A product optimization method, device, equipment and medium for insurance services

Abstract

The application relates to the field of financial technology and medical health, and discloses a product optimization method, device, equipment and medium for insurance services, which comprises the following steps: processing electroencephalogram signals collected in real time in user cognitive training to obtain a neural activation index, obtaining a difficulty coefficient according to the neural activation index, adjusting the difficulty level of the training according to the difficulty coefficient, returning to the step of real-time collection until the training is completed, obtaining a current training score according to the neural activation index and the difficulty coefficient in the training process, and triggering a premium incentive mechanism of an insurance product corresponding to the cognitive training of the user according to the historical training score and the current training score. The application can be applied to the premium optimization scene of insurance products in the field of financial technology and medical health, the premium incentive mechanism is dynamically triggered through the cognitive training data of the user, the dynamic correlation between the premium and the actual cognitive condition of the user is realized, the matching degree of the premium and the user is improved, and the accuracy of insurance guarantee is enhanced.

Description

Technical Field

[0001] This invention relates to the fields of data processing, financial insurance, and healthcare, and in particular to a product optimization method, apparatus, equipment, and medium for insurance services. Background Technology

[0002] In recent years, with the continuous improvement of residents' risk awareness and insurance demand, insurance products have been widely used in areas such as old-age security and health care. In the health care and elderly care scenario, cognitive decline insurance products, such as cognitive care insurance, are mainly used to provide the elderly with long-term care expenses and economic losses risk protection due to cognitive decline, effectively filling the protection gap for the elderly with cognitive impairment and meeting the social elderly care service needs in the context of population aging.

[0003] However, existing insurance products related to cognitive decline generally follow the traditional model of fixed premiums and post-event claims. Specifically, a fixed premium can be determined based on the results of a static health assessment at the initial stage of insurance, and the insurance benefit can be paid in a lump sum or in installments after the insured is diagnosed with cognitive impairment. However, this model has obvious drawbacks. Individual cognitive health status is dynamic. The fixed judgment criteria and uniform protection standards based on static health assessments lead to a mismatch between risk and premium, making it impossible to adapt to the phased fluctuations in individual cognitive health. It is difficult to differentiate and cover the potential risks of cognitive decline for different groups of people, the protection plan lacks dynamic adaptability, the protection resources are allocated irrationally, it is difficult to prevent cognitive health risks in advance, and the overall accuracy and actual protective effect of the protection are insufficient.

[0004] Therefore, optimizing insurance product premiums to improve their suitability for users has become an urgent issue to be addressed. Summary of the Invention

[0005] This invention provides a product optimization method, apparatus, equipment, and medium for insurance services, to address the problem of how to optimize insurance product premiums to improve the suitability of premiums to users.

[0006] Firstly, a product optimization method for insurance services is provided, including: During cognitive training, the user's EEG signals are collected in real time, and the EEG signals are processed to obtain a neural activation index that characterizes the user's brain activity level. Based on the neural activation index, a difficulty coefficient representing the degree of difficulty of the cognitive training is obtained, and the degree of difficulty of the cognitive training is adjusted according to the difficulty coefficient. Return to the step of real-time acquisition of the user's EEG signals until the cognitive training ends. Based on all the neural activation indices and the difficulty coefficient during the cognitive training process, obtain the current training score corresponding to the cognitive training. Obtain the user's historical training score during the historical cognitive training process, and determine the user's total training score based on the historical training score and the current training score; Based on the total training score, the premium incentive mechanism for the insurance product corresponding to the cognitive training is triggered for the user.

[0007] Secondly, a product optimization device for insurance services is provided, comprising: The data acquisition module is used to collect the user's electroencephalogram (EEG) signals in real time during cognitive training, process the EEG signals, and obtain a neural activation index that characterizes the degree of neural activity in the user's brain. The first calculation module is used to obtain a difficulty coefficient representing the difficulty level of the cognitive training based on the neural activation index, and to adjust the difficulty level of the cognitive training based on the difficulty coefficient. The second calculation module is used to return to the step of real-time acquisition of the user's EEG signals until the cognitive training ends, and to obtain the current training score corresponding to the cognitive training based on all the neural activation indices and the difficulty coefficient during the cognitive training process. The third calculation module is used to obtain the user's historical training score during the historical cognitive training process, and determine the user's total training score based on the historical training score and the current training score. The incentive module is used to trigger the premium incentive mechanism for the insurance product corresponding to the cognitive training for the user based on the total training score.

[0008] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the product optimization method for insurance services described in the first aspect.

[0009] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the product optimization method for insurance services described in the first aspect.

[0010] The aforementioned product optimization method, apparatus, computer equipment, and storage medium for insurance services determine the user's neural activation index based on real-time collected EEG signals during cognitive training. The difficulty level of the cognitive training is adjusted based on the neural activation index, and the process returns to the step of real-time collection of the user's EEG signals until the cognitive training ends. The current training score is obtained based on all neural activation indices and difficulty coefficients during the cognitive training process. The total training score is obtained based on the user's historical training score and the current training score. Based on the total training score, a premium incentive mechanism for the corresponding insurance product is triggered for the user.

[0011] By dynamically adjusting the training difficulty based on real-time EEG signals, the cognitive training can be kept within the user's effective workload range to improve brain health, while objectively quantifying cognitive engagement and progress. The total training score generated dynamically triggers the premium incentive mechanism for the insurance policy purchased by the user for cognitive training, realizing a dynamic correlation between the premium and the user's actual cognitive status. This improves the matching degree between the premium and the user, enhances the accuracy of insurance risk protection, and achieves a win-win situation for both user health improvement and insurance company risk control optimization. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of an application environment for a product optimization method for insurance services provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart illustrating a product optimization method for insurance services provided in Embodiment 2 of the present invention; Figure 3 This is a flowchart illustrating a product optimization method for insurance services provided in Embodiment 3 of the present invention. Figure 4 This is a flowchart illustrating a product optimization method for insurance services provided in Embodiment 4 of the present invention. Figure 5 This is a flowchart illustrating a product optimization method for insurance services provided in Embodiment 5 of the present invention. Figure 6 This is a schematic diagram of a product optimization device for insurance services provided in Embodiment Six of the present invention; Figure 7This is a schematic diagram of the structure of a computer device provided in Embodiment 7 of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] The product optimization method for insurance services provided in Embodiment 1 of this invention can be applied to, for example... Figure 1 In the application environment of the server, specifically, the product optimization method for insurance services is applied in an optimization system, which includes, for example, the following: Figure 1 The diagram illustrates a client and server that communicate over a network to optimize insurance product premiums and improve their suitability for users. The client, also known as the user terminal, is the program that provides local services to the customer, corresponding to the server. The client can be installed on, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0016] For example, in the context of elderly care within healthcare, during cognitive training for seniors, a neural activation index is determined based on real-time collected EEG signals. This index is then used to adjust the difficulty level of the cognitive training until the training concludes, yielding a training score for the current session. This current score, combined with historical training scores, results in a total training score. This total score triggers a premium incentive mechanism for insurance products related to cognitive decline (such as cognitive health insurance). This approach ensures that cognitive training remains within the senior's effective workload range to enhance brain health, while objectively quantifying their cognitive engagement and progress. The generated total training score dynamically triggers the premium incentive mechanism for cognitive decline-related insurance products, achieving a dynamic correlation between premiums and the senior's actual cognitive status. This improves the matching degree between premiums and users, enhances the accuracy of insurance risk protection, and achieves a win-win situation for both improved health for seniors and optimized risk control for insurance companies.

[0017] Please see Figure 2 The diagram shown is a flowchart illustrating a product optimization method for insurance services provided in Embodiment 2 of the present invention. This method is applied to... Figure 1 Taking the server in the example, the following steps are included: Step S201: During the cognitive training process, the user's EEG signals are collected in real time, and the EEG signals are processed to obtain the neural activation index, which represents the degree of neural activity in the user's brain.

[0018] Step S202: Obtain the difficulty coefficient representing the degree of difficulty in cognitive training based on the neural activation index, and adjust the degree of difficulty in cognitive training based on the difficulty coefficient.

[0019] In this embodiment, cognitive training can refer to a series of standardized task exercises aimed at improving or maintaining specific cognitive functions such as attention, memory, and executive function. For example, specific training tasks such as image recognition, short-term memory memorization, logical sequencing, attention focusing, and contextual recall. EEG signals can refer to bioelectrical signals recorded through scalp electrodes that reflect the electrophysiological activity of neuronal groups in the cerebral cortex. The neural activation index can refer to an indicator based on the quantitative representation of the user's overall excitation level and neural mobilization intensity in the cerebral cortex during cognitive training. The difficulty coefficient can refer to an indicator that combines the neural activation index to quantitatively represent the user's subjective acceptance of the cognitive training task and the objective workload level.

[0020] Specifically, during cognitive training, users can wear flexible electrode caps, and the electrode array in the caps can collect the user's EEG signals in real time. The EEG signals are then processed by filtering, frequency band decomposition, and feature quantification to obtain a neural activation index. Based on the neural activation index, the difficulty level of cognitive training can be adjusted.

[0021] Step S203: Return to the step of real-time acquisition of the user's EEG signals until the cognitive training ends. Based on all neural activation indices and difficulty coefficients during the cognitive training process, obtain the current training score corresponding to the cognitive training.

[0022] In this embodiment, the current training score can refer to a comprehensive evaluation value based on the neural activation level and task difficulty throughout the training process, used to quantitatively assess the user's overall performance in this cognitive training.

[0023] Specifically, after adjusting the difficulty level of cognitive training according to the difficulty coefficient, the process returns to the step of real-time acquisition of the user's EEG signals in step S201 above until the cognitive training ends. Effective neural activation indices exceeding the preset second threshold are determined from all neural activation indices. For any effective neural activation index, the duration of the effective neural activation index during the cognitive training process is determined. The difficulty coefficient corresponding to each effective neural activation index and the number of consecutive training cycles in the user's historical cognitive training process are obtained. Based on the duration of all effective neural activation indices, the difficulty coefficient corresponding to the corresponding effective neural activation index, and the number of consecutive training cycles, the current training score is obtained.

[0024] The preset second threshold can refer to the value that the neural activation index needs to reach during effective training, and the effective neural activation index can refer to the neural activation index that exceeds the preset second threshold.

[0025] That is, in obtaining the current training score, based on the number of consecutive training cycles in the user's historical cognitive training process, that is, the total number of training cycles that the user has completed sequentially without long-term interruption in the historical training process, each training cycle can include training days and non-training days, a historical time weight is determined to encourage the user's continuous participation. For any effective neural activation index, the duration of the effective neural activation index is multiplied by the corresponding difficulty coefficient and the historical time weight to obtain the training score representing the time corresponding to the effective neural activation index. The training scores corresponding to the time of all effective neural activation indices are summed to obtain the current training score of the cognitive training.

[0026] Step S204: Obtain the user's historical training score during the historical cognitive training process, and determine the user's total training score based on the historical training score and the current training score; Step S205: Based on the total training score, trigger the premium incentive mechanism for the corresponding insurance product for the user's cognitive training.

[0027] In this embodiment, the historical training score can refer to the user's cumulative training score during the historical cognitive training process, and the total training score can refer to the sum of the historical training score and the current training score.

[0028] Specifically, after each cognitive training session, the user's historical training score is obtained, and the historical training score is summed with the current training score to obtain the total training score. The total training score is then checked to see if it meets the standard of the premium incentive mechanism. If the total training score meets the standard of the premium incentive mechanism, a corresponding discount mechanism is given to the premium of the insurance product corresponding to the cognitive training. If the total training score does not meet the standard of the premium incentive mechanism, the process returns to the step S201 above, which involves real-time collection of the user's EEG signals during the cognitive training process, until the standard of the premium incentive mechanism is met.

[0029] For example, in the process of summing historical training scores and current training scores to obtain the total training score, the historical training scores can be assigned progressively decreasing weights (e.g., the earliest score has a weight of 0.1, the middle scores 0.2, and the most recent historical score 0.3), while the current training score is given the highest weight of 0.4. This reflects the greater impact of recent cognitive state on premium incentives. Based on the weights of each historical training score and current training score, all historical training scores and current training scores are weighted and summed to obtain the total training score.

[0030] Based on the above method of weighting and summing all historical and current training scores according to their weights, the number of consecutive training cycles can also be introduced as a reward coefficient. That is, after obtaining the weighted sum by weighting and summing all historical and current training scores according to their weights, the weighted sum is multiplied by a weighting factor that increases with the number of consecutive training cycles (e.g., multiply by 1.25 for 5 consecutive cycles) to obtain the total training score, thereby incentivizing users to participate in training continuously over a long period of time.

[0031] Optionally, the system can also obtain the user's training score for the current quarter and the training score for the previous quarter, calculate the quarterly score change rate based on the current quarter's training score and the training score for the previous quarter, determine the user's cognitive decline probability based on the quarterly score change rate, detect whether the cognitive decline probability exceeds a preset fourth threshold, and if the cognitive decline probability exceeds the preset fourth threshold, push an enhanced training plan to the user.

[0032] Among them, the probability of cognitive decline can refer to a risk indicator calculated based on the user's training scores for two consecutive quarters, used to quantify the possibility of a negative trend in the user's cognitive ability. The preset fourth threshold can refer to the value required to trigger the push of the reinforcement training program and the probability of cognitive decline.

[0033] In other words, the system obtains the user's training score for the current quarter and the previous quarter. Based on these scores, it calculates the quarterly score change rate, objectively reflecting the fluctuation trend of the user's cognitive ability. Using this quarterly score change rate, combined with historical monitoring data such as cognitive training performance and neural activation index, the system comprehensively and quantitatively assesses the user's cognitive decline probability and evaluates the risk of cognitive function decline. The cognitive decline probability is compared with a preset fourth threshold. When a significant decline in the user's quarterly score and a continuous weakening of cognitive state are detected, causing the cognitive decline probability to exceed the preset fourth threshold, it indicates a significantly increased risk of cognitive decline. In this case, a targeted, high-intensity, highly adaptable personalized cognitive enhancement training program can be customized and pushed to help the user strengthen their mental exercise, improve neural activity levels, and intervene in the cognitive degeneration process in a timely manner. If the cognitive decline probability does not exceed the threshold, the regular training plan remains unchanged, achieving periodic dynamic monitoring and graded intervention of cognitive health.

[0034] In this embodiment, by dynamically adjusting the training difficulty based on real-time EEG signals, it is possible to ensure that cognitive training is always within the user's effective workload range to improve brain health, while also objectively quantifying the user's cognitive engagement and progress. Based on the total training score generated, the premium incentive mechanism for the insurance premium purchased by the user for cognitive training is dynamically triggered, realizing a dynamic correlation between the premium and the user's actual cognitive status. This improves the matching degree between the premium and the user, enhances the accuracy of insurance risk protection, and achieves a win-win situation for both the user's health improvement and the insurance company's risk control optimization.

[0035] like Figure 3 The diagram shown is a flowchart of a product optimization method for insurance services provided in Embodiment 3 of the present invention. In step S201, the electroencephalogram (EEG) signal is processed to obtain a neural activation index characterizing the level of neural activity in the user's brain, including the following steps: Step S301: Decompose the EEG signal into frequency bands to obtain the signal frequency bands.

[0036] Step S302: For any signal frequency band, calculate the power spectral density of the signal frequency band.

[0037] Step S303: Obtain the neural activation index based on the power spectral density of all signal frequency bands.

[0038] In this embodiment, the signal frequency band can refer to the frequency band obtained by decomposing the EEG signal, and the power spectral density can refer to the power contained in the EEG signal within the signal frequency band.

[0039] Specifically, an adaptive Kalman filter can be used to filter noise from EEG signals, dynamically identifying 50-100Hz high-frequency noise generated by eye movements / blinking, eliminating interference in real time, and obtaining the filtered EEG signal. The state equation in the Kalman filter can be: Signal estimate = Previous time estimate + Kalman gain × (Current observation - Previous time estimate). The Kalman gain is dynamically adjusted according to the noise covariance. Using a fast Fourier transform, the filtered EEG signal is... (4-8Hz) (8-12Hz) (12-30Hz) and Four signal frequency bands (30-100Hz) were used to calculate the power spectral density of each band. The Welch method was employed for power spectral density calculation, with a window length of 1024 points and an overlap rate of 50%. Based on the power spectral density of all signal frequency bands, the neural activation index was obtained. The formula for calculating the neural activation index is: Neural activation index = ( Band power spectral density / Band power spectral density) × natural logarithm function (1+ Band power spectral density / Band power spectral density).

[0040] In this embodiment, by performing frequency band decomposition on the EEG signal to obtain signal frequency bands, and calculating and obtaining the neural activation index based on the power spectral density of each signal frequency band, it is possible to more sensitively and stably capture the user's true neural effort and mental engagement during cognitive training, providing an accurate data foundation for subsequent dynamic adjustment of training difficulty and premium incentive mechanisms.

[0041] like Figure 4 The diagram shown is a flowchart of a product optimization method for insurance services provided in Embodiment 4 of the present invention. In step S202 above, a difficulty coefficient representing the degree of difficulty in cognitive training is obtained based on the neural activation index, including the following steps: Step S401: Detect whether the neural activation index exceeds the preset first threshold. If the neural activation index exceeds the preset first threshold, obtain the user's historical performance coefficient during the historical cognitive training process.

[0042] Step S402: Obtain the difficulty coefficient based on the neural activation index and historical performance coefficient.

[0043] In this embodiment, the preset first threshold can refer to the value required to upgrade the difficulty of cognitive training and the neural activation index, which can be pre-set. The historical performance coefficient can be used to characterize the user's performance in the historical cognitive training process.

[0044] Specifically, the neural activation index is detected to exceed a preset first threshold. If the neural activation index exceeds the preset first threshold, the historical performance coefficient of the user in the historical cognitive training process is obtained, the difference between the neural activation index and the preset first threshold is calculated, and the new difficulty value is determined based on the difference and the historical performance coefficient. The current difficulty coefficient of the cognitive training is obtained, and the difficulty coefficient after the difficulty upgrade is obtained based on the new difficulty value and the current difficulty coefficient.

[0045] For example, if the preset first threshold is 0.7, when the neural activation index exceeds 0.7, a difficulty upgrade protocol is triggered. The newly added difficulty value = (neural activation index - 0.7) × 0.3 × historical performance coefficient, where the historical performance coefficient = The newly added difficulty value is summed with the current difficulty coefficient to obtain the difficulty coefficient after the difficulty upgrade.

[0046] After detecting whether the neural activation index exceeds the preset first threshold, if the neural activation index does not exceed the preset first threshold, the current training time and the preset standard training time of the user in the cognitive training process are obtained. Based on the current training time and the standard training time, the fatigue decay factor for the user in the cognitive training process is obtained. Based on the neural activation index and the fatigue decay factor, the difficulty coefficient is obtained.

[0047] Among them, the current training duration can refer to the duration of training that the user has already completed during the cognitive training process, the standard training time can refer to the maximum recommended training duration set in advance, and the fatigue decay factor can refer to a coefficient calculated based on the ratio of the user's current training duration to the standard training duration, used to quantify the degree of decline in cognitive performance or engagement caused by training fatigue.

[0048] That is, if the neural activation index is not detected to exceed the preset first threshold, the current training time and the preset standard training time of the user in the cognitive training process are obtained. The current training time and the standard training time are divided to obtain the fatigue decay factor. The difference between the neural activation index and the preset first threshold is calculated. Based on the difference and the fatigue decay factor, the reduced difficulty value is determined. The current difficulty coefficient of the cognitive training is obtained. Based on the reduced difficulty value and the current difficulty coefficient, the difficulty coefficient after the difficulty reduction is obtained.

[0049] For example, when the neural activation index does not exceed 0.7, the protection mechanism is triggered, and the reduced difficulty value is (0.7 - neural activation index) × 0.5 × fatigue decay factor. The fatigue decay factor is the current training time / standard training time. The reduced difficulty value is subtracted from the current difficulty coefficient to obtain the reduced difficulty coefficient.

[0050] In this embodiment, when the neural activation index exceeds a preset first threshold, the difficulty is increased based on the difference between the neural activation index and the preset first threshold and historical performance. This encourages users to continuously challenge themselves while avoiding frustration caused by excessively large jumps in difficulty, thus achieving personalized difficulty upgrades. When the neural activation index does not exceed the preset first threshold, a fatigue decay factor is introduced. This factor can detect the user's decreased attention and cognitive fatigue caused by prolonged training and reduce the difficulty accordingly. This effectively prevents users from experiencing excessive pressure and negative emotions due to overly difficult tasks while fatigued, ensuring that cognitive training is always within the user's effective workload range to improve brain-training effects.

[0051] like Figure 5 The diagram shown is a flowchart of a product optimization method for insurance services provided in Embodiment 5 of the present invention. In step S204 above, based on the total training score, a premium incentive mechanism for the insurance product corresponding to the user's cognitive training is triggered, including the following steps: Step S501: Detect whether the total training score exceeds the preset third threshold. If the total training score exceeds the preset third threshold, determine the excess difference based on the total training score and the preset third threshold, and determine the corresponding discount rate based on the excess difference.

[0052] Step S502: Obtain the premium of the insurance product corresponding to the cognitive training purchased by the user, update the premium according to the discount rate, and obtain the updated premium.

[0053] In this embodiment, the preset third threshold can refer to the total training score value that needs to be achieved to trigger the premium incentive mechanism, and the excess difference can refer to the difference between the total training score and the preset third threshold.

[0054] Specifically, the system detects whether the total training score exceeds a preset third threshold. If the total training score exceeds the preset third threshold, the system performs a difference operation between the total training score and the preset third threshold to obtain an excess difference. Based on the excess difference, the system matches the corresponding discount rate, obtains the premium for the insurance purchased by the user for cognitive training, and updates the premium based on the discount rate to obtain the updated premium.

[0055] After detecting whether the total training score exceeds the preset third threshold, if the total training score does not exceed the preset third threshold, the process returns to the step of collecting the user's EEG signal in real time during the cognitive training process in step S201, until the historical training score exceeds the preset third threshold, triggering the premium incentive mechanism of the insurance product corresponding to the cognitive training.

[0056] For example, in the premium incentive scenario of insurance products for cognitive decline in the elderly, the total training score that can trigger premium discounts is preset as a third threshold. The elderly complete cognitive training tasks such as image recognition, scene recall, and logical sequencing every day. The device collects EEG signals and calculates neural activation index throughout the process, dynamically adapts the training difficulty, and continuously accumulates single training scores and historical training scores to generate a total training score. The system verifies in real time whether the elderly person's total training score meets the target. When the elderly person consistently engages in scientific cognitive training, has good brain activity, and demonstrates excellent overall performance, resulting in a total training score exceeding the preset third threshold, the system automatically calculates the excess score difference. Based on the magnitude of the difference, a tiered premium discount rate is matched, and the current premium payable for the user's cognitive decline insurance is retrieved and deducted according to the corresponding discount ratio to generate an updated preferential premium. If the elderly person's cognitive training completion rate is insufficient and the total training score does not reach the preset third threshold, the premium reduction will not be triggered. The system automatically guides the elderly person to continue participating in cognitive training, continuously collecting EEG data, and conducting dynamic training assessments until the total training score meets the target, at which point the premium incentive policy for cognitive decline insurance is officially activated. This guides the elderly person to actively maintain cognitive health and achieves dynamic preferential adjustment of the cognitive decline insurance premium.

[0057] In this embodiment, the premium incentive mechanism for the insurance purchased by the user for cognitive training is dynamically triggered by the total training score, thereby realizing the dynamic correlation between the premium and the user's actual cognitive status, which improves the accuracy of premium pricing, enhances the accuracy of insurance risk protection, and achieves a win-win situation of improving user health and optimizing insurance company risk control.

[0058] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0059] like Figure 6 The diagram shown is a structural schematic of a product optimization device for insurance services provided in Embodiment Six of the present invention. This product optimization device for insurance services corresponds one-to-one with the product optimization method for insurance services described in the above embodiments. Figure 6 As shown, the product optimization device for insurance services includes a data acquisition module 61, a first calculation module 62, a second calculation module 63, a third calculation module 64, and an incentive module 65. Detailed descriptions of each functional module are as follows: Data acquisition module 61 is used to collect the user's electroencephalogram (EEG) signals in real time during the user's cognitive training process, process the EEG signals, and obtain a neural activation index that characterizes the degree of neural activity in the user's brain. The first calculation module 62 is used to obtain a difficulty coefficient representing the difficulty of the cognitive training based on the neural activation index, and to adjust the difficulty of the cognitive training based on the difficulty coefficient. The second calculation module 63 is used to return to the step of real-time acquisition of the user's EEG signals until the cognitive training ends, and to obtain the current training score corresponding to the cognitive training based on all the neural activation indices and the difficulty coefficient during the cognitive training process. The third calculation module 64 is used to obtain the user's historical training score in the historical cognitive training process, and determine the user's total training score based on the historical training score and the current training score. The incentive module 65 is used to trigger the premium incentive mechanism for the insurance product corresponding to the cognitive training for the user based on the total training score.

[0060] Optionally, the data acquisition module 61 mentioned above includes: A frequency band decomposition unit is used to decompose the EEG signal into frequency bands to obtain signal frequency bands; The fourth calculation unit is used to calculate the power spectral density of the signal frequency band for any given signal frequency band. The fifth calculation unit is used to obtain the neural activation index based on the power spectral density of all signal frequency bands.

[0061] Optionally, the first calculation module 62 mentioned above includes: The first detection unit is used to detect whether the neural activation index exceeds a preset first threshold. If the neural activation index exceeds the preset first threshold, the user's historical performance coefficient in the historical cognitive training process is obtained. The sixth calculation unit is used to obtain the difficulty coefficient based on the neural activation index and the historical performance coefficient.

[0062] Optionally, the first calculation module 62 described above further includes: The first data acquisition subunit is used to acquire the user's current training duration and the preset standard training duration during the cognitive training process if the neural activation index is detected to be less than the preset first threshold. The seventh calculation subunit is used to obtain the fatigue decay factor for the user during the cognitive training process based on the current training duration and the standard training duration. The eighth calculation subunit is used to obtain the difficulty coefficient based on the neural activation index and the fatigue decay factor.

[0063] Optionally, the second calculation module 63 mentioned above includes: A determining unit is configured to determine, from all neural activation indices, an effective neural activation index that exceeds a preset second threshold, and for any one of the effective neural activation indices, determine the duration of the effective neural activation index during the cognitive training process. The second data acquisition unit is used to acquire the difficulty coefficient corresponding to each effective neural activation index and the number of consecutive training cycles of the user in the historical cognitive training process. The ninth calculation unit is used to obtain the current training score based on the duration of all the effective neural activation indices, the difficulty coefficient corresponding to the effective neural activation index, and the number of consecutive training cycles.

[0064] Optionally, the third calculation module 64 mentioned above includes: The second detection unit is used to detect whether the total training score exceeds a preset third threshold. If the total training score exceeds the preset third threshold, the excess difference is determined based on the total training score and the preset third threshold, and the corresponding discount rate is determined based on the excess difference. The premium update unit is used to obtain the premium of the cognitive training-related insurance product purchased by the user, and update the premium according to the discount rate to obtain the updated premium.

[0065] Optionally, the third calculation module 64 mentioned above further includes: A loop unit is used to return to cognitive training if the total training score is detected to be less than the preset third threshold, until the historical training score exceeds the preset third threshold.

[0066] Specific limitations regarding the product optimization device used for insurance services can be found in the limitations of the product optimization method used for insurance services described above, and will not be repeated here. Each module in the aforementioned product optimization device for insurance services can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0067] Embodiment 7 of the present invention provides a computer device, which may be a server, and its internal structure diagram may be as follows. Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores the user's electroencephalogram (EEG) signals. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a product optimization method for insurance services.

[0068] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the product optimization method for insurance services described in the above embodiments, for example... Figure 2 As shown in S201-S204, or Figures 3 to 5 As shown, to avoid repetition, it will not be described again here. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the product optimization device for insurance services, for example, Figure 6 The functions of the data acquisition module 61, the first calculation module 62, the second calculation module 63, the third calculation module 64, and the excitation module 65 shown are not described again here to avoid repetition.

[0069] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program implements the product optimization method for insurance services described in the above embodiments, for example... Figure 2 As shown in S201-S204, or Figures 3 to 5 As shown, to avoid repetition, it will not be described again here. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the product optimization device for insurance services, for example, Figure 6 The functions of the data acquisition module 61, the first calculation module 62, the second calculation module 63, the third calculation module 64, and the excitation module 65 shown are not described again here to avoid repetition.

[0070] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0072] If any software tools or components not belonging to this company appear in the embodiments of this invention, they are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this invention is authorized (with knowledge and consent) by the relevant parties or fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with the relevant laws and regulations of the relevant countries and regions, and do not violate public order and good morals.

[0073] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A product optimization method for insurance services, characterized in that, include: During cognitive training, the user's EEG signals are collected in real time, and the EEG signals are processed to obtain a neural activation index that characterizes the user's brain activity level. Based on the neural activation index, a difficulty coefficient representing the degree of difficulty of the cognitive training is obtained, and the degree of difficulty of the cognitive training is adjusted according to the difficulty coefficient. Return to the step of real-time acquisition of the user's EEG signals until the cognitive training ends. Based on all the neural activation indices and the difficulty coefficient during the cognitive training process, obtain the current training score corresponding to the cognitive training. Obtain the user's historical training score during the historical cognitive training process, and determine the user's total training score based on the historical training score and the current training score; Based on the total training score, the premium incentive mechanism for the insurance product corresponding to the cognitive training is triggered for the user.

2. The product optimization method for insurance services according to claim 1, characterized in that, The process of processing the electroencephalogram (EEG) signals to obtain a neural activation index characterizing the level of neural activity in the user's brain includes: The EEG signal is decomposed into frequency bands to obtain the signal frequency bands; For any given signal frequency band, calculate the power spectral density of that signal frequency band; The neural activation index is obtained based on the power spectral density of all signal frequency bands.

3. The product optimization method for insurance services according to claim 1, characterized in that, The process of obtaining a difficulty coefficient characterizing the degree of difficulty in cognitive training based on the neural activation index includes: Detect whether the neural activation index exceeds a preset first threshold. If the neural activation index exceeds the preset first threshold, obtain the user's historical performance coefficient in the historical cognitive training process. The difficulty coefficient is obtained based on the neural activation index and the historical performance coefficient.

4. The product optimization method for insurance services according to claim 3, characterized in that, The step of obtaining a difficulty coefficient characterizing the degree of difficulty in cognitive training based on the neural activation index further includes: If the neural activation index is detected to be within the preset first threshold, then the user's current training duration and the preset standard training duration are obtained during the cognitive training process. Based on the current training duration and the standard training duration, a fatigue decay factor is obtained for the user during the cognitive training process; The difficulty coefficient is obtained based on the neural activation index and the fatigue decay factor.

5. The product optimization method for insurance services according to claim 1, characterized in that, The step of obtaining the current training score corresponding to the cognitive training based on all the neural activation indices and the difficulty coefficient during the cognitive training process includes: From all neural activation indices, determine the effective neural activation index that exceeds a preset second threshold, and for any one of the effective neural activation indices, determine the duration of the effective neural activation index in the cognitive training process; Obtain the difficulty coefficient corresponding to each effective neural activation index and the number of consecutive training cycles of the user in the historical cognitive training process; The current training score is obtained based on the duration of all effective neural activation indices, the difficulty coefficient corresponding to the effective neural activation index, and the number of consecutive training cycles.

6. The product optimization method for insurance services according to claim 1, characterized in that, The step of triggering the premium incentive mechanism for the insurance product corresponding to the cognitive training for the user based on the total training score includes: Detect whether the total training score exceeds a preset third threshold. If the total training score exceeds the preset third threshold, determine the excess difference based on the total training score and the preset third threshold, and determine the corresponding discount rate based on the excess difference. Obtain the premium of the cognitive training-related insurance product purchased by the user, and update the premium according to the discount rate to obtain the updated premium.

7. The product optimization method for insurance services according to claim 6, characterized in that, After detecting whether the total training score exceeds a preset third threshold, the method further includes: If the total training score is not detected to exceed the preset third threshold, then return to the cognitive training until the historical training score exceeds the preset third threshold.

8. A product optimization device for insurance services, characterized in that, include: The data acquisition module is used to collect the user's electroencephalogram (EEG) signals in real time during cognitive training, process the EEG signals, and obtain a neural activation index that characterizes the degree of neural activity in the user's brain. The first calculation module is used to obtain a difficulty coefficient representing the difficulty level of the cognitive training based on the neural activation index, and to adjust the difficulty level of the cognitive training based on the difficulty coefficient. The second calculation module is used to return to the step of real-time acquisition of the user's EEG signals until the cognitive training ends, and to obtain the current training score corresponding to the cognitive training based on all the neural activation indices and the difficulty coefficient during the cognitive training process. The third calculation module is used to obtain the user's historical training score during the historical cognitive training process, and determine the user's total training score based on the historical training score and the current training score. The incentive module is used to trigger the premium incentive mechanism for the insurance product corresponding to the cognitive training for the user based on the total training score.

9. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the product optimization method for insurance services as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the product optimization method for insurance services as described in any one of claims 1 to 7.

Images