthy physical and mental development. In corporate human resource management, psychological testing can help companies select suitable talent, understand employees' career interests and personality traits, and improve employee job satisfaction and performance.
[0026] Traditional offline psychological assessments rely on on-site guidance from professionals. During the assessment process, professionals need to provide guidance to each test taker individually, which not only consumes a lot of time but also increases labor costs, thus affecting the efficiency of psychological assessments. Moreover, the collection and processing of assessment data also need to be done manually, which is prone to problems such as data entry errors or untimely processing, further affecting the efficiency of the assessment.
[0027] In addition, existing psychological assessments evaluate users based on items in fixed scales, such as classic standardized scales, Symptom Checklist-90 (SCL-90), Self-Rating Anxiety Scale (SAS), and Self-Rating Depression Scale (SDS). The fixed presentation of items affects the user experience.
[0028] Based on this, this application proposes a psychological assessment method. This technical solution can automatically determine the scale questions to be asked and automatically perform psychological analysis to achieve automatic psychological assessment. Furthermore, based on historical interaction data and current user feedback, the scale questions can be modified to make the scale questions more suitable for users, thereby solving the problems of low efficiency and low user experience in psychological assessment in the prior art.
[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0030] Exemplary methods See Figure 1 As shown in the embodiment of this application, a psychological assessment method is proposed. The method includes: S101. Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, modify the questions in the pre-determined scale corpus to obtain an updated scale corpus, and determine the scale questions for the next question-and-answer round from the updated scale corpus.
[0031] In this embodiment, human-computer interaction data is recorded, and interaction data prior to the current question-and-answer round is used as historical interaction data. It is also necessary to output the pre-determined questionnaire questions for the current question-and-answer round and obtain user feedback on the questionnaire questions for the current question-and-answer round.
[0032] If the current question-and-answer round is the first round, then scale questions can be directly selected from a pre-determined scale corpus. This pre-determined scale corpus is a scale corpus that matches the user based on their basic information. Specifically, this embodiment can pre-construct multiple scale corpora applicable to different types of users, such as scale corpora for students, scale corpora for employees, and scale corpora for the elderly. The construction of the scale corpus can be based on classic standardized scales, such as the Symptom Checklist-90 (SCL-90), the Self-Rating Anxiety Scale (SAS), and the Self-Rating Depression Scale (SDS). Scale questions for different types of users are selected from these standardized scales to form scale corpora applicable to different types of users. For example, a scale corpus applicable to students will not contain work-related scale questions. Then, before proceeding to the psychological assessment question-and-answer round, basic user information can be exchanged through human-computer interaction to obtain the user's basic information and construct a user profile based on this information. Based on the constructed user profile, the scale corpus that matches the user profile is selected from all scale corpora as the pre-determined scale corpus.
[0033] If the current question-and-answer round is not the first question-and-answer round, then the scale questions for the next question-and-answer round determined in the previous question-and-answer round are the scale questions for this question-and-answer round, and the scale corpus pre-determined for the current question-and-answer round is the scale corpus updated in the previous question-and-answer round.
[0034] This embodiment, after acquiring historical interaction data and determining user feedback corresponding to the scale questions in the current question-and-answer round through the aforementioned methods, needs to modify the pre-determined scale corpus based on the historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, resulting in an updated scale corpus. This updated scale corpus is the pre-determined scale corpus for the next question-and-answer round. Specifically, this embodiment can analyze user acceptance of the current question-and-answer round based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, and modify unasked scale questions in the pre-determined scale corpus according to user acceptance to improve user acceptance of the scale questions. For example, unasked scale questions can be modified to more subtle expressions, thereby achieving a more seamless psychological assessment, that is, asking scale questions without the user realizing that a psychological assessment is being conducted. Furthermore, modifications to scale questions that have not yet been asked in the pre-defined scale corpus can be made based on pre-constructed user profiles to ensure that the modified scale questions are more suitable for users. The construction of user profiles can be based on historical interaction data to determine the user's basic information, which can be used to construct the scale. This basic information may include name, gender, age, and current status (e.g., for a student, current status includes before studying, during studying, and after studying; for an employee, current status includes working, working overtime, and on vacation).
[0035] In this embodiment, after modifying the questions in the pre-determined scale corpus to obtain the updated scale corpus, it is also necessary to select the scale questions for the next round of question and answer from the updated scale corpus. The selection of scale questions for the next round of question and answer can be based on historical interaction data, the scale questions of the current round of question and answer, and the corresponding user feedback. The most suitable scale question for the next round of question and answer can be selected from the updated scale corpus.
[0036] In one specific implementation, based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the questions in a pre-determined scale corpus are modified to obtain an updated scale corpus. This process includes the following steps: First, based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, determine the user's current emotional information and the user's level of acceptance of the scale questions in the current question-and-answer round.
[0037] This embodiment analyzes historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round to determine the user's current emotional information and the user's level of acceptance of the scale questions in the current question-and-answer round. The analysis of the user's current emotional information can be based on information such as the tone and intonation of the user's feedback to classify emotions, thereby determining the user's current emotional information. This current emotional information can include emotion type and emotion level. For example, if the emotion type is "irritable" and the emotion level is "high," it means that the user is currently very irritable and impatient, indicating that the user is impatient with the scale questions in the current question-and-answer round, and the user's acceptance of the scale questions is also low. Furthermore, the user's acceptance of the scale questions in the current question-and-answer round can be analyzed based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round. For example, if the user repeatedly denies the scale questions, it indicates that the user's acceptance of the scale questions in the current question-and-answer round is low.
[0038] Second, based on the user's current emotional information and the user's acceptance of the scale questions in the current question-and-answer round, the questions not raised in the pre-determined scale corpus are modified to obtain an updated scale corpus.
[0039] This embodiment requires modifying unasked questions from a pre-determined scale corpus based on the user's current emotional information and their acceptance of the scale questions in the current question-and-answer round. This modification ensures the revised scale questions better match the user's current emotional information and are more readily accepted by the user. Furthermore, when modifying unasked questions from the pre-determined scale corpus, modifications can also be made based on pre-constructed user images. This makes the revised scale questions more compatible with the user images, thereby increasing user acceptance of the scale questions. The construction of user images has been specifically described above and will not be repeated here.
[0040] In one specific implementation, based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, questions in a pre-determined scale corpus are modified to obtain an updated scale corpus. Alternatively, a pre-trained scale question generation model can be used. That is, historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round are input into the pre-trained scale question generation model, causing the model to modify questions according to pre-built prompts, resulting in an updated scale corpus and scale questions for the next question-and-answer round. When modifying questions according to the prompts, the scale question generation model also needs to analyze the user's current emotional information and the user's level of acceptance of the scale questions in the current question-and-answer round.
[0041] In this embodiment, a large language model is preferably used for the scale item generation model, and supervised fine-tuning training is performed on the large language model to obtain the trained scale item generation model. The supervised fine-tuning training of the large language model first requires collecting training samples, which include sample interaction data, sample feedback corresponding to sample scale questions, and a sample scale corpus. These samples also need to carry labels for the expected scale corpus, expected scale questions, expected sentiment information, and expected acceptance levels. The training samples are then input into the large language model, enabling it to determine the predicted sentiment information and the user's predicted acceptance level of the sample feedback corresponding to the sample scale questions, based on pre-constructed prompts and the sample interaction data and sample feedback. Then, based on the predicted sentiment information and the user's predicted acceptance level of the sample feedback, the model modifies the questions in the sample scale corpus to obtain the predicted scale corpus and the predicted scale questions for the next question-and-answer round. Finally, with the objectives of minimizing the differences between predicted and expected emotional information, the differences between predicted and expected acceptance, the differences between the predicted scale corpus and the expected scale corpus, and the differences between predicted scale questions and expected scale questions, the parameters of the large language model are adjusted to obtain the trained scale question generation model.
[0042] Specifically, pre-built prompts guide the scale item generation model in task execution. These prompts preferably include a task description block, an information input block, and a personalized instruction block. The task description block primarily describes the specific content of the question modification task performed by the scale item generation model. The information input block is mainly used to write the input information for the scale item generation model, such as historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round; it can also write pre-built user images. The personalized instruction block mainly describes the user-based personalized instructions in the scale item generation model to make the output content of the scale item generation model more user-friendly.
[0043] S102. Repeat the above operation to output scale questions in each question-and-answer round and obtain corresponding user feedback.
[0044] This embodiment, by repeating the above operations, can output scale questions in each question-and-answer round and obtain corresponding user feedback. Furthermore, in each question-and-answer round, the scale corpus updated in the previous round is modified to achieve another update. The scale questions for the next round are then determined from the updated scale corpus, until the question-and-answer termination condition is met. The termination condition can be set to reaching a preset number of question-and-answer rounds, or to outputting all scale questions in the scale corpus, etc.
[0045] S103. After the question-and-answer session ends, conduct psychological analysis based on the scale questions from each round of question-and-answer, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions from each round of question-and-answer, to obtain the user's psychological assessment results.
[0046] In this embodiment, after the question-and-answer session ends and the conditions for its conclusion are met, it is necessary to obtain the scale questions for each round of question-and-answer, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions for each round. Specifically, after modifying the scale questions in the scale corpus, this embodiment needs to record the correspondence between the modified scale questions and their corresponding original scale questions. This allows for the identification of the original scale questions corresponding to each modified scale question, enabling psychological analysis of the user feedback for each scale question according to pre-set assessment rules.
[0047] In this embodiment, after the question-and-answer session ends, a psychological analysis is conducted on the user based on the scale questions from each round of question-and-answer, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions from each round of question-and-answer. This analysis determines the user's psychological assessment results. The user's psychological assessment results include the user's psychological state type and corresponding level. For example, the psychological state type may include depression, anxiety, and normal, and the level is divided into high, medium, and low.
[0048] In this embodiment, psychological analysis can be implemented in the following ways: First, based on the scoring rules of the original scale questions corresponding to each scale question, the user feedback corresponding to each scale question is scored to obtain the final user psychological score. Based on the pre-set psychological score range corresponding to each psychological state type and level, the user's psychological assessment result is determined. Second, an analysis model is pre-trained. This analysis model preferably uses a large language model. Training samples are collected, including sample scale questions, the original scale questions corresponding to the sample scale questions, sample feedback corresponding to the sample scale questions, and pre-labeled expected psychological assessment results. The training samples are input into the analysis model to obtain predicted psychological assessment results. The parameters of the analysis model are adjusted with the goal of minimizing the difference between the predicted psychological assessment results and the expected psychological assessment results, resulting in a trained analysis model. The scale questions of each question-and-answer round, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions of each question-and-answer round are all input into the trained analysis model to obtain the user's psychological assessment result. Third, a machine learning model is pre-built, and the aforementioned training samples are used to train the machine learning model for psychological analysis. The training method is the same as that for the large language model. The trained analysis model is obtained, and the scale questions of each question-and-answer round, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions of each question-and-answer round are all input into the trained analysis model to obtain the user's psychological assessment results.
[0049] As described above, the psychological assessment method proposed in this application modifies a pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, resulting in an updated scale corpus. The scale questions for the next question-and-answer round are then determined from the updated corpus. After the question-and-answer session concludes, psychological analysis is performed based on the scale questions from each question-and-answer round, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions in each question-and-answer round, to obtain the user's psychological assessment result. Using the technical solution of this embodiment, the scale questions can be automatically determined, and psychological analysis can be automatically performed, achieving automated psychological assessment and improving the efficiency of psychological assessment. Furthermore, modifying the scale questions based on historical interaction data and current user feedback makes the scale questions more suitable for users, thereby improving the user experience of the psychological assessment.
[0050] As an optional implementation, this application also proposes a psychological testing method. See [link to relevant documentation]. Figure 2 As shown, before modifying the pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round to obtain an updated scale corpus, the method also includes the following steps: S201. Determine the current scheduling strategy based on pre-built user status data and current user feedback.
[0051] This embodiment pre-constructs user state data, which includes the user's current emotional information, user profile, and the user's current state time period. The user's current emotion is obtained through emotion recognition based on current user feedback. For example, information such as tone of voice and intonation in the current user feedback can be identified to determine the user's current emotional information. This current emotional information can include emotion type and emotion level; for example, the emotion type is irritability, and the emotion level is high. The user profile is determined based on historical interaction data. For example, basic information related to the user is extracted from historical interaction data to construct the user profile. This basic information includes name, age, gender, occupation, etc. The user's current state time period refers to the user's current state stage. For example, if the user is a student, the user's current state time period includes before studying, during studying, and after studying; if the user is an employee, the user's current state time period includes working, working overtime, and on vacation. The user's current state time period is also identified and extracted from historical interaction data.
[0052] In this embodiment, the user's current emotional information and the user's current time period in the user status data need to be updated in real time after each user feedback is received. The user profile in the user status data only needs to be updated when modification conditions are met. Meeting modification conditions means that the obtained user feedback does not match the current user profile; that is, when the obtained user feedback does not match the current user profile, the user profile is updated based on that feedback. For example, if the current user profile indicates that the user's occupation is a student, but the user feedback includes information that the user describes themselves as working at a certain company, then the user feedback does not match the current user profile, and the user's occupation in the user profile needs to be updated.
[0053] This embodiment needs to determine the current scheduling strategy based on pre-built user status data and current user feedback. The current scheduling strategy includes an assessment workflow strategy and an empathy interaction workflow strategy. The assessment workflow strategy indicates entering or continuing the psychological assessment process, while the empathy interaction workflow strategy indicates exiting the psychological assessment process and performing psychological empathy interaction. In this embodiment, this step specifically includes: First, based on pre-built user status data and current user feedback, determine the user's psychological state and assessment status.
[0054] In this embodiment, psychological state refers to whether the user is in a psychological crisis state. This embodiment can detect the user's psychological state based on current user feedback, that is, whether the user is in a psychological crisis state. A psychological crisis state includes tendencies towards extreme behavior, depression, or mental illness. This embodiment can pre-set keywords indicating a psychological crisis state, segment the current user feedback into words, and match each segment with the keywords. If the current user feedback contains a segment that matches the keyword, it indicates that the user is in a psychological crisis state; if the current user feedback does not contain a segment that matches the keyword, it indicates that the user is not in a psychological crisis state. This embodiment can also pre-build a psychological state detection model, input the current user feedback into the model, and directly output the psychological state indicating whether the user is in a psychological crisis state. The psychological state detection model can employ large language models, binary classification models, etc. The training method for the psychological state detection model can be supervised training, that is, pre-collecting sample feedback carrying psychological state labels. These psychological state labels are pre-labeled contents indicating whether a psychological crisis state is present. The sample feedback is input into the psychological state detection model to obtain the predicted psychological state. The parameters of the psychological state detection model are adjusted with the goal of minimizing the difference between the predicted psychological state and the psychological state label.
[0055] In this embodiment, the assessment status indicates whether the user has exited the assessment. This embodiment can determine the user's assessment status based on user status data and current user feedback. Specifically, the user's assessment status, i.e., whether to exit the assessment, is determined based on at least one of the following: the user's current emotional information in the user status data, the time period in which the user is currently in the assessment, and whether the current user feedback corresponds to the question in the current user feedback. For example, if the user's current emotional state is unhealthy but relatively calm, such as anxiety, and the user can maintain a relatively stable interaction during the assessment, then there is no need to exit the assessment. If the user's current emotional state is irritable, agitated, or otherwise unstable, and the user cannot maintain a stable interaction during the assessment, then the assessment needs to be exited. If the user's current state is during a time when it is inconvenient to take the assessment (e.g., while studying), then the assessment needs to be exited. If the user's current state is during a time when it is convenient to take the assessment (e.g., after studying), then there is no need to exit the assessment. If the current user feedback corresponds to the question, it means that the user is providing accurate feedback, and there is no need to exit the assessment. If the current user feedback does not correspond to the question, it means that the user is not interacting seriously and cannot provide accurate feedback, and then the assessment needs to be exited.
[0056] In addition, this embodiment can also divide the evaluation status into three states: entering evaluation, continuing evaluation, and exiting evaluation. Entering evaluation means that no evaluation has been conducted before. In this case, entering evaluation means that the evaluation starts from the first round of questions and answers. Continuing evaluation means that part of the evaluation has been conducted before. In this case, continuing evaluation means that the evaluation continues from the previous part of the evaluation.
[0057] Second, the current scheduling strategy is determined based on the user's psychological state and assessment status.
[0058] Based on the user's psychological state and assessment status determined in the above steps, the current scheduling strategy is determined according to the pre-set scheduling strategy selection rules. For example, if the user's psychological state indicates a psychological crisis and the assessment status indicates not exiting the assessment, then the current scheduling strategy is determined to be the assessment workflow strategy; if the user's psychological state indicates a psychological crisis and the assessment status indicates exiting the assessment, then the current scheduling strategy is determined to be the empathy interaction workflow strategy; if the user's psychological state indicates not a psychological crisis and the assessment status indicates exiting the assessment, then the current scheduling strategy is determined to be the empathy interaction workflow strategy; if the user's psychological state indicates not a psychological crisis and the assessment status indicates not exiting the assessment, then the current scheduling strategy is determined to be the assessment workflow strategy.
[0059] Furthermore, when the assessment status is divided into three states: entering assessment, continuing assessment, and exiting assessment, the pre-set scheduling strategy selection rules can be as follows: If the user's psychological state indicates a psychological crisis and the assessment status indicates entering assessment, then the current scheduling strategy is determined to be the assessment workflow strategy; if the user's psychological state indicates a psychological crisis and the assessment status indicates continuing assessment, then the current scheduling strategy is determined to be the assessment workflow strategy; if the user's psychological state indicates a psychological crisis and the assessment status indicates exiting assessment, then the current scheduling strategy is determined to be the empathy interaction workflow strategy; if the user's psychological state indicates no psychological crisis and the assessment status indicates entering assessment, then the current scheduling strategy is determined to be the empathy interaction workflow strategy; if the user's psychological state indicates no psychological crisis and the assessment status indicates continuing assessment, then the current scheduling strategy is determined to be the assessment workflow strategy; if the user's psychological state indicates no psychological crisis and the assessment status indicates exiting assessment, then the current scheduling strategy is determined to be the empathy interaction workflow strategy.
[0060] S202. If the current scheduling strategy is the evaluation workflow strategy, then output the pre-determined scale questions to obtain user feedback corresponding to the scale questions.
[0061] If the current scheduling strategy is determined to be an assessment workflow strategy, then pre-determined scale questions are output to obtain user feedback corresponding to those scale questions. If assessment has not yet begun, this is the first round of question-and-answer, where scale questions are selected from a pre-determined scale corpus. This scale corpus can be pre-defined to correspond to the scale questions for the first round of question-and-answer. If assessment has already been conducted, then the scale questions for the next round, determined in the previous round, are directly output as pre-determined scale questions. Furthermore, the scale corpus updated in the previous round is used as the pre-determined scale corpus for the current round.
[0062] This embodiment outputs the pre-determined scale questions, obtains user feedback on the scale questions, and then continues to execute steps S101-S103 in the above embodiment. Before outputting the scale questions in each question-and-answer round, this embodiment must be executed to determine the current scheduling strategy. Only if the current scheduling strategy is the assessment workflow strategy can the next question-and-answer round be continued.
[0063] As an optional implementation method, see [link to implementation details]. Figure 3 As shown, in another embodiment of this application, after determining the current scheduling strategy based on pre-built user state data and current user feedback, the following steps are also included: S301. If the current scheduling strategy is the empathic interaction workflow strategy, then determine and output the psychological empathic response based on the user status data and the current user feedback.
[0064] If the current scheduling strategy is determined to be an empathic interaction workflow strategy, it means that the user is not suitable for the assessment at this time and needs to temporarily withdraw from the assessment. Instead of outputting questionnaire questions, a psychological empathic response is determined and output based on the user's status data and current user feedback. This psychological empathic response is content that adapts to the user's status data and current user feedback, and can provide empathic comfort and mediation, promoting the user's emotional regulation. In this embodiment, a large language model can be used to determine the corresponding psychological empathic response based on the user's status data and current user feedback.
[0065] As an optional implementation, this application also proposes a psychological testing method. See [link to relevant documentation]. Figure 4 As shown, the method also includes the following steps: S401. Detect whether the user feedback corresponding to the scale question in the current question-and-answer round matches the pre-built user status data.
[0066] In this embodiment, after obtaining the user feedback corresponding to the scale questions in each question-and-answer round, it is necessary to check whether the user feedback corresponding to the scale questions in the current question-and-answer round matches the pre-built user status data. For example, if the user profile in the user status data indicates that the user's occupation is a student, but the user feedback includes the user introducing themselves as working in a certain company, then the user feedback does not match the user profile in the user status data.
[0067] S402. If the user feedback does not match the user status data, the user status data is updated based on the user feedback to obtain the updated user status data.
[0068] If the user feedback for the current question round does not match the pre-built user status data, the feedback needs to be analyzed. The information in the user feedback should replace the corresponding information in the current user status data to obtain updated user status data. For example, if the user profile in the user status data indicates the user's occupation is a student, but the user feedback includes information about working at a certain company, then the user's occupation should be determined based on the feedback, and the user's occupation in the feedback should replace the one in the current user status data.
[0069] S403. Modify the prompt instructions based on the updated user status data.
[0070] In this embodiment, the scale question generation model modifies the scale corpus and determines the scale questions for the next round of question and answer based on the pre-trained scale question generation model. When the scale question generation model is a large language model, it needs to execute the task according to the pre-built prompts. Since the pre-built prompts will set personalized instructions based on different users, after the user status data is updated, the personalized instructions in the prompts need to be modified accordingly according to the updated user status data. This is to ensure that the scale question generation model can better adapt to the user when performing the tasks of question modification and scale question determination, and further improve the user's assessment experience.
[0071] Furthermore, for other steps applying the large language model, it is also necessary to modify the prompts corresponding to the large language model based on the updated user state data. For example, based on the scale questions of each question-and-answer round, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions of each question-and-answer round, psychological analysis is performed. If the large language model is used, the personalized instructions in the prompts corresponding to the large language model also need to be modified according to the updated user state data. As another example, when the current scheduling strategy is an empathic interaction workflow strategy, a psychological empathic response is determined based on user state data and current user feedback. If the large language model is used, the personalized instructions in the prompts corresponding to the large language model also need to be modified according to the updated user state data.
[0072] Exemplary device Accordingly, this application also provides a psychological testing device, see [link to relevant documentation]. Figure 5 As shown, the device includes: The scale question determination module 100 is used to modify the questions in a pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, to obtain an updated scale corpus, and to determine the scale questions for the next question-and-answer round from the updated scale corpus. The scale question and answer module 110 is used to repeat the above operations to output scale questions in each question and answer round and obtain corresponding user feedback. The psychological analysis module 120 is used to conduct psychological analysis based on the scale questions of each question-and-answer round, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions of each question-and-answer round, to obtain the user's psychological assessment results.
[0073] As can be seen from the above description, the psychological assessment device proposed in this application can automatically determine the scale questions and automatically perform psychological analysis, thereby achieving automated psychological assessment and improving the efficiency of psychological assessment. Furthermore, by modifying the scale questions based on historical interaction data and current user feedback, the scale questions can be made more suitable for users, thus improving the user experience of psychological assessment.
[0074] As an optional implementation, another embodiment of this application discloses a scale problem determination module 100, specifically used for: Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, determine the user's current emotional information and the user's level of acceptance of the scale questions in the current question-and-answer round. Based on the user's current emotional information and the user's acceptance of the scale questions in the current question-and-answer round, questions not raised in the pre-determined scale corpus are modified to obtain an updated scale corpus.
[0075] As an optional implementation, another embodiment of this application discloses a psychological testing device, which further includes a strategy determination module and a feedback acquisition module.
[0076] The strategy determination module is used to determine the current scheduling strategy based on pre-built user status data and current user feedback; wherein, the user status data includes the user's current emotional information determined based on the current user feedback, the user profile determined based on historical interaction data, and the user's current state time period; The feedback acquisition module is used to output pre-determined scale questions to obtain user feedback corresponding to the scale questions if the current scheduling strategy is the assessment workflow strategy; the assessment workflow strategy indicates whether to enter the psychological assessment process or continue the psychological assessment process.
[0077] As an optional implementation, another embodiment of this application discloses a psychological testing device, which further includes an empathy module.
[0078] The empathy module is used to determine and output a psychological empathy response based on user status data and current user feedback if the current scheduling strategy is an empathy interaction workflow strategy. The empathy interaction workflow strategy means exiting the psychological assessment process and performing psychological empathy interaction.
[0079] As an optional implementation, another embodiment of this application discloses a strategy determination module, specifically used for: Based on pre-built user status data and current user feedback, the user's psychological state and assessment status are determined; the psychological state indicates whether the user is in a psychological crisis state, and the assessment status indicates whether the user has withdrawn from the assessment. The current scheduling strategy is determined based on the user's psychological state and assessment status.
[0080] As an optional implementation, another embodiment of this application discloses a scale problem determination module 100, which is further used for: The historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round are input into the pre-trained scale question generation model, so that the scale question generation model modifies the questions according to the pre-built prompts, and obtains the updated scale corpus and the scale questions for the next question-and-answer round. The scale item generation model is a large language model.
[0081] As an optional implementation, another embodiment of this application discloses a psychological testing device, which further includes a detection module, an update module, and a prompt instruction modification module.
[0082] The detection module is used to detect whether the user feedback corresponding to the scale question in the current question-and-answer round matches the pre-built user status data; The update module is used to update the user status data based on the user feedback if the user feedback does not match the user status data, so as to obtain the updated user status data. The prompt instruction modification module is used to modify prompt instructions based on the updated user status data.
[0083] The psychological testing device provided in this embodiment belongs to the same concept as the psychological testing method provided in the above embodiments of this application. It can execute the psychological testing method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the psychological testing method. Technical details not described in detail in this embodiment can be found in the specific processing content of the psychological testing method provided in the above embodiments of this application, and will not be repeated here.
[0084] Exemplary electronic devices Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 6 As shown, the device includes: Memory 200 and processor 210; The memory 200 is connected to the processor 210 and is used to store programs; The processor 210 is used to implement the psychological assessment method disclosed in any of the above embodiments by running the program stored in the memory 200.
[0085] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 220, an input device 230, and an output device 240.
[0086] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them: A bus can include a pathway for transmitting information between various components of a computer system.
[0087] Processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0088] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.
[0089] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.
[0090] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.
[0091] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.
[0092] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.
[0093] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of any of the psychological assessment methods provided in the above embodiments of this application.
[0094] Exemplary computer program products and storage media In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the psychological assessment methods according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.
[0095] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of this application. The programming languages include object-oriented programming languages such as Java and C++, as well as conventional procedural programming languages such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0096] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor in the steps of the psychological testing methods according to various embodiments of this application described in the "Exemplary Methods" section above.
[0097] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0098] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0099] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.
[0100] The modules and sub-modules in the various embodiments of the present application's devices and terminals can be merged, divided, and deleted according to actual needs.
[0101] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.
[0102] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.
[0103] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.
[0104] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0105] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0106] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0107] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A psychological assessment method, characterized in that, include: Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the questions in the pre-determined scale corpus are modified to obtain an updated scale corpus, and the scale questions for the next question-and-answer round are determined from the updated scale corpus. Repeat the above steps to output scale questions in each round of question-and-answer sessions and obtain corresponding user feedback; After the Q&A session concludes, psychological analysis is conducted based on the scale questions from each round of Q&A, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions from each round of Q&A, to obtain the user's psychological assessment results.
2. The psychological assessment method according to claim 1, characterized in that, Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the questions in a pre-determined scale corpus are modified to obtain an updated scale corpus, including: Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, determine the user's current emotional information and the user's level of acceptance of the scale questions in the current question-and-answer round. Based on the user's current emotional information and the user's acceptance of the scale questions in the current question-and-answer round, questions not raised in the pre-determined scale corpus are modified to obtain an updated scale corpus.
3. The psychological assessment method according to claim 1, characterized in that, Before modifying the questions in a pre-defined scale corpus based on historical interaction data and user feedback corresponding to the current question-and-answer round, to obtain the updated scale corpus, the following steps are also included: Based on pre-built user status data and current user feedback, the current scheduling strategy is determined; wherein, the user status data includes the user's current emotional information determined based on current user feedback, the user profile determined based on historical interaction data, and the user's current state time period; If the current scheduling strategy is an assessment workflow strategy, then a pre-determined scale question is output to obtain user feedback corresponding to the scale question; the assessment workflow strategy indicates entering the psychological assessment process or continuing the psychological assessment process.
4. The psychological assessment method according to claim 3, characterized in that, Also includes: If the current scheduling strategy is an empathic interaction workflow strategy, then based on the user status data and the current user feedback, a psychological empathic response is determined and output; wherein, the empathic interaction workflow strategy indicates exiting the psychological assessment process and performing psychological empathic interaction.
5. The psychological assessment method according to claim 3, characterized in that, Based on pre-built user status data and current user feedback, the current scheduling strategy is determined, including: Based on pre-built user status data and current user feedback, the user's psychological state and assessment status are determined; wherein, the psychological state is used to indicate whether the user is in a psychological crisis state, and the assessment status indicates whether the user has withdrawn from the assessment. The current scheduling strategy is determined based on the user's psychological state and assessment status.
6. The psychological assessment method according to claim 1, characterized in that, Based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, the scale corpus is modified according to a pre-determined scale corpus to obtain an updated scale corpus. The scale questions for the next question-and-answer round are then determined from the updated scale corpus, including: Historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round are input into a pre-trained scale question generation model, so that the scale question generation model modifies the questions according to the pre-built prompts, resulting in an updated scale corpus and scale questions for the next question-and-answer round. The scale item generation model is a large language model.
7. The psychological assessment method according to claim 6, characterized in that, Also includes: Check whether the user feedback corresponding to the scale question in the current question-and-answer round matches the pre-built user status data; If the user feedback does not match the user status data, the user status data is updated based on the user feedback to obtain updated user status data. The prompt instructions are modified based on the updated user status data.
8. A psychological testing device, characterized in that, include: The scale question determination module is used to modify the questions in a pre-determined scale corpus based on historical interaction data and user feedback corresponding to the scale questions in the current question-and-answer round, to obtain an updated scale corpus, and to determine the scale questions for the next question-and-answer round from the updated scale corpus. The questionnaire module is used to repeat the above operations to output questionnaire questions in each round of questioning and to obtain corresponding user feedback. The psychological analysis module is used to conduct psychological analysis after the question-and-answer session ends, based on the scale questions from each round of question-and-answer, the original scale questions corresponding to each scale question, and the user feedback corresponding to the scale questions from each round of question-and-answer, to obtain the user's psychological assessment results.
9. An electronic device, characterized in that, include: Memory and processor; The memory is connected to the processor and is used to store programs; The processor is configured to implement the psychological assessment method as described in any one of claims 1 to 7 by running a program in the memory.
10. A computer program product, characterized in that, It includes computer program instructions that, when executed by a processor, cause the processor to implement the psychological assessment method as described in any one of claims 1 to 7.