Personnel selection method based on human factor intelligence and wearable technology and related equipment

Abstract

The invention discloses a human factor intelligence and wearable technology-based personnel selection method and related equipment, and relates to the field of human factor engineering. The method comprises the following steps: acquiring multi-modal physiological data of a candidate person through wearable equipment, wherein the multi-modal physiological data comprises first physiological data of the candidate person in a resting state and second physiological data of the candidate person in a special equipment driving training state; determining physiological feature data of the candidate members according to the multi-modal physiological data; inputting the physiological feature data into a preset physiological evaluation model to obtain a physiological evaluation result of the candidate person; and determining whether the candidate person is selected as a special equipment driver based on the physiological evaluation result. According to the invention, drivers which can reach the standard after training can be identified and selected at the initial stage of driving training, so that the consumption or waste of training resources is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of human factors engineering, and in particular to a personnel selection method based on human factors intelligence and wearable technology and related equipment. Background Art

[0002] Training drivers of special equipment (such as aircraft, tanks, etc.) is a difficult and time-consuming task, requiring a lot of time, manpower, material resources, financial resources and other training resources.

[0003] The operation of special equipment is extremely complex and the requirements for drivers are also extremely strict. Training usually takes a long time, and in this process, a lot of manpower is needed, including a professional coaching team for detailed guidance and strict supervision; in terms of material resources, advanced training equipment, simulation equipment and real special equipment should be provided for practical operation; the financial investment is even greater, covering site rental, equipment maintenance, personnel salaries and other aspects.

[0004] However, even after such long and arduous training, some drivers still fail to meet the standards for various reasons. This not only means that the large amount of manpower invested in the early stage has not received the due return, and material resources such as training equipment have not been fully utilized, but also caused a huge waste of financial resources.

[0005] Therefore, there is an urgent need for a technical solution that can identify and select drivers who can meet the standards after training in the early stages of driving training. Summary of the invention

[0006] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a personnel selection method and related equipment based on human intelligence and wearable technology, which can identify and select drivers who can meet the standards after training in the early stage of driving training, thereby reducing the consumption or waste of training resources.

[0007] To achieve the above-mentioned objectives, in a first aspect, the present invention provides a personnel selection method based on human factors intelligence and wearable technology, comprising: obtaining multimodal physiological data of a candidate through a wearable device, the multimodal physiological data including first physiological data of the candidate in a resting state and second physiological data of the candidate in a special equipment driving training state; determining physiological characteristic data of the candidate based on the multimodal physiological data; inputting the physiological characteristic data into a preset physiological assessment model to obtain a physiological assessment result of the candidate; and determining whether the candidate is selected as a special equipment driver based on the physiological assessment result.

[0008] The present invention utilizes human intelligence and wearable technology to obtain multimodal physiological data through wearable devices, which can comprehensively and objectively reflect the physical condition of candidates. The combination of the first physiological data in a resting state and the second physiological data in a special equipment driving training state provides more abundant information for selection, avoiding the limitations of relying solely on traditional subjective judgment. The evaluation results are obtained using a preset physiological evaluation model, making the selection process more scientific and accurate. This helps to screen out more potential driver candidates in the early stage of training, reducing the waste of manpower, material resources and financial resources caused by non-compliance in the later stage. The method of this embodiment not only reduces the dependence on traditional long-term training, reduces time and cost, but also improves the scientificity and accuracy of the selection, ensuring that the selected drivers can perform at their best in actual operations, thereby improving overall operational capabilities and safety. In this way, the employer can use limited resources more efficiently, cultivate more outstanding special equipment operators, and reduce the waste of resources caused by non-compliance with training standards.

[0009] In combination with some embodiments of the first aspect, in some embodiments, the step of determining whether the candidate is selected as a special equipment driver based on the physiological assessment results includes: when determining the cognitive ability test results of the candidate, determining the assessment performance based on the cognitive ability test results and the physiological assessment results; judging whether the assessment performance meets the requirements; if so, determining that the candidate is selected as a special equipment driver.

[0010] By adopting the technical solution of the above embodiment, the assessment performance is determined by combining cognitive ability and physiological evaluation results. This comprehensive evaluation method improves the accuracy and comprehensiveness of the selection of special equipment drivers. It not only considers the physiological adaptability of candidates, but also their cognitive ability, which is crucial for performing complex tasks. This method helps to identify candidates who can still maintain the best performance in a high-pressure environment, thereby improving the efficiency and safety of special equipment operations.

[0011] In combination with some embodiments of the first aspect, in some embodiments, before the step of determining the physiological characteristic data of the candidate person based on the multimodal physiological data, it also includes: obtaining cognitive ability test data of the candidate person undergoing multiple cognitive ability tests; evaluating and processing the cognitive ability test data through a preset cognitive ability test model to obtain the cognitive ability test result.

[0012] By adopting the technical solution of the above embodiment, by introducing cognitive ability test before physiological assessment, the dimension of assessment is expanded, making the selection process more comprehensive. Obtaining cognitive ability test data and using the preset model for evaluation can more accurately predict the performance of candidates in actual operation. This method helps to find candidates who are not only physiologically adaptable but also have excellent cognitive abilities, providing a more scientific basis for the selection of special equipment drivers.

[0013] In conjunction with some embodiments of the first aspect, in some embodiments, the cognitive ability test data includes working memory, hand-eye coordination, visual tracking, visual breadth and speed perception, and the mathematical model used by the cognitive ability test model is a multivariate linear model, which is: y=β0+β1x1+β2x2+β3x3+β4x4+β45x5+ϵ; Among them, y is the result of the cognitive ability test, x1 to x5 are the normalized values ​​of the working memory, hand-eye coordination, visual tracking, visual span and speed perception, β0 is the intercept, β1 to β5 are regression coefficients, and ϵ is the error term.

[0014] The technical solution of the above embodiment is adopted to process cognitive ability test data by using a multivariate linear model, providing a quantitative and objective evaluation method. Each variable in the model corresponds to a regression coefficient, making the evaluation process more accurate and adjustable. This method can adjust the coefficient according to different environments and task requirements to adapt to different selection criteria, thereby ensuring that the most suitable special equipment driver is selected.

[0015] In combination with some embodiments of the first aspect, in some embodiments, before the step of evaluating and processing the cognitive ability test data through a preset cognitive ability test model to obtain the cognitive ability test results, it also includes: determining the environmental information when the candidate undergoes multiple cognitive ability tests; and adjusting the regression coefficient of the cognitive ability test model based on the environmental information.

[0016] By adopting the technical solution of the above embodiment, the accuracy of the evaluation is further improved by considering the impact of environmental factors on the cognitive ability test model. The regression coefficient is adjusted to reflect environmental changes, ensuring the consistency and reliability of the test results under different conditions. This method helps to select truly adaptable drivers in a changing environment and improves the robustness of the selection system.

[0017] In combination with some embodiments of the first aspect, in some embodiments, the training steps of the physiological assessment model include: obtaining multimodal physiological sample data of multiple special equipment drivers in a resting state and a special equipment driving training state, the multimodal physiological sample data being annotated with corresponding physiological assessment result labels; extracting physiological feature sample data from the multimodal physiological sample data; and using the physiological feature sample data to train the physiological assessment model to be trained to obtain the trained physiological assessment model.

[0018] By adopting the technical solution of the above embodiment, the training steps of the physiological assessment model are described in detail to ensure the scientificity and effectiveness of the model. By using multimodal physiological sample data labeled with physiological assessment results for training, the model can learn how to accurately predict the physiological adaptability of candidates. This method improves the accuracy of physiological assessment and provides strong support for selection decisions.

[0019] In combination with some embodiments of the first aspect, in some embodiments, before the step of obtaining multimodal physiological data of the candidate through a wearable device, it also includes: obtaining the prediction accuracy of the physiological assessment model during training; when the prediction accuracy reaches a set threshold, determining the selection time for the special equipment driver.

[0020] By adopting the technical solution of the above embodiment, the prediction accuracy of the physiological evaluation model is obtained before the selection, and a threshold is set to determine the selection time, so as to ensure that the model can be used for actual selection only after reaching a certain accuracy. This method avoids the use of unverified or inaccurate models, thereby improving the reliability and effectiveness of the selection process and ensuring that the selected drivers can meet the requirements of actual operation.

[0021] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation method of the first aspect or the second aspect.

[0022] In a third aspect, the present invention provides a computer-readable storage medium comprising instructions, which, when executed on the electronic device, causes the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0023] In a fourth aspect, the present invention provides a computer program product comprising instructions, which, when the computer program product is run on the electronic device, enables the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0024] It is understandable that the electronic device provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0025] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. By combining human intelligence with wearable technology, a comprehensive assessment of the multimodal physiological data and cognitive abilities of candidates is achieved. This approach not only improves the accuracy of selecting special equipment drivers, but also significantly improves the efficiency of the selection process by real-time monitoring and analysis of physiological and cognitive data. In this way, candidates who are physiologically and psychologically adapted to special equipment operation can be quickly identified, providing employers with a more scientific and accurate talent selection tool.

[0026] 2. It not only considers the physiological characteristics of candidates, but also covers cognitive ability tests, including working memory, hand-eye coordination and other dimensions. This multi-dimensional evaluation method can more comprehensively reflect the overall ability of candidates, ensuring that the selected drivers are not only physiologically adaptable, but also cognitively able to cope with complex driving tasks, thereby improving the overall quality and work efficiency of drivers.

[0027] 3. The impact of environmental factors on cognitive ability test results is also considered, and the regression coefficient of the evaluation model can be adjusted according to environmental information. This environmentally sensitive evaluation mechanism makes the selection process more flexible and can adapt to different test environments, ensuring that drivers with strong environmental adaptability are selected under variable actual operating conditions. In addition, the real-time feedback system mentioned in the present invention makes the training and evaluation process more dynamic, and the training difficulty and method can be adjusted according to the real-time performance of the candidates, further improving the selection and training effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 is a flow chart of a personnel selection method based on human intelligence and wearable technology according to an embodiment of the present invention; Figure 2 is a flow chart of another personnel selection method based on human intelligence and wearable technology according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the architecture of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0031] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0032] The embodiment of the present invention provides a personnel selection method based on human intelligence and wearable technology, which evaluates and selects special equipment drivers by combining wearable devices and artificial intelligence technology. It comprehensively considers people's physiological and cognitive characteristics, and how these characteristics match the requirements of special equipment operation. This embodiment uses wearable devices to collect multimodal physiological data and cognitive test results of candidates, and then applies the principles of human factors engineering to analyze these data to identify which physiological and cognitive factors are critical to driving performance. Then, artificial intelligence algorithms, such as machine learning and data mining techniques, are used to extract patterns and associations from these complex data sets, predict the operating performance of candidates, and make selection decisions based on this. This method not only improves the scientificity and accuracy of the selection, but also enhances the safety and effectiveness of special equipment by optimizing human-computer interaction.

[0033] Combine the following Figure 1 The personnel selection method of this embodiment is specifically described, and includes the following steps: Step 201: Acquire multimodal physiological data of a candidate through a wearable device.

[0034] Among them, the multimodal physiological data includes the first physiological data of the candidate in a resting state, and the second physiological data in a special equipment driving training state. The first physiological data refers to the baseline physiological data of the candidate in a resting state, such as heart rate, blood pressure, respiratory rate, etc., which are used to establish the individual's physiological baseline under stress-free conditions. The second physiological data refers to the physiological data of the candidate during special equipment driving training, including heart rate variability, electromyographic activity, galvanic skin response, etc. in a simulated or actual driving environment. These data reflect the candidate's physical reaction and adaptability under pressure and operational requirements. By comparing the physiological data in these two states, the candidate's psychological and physiological adaptability can be more comprehensively evaluated, providing a scientific basis for selecting suitable special equipment drivers.

[0035] Wearable devices refer to portable technology devices that can be worn directly on the human body or close to clothing, including but not limited to smart watches, fitness trackers, heart rate monitors, EEG caps, EMG sensors, skin electrical activity sensors, blood pressure monitors, blood oxygen saturation meters, etc. Wearable devices can capture human physiological data such as heart rate, blood pressure, body temperature, brain waves, EMG activity, etc. in real time through integrated sensor technology.

[0036] The wearable device transmits the collected multimodal physiological data wirelessly or stores it in the memory of the computer device. Afterwards, the computer device further analyzes and processes the multimodal physiological data.

[0037] Step 202: determining the physiological characteristic data of the candidate according to the multimodal physiological data.

[0038] Specifically, we first use data analysis technology, including signal processing, feature extraction and pattern recognition methods, to extract key physiological characteristic data from multimodal physiological data, such as heart rate variability indicators, brain wave frequency band power, electromyography signal strength, etc. These physiological characteristic data can reflect the candidate's stress response, concentration level, emotional state, physical fatigue level and other physiological states, and then construct a unique physiological characteristic profile for each candidate, providing a scientific basis for evaluating whether they are suitable to become special equipment drivers.

[0039] In this embodiment, to extract key physiological characteristic data from multimodal physiological data, the collected original physiological signals need to be preprocessed first, including filtering to remove noise and artifacts, and then the time domain signals are converted into frequency domain signals through signal processing techniques such as Fourier transform, so as to analyze parameters such as heart rate variability index and brain wave frequency band power. Next, feature extraction algorithms such as peak detection and power spectrum density estimation are used to quantitatively extract key indicators of heart rate variability from the processed signals, such as changes in RR intervals, the effect of breathing frequency on heart rate, etc.; power spectrum density of brain waves, that is, the power distribution of different frequency bands (such as δ waves, θ waves, α waves, β waves and γ waves); and amplitude and frequency characteristics of electromyographic signals, such as the root mean square value and power spectrum density of the signal.

[0040] Step 203: input the physiological characteristic data into a preset physiological evaluation model to obtain the physiological evaluation result of the candidate.

[0041] Specifically, the candidate's physiological characteristic data collected from wearable devices are first organized into a format suitable for input, and then the data is input into a preset physiological assessment model. The physiological assessment model uses AI (artificial intelligence) technology, usually based on machine learning or statistical analysis technology, and is trained to identify and evaluate the relationship between different physiological characteristics and driving performance. The physiological assessment model will analyze the input physiological characteristic data and calculate the candidate's physiological assessment results, which may include physiological adaptability scores, stress response indexes, fatigue levels, etc. The purpose of this process is to objectively evaluate the candidate's physiological state through scientific data analysis, and provide a basis for subsequent selection decisions.

[0042] In some embodiments, the training steps of the physiological assessment model include the following: (1) Obtain multimodal physiological sample data of multiple special equipment drivers in a resting state and a special equipment driving training state, wherein the multimodal physiological sample data are annotated with corresponding physiological test result labels.

[0043] First, it is necessary to collect a large number of multimodal physiological data of people who have become special equipment drivers in different states. These data will be used as multimodal physiological sample data. The resting state can include their heart rate, blood pressure, EEG and other physiological indicators when they are quiet and resting. The special equipment driving training state covers their various physiological reaction data during the actual operation training process, such as changes in physiological indicators when driving an airplane for simulated flight training and tanks for off-road training. The source of these data can be collected through professional wearable devices, such as heart rate monitoring bracelets, EEG monitoring helmets, etc.

[0044] At the same time, in order to make these data have practical reference value, it is necessary to annotate each sample data in the multimodal physiological sample data with the corresponding physiological evaluation result label. This label can be given by professional evaluators based on the performance of these drivers in actual training and work, such as excellent, good, qualified, unqualified and other different levels of labels, so that the subsequent model can learn the corresponding relationship between different physiological data and the final performance.

[0045] (2) Extracting physiological feature sample data from the multimodal physiological sample data.

[0046] This step is mainly used for data preprocessing and feature engineering. For data in a resting state, features such as average heart rate, heart rate variability, and blood pressure stability can be extracted. For example, the average heart rate value over a period of time is calculated, and the standard deviation of heart rate changes is analyzed to measure heart rate variability. For data in a special equipment driving training state, features such as the peak heart rate, blood pressure rise, and specific frequency band power of EEG activity under specific operating tasks can be extracted. At the same time, the relationship characteristics between different physiological indicators can also be considered, such as the correlation between heart rate and blood pressure, and the coordinated changes in EEG activity and muscle tension. Through these feature extraction processes, the original multimodal physiological sample data is converted into more concise and representative physiological feature sample data to prepare for model training.

[0047] (3) Using the physiological characteristic sample data to train the physiological evaluation model to be trained, to obtain the trained physiological evaluation model.

[0048] Specifically, after the extracted physiological characteristic sample data is obtained, the physiological evaluation model can be trained. First, a suitable machine learning algorithm is selected as the physiological evaluation model to be trained, such as support vector machine, random forest, neural network, etc. The extracted physiological characteristic sample data is used as input, and the corresponding physiological evaluation result label is used as output. By continuously adjusting the parameters of the model, the model can predict the corresponding physiological evaluation results as accurately as possible based on the input physiological characteristic data.

[0049] During the training process, methods such as cross-validation can be used to evaluate the performance of the model and prevent overfitting. After multiple iterations of training, when the performance of the model on the validation set reaches a certain requirement, the trained physiological evaluation model is obtained. This model can be used to analyze the multimodal physiological data of new candidates and predict whether they are suitable to become special equipment drivers. Step 204: Determine whether the candidate is selected as a special equipment driver based on the physiological evaluation result.

[0050] Specifically, the physiological assessment results can be compared with the established qualification standards, such as whether the physiological adaptability score meets the minimum requirements, whether the stress response is within an acceptable range, etc. If the candidate's assessment results meet these standards, it can be determined that he or she will be selected as a special equipment driver and join the special equipment driver training team; otherwise, the candidate will be eliminated or recommended for further evaluation and training. This step ensures the scientificity and fairness of the selection process and maximizes the possibility of selecting excellent drivers.

[0051] This embodiment adopts a personnel selection method based on AI and wearable devices, which can effectively improve the selection efficiency and accuracy of special equipment drivers and reduce resource waste. Multimodal physiological data can be obtained through wearable devices, which can comprehensively and objectively reflect the physical condition of candidates. The combination of the first physiological data in a resting state and the second physiological data in a special equipment driving training state provides more abundant information for selection, avoiding the limitations of relying solely on traditional subjective judgment. The evaluation results are obtained using a preset physiological evaluation model, making the selection process more scientific and accurate. This helps to screen out more potential driver candidates in the early stage of training and reduce the waste of manpower, material resources and financial resources caused by non-compliance in the later stage. The method of this embodiment not only reduces the dependence on traditional long-term training, reduces time and cost, but also improves the scientificity and accuracy of the selection, ensuring that the selected drivers can perform at their best in actual operations, thereby improving overall operational capabilities and safety. In this way, employers can use limited resources more efficiently, cultivate better special equipment operators, and reduce the waste of resources caused by non-compliance with training standards.

[0052] Combine the following Figure 2 , further introducing the method of the embodiment of the present invention, comprising the following steps: Step 301, obtaining the prediction accuracy of the physiological assessment model during training.

[0053] In this step, the performance of the physiological assessment model during the training phase needs to be evaluated, specifically by calculating the prediction accuracy of the model for the training data set. This involves using the model to predict the physiological characteristic sample data in the training set and comparing its prediction results with the actual physiological assessment result labels. The prediction accuracy refers to the proportion of samples predicted correctly by the model to the total number of samples. This indicator can reflect the model's ability to identify and predict physiological states based on training data. Obtaining this accuracy is the key to evaluating the effectiveness and reliability of the model, and provides an important reference for subsequent model optimization and application.

[0054] Step 302: When the prediction accuracy reaches a set threshold, the special equipment driver selection time is determined.

[0055] This step is to determine when to select special equipment drivers based on the prediction accuracy of the physiological assessment model. A prediction accuracy threshold is set. When the physiological assessment model reaches or exceeds this threshold during training, it indicates that the model has sufficient prediction ability to accurately assess the physiological adaptability of the candidate. At this point, it can be determined that the model is ready for actual driver selection.

[0056] This threshold is set based on the requirements for model performance and the needs of actual application scenarios to ensure the scientificity and effectiveness of the selection process. Once the model's prediction accuracy meets or exceeds this standard, you can start using the model to evaluate candidates and determine their selection time accordingly.

[0057] Step 303: Acquire the first physiological data of the candidate in a resting state through the wearable device.

[0058] This step may refer to step 201 of the aforementioned embodiment and will not be described in detail here.

[0059] Step 304: Acquire cognitive ability test data of the candidate taking multiple cognitive ability tests.

[0060] Among them, cognitive ability tests may include but are not limited to working memory tests, hand-eye coordination tests, visual tracking tests, visual span tests, and speed perception tests. Working memory tests are used to measure the candidate's ability to store and process information in a short period of time; hand-eye coordination tests are used to assess the candidate's ability to coordinate hand movements with visual information; visual tracking tests are used to test the candidate's ability to track moving objects; visual span tests are used to measure the amount of information a candidate can notice in a single visual scan; and speed perception tests are used to assess the candidate's ability to perceive and estimate speed.

[0061] In this step, candidates will participate in a series of standardized cognitive ability tests designed to assess basic cognitive skills related to special equipment driving. The results of these cognitive ability tests will serve as cognitive ability test data, providing an important basis for subsequent cognitive ability assessments.

[0062] Step 305: evaluate and process the cognitive ability test data using a preset cognitive ability test model to obtain the cognitive ability test result.

[0063] Among them, cognitive ability test data include working memory, hand-eye coordination, visual tracking, visual span and speed perception.

[0064] After collecting the candidates' cognitive ability test data, the data will be analyzed and evaluated using a preset cognitive ability test model. The cognitive ability test model can be built based on machine learning or statistical methods, and can comprehensively evaluate the candidate's cognitive ability level based on test results such as working memory, hand-eye coordination, visual tracking, visual breadth, and speed perception. The cognitive ability test model will process each test data, identify the candidate's strengths and weaknesses in each cognitive dimension, and ultimately generate a comprehensive cognitive ability test result. This result will reflect the candidate's overall cognitive performance and provide a scientific cognitive ability assessment for the selection of special equipment drivers.

[0065] In some embodiments, the mathematical model used by the cognitive ability test model is a multivariate linear model, which is: y=β0+β1x1+β2x2+β3x3+β4x4+β45x5+ϵ; Among them, y is the result of the cognitive ability test, specifically the total score of the cognitive ability test, which is an indicator that comprehensively reflects the candidate's cognitive ability.

[0066] x1 to x5 are respectively the normalized values ​​of the working memory, the hand-eye coordination, the visual tracking, the visual span and the speed perception, which can be compared and calculated on the same scale or dimension; x1 to x5 are the independent variables in the multivariate linear model.

[0067] β0 is the intercept, representing the baseline cognitive score when all independent variables are zero.

[0068] β1 to β5 are the regression coefficients of the respective variables, which quantify the contribution of each cognitive dimension to the total score.

[0069] ϵ is the error term, reflecting individual differences that are not explained by the model.

[0070] Through this multivariate linear model, it is possible to assess each candidate's performance on different cognitive dimensions and combine these performances to predict their overall cognitive ability.

[0071] In some embodiments, different environmental conditions, such as temperature, altitude, environmental noise, etc., may also affect the cognitive ability test results, so the cognitive ability test model needs to be adjusted first, and then step 305 is performed.

[0072] Firstly, the environmental information when the candidate is taking multiple cognitive ability tests is determined; and then the regression coefficient of the cognitive ability test model is adjusted based on the environmental information.

[0073] Specifically, it is necessary to first record in detail the specific environmental conditions when each candidate takes multiple cognitive ability tests, including key factors such as temperature, altitude, and ambient noise. This environmental information is crucial to understanding the test results because they may directly affect the candidate's performance. For example, extreme temperatures may affect concentration, high altitudes may cause hypoxia and thus affect cognitive function, and excessive noise levels may interfere with working memory and concentration. By accurately recording these environmental parameters, we can analyze test results more accurately and identify the potential impact of environmental factors on cognitive performance.

[0074] After collecting detailed environmental information, the next step is to adjust the regression coefficients of the cognitive ability test model based on this data. This step involves using statistical methods, such as multiple regression analysis, to evaluate the impact of different environmental factors on cognitive test results and adjust the regression coefficients in the model accordingly. For example, if the analysis shows that candidates tested at higher altitudes generally perform worse on visual tracking tasks, it may be necessary to increase the difficulty weight of the visual tracking task (i.e., adjust the corresponding regression coefficient) to ensure that the model can accurately reflect the cognitive ability of candidates under standard testing conditions. In this way, it can be ensured that the model not only takes into account the individual's cognitive performance, but also the impact of environmental factors, thereby improving the fairness and accuracy of the selection process.

[0075] On the other hand, this embodiment adjusts the cognitive ability test model to take into account the impact of different environmental conditions, which can also more accurately evaluate the environmental adaptability of candidates. The purpose of this is to ensure that the selected drivers not only perform well in ideal or standard environments, but also maintain efficient cognitive functions and operational capabilities in actual working environments, such as complex conditions such as extreme temperatures, high altitudes or high noise. In this way, employers can select drivers who can maintain optimal performance even in the most challenging environmental conditions, thereby improving overall operational efficiency and safety. This comprehensive assessment method helps to identify candidates with stronger environmental adaptability and psychological resilience, enabling them to make quick and accurate decisions in changeable and stressful actual working environments.

[0076] Step 306: obtaining second physiological data of the candidate during the special equipment driving training state through the wearable device.

[0077] This step may refer to step 201 of the aforementioned embodiment and will not be described in detail here.

[0078] Step 307: Combine the first physiological data and the second physiological data into multimodal physiological data.

[0079] Specifically, data preprocessing techniques such as synchronization, alignment, and normalization are used to ensure that the first physiological data and the second physiological data are comparable in time series and dimension. Then, feature extraction techniques are used to identify key physiological indicators such as heart rate, blood pressure, respiratory rate, brain wave patterns, myoelectric activity, etc. from the two sets of data. Finally, through data fusion technology, these indicators are merged into a comprehensive multimodal physiological data set, which can provide detailed information about the physiological state and reaction of candidates in different states, providing a scientific basis for further physiological feature analysis and driver selection.

[0080] Step 308: Determine the physiological characteristic data of the candidate according to the multimodal physiological data.

[0081] This step may refer to step 202 of the aforementioned embodiment and will not be described in detail here.

[0082] Step 309: input the physiological characteristic data into a preset physiological evaluation model to obtain the physiological evaluation result of the candidate.

[0083] This step may refer to step 203 of the aforementioned embodiment, and will not be described in detail here.

[0084] Step 310, when the cognitive ability test result of the candidate is determined, the assessment performance is determined according to the cognitive ability test result and the physiological assessment result.

[0085] Specifically, a comprehensive cognitive test score of the cognitive ability test can be obtained based on the cognitive ability test results, which reflects the overall performance of the candidate in multiple cognitive dimensions.

[0086] Similarly, the physiological assessment results include physiological adaptability score, stress response index, fatigue level, etc. These data are also comprehensively evaluated to obtain a physiological assessment score for the physiological assessment results.

[0087] Then, based on the predetermined weight of each score for the importance of the driving task, the two scores are weighted and summed, that is, the calculation formula is: Assessment performance score = comprehensive cognitive test score × cognitive weight + physiological test certificate × physiological weight; the sum of the cognitive weight and the physiological weight is 1, thus obtaining the assessment performance score of each candidate. This assessment performance score integrates the performance of both cognitive and physiological aspects, providing a comprehensive evaluation basis for the final selection decision.

[0088] Step 311, determining whether the assessment performance meets the standards.

[0089] Specifically, the candidate's assessment performance score is compared to a pre-set passing score, which is based on the requirements of the special equipment driver position and historical performance data.

[0090] If the candidate's performance score is higher than or equal to the passing score, the candidate's performance score is considered to be up to standard, which means that the candidate's performance in cognitive ability and physiological adaptability has reached the standard for performing the driving task. Then, the process proceeds to step 312.

[0091] If a candidate's performance score is lower than the passing score, the candidate is considered eliminated.

[0092] Step 312, determining that the candidate is selected as a special equipment driver.

[0093] Once the candidate's performance is judged to be up to standard, they are formally selected as special equipment drivers. This decision is based on the candidate's performance in cognitive ability and physiological adaptability, which are quantified through the assessment performance score. If the candidate's score meets or exceeds the established performance standards, it shows that they have the ability to safely and effectively operate special equipment in a high-pressure and complex environment. Therefore, these candidates will be selected as special equipment drivers and enter the next step of professional training or directly participate in actual combat operations. This selection process ensures that only the best candidates can take on this critical role, thereby improving overall operational efficiency and safety.

[0094] The personnel selection method based on AI and wearable devices in this embodiment is designed specifically for selecting special equipment drivers. Multimodal physiological data of candidates in a resting state and a special equipment driving training state are collected through wearable devices, including first physiological data and second physiological data. These data are used to determine the physiological characteristic data of the candidates, and then input into a preset physiological evaluation model to obtain physiological evaluation results. In addition, the scheme also involves conducting multiple cognitive ability tests on candidates, including working memory, hand-eye coordination, visual tracking, visual breadth, and speed perception, and using a multivariate linear model to evaluate and process these test data to obtain cognitive ability test results. Environmental information, such as temperature, altitude, and ambient noise, is also taken into account to adjust the regression coefficient of the cognitive ability test model to ensure the accuracy of the evaluation.

[0095] The training steps of the physiological evaluation model include obtaining multimodal physiological sample data of multiple special equipment drivers, which are annotated with corresponding physiological evaluation result labels, and then extracting physiological feature sample data from them to train the physiological evaluation model to be trained. During the model training phase, the prediction accuracy of the model is also obtained, and the selection time of the special equipment driver is determined when the set threshold is reached.

[0096] Finally, the candidate's assessment performance is determined by combining the physiological assessment results and cognitive ability test results to determine whether it meets the standards. If the assessment performance meets the standards, the candidate is selected as a special equipment driver. This comprehensive technical solution uses scientific methods to combine data from both physiological and cognitive dimensions to improve the accuracy and efficiency of the selection process, ensuring that the selected special equipment drivers have stronger environmental adaptability and higher psychological and physiological qualities to meet high-standard operating requirements.

[0097] The above method of this embodiment is specifically performed by an electronic device. The following describes this electronic device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0098] It should be noted that Figure 3 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0099] like Figure 3As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In RAM 403, various programs and data required for system operation are also stored. CPU 401, ROM 402 and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0100] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0101] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0102] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0104] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0105] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.

[0106] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0107] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0108] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A personnel selection method based on human intelligence and wearable technology, characterized in that: include: Acquiring multimodal physiological data of the candidate through a wearable device, wherein the multimodal physiological data includes first physiological data of the candidate in a resting state and second physiological data of the candidate in a special equipment driving training state; Determining physiological characteristic data of the candidate person according to the multimodal physiological data; Inputting the physiological characteristic data into a preset physiological evaluation model to obtain the physiological evaluation results of the candidate; Determine whether the candidate is selected as a special equipment driver based on the physiological evaluation result.

2. The method according to claim 1, characterized in that The step of determining whether the candidate is selected as a special equipment driver based on the physiological evaluation result comprises: When the cognitive ability test result of the candidate is determined, determining the assessment performance according to the cognitive ability test result and the physiological assessment result; Determine whether the assessment performance meets the standards; If so, it is determined that the candidate is selected as a special equipment driver.

3. The method according to claim 2, characterized in that Before the step of determining the physiological characteristic data of the candidate person according to the multimodal physiological data, the method further includes: Obtaining cognitive ability test data of the candidate taking multiple cognitive ability tests; The cognitive ability test data is evaluated and processed by a preset cognitive ability test model to obtain the cognitive ability test result.

4. The method according to claim 3, characterized in that The cognitive ability test data includes working memory, hand-eye coordination, visual tracking, visual breadth and speed perception. The mathematical model used in the cognitive ability test model is a multivariate linear model, which is: y=β0+β1x1+β2x2+β3x3+β4x4+β45x5+ϵ; Wherein, y is the cognitive ability test result, x1 to x5 are the normalized values ​​of the working memory, the hand-eye coordination, the visual tracking, the visual span and the speed perception, β0 is the intercept, β1 to β5 are regression coefficients, and ϵ is the error term.

5. The method according to claim 3, characterized in that: Before the step of evaluating the cognitive ability test data by using a preset cognitive ability test model to obtain the cognitive ability test result, the method further includes: determining information about the environment in which the candidate is to perform a plurality of cognitive ability tests; The regression coefficient of the cognitive ability test model is adjusted based on the environmental information.

6. The method according to any one of claims 1 to 5, characterized in that: The training steps of the physiological evaluation model include: Acquire multimodal physiological sample data of a plurality of special equipment drivers in a resting state and a special equipment driving training state, wherein the multimodal physiological sample data is annotated with corresponding physiological test result labels; Extracting physiological characteristic sample data from the multimodal physiological sample data; The physiological characteristic sample data is used to train the physiological evaluation model to be trained to obtain the trained physiological evaluation model.

7. The method according to claim 1, characterized in that Before the step of acquiring the multimodal physiological data of the candidate through the wearable device, the method further includes: Obtaining the prediction accuracy of the physiological evaluation model during training; When the prediction accuracy reaches a set threshold, the special equipment driver selection time is determined.

8. An electronic device, characterized in that: including one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on an electronic device, the electronic device is caused to execute the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images