Technology that provides user-tailored services to users

Abstract

A technology that provides user-tailored services to users will be made public. [Solution] The method of implementing the technology is performed by a client device and includes the steps of obtaining a digital representation of the user's personality data via manual input by the user (S902), and processing the digital representation of the personality data to provide the user with a user-tailored service (S904). The client device may be a vehicle, and providing the user with a user-tailored service may include tailoring the vehicle's driving settings to the user's personality.

Description

Technical Field

[0001] The present disclosure generally relates to the field of data retrieval, and more particularly, to techniques for enabling the efficient retrieval of digital representations of a user's personality data from a server by a client device. Further, techniques for providing user-adapted services to a user of a client device are presented. This technology can be implemented as a method, computer program, apparatus, and system.

Background Art

[0002] Personality tests have been used for decades to assess human personality traits. Generally, they are based on personality survey data obtained from test subjects, which is then evaluated by experts such as psychologists to draw conclusions about the individual's personality. The so-called "OCEAN" model, also known as the "Big Five" personality traits, is a widely accepted taxonomy of personality traits, including personality dimensions such as openness, conscientiousness, extraversion, agreeableness, and neuroticism. Widely known personality tests utilizing the OCEAN model include the so-called International Personality Item Pool (IPIP), the HEXACO-60 inventory, and tests based on the Big-Five-Inventory-10 (BFI-10), which, for example, include sets of questions to test a person for each of the five personality dimensions. Traditional personality tests generally require review by human experts, such as psychologists, to obtain an accurate assessment of a person's personality traits. However, integrating the execution of personality tests and their results into processes run on technical systems is difficult. Such integration can be beneficial because it allows for adjustments to better suit the user's personality, thereby improving the user experience, for example, by providing user-tailored services to the user. [Overview of the Initiative]

[0003] Therefore, a technical implementation is needed that makes it actually possible to integrate personality tests and their results into processes running on a technical system.

[0004] According to aspects of this disclosure, a method for providing user-conformed services to a user of a client device, a computer program product, and a client device are provided in accordance with the independent claims. Preferred embodiments are described in the dependent claims.

[0005] According to a first exemplary embodiment, a method is provided that enables a client device to efficiently obtain a digital representation of a user's personality data from a server, the digital representation of the personality data being processed on the client device to provide the user with user-tailored services. This method is performed by a server and includes storing a neural network trained to compute the user's personality data based on user inputs, receiving a request for a digital representation of the user's personality data from a client device, and transmitting the requested digital representation of the user's personality data to the client device, where the user's personality data is computed using a neural network based on user inputs.

[0006] By storing a trained neural network on a server and applying it to the calculation of user personality data, the acquisition of a digital representation of the user's personality data becomes automated (eliminating the need for traditional human review), thus enabling the integration of user personality data acquisition and use into (e.g., automated) processes running on a technical system. In particular, neural networks can be described as efficient functional data structures, capable of calculating requested personality data in a single computational execution; that is, by inputting user inputs into the neural network's input nodes and reading the resulting output values ​​representing the personality data from the neural network's output nodes. Thus, neural networks enable the efficient delivery of personality data in digital form to client devices, which can be used to provide services tailored to the user's specific personality, thereby improving the user experience on the client device side. The efficient delivery of data means that the digital representation of personality data is delivered to the client device without significant delay and processed immediately on the client device, making the integration of personality data acquisition and use particularly practical. This achieves a practically feasible technical implementation that generally integrates the acquisition and use of personality data into processes running on technical systems.

[0007] Since user personality data can indicate a user's psychological traits and / or preferences, personality data may generally include psychological data, such as classical personality data based on personality dimensions like openness, conscientiousness, extraversion, agreeableness, and neuroticism (known as the Big Five as described above), as well as medical data (e.g., data indicating tendencies such as curiosity, anxiety, and depression). A digital representation of a user's personality data may include digital representations of the aforementioned traits, such as a digital representation of at least one of the personality dimensions of openness, conscientiousness, extraversion, agreeableness, and neuroticism, calculated for the user by a neural network.

[0008] A client device may be configured to process a digital representation of personality data for the purpose of enabling the provision of user-tailored services to the user. In one variation, the client device itself may be configurable based on the digital representation of personality data. An exemplary device that may be configurable by a digital representation of personality data is, for example, a vehicle, in which case the vehicle may be the client device. The vehicle may process the received digital representation of the user's (e.g., the vehicle's driver) personality data and configure itself (including, for example, its subcomponents) to adapt the vehicle's driving settings to the driver's personality, thereby enabling the provision of driving services tailored to the user's personality. If the personality data indicates that the driver tends to be risk-averse or anxious, for example, the vehicle's driving settings may be set to be more safety-oriented, while if the driver tends to have a more risk-seeking personality, the vehicle's driving settings may be set to be more sporty. For this purpose, among other settings, the vehicle's fuel and brake response behavior may be adapted accordingly. Subcomponents of a vehicle that provide vehicle-related services, such as the vehicle's sound system including sound and volume settings, may be configured based on personality data to further suit the user's personality. Optionally, the user may be shown a digital representation of their personality data and given the opportunity to modify at least one value of the digital representation before being provided with a user-tailored service, thereby modifying the user-tailored service (at least to some extent) according to the user's current preferences.

[0009] In other variations, the client device may configure at least one other device based on a digital representation of personality data, for example, if that other device provides services to the user. In such variations, the client device may be, for example, a mobile terminal (e.g., a smartphone) that can interact with a vehicle (i.e., in this case the vehicle corresponds to at least one other device) (e.g., using Bluetooth®), and upon receiving a digital representation of personality data from the server, the mobile terminal can configure the vehicle via an interface. Thus, it can be said that a digital representation of a user's personality data may be processed in the client device to configure at least one device that provides services to the user. Configuring at least one device may include configuring at least one setting of at least one device and / or configuring at least one setting of the services provided by at least one device. It will be understood that a vehicle is merely one example of a device that can be configured based on personality data, and the client device and / or at least one other device may correspond to other types of devices.

[0010] In one embodiment, the method performed by the server may further include receiving user-characterizing feedback, updating a neural network based on the feedback, and transmitting a digital representation of the user's updated personality data to a client device, where the updated personality data is computed using the updated neural network. The digital representation of the user's updated personality data is processed in the client device to improve the settings of at least one device providing services to the user (e.g., one of the vehicle settings described above). Feedback may be collected by the client device and / or at least one device providing services to the user and may indicate the user's personality. Feedback may include, for example, behavioral data reflecting the user's behavior monitored by at least one device when using services provided by at least one device, and in one variation, the behavioral data may be monitored by at least one device providing services to the user using (e.g., sensor-based) measurements. In the vehicle example, the monitored user behavior may be, for example, the user's driving behavior, which is measured by the vehicle's sensors. To measure driving behavior, sensors can, for example, detect the user's braking response and intensity. Since such measurements can indicate the user's personality (e.g., their willingness to drive), this information is sent to a server as feedback to update the neural network, thereby improving the functionality of the neural network that calculates the user's personality data.

[0011] Updating a neural network can involve training it based on feedback received from a client device. If the feedback represents new input values ​​not yet entered into the neural network, new input nodes can be added to the neural network during training, assigning the new input values ​​to the new input nodes. This particularly highlights the neural network's capability as an efficient functional data structure, as employed in the technical implementations presented herein. That is, the neural network represents an efficiently updatable data structure, which can be updated based on arbitrary feedback about the user's personality received from a client device, improving its ability to compute personality data. The information conveyed by the feedback can be directly integrated into the neural network, and once trained, it is immediately reflected in subsequent requests sent to a server requesting a digital representation of the personality data. Conventional personality assessment methods are often quite fixed and may not support such updatable capabilities at all.

[0012] The digital representation of a user's personality sent from the server to a client device may correspond to a digital representation of the user's personality previously calculated by the server in response to a previous request for the calculation of the user's personality (for example, when the user takes a personality test by answering a set of questions). Thus, the user's personality data can be calculated before receiving a request from the client device, and the request may include an access code provided to the user in advance by the server when calculating the user's personality data, which allows the user to access the digital representation of the user's personality data from other client devices. Such an implementation can save computational resources on the server because it does not need to recalculate the digital representation of the user's personality each time that particular digital representation of the user's personality data is requested from a client device, and it can also respond based on the pre-calculated personality data. The user can then use the access code to access the digital representation of their personality data from multiple other client devices, such as other vehicles the user can drive, e.g., cars and motorcycles, or other types of devices.

[0013] The input obtained from the user can correspond to digital scores (e.g., obtained in a question-answering scheme in a personality testing method) that reflect the user's answers to questions about at least one of their personality, goals, and motivations (optionally, the questions may include questions from an intelligence ("IQ") test), and each digital score can be used as input to a separate input node of the neural network when calculating the user's personality data using the neural network. The digital scores can correspond to, for example, a 5-level Likert scale with values ​​from 1 to 5. The neural network can correspond to a deep neural network having at least two hidden layers between the input layer containing the neural network's input nodes and the output layer containing the output nodes. Questions about personality can correspond to (or "include"), for example, questions in traditional IPIP, HEXACO-60, and / or BFI-10 pools, but it will be understood that other questions about the user's personality, including questions about the user's psychological traits and / or preferences, can be used as well. In particular, questions about the user's goals and motivations can define additional dimensions (e.g., in addition to the Big Five) that improve the accuracy of the calculated personality data compared to traditional IPIP, HEXACO-60, and BFI-10 methods. The network can be trained on data collected in a baseline survey conducted with multiple testers (e.g., 1000 or more), and the baseline survey can be conducted using the questions described above.

[0014] To reduce the computational complexity when calculating user personality data, neural networks can be designed to have a specific network structure. Considering the context of the questions above, the structure of the neural network can generally be designed such that the number of input nodes is reduced compared to the number of input nodes available when all of the questions above are used. Thus, the questions can correspond to questions selected from a set of questions that represent the optimally achievable outcome for calculating user personality data (i.e., if the user answers all questions in the set), where the selected questions can correspond to questions in the set of questions that are determined to have the most influence on the optimally achievable outcome. As mentioned above, since each answer to a question is input to a separate input node in the neural network, selecting a subset of the question set reduces the number of input nodes when calculating personality data, thereby reducing computational complexity. The fact that the most influential questions on the achievable outcome are selected ensures that the accuracy of the results output by the neural network is maintained to a near-perfect degree.

[0015] In fact, tests have shown that the number of questions can be significantly reduced without sacrificing considerable accuracy in the results. When considering a question set that includes standard IPIP, HEXACO-60, and BFI-10 questions (370 questions in total) as the optimally achievable outcome for calculating personality data, supplemented optionally with additional questions about the user's goals and motivations (resulting in a total of over 370 questions), tests have shown that using only the 30 most influential questions achieves approximately 90% accuracy of the optimally achievable outcome. Therefore, the number of selected questions can be less than 10% (preferably less than 5%) of the number of questions in the optimally achievable outcome set. In this case, the number of input nodes in the neural network can be significantly reduced, resulting in substantial savings in computational resources and more efficient calculation of personality data.

[0016] To determine which questions in the question set have the most influence on the optimally achievable outcome, one variation is to select questions from the question set based on correlating the outcome achievable by each individual question in the question set with the optimally achievable outcome, and then selecting questions from the question set with the highest correlation to the optimally achievable outcome. Thus, a fixed subset of the question set that represents the optimally achievable outcome can be determined and used to train a neural network with a reduced number of input nodes, as described above.

[0017] As described above, the optimally achievable result can correspond to the result achieved when the user answers all questions in a set of questions including standard IPIP, HEXACO-60, and BFI-10 questions, optionally supplemented with additional questions about the user's goals and motivations, as described above. On the other hand, in one variation, the standard IPIP score (obtained by answering all questions in the standard IPIP test), the standard HEXACO-60 score (obtained by answering all questions in the standard HEXACO-60 test), and the standard BFI-10 score (obtained by answering all questions in the standard BFI-10 test) can be obtained individually as references to the optimally achievable result, while in other variations, improvements can be achieved by calculating a combined score of these individual scores as a reference to the optimally achievable result, where the combined score is calculated, for example, as the (e.g., weighted) average of the individual scores. The combined score can also be represented as a "super score" that represents the "truth" that can be derived from the individual scores, generally improving the meaning of the determined score and improving the reference to the optimally achievable result.

[0018] In other variations, questions can be repeatedly selected from a set of questions, and in each iteration, the next question can be selected based on the user's answer to the previous question, and in each iteration, the next question can be selected as one of the questions in the set that is determined to have the most impact on the achievable outcome for calculating the user's personality data. This can be considered adaptive selection of questions, and the questions are determined on a per-user basis in a stepwise manner, taking into account the user's answers to previous questions. In one particular variation, the neural network may include multiple output nodes representing the probability curve of the user's personality data outcomes, where determining the most influential question in the set of questions as the next question in each iteration may include determining, for each input node of the neural network, the extent to which the change in the digital score input to each input node of the neural network changes the probability curve. The question associated with the input node that is determined to have the greatest degree of change in the probability curve can be selected as the most influential question in each iteration.

[0019] To further reduce computational complexity, the iterative and adaptive selection described above may be performed under at least one constraint, such as the maximum number of questions to be selected, the minimum outcome accuracy to be achieved (the outcome accuracy improves with each iteration and the question answers, and the calculation can be stopped when the required minimum outcome accuracy is reached), and the maximum available time (the test can be stopped when the maximum available time has elapsed, or each question can be associated with the user's estimated response time, and the number of questions to be selected can be determined based on the estimated time). These constraints can be set individually for each calculation of personality data.

[0020] A second exemplary embodiment provides a method for enabling a client device to efficiently obtain a digital representation of a user's personality data from a server. This method is performed by the client device and includes sending a request for a digital representation of the user's personality data to a server and receiving the requested digital representation of the user's personality data from the server, wherein the user's personality data is computed based on user input using a neural network trained to compute the user's personality data based on user input, and processing the digital representation of the personality data to provide the user with a user-tailored service.

[0021] The method according to the second embodiment defines a method from the perspective of a client device that can complement the method performed by the server according to the first embodiment. The server and client devices of the second embodiment may correspond to the server and client devices described above in relation to the first embodiment. Therefore, those embodiments described in relation to the method of the first embodiment that are applicable to the method of the second embodiment are also included by the method of the second embodiment, and vice versa. Therefore, unnecessary repetition is omitted below.

[0022] Similar to the method of the first embodiment, a digital representation of a user's personality data may be processed in a client device to configure at least one device that provides services to the user, where at least one device may include a client device. The method performed by the client device may further include sending feedback characterizing the user to a server and receiving an updated digital representation of the user's personality data from the server, where the updated personality data may be computed using a neural network updated based on the feedback. The updated digital representation of the user's personality data may be processed in the client device to improve the configuration of at least one device that provides services to the user. The feedback may include behavioral data reflecting the user's behavior monitored by at least one device when using the services provided by at least one device, where the behavioral data may be monitored using measurements performed by at least one device that provides services to the user. At least one device may include a vehicle, and the behavioral data may include data reflecting the user's driving behavior. User personality data can be calculated before sending a request to the server, and the request may include an access code provided to the user in advance by the server when calculating the user's personality data, which allows the user to access a digital representation of the user's personality data from other client devices. Input obtained from the user may correspond to a digital score reflecting the user's answers to questions about at least one of the user's personality, goals, and motivations.

[0023] According to a third exemplary embodiment, a computer program product is provided. The computer program product includes a portion of program code for performing at least one of the embodiments described above (including the first and second embodiments) when the computer program product is executed on one or more computing devices (e.g., a processor or a distributed set of processors). The computer program product may be stored on a computer-readable recording medium such as semiconductor memory, DVD, or CD-ROM.

[0024] According to a fourth exemplary embodiment, a server is provided that enables a client device to efficiently retrieve a digital representation of a user's personality data from the server, wherein the digital representation of the personality data is processed in the client device to provide the user with user-tailored services. The server includes at least one processor and at least one memory, the at least one memory including instructions executable by the at least one processor, such that the server is operable to perform any of the method steps presented herein in relation to the first embodiment.

[0025] According to a fifth exemplary embodiment, a client device is provided that enables efficient retrieval of a user's personality data from a server. The client device includes at least one processor and at least one memory, the at least one memory including instructions executable by the at least one processor, such that the client device is operable to perform any of the method steps presented herein in relation to a second embodiment.

[0026] According to a sixth exemplary embodiment, a system is provided comprising a server according to the fourth embodiment and at least one client device according to the fifth embodiment.

[0027] Further details and advantages of the technologies presented herein will be explained with reference to exemplary implementations shown in the following figures.

Brief Description of the Drawings

[0028] [Figure 1a] FIG. 1a shows an exemplary configuration of a server according to the present disclosure. [Figure 1b] FIG. 1b shows an exemplary configuration of a client device according to the present disclosure. [Figure 2] FIG. 2 shows a method executed by a server according to the present disclosure. [Figure 3] FIG. 3 shows a method executed by a client device according to the present disclosure. [Figure 4] FIG. 4 shows an exemplary interaction among a user, a server, and a client device (exemplified by a vehicle) according to the present disclosure. [Figure 5] FIG. 5 shows other connection options among a user's mobile terminal, a vehicle, and a server according to the present disclosure. [Figure 6a] FIG. 6a shows an exemplary structure of a neural network according to the present disclosure. [Figure 6b] FIG. 6b shows an exemplary structure of a neural network according to the present disclosure. [Figure 7] FIG. 7 shows an exemplary implementation including considering a driver's attention level to adapt vehicle settings according to the present disclosure. [Figure 8] FIG. 8 shows an exemplary implementation including considering a user's body scan data to provide a user-adapted service to the user according to the present disclosure. [Figure 9] FIG. 9 shows an alternative method that can be executed by a client device according to the present disclosure.

Best Mode for Carrying Out the Invention

[0029] In the following, specific details are described for the purpose of illustration rather than limitation to provide a thorough understanding of the present disclosure. It will be apparent to those skilled in the art that the present disclosure can be implemented by other implementations departing from these specific details.

[0030] Those skilled in the art will further understand that the steps, services, and functions described herein may be implemented using individual hardware circuits, software that functions in conjunction with programmed microprocessors or general-purpose computers, one or more application-specific integrated circuits (ASICs), and / or one or more digital signal processors (DSPs). Where this disclosure describes a method, it will also be understood that it is embodied in one or more processors and one or more memories coupled to one or more processors, where the one or more memories may be coded in one or more programs that perform the steps, services, and functions presented herein when executed by one or more processors.

[0031] Figure 1a schematically illustrates an exemplary configuration of server 100 that enables a client device to efficiently retrieve a digital representation of a user's personality data from server 100, which is then processed in the client device to provide the user with user-tailored services. Server 100 comprises at least one processor 102 and at least one memory 104, the at least one memory 104 including instructions executable by at least one processor 102, such that the request server 100 is operable to perform steps of the method described herein with reference to “server”.

[0032] It will be understood that Server 100 may be implemented on a physical computing unit or a virtualized computing unit, such as a virtual machine. Furthermore, it will be understood that Server 100 is not necessarily limited to being implemented on a standalone computing unit, but may also be implemented as a component residing on multiple distributed computing units, such as a cloud computing environment, which is implemented in software and / or hardware.

[0033] Figure 1b schematically illustrates an exemplary configuration of a client device 110 that enables the client device 110 to efficiently retrieve a digital representation of a user's personality data from a server. The client device 110 has at least one processor 112 and at least one memory 114, the at least one memory 114 containing instructions executable by at least one processor 112 so that the requesting client device 110 is operable to perform steps of the method described herein with reference to “client device”.

[0034] Figure 2 illustrates a method that may be performed by the Server 100 according to this Disclosure. This method is specifically designed to enable a client device (e.g., client device 110) to efficiently obtain a digital representation of a user's personality data from the Server 100. In this method, the Server 100 can perform steps described herein with reference to “Server,” and in accordance with the above description, in step S202, the Server 100 can store a neural network trained to compute the user’s personality data based on input from the user; in step S204, the Server 100 can receive a request from the client device for a digital representation of the user’s personality data; and in step S206, the Server 100 can transmit the requested digital representation of the user’s personality data to the client device, where the user’s personality data is computed using a neural network based on input from the user.

[0035] Figure 3 illustrates a method that can be performed by the client device 110 according to this disclosure. This method is specifically designed to enable the client device 110 to efficiently obtain a digital representation of a user's personality data from a server (e.g., server 100). In this method, the client device 110 can perform steps described herein with reference to “client device,” and in accordance with the above description, in step S302, the client device 110 can send a request for a digital representation of the user's personality data to the server; in step S304, the client device 110 can receive the requested digital representation of the user's personality data from the server, where the user's personality data is computed using a neural network trained to compute the user's personality data based on user inputs; and in step S306, the client device 110 can process the digital representation of the personality data to provide the user with a user-tailored service.

[0036] Figure 4 illustrates an exemplary interaction between a user 402, a server 404 that stores a neural network trained to compute the user's personality data based on input from the user, and a client device that retrieves a digital representation of the user 402's personality data and provides the user 402 with a user-tailored service. In the example shown, the client device could be a vehicle 406 driven by the user 402. As shown in the figure, the user 402 can perform an automated personality test, for example, by answering questions using a web interface or app on his laptop or smartphone, providing input to the neural network stored in the server 404, which can then compute the user 402's personality data. Instead of sending the digital representation of the personality data to the user 402, in the shown figure, the server 404 can provide the user 402 with an access code that the user can use to access the personality data using other client devices, including the vehicle 406. User 402 can register or log in to vehicle 406 (more specifically, its board computer) using an access code, and vehicle 406 can use the access code to request a digital representation of the user's personality data from server 404 (in the diagram, the user's personality data is referred to as the user's "MindDNA").

[0037] Upon receiving a request from vehicle 406, server 404 can return user personality data to vehicle 406, and vehicle 406 can configure its driving settings (and optionally, subcomponents of vehicle 406) according to user 402's personality data, for example by adapting the fuel and brake response behavior of vehicle 406 to provide a driving experience particularly suited to the user's personality (e.g., risk avoidance, risk pursuit, etc.). When user 402 drives vehicle 406, vehicle 406 can monitor the user's driving behavior, for example using sensors that measure the user's brake response and force, and vehicle 406 can provide this information to server 404 as feedback, where the feedback is processed to update a neural network (by training) to improve its ability to compute user 402's personality data. In response, server 404 can transmit the correspondingly updated personality data of user 402 to vehicle 406, and vehicle 406 can use the updated digital representation of the personality data to further improve vehicle settings to better match user 402's actual personality. In summary, a system is provided that integrates the acquisition and use of user personality data into an automated process and adapts the settings of the devices or services provided according to the user's preferences derived from the user's personality data, thereby improving the user experience.

[0038] Figure 5 illustrates other connectivity options between user 402's mobile terminal 502 (e.g., a smartphone), vehicle 406, and server 404 as provided in this disclosure. In one variation, vehicle 406 can communicate directly with server 404 via the internet, and once user 402 is authenticated in vehicle 406 (e.g., using a key, smart card, NFC / RFID, NFC-equipped smartphone, fingerprint, manually entered code, etc.), vehicle 406 can request user personality data (again, labeled as user's "MindDNA" in Figure 5) to improve user 402's driving experience. In another variation, when user 402 is carrying mobile terminal 502, mobile terminal 502 can communicate with server 404 via the internet (e.g., using a dedicated app installed thereon) and request user 402's personality data. In this modified version, vehicle 406 can communicate locally with mobile terminal 502 (for example, using Bluetooth®, Wi-Fi, or a USB cable) and obtain user personality data from mobile terminal 502. The direct connection between vehicle 406 and mobile terminal 502 can be further used to utilize sensors installed in mobile terminal 502 (for example, a gyroscope for motion and acceleration detection, GPS for motion and acceleration detection and driving path detection, or medical sensors for measuring pulse, blood pressure, etc.), supplementing the feedback collected by vehicle 406 itself (for example, related to the user's driving behavior), thereby providing additional feedback detected by mobile terminal 502 to server 404, and updating the neural network based on the feedback as described above.

[0039] Figure 6a shows an exemplary structure of the neural network 602 according to this disclosure. The neural network 602 includes an input layer, an output layer, and two hidden layers. The neural network 602 shown in Figure 6a is merely an example of a general deep neural network structure, and the actual number of nodes (at least in the input and hidden layers) of the neural network 602 stored in server 404 can be significantly higher than illustrated. As described above, the test is performed using 30 of the most influential questions from a total of more than 370 questions (taken from standard IPIP, HEXACO-60, and BFI-10 questions, optionally supplemented by additional questions on goals and motivations), resulting in 30 input nodes in the input layer of the neural network 602. In this case, for example, each hidden layer could consist of 50 nodes. Furthermore, as illustrated, the neural network 602 may include a single output node in the output layer. In this case, the resulting value of the output node in the output layer may represent the value of one personality dimension (of the Big Five) on which the neural network 602 was trained. This structure of neural network 602 is merely illustrative, and it should be understood that other structures are generally conceivable.

[0040] A more advanced structure of the neural network 602 has input nodes corresponding to the number of complete sets of available questions, which can be taken from standard IPIP, HEXACO-60, and BFI-10 questions, and may also include further questions about the user's goals and motivations, as well as questions about other psychological characteristics and / or preferences of the user that are not covered by the above questions, potentially adding hundreds of additional questions, e.g., more than 600 questions. Thus, such a neural network 602 can have more than 600 input nodes, each corresponding to a single question in the complete set of available questions, and the number of nodes in the hidden layer can be selected according to the performance of the neural network 602. For example, the neural network 602 can consist of two hidden layers, each with 100 nodes. Furthermore, in the input layer, the above 600 or more input nodes can be duplicated, and each of the duplicated input nodes can be used as a missing-question-indicator. The missing question indicator is dichotomous, meaning it can have two values ​​(e.g., 0 and 1) indicating whether the question for the corresponding (original) input node has been answered. Due to duplicate input nodes, the input layer can have more than 1200 input nodes in total.

[0041] The output layer of a more advanced neural network 602 may have multiple output nodes that together represent the probability curve of a single personality dimension. For example, if the scale used for the output of this personality dimension is in the range of 0 to 10 and there are 50 output nodes, each output node may represent a portion of the scale, i.e., a scale portion corresponding to the 0-0.2, 0.2-0.4, 0.4-0.6, ... 9.8-10 parts of the scale. Such an output layer can provide the entire probability curve of the output values ​​for this personality dimension, instead of a single output value. Figure 6b shows an exemplary output layer with the corresponding probability curve 604. Such a curve makes it possible to determine where the mode of the output value (i.e., indicated by the peak of the curve) lies, as well as the accuracy with which the neural network 602 calculates the result (i.e., indicated by the width of the curve). Using the advanced neural network 602, the neural network 602 can compute user personality data in the form of several probability curves (e.g., five probability curves corresponding to the Big Five) for any number of answered questions, by training the neural network 602 separately for each dimension. In the initial state where no questions have been answered, all missing question indicators can have a "missing" value (e.g., 0). Each time a question is answered, an update to the output value is computed, and as the number of answered questions increases, the width of the probability curves in the output layer decreases, and the accuracy of the neural network 602 in computed the results steadily improves.

[0042] Such a structure of neural network 602 is particularly advantageous because it allows the user to iteratively select the next question to be answered from a complete set of questions, where in each iteration, the next question can be selected according to the user's answer to the previous question, where in each iteration, the next question can be selected as one question from a complete set of questions that is determined to have the greatest impact on the achievable results for calculating the user's personality data. For this purpose, for each question answered, several (e.g., five) probability curves can be recalculated, and among the recalculated probability curves, the one with the largest width (i.e., representing the probability curve with the lowest accuracy at present) can be determined. As the next question in the iteration, a question for this dimension can be selected to improve the accuracy of this dimension. To determine the most influential question, the extent to which a change in the digital score input to each input node changes the probability curve (e.g., the extent to which the width of the curve changes) can be determined for each input node of neural network 602. Based on this, the question associated with the input node that is determined to have the greatest degree of change in the probability curve can be selected as the most influential question in each iteration.

[0043] The advanced structure of neural network 602 can also be advantageous because it allows for the easy integration of feedback into the neural network. As mentioned above, if the feedback represents a new input value that has not yet been input to neural network 602, then when training neural network 602, the new input node can simply be added to neural network 602, and the new input value is assigned to the new input node. In this way, any kind of new feedback can be easily integrated into the network, and neural network 602 can improve its ability to compute personality data. As an implementation to reduce the computational complexity when adding new input nodes, when the network is trained to correlate the new input node with the other nodes in the network, one could consider including only the node that is determined to have the most influence on the optimally achievable outcome in the computation, thereby avoiding including all nodes in the computation. Alternatively, when the network is trained to correlate the new input node with the other nodes in the network, one could consider, for example, limiting the number of layers to be pre-computed (e.g., to 2 or 3) so as not to compute all subsequent combinations of nodes.

[0044] In the above description, the technology for efficiently acquiring a digital representation of a user's personality data was illustrated in the context of adapting vehicle driving settings, such as the vehicle's fuel and brake response behavior, to the user's personality. In this case, the method described herein may also be shown as a method for adapting vehicle driving settings, which includes efficiently acquiring a digital representation of a user's personality data. Adapting the vehicle's fuel and brake response behavior is merely one example of adapting vehicle driving settings; more generally, it will be understood that adapting vehicle driving settings may include adapting any vehicle settings that affect the vehicle's driving behavior. Adapting vehicle driving settings may include adapting the vehicle's fuel and brake response behavior, adapting the vehicle's chassis settings, adapting the vehicle's drive mode, and adapting the settings of the vehicle's adaptive cruise control (ACC), etc., to the user's personality. Adapting a vehicle's drive mode may include setting economy, comfort, or sport modes that affect the vehicle's accelerator pedal and fuel consumption behavior according to the driver's personality. If personality data indicates that the driver tends to avoid risk, for example, the drive mode may be set to economy or comfort; on the other hand, if the driver tends to have a risk-seeking personality, the drive mode may be set to sport mode. Adapting a vehicle's drive mode may also include, for example, enabling / disabling the vehicle's automatic four-wheel drive (4WD) mode. Adapting ACC settings may include, for example, setting the distance to the vehicle ahead and / or the target driving speed according to the driver's risk-averseness.

[0045] It will be understood that the technologies presented herein may also be used for other purposes in the context of vehicles, such as adapting the environmental conditions inside the vehicle's passenger compartment (or, more generally, may be similarly applied to other means of transport, such as aircraft and trains, such as adapting the environmental conditions inside the passenger compartment of a means of transport). In this case, the methods presented herein may also be shown as methods for adapting the environmental conditions inside the passenger compartment of a means of transport, including efficiently obtaining a digital representation of the user's personality data. Adapting the environmental conditions inside the passenger compartment of a means of transport may include adapting the passenger compartment temperature (for example, by adapting the passenger compartment air conditioning settings), adapting the interior lighting of the passenger compartment, and adjusting the oxygen level inside the passenger compartment to suit the user's personality. In addition to, or instead of, adapting the environmental conditions inside the passenger compartment, the technologies presented herein may also be used to adapt user-specific settings related to the passenger compartment. Adapting user-specific settings for the passenger compartment of a means of transport may include at least one of the following: adapting seat settings (e.g., seat height, seat position, seat massage settings, seat belt tension, etc.) to the user in the passenger compartment; and adapting equalizer settings of the sound system provided to the user in the passenger compartment (e.g., increasing or decreasing bass or treble) to the user's personality.

[0046] At least some of the above-mentioned adaptations, namely the adaptation of vehicle driving settings, the adaptation of in-cabin environmental conditions, and the adaptation of user-specific settings related to the cabin, may be performed adaptively and in an interdependent manner. That is, if a setting is adapted to take into account the user's personality data, this may be automatically accompanied by a series of further adaptations of settings. For example, if the vehicle's accelerator and brake response behavior is adapted to the user's personality, this may be automatically accompanied by further adaptations such as adapting the chassis settings and steering wheel settings accordingly. As another example, if the vehicle's headlights are turned on for a cautious driver, the 4WD and differential gears may also be automatically activated.

[0047] Any of the above-described adaptations of vehicle / transportation settings can be performed taking into account (or "based on") user sensor data indicating the user's attention level obtained in the cabin, in addition to adapting to the user's personality. In other words, the client device may be configured to adapt at least one of the vehicle's driving settings, cabin environmental conditions, and user-specific settings related to the cabin, taking into account not only the digital representation of the user's personality data, but also sensor data indicating the user's attention level. That is, the digital representation of the user's personality data and the sensor data indicating the user's attention level can be combined before performing the above-described adaptations. Sensor data indicating the user's attention level may include, for example, data on at least one of the user's heart rate, respiration, fatigue, reaction time, and alcohol / drug level. Sensor data is collected, for example, by at least one sensor installed in the cabin or the user's mobile device.

[0048] Figure 7 shows an exemplary implementation that includes considering the driver's attention level in combination with the driver's personality data to adapt vehicle driving settings, in-cabin environmental conditions, and / or user-specific settings related to the cabin. The driver's attention level is checked by corresponding sensors regarding, for example, the user's reaction time, fatigue, heart rate, respiration, alcohol / drug level, or abnormal user behavior. In the left portion of the figure, the collected sensor data indicates the user's normal attention level, so vehicle settings, including speed, volume, temperature, and seat settings, can remain at normal levels (for example, adapted to the driver's personality, i.e., "MindDNA"). In the middle portion of the figure, the sensor data indicates a decrease in the driver's attention level, so vehicle settings can be changed, such as slowing down, increasing volume, or decreasing temperature settings, including turning on the seat massage function, in order to refresh the driver's attention. Optionally, attention tests can be performed, for example, by requiring the driver to provide voice-based responses in a question / answer scheme, and the results of the attention tests may be considered when adapting the settings described above. On the other hand, in the right-hand portion of the diagram, the sensor data indicates that the driver's attention level is very low, so the system can issue a warning to the user and adjust the vehicle settings accordingly, for example, by slowing the speed to a very low level (and, for example, forcibly stopping the vehicle at the next opportunity to stop), muting the voice, and / or guiding the driver to the next hotel via the navigation system.

[0049] The above-mentioned vehicle / transportation method configuration adjustments may also be performed considering (or "based on" / "corresponding to") at least one of geographic data, weather data, and time data relating to the planned route to be traveled using the vehicle or transportation method. That is, the client device may be configured to adapt at least one of the vehicle's driving settings, cabin environmental conditions, and user-specific settings relating to the cabin, taking into account not only the digital representation of the user's personality data, but also the geographic data, weather data, and / or time data relating to the planned route. The digital representation of the user's personality data and the additional data relating to the planned route may, in other words, be combined before the adaptation is performed. Geographic data may include data relating to the terrain of the planned route, e.g., uphill / downhill gradients of mountain roads, information on winding roads and coastal roads, elevation, etc. Weather data may include information on current weather conditions (e.g., detected by the vehicle or transportation method itself using rain sensors, temperature sensors, etc.) or predicted weather conditions for the planned route (e.g., rain, cloudy, sunny, etc.). Time data may include, for example, information regarding the time schedule of the planned route, such as daytime driving, driving during transitional light periods (dusk or dawn), or nighttime driving. Depending on such data, the vehicle's driving settings, the environmental conditions inside the cabin, and user-specific settings related to the cabin may be tailored to the user's personality. For example, if difficult terrain / weather / time conditions occur on the planned route, 4WD or similar systems may be activated to provide safe driving for risk-averse drivers.

[0050] As described above, in order to provide a user-tailored service to the user (for example, by adapting at least one of the vehicle's driving settings, the cabin environment conditions, and user-specific settings related to the cabin), the client device may further consider body scan data that reveals the user's (e.g., physical) characteristics that can be derived by scanning the user's body (e.g., at least a portion of it) before providing a user-tailored service to the user (for example, before the user drives the vehicle). User characteristics that can be derived by scanning the user's body may include, for example, at least one of the user's size, weight, gender, age, height, posture, and emotional state. Alternatively or additionally, user characteristics that can be derived by body scanning may also include, for example, specific movements of the user or items the user is carrying. Body scan data is acquired by obtaining one or more images or audio signals of the user by a radar device, a camera (including, for example, a 360-degree camera, an infrared (IR) camera, etc., installed on the user's mobile device or vehicle / transportation vehicle), or a voice recorder, where body / face / voice recognition technology can be used to scan the user's body and derive the user characteristics described above. Therefore, the client device is configured to provide user-tailored services by considering (or "based on") the body scan data as well as the digital representation of the user's personality data. That is, the digital representation of the user's personality data and the body scan data can be combined before providing the user-tailored service to the user. Figure 8 shows an exemplary implementation that includes considering the driver's body scan data (for example, acquired by the driver's mobile device, such as the driver's smartphone, smartwatch, or fitness tracker, before entering the vehicle) in combination with the driver's personality data in order to appropriately adapt the vehicle's driving settings, the environmental conditions inside the cabin, and / or user-specific settings related to the cabin. In this diagram, body scan data is labeled "BodyDNA," and when combined with "MindDNA," it forms what is known as "LifeDNA."It will also be understood that the acquired body scan data can be used, as mentioned above, to provide feedback that characterizes the user in order to update the neural network.

[0051] Furthermore, it will be understood that in other embodiments, the client device may be configured to provide user-tailored services by considering only body scan data, i.e., without considering a digital representation of the user's personality data. In such an example, the body scan may detect the user (e.g., using facial recognition for authentication purposes) and open the vehicle doors when the user's movements (determined by the body scan) indicate that the user is approaching the vehicle. Similarly, the vehicle's trunk may be automatically opened, for example, when it is detected that the user is carrying an item (e.g., a bag or suitcase). Such a method can generally be called a method of providing user-tailored services to a user, and this method may include obtaining body scan data that represents the user's characteristics, which is performed by the client device and derived by scanning at least a portion of the user's body, and processing the body scan data to provide user-tailored services. Any of the exemplary body scan data described above may be used for such purposes, and for example, if the client device is a vehicle, the body scan data may be used to tailor at least one of the vehicle's driving design, the environmental conditions in the passenger compartment, and user-specific settings regarding the passenger compartment (i.e., without further consideration of the user's personality data in the sense described above). If at least some of the body scan data is already available in the user's user profile (e.g., pre-stored), then such data may be retrieved from the user profile when authenticating the user, in which case it will be understood that a body scan to determine the corresponding data does not necessarily need to be performed in real time.The fact described in this paragraph, namely that the client device may be configured to provide user-tailored services considering only body scan data, i.e., without considering a digital representation of the user's personality data, is also applicable to other vehicle-related use cases described herein, such as the use case that considers sensor data indicating the user's attention level, the use case that considers at least one of the geographic data, weather data, and time data relating to the aforementioned planned driving route, the use case that considers predetermined conditions that are monitored and potentially indicate the user's suicidal intent, and the use case that considers the goals and / or preferences of a user driving another vehicle nearby in order to implement the collectively improved driving behavior of the group of vehicles described below, and it is generally conceivable that all of these operate similarly without additionally (or "combined") considering a digital representation of the user's personality data.

[0052] In other vehicle-related use cases, the technologies presented herein can also be used to determine vehicle settings that are suited to the user's personality before manufacturing the vehicle, and the vehicle may be manufactured based on (or "according to") the determined vehicle settings. Vehicles can be manufactured with different setting options (e.g., provided by the vehicle manufacturer), such as different motor options with different motor outputs, drive technology options (e.g., support for two-wheel drive (2WD) or four-wheel drive technology), chassis options, different drive mode options, ACC support, etc., and when a new vehicle is manufactured for a user, the vehicle settings are determined to be specifically suited to the user's personality. For example, if personality data indicates that the user tends to avoid risk, the determined vehicle settings may include the selection of a motor with lower output compared to the vehicle settings determined for a user whose personality data indicates that they seek risk. Based on the determined vehicle settings, the vehicle may be manufactured as appropriate. Therefore, in accordance with the above description, a vehicle manufacturing method can also be envisioned that includes efficiently obtaining a digital representation of a user's personality data from a server via a client device, where the digital representation of the personality data is processed on the client device to provide a vehicle configuration suited to the user's personality. This method may include sending a request for a digital representation of the user's personality data from the client device to the server, and the client device receiving the requested digital representation of the user's personality data from the server, wherein the digital representation of the user's personality data is computed using a neural network trained to compute the user's personality data based on inputs obtained from the user, processing the digital representation of the personality data to determine a vehicle configuration suited to the user's personality, and manufacturing the vehicle based on the determined vehicle configuration. In the vehicle manufacturing process, it will be understood that the determined vehicle configuration may also influence the manufacturing of vehicle parts necessary for the vehicle's production.For example, vehicle manufacturing may include the manufacture of one or more vehicle parts used in the manufacture of the vehicle, and the vehicle parts are manufactured according to the determined vehicle configuration (for example, using a 3D printer).

[0053] Furthermore, in other vehicle-related use cases, the provision of user-tailored services to users may involve security features aimed at preventing harm from users who have a potential suicidal tendency. For this purpose, a client device (e.g., a vehicle) may monitor predefined conditions (e.g., based on sensor measurements) that potentially indicate a user's suicidal intent. If a suicidal intent is determined based on such conditions, the client device may compare the detected conditions with the user's personality data and, if it concludes that the combination of the detected conditions and the user's personality data (e.g., indicating that the user suffers from severe depression) may actually pose a risk of suicide, it may take preventive measures. Therefore, the client device may be configured to provide user-tailored services, taking into account (or "based on" / "in response to") predefined conditions that are monitored and potentially indicate the user's suicidal intent, in addition to a digital representation of the user's personality data (the digital representation of the user's personality data and the detected predefined conditions may, in other words, be combined before providing user-tailored services to the user), and providing user-tailored services to the user may include triggering one or more precautionary measures to counteract the user's suicidal intent. An exemplary condition may include detecting that the user is sitting or lying down inside the vehicle while the vehicle's motor is still running but the vehicle has not moved for at least a predetermined time (potentially indicating that exhaust fumes are entering the passenger compartment; optionally, this may be detected by a sensor inside the passenger compartment). The corresponding measures may include triggering an alarm, triggering an emergency call (e.g., depression hotline, police, friend, family, etc.), or simply stopping the motor. Other predefined conditions may include detecting that the user has parked the vehicle in a location where there is a risk of suicide, such as a bridge, a steep cliff, or the side of a river or lake, and similarly, this may trigger an alarm or emergency call.Further conditions may include detecting that the user is tailgates while driving at high speed, and optionally, in combination with detecting a scream inside the vehicle indicating an outburst of anger, simultaneously detecting that the user is alone in the vehicle (e.g., using seat occupancy detection) to rule out the possibility that the scream is the result of a dispute between multiple passengers. Corresponding measures may include, for example, automatically slowing / limiting the vehicle's speed, automatically maintaining a safe distance, initiating an automated conversation or playing music to relax the user, and suggesting an alternative driving route. These conditions and measures are merely illustrative, and it should be understood that a variety of other use cases are generally conceivable.

[0054] Furthermore, in other vehicle-related use cases, the provision of user-tailored services to a user may relate not only to the user's vehicle itself, but also to an entire group of vehicles. If a group of vehicles (including the user's vehicle) are traveling close to each other (e.g., within their line of sight), and personality data of users (e.g., drivers / passengers) of other vehicles is available (e.g., in the same / similar manner as described above for the current user), the current user's personality data may be compared (or "matched") with the personality data of each of the other drivers to determine and implement improvements to the collective driving behavior of the group of vehicles, that is, taking into account (or "respecting") the personalities of individual drivers, and optionally further considering additional individual drivers' driving goals or preferences, the driving behavior (or "composition") of the group of vehicles may improve (or "optimize") traffic. Therefore, a vehicle may be one of several vehicles traveling in close proximity to each other, and the digital representation of a user's personality data may be compared to one or more digital representations of the user's personality data of other vehicles in the group, taking into account the individual personality of each user and, at an optional further consideration, each user's driving goals or preferences, in order to implement collectively improved driving behavior for the group of vehicles. For example, if a group of vehicles is driving autonomously, a vehicle with a stressed driver may be allowed to overtake another vehicle with a more relaxed driver who is more accepting of such an overtaking maneuver. Collectively improved driving behavior may be directed, for example, to improve (or "optimize") traffic flow or energy consumption among the group of vehicles. Therefore, in a vehicle platoon, it is conceivable that vehicles driven by more relaxed drivers may travel in the slipstream of other vehicles, or that electric vehicles traveling short distances with sufficient electrical energy may transfer some of their energy (for example, using induction) to other vehicles driven by more conservative drivers traveling longer distances.To take into account a user's specific driving goals or preferences, the user may input corresponding goals or preferences at the start or during a vehicle journey, for example, by using statements such as "hurrying," "relaxed," or "under pressure." If there are multiple passengers in the vehicle, the personality data of all passengers in the vehicle may be used to determine collective personality data that represents all passengers in the vehicle and to compare it with the personality data of other vehicles. Determining the collective personality data may include, for example, the personality data of individual passengers in the vehicle and averaging or weighting their values. The same may apply to the user's driving goals and preferences, which may also be combined with collective goals and / or preferences for comparison with other vehicles. To implement collectively improved driving behavior among vehicle groups, vehicles may communicate with each other, for example, using vehicle-to-vehicle (V2V) communication, and adjust themselves accordingly.

[0055] It will be understood that the technologies presented herein are applicable not only to use cases related to vehicles / transportation methods, but also to other use cases, such as adapting the settings of smart home appliances or robots to a user's personality. Thus, in accordance with the above description, a method can also be envisioned for adapting the settings of smart home appliances (e.g., automatic roller shutters, air conditioners, refrigerators, washing machines, televisions, set-top boxes, etc.) to efficiently acquire a digital representation of the user's personality data, which is processed on a client device in order to adapt the settings of the smart home appliance to the user's personality (e.g., how the smart home appliance performs key tasks such as shutters (roller shutters), heating / cooling (air conditioners), refrigeration (refrigerators), washing (washing machines), or recording / displaying (televisions / set-top boxes) tasks). Similarly, in accordance with the above description, we can envision a method for adapting the settings of a robot (e.g., a humanoid robot configured to perform one or more household tasks, a household robot, a robot that functions as a virtual driver for a vehicle, a vendor robot in a supermarket, etc.) to efficiently acquire a digital representation of the user's personality data, where the digital representation of the user's personality is processed on the client device to adapt the robot's settings to the user's personality (e.g., to adapt the robot's movements, such as how a humanoid robot mimics facial expressions (e.g., lip or eye movements), or how it performs controls, or to adapt how a household robot performs household chores).

[0056] A variety of other use cases are generally conceivable. These other use cases may include, for example, adapting the settings of a virtual robot, adapting the settings of a medical device, or even stimulating the brain. Accordingly, in accordance with the above description, a method for adapting the settings of a virtual robot (e.g., a chatbot, a virtual service provider, a virtual personal assistant) can be envisioned, which involves efficiently acquiring a digital representation of the user's personality data, where the digital representation of the user's personality is processed on the client device in order to adapt the virtual robot's settings to the user's personality (e.g., to adapt how the virtual robot performs tasks to support the user). Similarly, in accordance with the above description, a method for adapting the settings of a medical device (e.g., a bedside medical device) can be envisioned, which involves efficiently acquiring a digital representation of the user's personality data, where the digital representation of the user's personality may be processed on the client device in order to adapt the medical device's settings to the user's personality (e.g., to adapt an administration plan, such as the dosage of analgesics). Furthermore, we can envision a method for stimulating the brain (e.g., a biological or virtual representation of the brain) that includes efficiently acquiring a digital representation of the user's personality data, where the digital representation of personality is processed on the user's client device to adapt a brain stimulation procedure based on the user's personality. The stimulation procedure may include, for example, electrical stimulation of a biological brain or adapting / reconfiguring a virtual representation of the brain. The virtual representation of the brain is supplied, for example, to a robot or other form of intelligent system to influence the behavior of such a system based on the user's personality.

[0057] In all the examples and use cases described above, when referring to "adapting" a configuration or setting to a user's personality, it will be understood that such adaptation can be implemented using predefined mappings that map certain characteristics of the user's personality (as indicated by the digital representation of the user's personality data) to specific configurations or settings of the corresponding device / equipment (e.g., vehicles, means of transport, smart appliances, robots, medical devices, etc., as described above). As mentioned above, for example, if personality data indicates that a driver tends to avoid risk, the vehicle's drive mode can be set to economy or comfort, while if the driver tends to have a risk-seeking personality, the drive mode can be set to sport mode. Such mappings can be predefined for each possible personality trait-configuration / setting combination, and the device / equipment configuration or settings can be adapted as appropriate according to the acquired user personality data. A user's personality traits can, for example, correspond to the values ​​of personality dimensions (e.g., from the Big Five personality model) output by a neural network, as described above.

[0058] While the above description explains that the technology presented herein enables a client device to efficiently retrieve a digital representation of a user's personality data from a server (which is applicable in various use cases), it will be understood that the calculated digital representation of the user's personality data does not necessarily need to be sent directly from the server to the client device. Rather, once the user's personality data is available to the user, it may be manually entered into the client device by the user. Therefore, a method may also be envisioned in which the client device provides user-tailored services to the user of the client device (in this case, there may not be a direct client-server relationship, so this "client device" may not necessarily be understood as a device in a client-server relationship, and thus the client device may be simply referred to as "device"), where this method may be performed by the client device and may have the steps of: retrieving a digital representation of the user's personality data via manual input by the user; and processing the digital representation of the personality data to provide user-tailored services to the user. Such a method is illustrated in Figure 9, where step S902 shows a corresponding step of obtaining a digital representation of the user's personality data, and step S904 shows a corresponding step of processing the digital representation of the user's personality data. All the embodiments described above may be applied to the method in Figure 9, particularly with respect to the client device and server, except that the method of inputting the digital representation of the user's personality data into the client device is different (i.e., inputting it via manual input instead of directly from the server).Therefore, the digital representation of the user's personality data obtained by the client device via the user's manual input may be computed by the server based on the user's input using a neural network trained to compute the user's personality data based on the user's input (however, it is not necessarily required to be computed in this manner, as the user's manual input may also correspond to the user's personality data determined by other means). In one variation, as described above, the client device may be a vehicle, and providing a user-tailored service to the user may include tailoring the vehicle's driving settings to the user's personality.

[0059] Instead of manually entering a digital representation of the user's personality data, a vehicle identification number may be used to identify the selected vehicle configuration option, where the vehicle may be manufactured based on the vehicle configuration option (for example, provided by the vehicle manufacturer as described above). The thus identified vehicle configuration may then be used as "user input" in the sense described above, that is, to request the server to use a neural network to compute the user's personality data based on the input. The user's personality data thus obtained may then be used in any of the ways described above to provide user-tailored services to the vehicle user.

[0060] The advantages of the technology presented herein will be fully understood from the above description, and it will be clear that various modifications can be made to the form, structure, and arrangement of its exemplary embodiments without departing from the scope of this disclosure or sacrificing all of its advantageous effects. Since the technology presented herein can be modified in many ways, it will be understood that this disclosure should be limited only by the following claims.

[0061] A favorable example of this disclosure can be expressed as follows: [Example 1] A method for efficiently obtaining a digital representation of a user's (402) personality data from a server (404) by client devices (502, 406), wherein the digital representation of the personality data is processed in the client device (406) to provide user-appropriate services to the user (402), and the method is executed by the server (404). (S202) saves a neural network (602) that has been trained to calculate the personality data of the user (402) based on the input obtained from the user (402), The system receives a request from the client devices (502, 406) for a digital representation of the user's (402) personality data (S204), S206) transmits the requested digital representation of the user's (402) personality data to the client devices (502, 406), wherein the user's (402) personality data is calculated using the neural network (602) based on input from the user (402). A method of having. [Example 2] The digital representation of the user (402)'s personality data is processed in the client devices (502, 406) to configure at least one device (406) to provide services to the user (402). Optionally, the at least one device (406) includes the client device (406), The method described in Example 1. [Example 3] Receiving feedback that characterizes the aforementioned user (402), The neural network (602) is updated based on the aforementioned feedback, The method involves transmitting a digital representation of the user's (402) updated personality data to the client devices (502, 406), further comprising the fact that the updated personality data of the user (402) is calculated using the updated neural network (602). Optionally, the digital representation of the updated personality data of the user (402) is processed in the client device (502, 406) to improve the settings of the at least one device (406) that provides the service to the user (402). The method described in Example 1 or 2. [Example 4] The feedback includes behavioral data that reflects the user's (402) behavior as monitored by the at least one device (406) when using the service provided by the at least one device (406). Optionally, the behavioral data is monitored using measurements performed by at least one device (406) that provides the service to the user (402). The method described in Example 3. [Example 5] The at least one device (406) includes a vehicle, and the behavioral data includes data reflecting the driving behavior of the user (402). The method described in Example 4. [Example 6] The personality data of user (402) is calculated before receiving the request from the client devices (502, 406), and the request includes an access code provided to user (402) in advance by the server (404) when calculating the personality data of user (402), the access code enabling user (402) to access the digital representation of user (402)'s personality data from other client devices (502, 406). The method described in any one of Examples 1 to 5. [Example 7] The input obtained from the user corresponds to a digital score that reflects the user's (402) answers to questions relating to at least one of the user's personality, goals, and motivations, and each digital score is used as input to a separate input node of the neural network (602) when the neural network (602) is used to compute the user's (402) personality data. The method described in any one of Examples 1 to 6. [Example 8] The aforementioned questions correspond to questions selected from a set of questions that represent the most optimal outcome for calculating the user's (402) personality data. The selected questions correspond to the questions in the set of questions that were determined to have the most influence on the optimally achievable outcome. The number of questions selected is optional, and the number of selected questions is less than 10% of the number of questions included in the set of questions. The method described in Example 7. [Example 9] The questions are selected from the set of questions based on correlating the results achievable by each of the single questions in the set of questions with the optimally achievable results, and selecting questions from the set of questions that have the highest correlation with the optimally achievable results, or The questions are repeatedly selected from the set of questions, and in each iteration, the next question is selected in accordance with the user's answer to the previous question, and in each iteration, the next question is selected as one of the questions in the set of questions that is determined to have the most influence on the achievable results for calculating the user's personality data. Optionally, the neural network (602) includes a plurality of output nodes representing a probability curve (604) of the results of the user's (402) personality data, and determining the most influential question in the set of questions as the next question in each of the repetitions includes, for each input node of the neural network (602), determining to what extent the change in the digital score input to each input node of the neural network (602) changes the probability curve (604). The method described in Example 8. [Example 10] A method for efficiently obtaining a digital representation of a user's (402) personality data from a server (404) by client devices (502, 406), wherein the method is performed by the client devices (502, 406), Sending a request for a digital representation of the user's (402) personality data to the server (404) (S302), S304) receiving the requested digital representation of the user's (402) personality data from the server (404), wherein the user's (402) personality data is calculated based on the input obtained from the user (402) using a neural network (602) trained to calculate the user's (402) personality data based on the input obtained from the user (402). Processing the digital representation of the personality data (S306) in order to provide the user (402) with a user-appropriate service, A method of having. [Example 11] A computer program product comprising a program code portion for performing the method described in any one of Examples 1 to 10 when the computer program product is executed on one or more computing units. [Example 12] A computer program product as described in Example 11, stored on one or more computer-readable recording media. [Example 13] A server (100, 404) that enables a client device (502, 406) to efficiently obtain a digital representation of a user's (402) personality data from the server (404), wherein the digital representation of the personality data is processed in the client device (502, 406) to provide the user-tailored service to the user (402), and the server (404) comprises at least one processor (102) and at least one memory (104), the at least one memory (104) containing instructions executable by the at least one processor (102) so that the server (404) is operable to perform the method described in any one of Examples 1 to 9. [Example 14] A client device (110, 502, 406) that enables efficient retrieval of a user's (402) personality data from a server (404), wherein the client device (110, 502, 406) comprises at least one processor (112) and at least one memory (114), the at least one memory (114) containing instructions executable by the at least one processor (112) such that the client device (110, 502, 406) is operable to perform the method described in Example 10. [Example 15] A system comprising the server (100, 404) described in Example 13 and at least one client device (110, 502, 406) described in Example 14.

Claims

1. A method for providing a user-appropriate service to a user (402) of a vehicle (406), wherein the method is: Step (S902) of obtaining a digital representation of the personality data of the user (402), wherein the personality data of the user (402) represents the psychological characteristics of the user (402), The process includes the step (S904) of processing the digital representation of the personality data to provide a user-tailored service to the user (402), wherein the step of providing a user-tailored service to the user (402) includes tailoring the settings of the vehicle (406) to the personality of the user (402). To adapt the above settings of the vehicle (406) is to (a) Adapting the driving settings of the vehicle (406) to the personality of the user (402), wherein the driving settings of the vehicle (406) correspond to vehicle settings that affect the driving behavior of the vehicle (406), Includes, Adapting the settings of the vehicle (406) to the personality of the user (402) is implemented using a mapping that maps the characteristics of the user's (402) personality, as indicated by the digital representation of the user's (402) personality data, to specific settings of the vehicle (406). Adapting the settings of the vehicle (406) to the personality of the user (402) is further performed based on geographic data relating to the planned route to be traveled using the vehicle (406). method.

2. The method according to claim 1, wherein providing the user-tailored service to the user (402) is monitored and further performed in consideration of predefined conditions that potentially indicate the user (402)'s suicidal intent, and providing the user-tailored service to the user (402) further comprises triggering one or more precautionary measures to counteract the user (402)'s suicidal intent.

3. The method according to claim 1 or 2, wherein the vehicle (406) is one of a plurality of vehicles (406) traveling in close proximity to each other, and the digital representation of the user's (402) personality data is compared with one or more digital representations of the user's (402) personality data of other vehicles among the plurality of vehicles (406) in order to implement collectively improved driving behavior of the plurality of vehicles (406), with consideration to the individual personality of each user (402) and optionally further considering each user's (402) driving goals or preferences.

4. The method according to any one of claims 1 to 3, wherein the personality data of the user (402) is calculated by the server (404) based on the input obtained from the user (402), using a neural network (602) trained to calculate the personality data of the user (402) based on the input obtained from the user (402).

5. The method according to claim 4, wherein the input obtained from the user (402) corresponds to a digital score reflecting the user's (402) answers to questions relating to at least one of the user's (402) personality, goals, and motivations, and each digital score is used as input to a separate input node of the neural network (602) when the neural network (602) is used to compute the user's (402) personality data.

6. The aforementioned questions correspond to questions selected from a set of questions that represent the most optimal outcome for calculating the user's (402) personality data. The selected questions correspond to the questions in the set of questions that were determined to have the most influence on the optimally achievable outcome. The method according to claim 5, wherein, at the discretion of the user, the number of selected questions is less than 10% of the number of questions included in the set of questions.

7. The questions are selected from the set of questions based on correlating the results achievable by each of the single questions in the set of questions with the optimally achievable results, and selecting questions from the set of questions that have the highest correlation with the optimally achievable results, or The questions are repeatedly selected from the set of questions, and in each iteration, the next question is selected in accordance with the user's answer to the previous question, and in each iteration, the next question is selected as one of the questions in the set of questions that is determined to have the most influence on the achievable results for calculating the user's personality data. The method according to claim 6, wherein the neural network (602) optionally includes a plurality of output nodes representing a probability curve (604) of the results of the user's (402) personality data, and determining the most influential question of the set of questions as the next question in each of the repetitions includes determining, for each input node of the neural network (602), the extent to which a change in the digital score input to each input node of the neural network (602) changes the probability curve (604).

8. A computer program, which includes a program code portion for performing the method according to any one of claims 1 to 7 when the computer program is executed on one or more computing units.

9. A computer-readable recording medium that stores the computer program described in claim 8.

10. A vehicle (406) for providing user-conformed services to a user (402), the vehicle (406) having at least one processor (112) and at least one memory (114), wherein the at least one memory (114) includes instructions executable by the at least one processor (112) such that the vehicle (406) is operable to perform the method according to any one of claims 1 to 7.

Images