Environment design illumination adjustment interaction method and system

Abstract

The invention relates to the technical field of illumination, and discloses an environment design illumination adjustment interaction method and system, and the method comprises the steps: receiving an illumination adjustment instruction sent by a user, and obtaining the task intention of the user based on the instruction; and when the task intentions have conflicts, the system can process the conflicting task intentions so as to obtain and execute the lighting target. According to the method, the problem that in the prior art, illumination demand conflicts in a multi-user shared space are difficult to coordinate is effectively solved, the situation that the illumination environment is unstable due to instruction conflicts is avoided, and the working experience of the users and the trust of the users to the system are improved. Through an intelligent conflict processing mechanism, the stability and comfort of the lighting environment can be ensured, so that the user satisfaction and practicability of the intelligent lighting system are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of lighting technology, and more particularly to an interactive method and system for environmental design lighting adjustment. Background Technology

[0002] In modern office environments, intelligent lighting systems are widely used to improve work efficiency and comfort. These systems typically offer multiple interaction methods, allowing users to adjust lighting according to their individual needs. However, in open spaces shared by multiple users, different users may have immediate and differentiated lighting requirements for the same lighting area. This often leads to difficulties in handling conflicting adjustment commands from different users. Traditional lighting adjustment methods often struggle to effectively coordinate these conflicts, resulting in instability in the lighting environment and even impacting users' work experience and trust in the system. Summary of the Invention

[0003] This invention provides an interactive method and system for environmental design lighting adjustment. In an open office environment shared by multiple users, the lighting instability caused by conflicting adjustment commands issued by different users to the same lighting unit is addressed by understanding the true task intent behind the user's operation and performing intelligent arbitration, thereby providing a stable lighting environment that meets the user's needs.

[0004] In a first aspect, to solve the above-mentioned technical problems, the present invention provides an interactive method for environmental design lighting adjustment, comprising: Receive lighting adjustment commands from users; Based on the lighting adjustment command, the user's task intent is obtained; When there is a conflict between the task intentions, the conflicting task intentions are processed and the lighting target is obtained. Perform the lighting objective.

[0005] Preferably, when there is a conflict in the task intent, the conflicting task intents are processed before obtaining the illumination target, including: Calculate the overall priority of the conflicting task intentions; Based on the comprehensive priority, identify the highest priority task intent and the second highest priority task intent and calculate the priority difference; Preset priority elastic range threshold; When the priority difference is less than or equal to the priority elastic range threshold, the current lighting state is maintained; When the highest priority task intent has a continuously higher priority than other task intents, and the priority difference has a continuously greater than the priority elastic range threshold, or when a user forces a switch command, the current lighting state is canceled.

[0006] Preferably, the calculation of the comprehensive priority of the conflicting task intent includes: Obtain the user's identity information, which includes the user's role level and permission weight; The weight factor of the user role is determined based on the user role level and the permission weight. The weighting factor is weighted together with the basic priority of the task intent, the time context weight, the activity type context weight, the number of users, and the intent intensity weight to obtain the comprehensive priority.

[0007] Preferably, obtaining the user's task intent based on the lighting adjustment command includes: According to a preset set of digital context mapping rules, the lighting adjustment command is mapped to a preset task scenario; If mapping fails, obtain the window title or document name of the active application and perform keyword matching; When a match is found, the user's task intent is inferred based on the keywords. If there is a mismatch, a query is sent to the user to obtain the user's task intent.

[0008] Preferably, when a user forces a switch command, the current lighting state is deactivated, including: Record the duration of the current lighting state; Periodically evaluate the degree of match between the current lighting state and the ideal lighting parameters of the conflicting task intent; When the matching degree is lower than the preset matching degree threshold and the maintenance time exceeds the preset maximum maintenance time, an inquiry is sent to the user to obtain the user's confirmation instruction on whether the current lighting state needs to be adjusted. If necessary, the current lighting state is deactivated. Preferably, the periodic evaluation of the match between the current lighting state and the ideal lighting parameters of the conflicting task intent includes: Obtain the brightness, color temperature, and directionality parameters of the current lighting state; Obtain the ideal lighting parameters for the conflicting task intent, including ideal brightness, ideal color temperature, and ideal directionality parameters; Calculate the brightness deviation, color temperature deviation, and directionality deviation between the current lighting state and the conflicting task intent, respectively; The weighted sum of the brightness deviation, the color temperature deviation, and the directionality deviation is obtained by weighting and summing them. After performing a nonlinear mapping on the weighted bias, the matching degree of the conflicting task intent is obtained; after performing a weighted average on the matching degree, the overall matching degree is obtained.

[0009] Preferably, the ideal lighting parameters for obtaining the conflicting task intent include ideal brightness, ideal color temperature, and ideal directionality parameters, including: Obtain the user's task intent and obtain the preset ideal lighting parameters corresponding to the task intent; Obtain the user's satisfaction feedback on the current lighting status; Based on the satisfaction feedback, the preset ideal lighting parameters are adjusted to obtain the ideal lighting parameters.

[0010] Preferably, obtaining the user's satisfaction feedback on the current lighting status includes: The agent program deployed on the user's personal computing device monitors the user's keyboard input frequency and mouse movement frequency on the personal computing device. When the keyboard input frequency and the mouse movement frequency are consistently lower than a preset activity threshold, the user is determined to be in an inactive state. When the keyboard input frequency and the mouse movement frequency are consistently higher than a preset activity threshold, the user is determined to be in an active state. When the user is in the active state, a satisfaction rating slider or emoji selection is provided through the application interface on the personal computing device to obtain the satisfaction level expressed by the user by actively clicking or dragging. When the user is in the inactive state, the system uses cameras deployed in the lighting area, combined with image recognition technology, to analyze the user's facial expressions or body posture and infer the user's satisfaction with the current lighting state.

[0011] The analysis of the user's facial expressions or body posture to infer the user's satisfaction with the current lighting condition includes: Obtain the user's facial key points and body key points, and extract facial expression features and body posture features; Monitor ambient noise levels and voice content to identify whether the user is communicating. Monitor the temperature and humidity at the user's workstation to determine if the user is experiencing any physical discomfort; The facial expression features, body posture features, ambient noise intensity, voice content, and user health data are integrated. Based on preset interference elimination rules, identify and eliminate the influence of non-lighting factors on the facial expression features or the body posture features; The removed facial expression features and body posture features are compared with preset satisfaction expression patterns and posture patterns to infer the user's satisfaction with the current lighting state.

[0012] Secondly, the present invention provides an environmental design lighting adjustment interactive system, comprising: The data acquisition unit is used to receive lighting adjustment commands issued by the user. The processing unit is used to obtain the user's task intent based on the lighting adjustment command; when there is a conflict between the task intents, the conflicting task intents are processed and the lighting target is obtained. The execution end is used to execute the lighting target.

[0013] This application discloses an interactive method and system for environmental lighting adjustment. It receives lighting adjustment commands from users and obtains the user's task intent based on these commands. When conflicting task intents exist, the system can process the conflicting intents, thereby obtaining and executing the lighting target. This method effectively solves the problem of difficulty in coordinating conflicting lighting needs in shared spaces with multiple users in existing technologies, avoiding instability in the lighting environment caused by command conflicts, and improving the user's work experience and trust in the system. Through an intelligent conflict handling mechanism, this application can ensure the stability and comfort of the lighting environment, thereby significantly improving user satisfaction and practicality of intelligent lighting systems. Attached Figure Description

[0014] Figure 1 This is a flowchart of an interactive method for adjusting lighting in environmental design, provided by an embodiment of the present invention; Figure 2 This is a flowchart of another environmental design lighting adjustment interaction method provided by an embodiment of the present invention; Figure 3 This is a flowchart of another environmental design lighting adjustment interaction method provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of an environmental design lighting adjustment and interaction system provided in an embodiment of the present invention. Detailed Implementation

[0015] 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 embodiments of the present invention, and not all embodiments. 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.

[0016] Reference Figure 1 This invention provides a flowchart of an interactive method for adjusting lighting in environmental design, comprising the following steps: S1 receives lighting adjustment commands from the user; S2, Based on the lighting adjustment command, obtain the user's task intent; S3, When there is a conflict between the task intentions, the conflicting task intentions are processed and the lighting target is obtained; S4, execute the lighting target.

[0017] Specifically, this method first receives lighting adjustment commands from the user. These commands can be received in various ways. For example, users can tap preset scene buttons (such as "Reading Mode" or "Focus Mode") through a smartphone application interface, or issue commands via a voice assistant (such as "Xiaoming, please turn up the lights"). Alternatively, commands can be received via physical switches, gesture recognition devices, etc. For instance, in a meeting room, a user can select "Presentation Mode" via a touchscreen on the wall, and the system will then receive the corresponding lighting adjustment command.

[0018] Upon receiving a lighting adjustment command, this method will determine the user's task intent based on that command. One implementation is that the system can pre-set a set of rules to directly map specific commands to corresponding task intents. For example, upon receiving a "reading mode" command, the system directly infers that the user's task intent is "reading." Another implementation is that the system can infer the user's task intent by analyzing the semantic content of the command, combined with the user's usage habits and historical data. For example, when a user says "Please turn on the lights," the system might combine the current time (day or night), the user's location (office or rest area), and the user's recent activities (such as using a computer for document editing) to infer that the user's task intent might be "focusing on work."

[0019] Once the user's task intent is obtained, the system needs to determine if there is a task intent conflict. A task intent conflict refers to a situation where different users or the same user issuing lighting adjustment commands at different times within the same lighting area have contradictory task intents. For example, in an open-plan office area, user A's task intent is "focus on work," requiring higher brightness and a cooler color temperature; while user B's task intent is "rest," requiring lower brightness and a warmer color temperature. In this case, the system will identify a conflict between these two task intents.

[0020] When conflicting task intentions exist, this method will process the conflicting intentions to achieve the final lighting target. One approach is for the system to simply adopt a "first-come, first-served" principle, prioritizing the task intention corresponding to the most recently received instruction and ignoring previous conflicting instructions. For example, if user A first issues the instruction "focus on work," and then user B issues the instruction "rest," the system will prioritize user B's "rest" instruction. Another approach is for the system to pre-set a priority list, determining priority based on the type of task intention. For example, "urgent meeting" has a higher priority than "routine office work," thus prioritizing the lighting needs of the "urgent meeting" in case of conflict.

[0021] Finally, this method executes the stated lighting goal. Once the final lighting goal is determined, the system adjusts various parameters of the lighting equipment, such as brightness, color temperature, and directionality, accordingly. For example, if the lighting goal is "reading mode," the system will adjust the light brightness to 500 lux, the color temperature to 4000K, and ensure uniform light distribution to avoid glare. This execution process can be achieved by sending control signals to intelligent lighting devices, such as smart bulbs, LED panel lights, and dimmers.

[0022] The environmental design lighting adjustment interaction method proposed in this application effectively solves the problem of traditional lighting systems struggling to coordinate conflicting lighting needs in multi-user environments by introducing intelligent task intent recognition and conflict resolution mechanisms. When faced with conflicting lighting adjustment commands from multiple users simultaneously, traditional lighting systems often simply execute the latest command or a preset single priority rule, leading to frequent fluctuations in the lighting environment, failing to meet the needs of all users, and potentially even causing user dissatisfaction.

[0023] This application receives lighting adjustment commands from users and, based on these commands, obtains the users' task intentions, enabling the system to understand the underlying needs behind user behavior. When conflicting task intentions are identified, this method no longer simply executes a single command but intelligently processes the conflicting intentions to obtain a comprehensive and optimized lighting goal. For example, in an open-plan office area, when multiple users simultaneously issue commands with different lighting needs, this method can analyze each user's task intention, handle conflicts, and ultimately determine a lighting solution that best balances the needs of all users, rather than simply satisfying one at the expense of another. Finally, the system executes the lighting goal, ensuring the stability of the lighting environment and improving the user experience. This method not only improves the intelligence level of the lighting system but also significantly enhances the user's lighting experience in complex environments, avoiding the problems of decreased work efficiency and reduced user satisfaction caused by lighting conflicts.

[0024] Compared to the closest existing technologies, the core innovation of this application lies in its intelligent handling mechanism for "task intent conflicts." Existing technologies typically lack a deep understanding of user task intent and are unable to perform fine-grained coordination when conflicts occur. For example, some existing systems may resolve conflicts simply by setting priorities, but this approach is often too rigid and cannot adapt to complex and ever-changing user needs. This application, by acquiring user task intent and processing conflicts, can more flexibly and intelligently balance the needs of different users, thereby providing a more stable and personalized lighting environment. This deep mining of user intent and intelligent handling of conflicts gives this application a significant advantage in improving user experience and system intelligence.

[0025] In some embodiments described above, an interactive method for environmental design lighting adjustment is proposed. This method can receive lighting adjustment commands issued by users and obtain the user's task intent based on the commands. When conflicting task intents exist, the conflicting task intents are processed to obtain the lighting target. However, in practical applications, simply processing conflicting task intents may lead to frequent switching of lighting states, or difficulty in making stable and user-expected decisions when multiple task intents have similar priorities, thereby affecting user experience and system stability.

[0026] refer to Figure 2 , Figure 2 S3 in the formula includes the following steps: S31, Calculate the overall priority of the conflicting task intentions; S32, Based on the comprehensive priority, identify the highest priority task intent and the second highest priority task intent and calculate the priority difference; S33, preset priority elastic range threshold; S34, when the priority difference is less than or equal to the priority elastic range threshold, the current lighting state is maintained; S35, when the priority of the highest priority task intent is consistently higher than that of other task intents, and the priority difference is consistently greater than the priority elastic range threshold, or when a user forces a switch command, the current lighting state is deactivated.

[0027] Specifically, the system calculates the overall priority of conflicting task intentions to quantify the importance of each conflicting task intention. This overall priority can be calculated based on various factors, such as the task's base priority, user identity, time context, activity type, number of users, and intention intensity. Through weighted calculation, a numerical value reflecting the true importance of the task intention in the current context can be obtained. After obtaining the overall priority of each conflicting task intention, the system identifies the highest-priority and second-highest-priority task intentions based on these overall priorities. Subsequently, the priority difference between these two highest-priority and second-highest-priority task intentions is calculated. This priority difference is used to measure the significance of the highest-priority task intention relative to the other task intentions.

[0028] To avoid frequent switching of lighting states, this application presets a priority elasticity range threshold. This threshold defines a tolerance range. When the priority difference between the highest priority task intent and the second highest priority task intent is small, i.e., less than or equal to the priority elasticity range threshold, it indicates that the priority difference between these task intents is not significant. In this case, the system will choose to maintain the current lighting state to avoid unnecessary lighting adjustments, thereby improving system stability. However, when the highest priority task intent consistently has a higher priority than other task intents, and the priority difference consistently exceeds the priority elasticity range threshold, it indicates that the highest priority task intent has a significant and stable advantage. In this case, the system will deactivate the current lighting state and adjust the lighting according to the highest priority task intent. Furthermore, to give the user ultimate control, even if the priority difference does not meet the deactivation condition, once a forced switching command is received from the user, the system will immediately deactivate the current lighting state to respond to the user's explicit needs.

[0029] This application's solution effectively addresses the issues of frequent lighting state switching and unstable decision-making that may arise when handling conflicting task intentions using the aforementioned basic methods. Specifically, the comprehensive priority calculation allows the system to more comprehensively assess the importance of each task intention, rather than relying solely on a single dimension. By comparing the priority difference between the highest and second-highest priority task intentions and combining this with a preset priority elasticity threshold, the system can intelligently determine when to maintain the current lighting state to avoid interference and when to decisively adjust the lighting to respond to the user's primary needs. When the priority difference is small, maintaining the current lighting state effectively suppresses lighting flickering or frequent adjustments caused by minor priority fluctuations, thereby improving the user experience. When the highest priority task intention consistently and significantly outperforms other task intentions, the system can respond promptly, ensuring the lighting environment matches the user's most pressing needs. Furthermore, the introduction of user-mandated switching commands guarantees the user's ultimate control over lighting adjustments, further enhancing system flexibility and user satisfaction.

[0030] Through the above technical solution, this application provides a more intelligent, stable, and user-friendly method for environmental lighting adjustment interaction. This method, through refined priority evaluation and a dynamic decision-making mechanism, effectively avoids the problem of frequent lighting state switching that may occur when task intentions conflict, significantly improving system stability and user experience. Furthermore, the introduced priority elasticity threshold makes the system more "tolerant" when handling conflicts with similar priorities, reducing unnecessary interference; while the setting of user-mandated switching commands ensures the user's ultimate control over the lighting environment, further enhancing the system's practicality and flexibility.

[0031] In some preferred embodiments, a specific example is given below. Suppose a user is working in an open-plan office environment, and the system detects two conflicting task intentions: one is that the user is performing a "focused reading" task, with ideal lighting parameters of high brightness and cool color temperature; the other is that the user is simultaneously playing "relaxing music" in the background, and their task intention may favor softer, warmer lighting.

[0032] First, the system calculates the combined priority of the two task intentions: "Focused Reading" and "Relaxed Music." Let's assume that after calculation, "Focused Reading" has a combined priority of 90, while "Relaxed Music" has a combined priority of 80. In this case, the highest priority task intention is "Focused Reading," and the second highest priority task intention is "Relaxed Music," with a priority difference of 10.

[0033] The system's preset priority flexibility threshold is 5. Since the current priority difference of 10 is greater than the preset priority flexibility threshold of 5, the system will further determine whether the priority of "Focused Reading" continues to be higher than that of "Leisure Music". If the priority of "Focused Reading" continues to be higher and the priority difference continues to be greater than 5, the system will deactivate the current lighting status and adjust the lighting according to the task intent of "Focused Reading", such as increasing the brightness and cooling the color temperature, to support the user's reading activity.

[0034] However, if the priority difference is only 3 (e.g., "Focus Reading" priority 83, "Leisure Music" priority 80), which is less than or equal to the preset priority elasticity range threshold of 5, the system will maintain the current lighting state to avoid frequent lighting adjustments due to small priority fluctuations, thereby reducing interference to the user.

[0035] Furthermore, if the user suddenly issues a forced switching command to "switch to leisure mode" via voice or gesture when the priority difference above continues to be greater than the threshold, the system will immediately respond to the command, cancel the current lighting state, and adjust the lighting according to the task intent of "leisure music". Even if the priority of "focused reading" is still higher, the system will respond to the user's explicit intent first.

[0036] refer to Figure 3 S31 includes the following steps: S311, Obtain the user's identity information, the identity information including user role level and permission weight; S312 determines the weight factor of the user role based on the user role level and the permission weight; S313, the weighting factor is weighted and calculated with the basic priority of the task intent, the time context weight, the activity type context weight, the number of users and the intent intensity weight to obtain the comprehensive priority.

[0037] The user's identity information can be understood as a set of data used to identify the user's status and authority within a specific environment or organization. This identity information includes user role level and authority weight. The user role level indicates the user's position within the organizational hierarchy, such as a regular employee, department manager, or senior executive. The authority weight quantifies the user's decision-making influence or control scope within the system or a specific operation. For example, a department manager's user role level may be higher than that of a regular employee, and their authority weight will be correspondingly higher, meaning that their lighting adjustment instructions may have greater influence in conflict resolution.

[0038] Furthermore, based on the user role level and the permission weight, a weight factor for the user role can be determined. The weight factor is a numerical value used to reflect the importance of the user's identity in priority calculation. For example, a mapping table can be preset to map different combinations of user role levels and permission weights to different weight factors. For instance, the weight factor for a senior manager might be set to 1.5, for a department manager to 1.2, and for a regular employee to 1.0.

[0039] Based on this, the weighting factors are weighted together with the basic priority of the task intent, the time context weight, the activity type context weight, the number of users, and the intent intensity weight to obtain the comprehensive priority. The basic priority of the task intent refers to the inherent, preset priority of each task intent; for example, the basic priority of "urgent meeting" is higher than that of "daily office work." The time context weight reflects the importance of the task intent within a specific time period; for example, the lighting needs for nighttime rest have a higher weight during late night. The activity type context weight can be adjusted according to the current activity type; for example, the lighting needs for a presentation have a higher weight than for reading. The number of users reflects the range of affected users; the more users, the higher the weight of their task intent may be. The intent intensity weight quantifies the intensity or persistence of a user's demand for specific lighting adjustments. By weighting these factors, the comprehensive priority of each conflicting task intent can be comprehensively and objectively evaluated.

[0040] This application's solution employs a multi-dimensional weighted calculation mechanism to refine the overall priority assessment of conflicting task intentions. Specifically, by acquiring user identity information, including user role level and permission weight, and determining the weight factor for each user role, the influence of different users in lighting adjustment conflicts can be quantified. For example, when multiple users simultaneously issue conflicting lighting adjustment commands, the system can assign different initial weights to the task intentions issued by different users based on their identity information. On this basis, a weighted calculation is performed, incorporating contextual factors such as the basic priority of the task intention, time context weight, activity type context weight, number of users, and intention intensity weight, resulting in a more comprehensive and dynamic overall priority. This multi-factor fusion calculation method ensures that priority assessment is no longer a single-dimensional static judgment, but rather fully considers various complex contexts such as user identity, task nature, time, environment, and user intentions, thus providing a more reasonable and accurate basis for subsequent conflict resolution.

[0041] The above technical solution enables more refined and intelligent calculation of the comprehensive priority of conflicting task intentions. Compared to methods that rely solely on a single priority or simple rules, this application introduces user identity information (including user role level and permission weight) to determine the weight factor of the user role, and then weights it with multiple contextual factors such as the basic priority of the task intention, time context weight, activity type context weight, number of users, and intention intensity weight, significantly improving the accuracy and fairness of priority assessment. Therefore, when handling lighting adjustment conflicts, the system can more comprehensively understand and weigh the importance of different task intentions, avoiding unreasonable decisions due to one-sided considerations, thereby ensuring that the final lighting goal better meets actual needs and improves user experience and environmental adaptability.

[0042] Preferably, obtaining the user's task intent based on the lighting adjustment command includes: According to a preset set of digital context mapping rules, the lighting adjustment command is mapped to a preset task scenario; If mapping fails, obtain the window title or document name of the active application and perform keyword matching; When a match is found, the user's task intent is inferred based on the keywords. If there is a mismatch, a query is sent to the user to obtain the user's task intent.

[0043] The digital context mapping rule set can be understood as a set of predefined rules or algorithms, designed to associate user-issued lighting adjustment commands with specific task scenarios. For example, when a user issues a "reading mode" command, the rule set can map it to a "reading" task scenario, which may have preset specific brightness, color temperature, and directionality parameters. The digital context mapping rule set can be stored in the system's database and can be updated and expanded according to actual application needs to adapt to constantly changing user habits and scenario requirements.

[0044] Furthermore, when the lighting adjustment command cannot be directly mapped to a preset task scenario, the system will attempt to infer the user's task intent by analyzing the application the user is currently using. Specifically, the system can obtain the window title or document name of the currently active application. For example, when the user is using "Microsoft Word - Patent Application.docx", the system can obtain the document name "Patent Application". Subsequently, the system will match the obtained window title or document name against a preset keyword library. The keyword library may contain words related to common tasks, such as "report", "design", "meeting", and "reading", with the aim of identifying potential task types from the user's actual work content.

[0045] When the window title or document name matches a keyword in the keyword library, the system can infer the user's task intent based on the matched keyword. For example, if the word "report" is matched, it can be inferred that the user is performing a "report writing" task. If no keyword is matched, it indicates that the system cannot automatically infer the user's task intent. In this case, the system will proactively send a query to the user, such as through a pop-up dialog box or voice prompt, to inquire about the user's current specific task intent and receive the user's feedback to clarify their intent, thereby ensuring that the system can accurately grasp the user's needs in any situation.

[0046] This application's solution achieves accurate identification of user task intent through a multi-layered, multi-modal information acquisition and inference mechanism. First, using a pre-set set of digital context mapping rules, the system can quickly respond to explicit lighting adjustment commands, directly associating them with the corresponding task scenario, thus efficiently acquiring the user's task intent. When the command is not explicit enough or cannot be directly mapped, the system further utilizes information about the user's active applications on their personal computing device, analyzing keywords in window titles or document names to infer the user's potential task intent from their actual work content. This effectively compensates for the limitations of direct command mapping. If neither of the above two automatic inference methods can determine the user's task intent, the system will proactively interact with the user, directly obtaining the user's explicit intent through questioning, thereby ensuring accurate understanding of the user's needs in all situations. This progressive intent recognition mechanism significantly improves the accuracy and robustness of the system in acquiring user task intent.

[0047] Through the above technical solution, this application can obtain the user's task intent in a more intelligent and flexible way. Compared with relying solely on direct commands or a single mapping rule, this solution combines multiple methods such as digital context mapping, active application content analysis, and user-initiated inquiries, greatly improving the accuracy and coverage of task intent recognition. This enables the lighting control system to more accurately understand the user's actual needs, and even when the user's commands are ambiguous or the intent is not clearly expressed, it can effectively infer from contextual information, thereby providing users with more personalized and intelligent lighting services, significantly improving the user experience and the system's intelligence level.

[0048] In some embodiments described above, the system directly cancels the current lighting state when a user's forced switching command is detected. However, in practical applications, the user's task intent or environmental needs may change after issuing the forced switching command, or the current lighting state, while not optimal, may still be within an acceptable range. In such cases, immediately canceling the current lighting state may lead to unnecessary interference or a degraded user experience. Without optimization, the system may not be able to flexibly respond to the user's actual and dynamic needs, thereby reducing the intelligence level of lighting adjustment and user satisfaction.

[0049] Preferably, when a user forces a switch command, the current lighting state is deactivated, including: Record the duration of the current lighting state; Periodically evaluate the degree of match between the current lighting state and the ideal lighting parameters of the conflicting task intent; When the matching degree is lower than the preset matching degree threshold and the maintenance time exceeds the preset maximum maintenance time, an inquiry is sent to the user to obtain the user's confirmation instruction on whether the current lighting state needs to be adjusted. If necessary, the current lighting state can be deactivated.

[0050] Specifically, recording the duration of the current lighting state refers to the time elapsed since the current lighting state was set or maintained. This duration can be accumulated in minutes or hours and stored in the system's memory or persistent storage for later querying and comparison. Its purpose is to provide a temporal basis for evaluating the suitability of the current lighting state.

[0051] Periodically assessing the matching degree between the current lighting state and the ideal lighting parameters of the conflicting task intent can be understood as the system automatically comparing and analyzing the lighting parameters of the current environment (such as brightness, color temperature, directionality, etc.) with the ideal parameters corresponding to the user's current conflicting task intent within a preset time interval (e.g., every 5 minutes, 10 minutes, or longer) to quantify the degree of fit between the two. This assessment aims to determine whether the current lighting state can still effectively support the user's task intent, or whether it has deviated from the ideal state.

[0052] In practical applications, when the matching degree is lower than a preset matching degree threshold and the maintenance time exceeds a preset maximum maintenance duration, the system will trigger an active intervention mechanism. The matching degree threshold and maximum maintenance duration are preset parameters used to define when the current lighting state is considered unsuitable. For example, the matching degree threshold can be set to 0.7 (representing 70% matching degree), and the maximum maintenance duration can be set to 30 minutes. When both conditions are met simultaneously, the system will send a query to the user, such as through a pop-up window on the display, a voice prompt, or a mobile device notification, to obtain the user's confirmation instruction whether they need to adjust the current lighting state. This query aims to respect the user's final decision-making right and avoid forced adjustments without the user's consent.

[0053] If the user confirms the need for adjustment (i.e., a confirmation command is received), the system will deactivate the current lighting status and prepare for the execution of subsequent lighting objectives.

[0054] Preferably, the periodic evaluation of the match between the current lighting state and the ideal lighting parameters of the conflicting task intent includes: Obtain the brightness, color temperature, and directionality parameters of the current lighting state; Obtain the ideal lighting parameters for the conflicting task intent, including ideal brightness, ideal color temperature, and ideal directionality parameters; Calculate the brightness deviation, color temperature deviation, and directionality deviation between the current lighting state and the conflicting task intent, respectively; The weighted sum of the brightness deviation, the color temperature deviation, and the directionality deviation is obtained by weighting and summing them. After performing a nonlinear mapping on the weighted bias, the matching degree of the conflicting task intent is obtained; after performing a weighted average on the matching degree, the overall matching degree is obtained.

[0055] Specifically, acquiring the brightness, color temperature, and directionality parameters of the current lighting state refers to real-time collection of physical quantities such as illuminance, color temperature, and light projection direction or diffusion angle of the current lighting area through sensors deployed in the environment or the feedback mechanism of the lighting system itself. For example, the brightness parameter can refer to the average illuminance of the current lighting area, the color temperature parameter can refer to the Kelvin color temperature value of the current lighting, and the directionality parameter can refer to the projection angle or beam angle of the main light source.

[0056] The process of obtaining ideal lighting parameters for the conflicting task intent, including ideal brightness, ideal color temperature, and ideal directionality, refers to obtaining the lighting conditions that best match the user's current conflicting task intent from a preset database or through an intelligent recommendation algorithm. For example, for the task intent of "focused reading," the ideal brightness might be set to 500 lux, the ideal color temperature might be set to 6500K cool white light, and the ideal directionality parameter might be set to focused lighting; while for the task intent of "relaxation," a lower ideal brightness, warmer color temperature, and soft diffused light might be used.

[0057] Furthermore, calculating the brightness deviation, color temperature deviation, and directionality deviation between the current lighting state and the conflicting task intent involves quantitatively comparing the actually collected current lighting state parameters with the corresponding ideal lighting parameters to determine the degree of difference for each parameter. For example, the brightness deviation can be calculated as the absolute difference or percentage difference between the current brightness and the ideal brightness; the color temperature deviation and directionality deviation can be calculated in a similar manner.

[0058] Therefore, the weighted sum of the brightness deviation, color temperature deviation, and directionality deviation yields the weighted deviation. This means that different lighting parameter deviations may have different importance when evaluating overall matching. By assigning different weighting factors to each deviation, their impact on the user's task experience can be reflected more accurately. For example, in tasks requiring high visual clarity, the weight of brightness deviation may be higher than that of color temperature deviation.

[0059] Subsequently, the weighted biases are nonlinearly mapped to obtain the matching degree of the conflicting task intent. The purpose of the nonlinear mapping is to transform the original, potentially large, bias values ​​into a standardized matching degree score (e.g., 0 to 100) that better aligns with human perception, where larger weighted biases correspond to lower matching degrees and smaller weighted biases correspond to higher matching degrees. This mapping can be implemented using a Sigmoid function, a Gaussian function, or other custom nonlinear functions to capture the nonlinear relationship between matching degree and bias.

[0060] Finally, the matching scores are weighted and averaged to obtain the overall matching score. If there are multiple conflicting task intentions, or if the matching score evaluation involves multiple dimensions (e.g., considering glare, uniformity, etc. in addition to the parameters mentioned above), the individual matching scores can be integrated into a comprehensive overall matching score through weighted averaging, so that the system can make a unified decision.

[0061] The proposed solution acquires various quantifiable parameters of the current lighting state and compares them one by one with the ideal lighting parameters corresponding to the conflicting task intent, thereby quantifying the deviation of each lighting parameter. It is precisely because these deviations are weighted and summed, and further transformed into an intuitive matching degree through nonlinear mapping, that the system can objectively and comprehensively assess the degree of fit between the current lighting state and the user's task intent. This refined evaluation mechanism allows the system to move beyond simple threshold judgments when faced with task intent conflicts, and instead deeply analyze the actual support of the current lighting environment for the user's task intent, providing a solid data foundation for deciding whether to maintain or discontinue the current lighting state.

[0062] Through the above technical solution, this application provides a more refined and objective lighting status evaluation mechanism. Compared to relying solely on user-mandated switching commands or simple matching threshold judgments, this solution quantifies multiple dimensions such as brightness, color temperature, and directionality, and introduces weighted summation and nonlinear mapping to make the matching evaluation results more accurate and representative. Therefore, the system can more accurately determine whether the current lighting status truly meets the user's task intent, especially in complex scenarios with conflicting intents. This effectively avoids misjudgments or unnecessary lighting adjustments caused by coarse evaluation, thereby improving the intelligence level of lighting adjustment and the user experience.

[0063] In some embodiments of this application, when periodically evaluating the match between the current lighting state and the ideal lighting parameters of the conflicting task intent, it is necessary to obtain the ideal lighting parameters of the conflicting task intent. However, relying solely on preset ideal lighting parameters may not adequately adapt to the user's personalized needs, real-time preferences, and subtle changes in the environment, leading to a deviation between the lighting adjustment results and the user's actual expectations, thereby affecting user experience and work efficiency. To address this, this application further proposes a method for obtaining ideal lighting parameters by introducing a user satisfaction feedback mechanism to dynamically adjust the preset ideal lighting parameters, thereby more accurately reflecting the user's true needs and subjective feelings.

[0064] Preferably, the ideal lighting parameters for obtaining the conflicting task intent include ideal brightness, ideal color temperature, and ideal directionality parameters, including: Obtain the user's task intent and the preset ideal lighting parameters corresponding to the task intent; obtain the user's satisfaction feedback on the current lighting state; Based on the satisfaction feedback, the preset ideal lighting parameters are adjusted to obtain the ideal lighting parameters.

[0065] Specifically, the system first retrieves the initial or default preset ideal lighting parameters corresponding to the identified user's task intent from a pre-set database or rule set. These preset ideal lighting parameters are derived from a large amount of user data, lighting design specifications, or expert experience, serving as a benchmark for subsequent adjustments. For example, for the "reading" task intent, the preset ideal lighting parameters might include higher brightness, neutral color temperature, and uniform directionality; for the "resting" task intent, they might include lower brightness, warm color temperature, and soft directionality.

[0066] Obtaining user satisfaction feedback on the current lighting status is a crucial aspect of this solution. This satisfaction feedback can be explicit, obtained through user input (e.g., via a rating slider, emoji selection, or voice commands provided in the application interface), or implicit, inferred from monitoring user behavior data (e.g., keyboard input frequency, mouse movement frequency, facial expressions, body posture, etc.). Satisfaction feedback is an important indicator of whether the current lighting status meets user expectations.

[0067] In practical applications, the system dynamically adjusts the preset ideal lighting parameters based on user satisfaction feedback. For example, if a user is dissatisfied with the brightness of the current lighting (e.g., deems it too bright), the system will appropriately lower the preset ideal brightness parameter according to the degree of dissatisfaction. Similarly, if a user deems the color temperature unsuitable, the system will adjust the preset ideal color temperature parameter accordingly. This adjustment can be based on preset adjustment rules, fuzzy logic algorithms, or machine learning models, with the aim of making the final ideal lighting parameters more closely reflect the user's actual experience and personalized needs.

[0068] This application's solution effectively addresses the problem of discrepancies between lighting adjustment results and users' actual expectations that may arise from relying solely on statically preset ideal lighting parameters by introducing a user satisfaction feedback mechanism. Specifically, the system first obtains an initial preset ideal lighting parameter as a baseline based on the user's task intent. Subsequently, by continuously acquiring user satisfaction feedback on the current lighting state, the system can understand the user's subjective feelings about the lighting environment in real time. It is precisely because of this satisfaction feedback that the system can dynamically and personalizedly adjust the initial preset ideal lighting parameters based on the user's actual experience. For example, when the user is dissatisfied with the current lighting state, the system will fine-tune brightness, color temperature, or directionality parameters based on the feedback information, thereby ensuring that the final determined ideal lighting parameters more accurately reflect the user's true needs and preferences. This iterative and adaptive adjustment process allows the lighting system to learn and optimize from the user's actual experience, ensuring that the set lighting goals are truly "ideal."

[0069] Through the above technical solution, this application enables the dynamic and personalized acquisition of ideal lighting parameters for conflicting task intentions. Compared to solutions that only use static preset parameters, this application, by integrating user satisfaction feedback, allows ideal lighting parameters to more accurately reflect users' real-time needs and subjective feelings, significantly improving the accuracy of lighting adjustment and user experience. This adaptive adjustment mechanism not only enhances the system's intelligence level but also effectively avoids potential discomfort or efficiency decline caused by lighting parameters not meeting user expectations, thereby providing users with a more comfortable, efficient, and personalized lighting environment.

[0070] In some preferred embodiments, a specific example is given below. Assume a user is performing a "reading" task. The system first retrieves a set of initial preset ideal lighting parameters from a preset parameter library based on the user's reading task intent. For example, the ideal brightness is 800 lux, the ideal color temperature is 4500K, and the directionality is uniform diffusion. After the system adjusts the lighting based on these parameters, the user may rate the current lighting status as "moderately low" using the satisfaction rating slider on the application interface, and may comment that "the light is a bit glaring." Upon receiving this satisfaction feedback, the system will adjust the preset ideal brightness parameter for the reading task intent according to preset adjustment rules, for example, to 700 lux, and may slightly lower the color temperature to 4200K to reduce glare. Subsequently, when the user performs the "reading" task again, the system will prioritize using the adjusted ideal lighting parameters (700 lux brightness, 4200K color temperature), thereby providing a lighting environment that better meets the user's personalized needs. In this way, ideal lighting parameters are no longer fixed, but can be continuously optimized and learned based on actual user feedback, ensuring that the final effect of lighting adjustment can meet the user's comfort and functional needs to the greatest extent.

[0071] In some of the embodiments described above in this application, it is proposed to adjust the preset ideal lighting parameters by obtaining user satisfaction feedback on the current lighting state. However, in practical applications, users may not always provide clear satisfaction feedback, or their feedback methods may be relatively simple, resulting in insufficient or untimely satisfaction information, which affects the accuracy of the ideal lighting parameter adjustment.

[0072] Preferably, obtaining the user's satisfaction feedback on the current lighting status includes: The agent program deployed on the user's personal computing device monitors the user's keyboard input frequency and mouse movement frequency on the personal computing device. When the keyboard input frequency and the mouse movement frequency are consistently lower than a preset activity threshold, the user is determined to be in an inactive state. When the keyboard input frequency and the mouse movement frequency are consistently higher than a preset activity threshold, the user is determined to be in an active state. When the user is in the active state, a satisfaction rating slider or emoji selection is provided through the application interface on the personal computing device to obtain the satisfaction level expressed by the user by actively clicking or dragging. When the user is in the inactive state, the system uses cameras deployed in the lighting area, combined with image recognition technology, to analyze the user's facial expressions or body posture and infer the user's satisfaction with the current lighting state.

[0073] Specifically, the personal computing device can refer to a user's desktop computer, laptop, tablet, or smartphone. The agent program is a software module running on these devices, configured to continuously monitor the user's interactive behavior in the background, such as keyboard input frequency and mouse movement frequency. The activity threshold is a pre-set value used to distinguish whether the user is actively using the device (active state) or temporarily away from or not using the device (inactive state). For example, if a user does not input keyboard data or move the mouse for a certain period of time (e.g., 5 minutes), or if their frequency is lower than a certain value, they can be judged as being inactive.

[0074] When users are active, they are typically interacting with the device. Providing a satisfaction rating slider or emoji selection through the application interface allows users to proactively express their satisfaction. This method is intuitive and easy to use; users can provide feedback on their feelings about the current lighting status with simple clicks or drags.

[0075] When a user is inactive, they may not be actively interacting with the device. In this case, analyzing the user's facial expressions or body posture using a camera combined with image recognition technology can achieve non-invasive and imperceptible satisfaction inference. The camera can be deployed in a suitable location in a well-lit area, such as on the ceiling, wall, or above a monitor, to capture images of the user's face and body. Image recognition technology is then used to extract features from these images to infer the user's satisfaction. For example, a smile and relaxed posture may indicate satisfaction, while a frown and stiff posture may indicate dissatisfaction.

[0076] This application's solution comprehensively and flexibly acquires user satisfaction feedback on the current lighting status by combining active feedback and passive monitoring. When the user is active, the system provides an intuitive interactive interface to encourage users to actively express their satisfaction, ensuring the directness and accuracy of the feedback. When the user is inactive, the system utilizes cameras and image recognition technology to infer satisfaction by analyzing facial expressions and body posture without disturbing the user, compensating for the information loss when the user does not actively provide feedback. This dual mechanism ensures that the system can continuously and effectively acquire user satisfaction information regardless of the user's state, thereby providing more reliable and comprehensive data support for subsequent adjustments to ideal lighting parameters.

[0077] Through the above technical solution, this application overcomes the limitations of traditional methods for obtaining satisfaction, such as being singular, untimely, or inaccurate. Specifically, by distinguishing between active and inactive user states and employing different feedback acquisition mechanisms accordingly, this application significantly improves the coverage and accuracy of satisfaction feedback. This allows the system to understand users' true feelings about the current lighting status more comprehensively and in real time, thereby enabling more precise adjustment of ideal lighting parameters and enhancing the intelligence level of lighting adjustment and user experience. Especially when users are inconvenient or unwilling to actively provide feedback, the introduction of a passive monitoring mechanism ensures the continuous acquisition of satisfaction information, avoids lighting adjustment deviations caused by information gaps, and greatly enhances the robustness and adaptability of the entire environmental design lighting adjustment interaction method.

[0078] In some preferred embodiments, a specific example is given below. Assume a user is working at their desk in an office. The system continuously monitors the user's keyboard input frequency and mouse movement frequency through an agent deployed on the user's personal computing device. If the user is frequently typing and moving the mouse, the system determines that the user is active. At this time, a small window pops up in the corner of the user's computer screen, displaying a satisfaction rating slider (e.g., from 1 to 5) or a set of emoticons (e.g., happy, calm, unhappy). The user can click or drag the slider to express their satisfaction with the current lighting (e.g., brightness, color temperature).

[0079] If a user temporarily leaves their workstation to answer a phone call or remains inactive for an extended period, the system determines that the user is inactive. In this case, a camera positioned above the workstation activates its image recognition function, analyzing the user's facial expressions (e.g., frowning, smiling) and body posture (e.g., relaxed, stiff). For example, if the camera detects a relaxed facial expression and comfortable posture, the system infers that the user is satisfied with the current lighting conditions; conversely, if the camera detects a frown or slightly tense posture, it may infer that the user is dissatisfied with the lighting conditions. In this way, even without active user interaction, the system can continuously gather satisfaction information, providing a basis for subsequent adjustments to lighting parameters.

[0080] In some embodiments described above, cameras deployed in the lighting area, combined with image recognition technology, analyze a user's facial expressions or body posture to infer the user's satisfaction with the current lighting condition. However, in practical applications, a user's facial expressions or body posture may be affected by various non-lighting factors, such as environmental noise, physical discomfort, or ongoing communication. These factors may lead to misjudgments of user satisfaction, thus affecting the accuracy of lighting adjustments. If these problems are not addressed, the system may make inappropriate lighting adjustments based on inaccurate satisfaction feedback, reducing the user experience. Therefore, this application further proposes a specific method for analyzing a user's facial expressions or body posture to infer the user's satisfaction with the current lighting condition, aiming to improve the accuracy of satisfaction inference by comprehensively considering multiple contextual factors and eliminating interference.

[0081] Preferably, the step of analyzing the user's facial expressions or body posture to infer the user's satisfaction with the current lighting condition includes: Obtain the user's facial key points and body key points, and extract facial expression features and body posture features; Monitor ambient noise levels and voice content to identify whether the user is communicating. Monitor the temperature and humidity at the user's workstation to determine if the user is experiencing any physical discomfort; The facial expression features, body posture features, ambient noise intensity, voice content, and user health data are integrated. Based on preset interference elimination rules, identify and eliminate the influence of non-lighting factors on the facial expression features or the body posture features; The removed facial expression features and body posture features are compared with preset satisfaction expression patterns and posture patterns to infer the user's satisfaction with the current lighting state.

[0082] Specifically, acquiring a user's facial and body key points aims to use computer vision technology to identify key facial features such as the eyes, nose, and mouth, as well as key body features such as joints and torso, from images or video streams captured by a camera. Based on these key points, facial expression features can be further extracted, such as eyebrow raising, mouth corner curvature, and eye opening / closing, as well as body posture features, such as sitting posture, head tilt angle, and arm placement. These features are the foundational data for quantifying a user's emotions and state.

[0083] Monitoring ambient noise intensity and voice content aims to acquire sound information from the environment using acoustic sensors such as microphones. Ambient noise intensity reflects the level of noise in the user's surroundings, while voice content recognition (e.g., through voice recognition technology) can determine whether the user is engaged in a conference call, talking to someone, or performing other voice-based interactive activities. This information helps determine whether the user's current mood or posture is related to the communication activity, rather than simply being caused by lighting.

[0084] In practical applications, monitoring the temperature and humidity at a user's workstation aims to acquire environmental parameters through temperature and humidity sensors deployed near the user's workstation. Workstation temperature and humidity are important factors affecting user comfort; excessively high or low temperatures or humidity can cause discomfort, manifesting as frowning, stiffness, or other facial expressions or postures. By acquiring this data, it's possible to determine whether the user's discomfort is the cause of their facial expressions or posture changes.

[0085] Furthermore, the fusion of facial expression features, body posture features, ambient noise intensity, voice content, and user health data aims to integrate information obtained from different sensors and data sources. User health data may include heart rate, blood pressure, sleep quality, etc., which can be obtained through wearable devices or active user input, providing a more comprehensive basis for assessing the user's overall physiological state. This fusion of multimodal data helps to build a more comprehensive user state model.

[0086] Based on this, and according to preset interference exclusion rules, the influence of non-lighting factors on facial expression features or body posture features is identified and eliminated. For example, if excessive ambient noise is detected while the user is engaged in voice communication, their frowning expression may be judged as related to the noise or the content of the communication, rather than dissatisfaction with the lighting. If excessive workstation temperature causes the user to sweat and exhibit an agitated posture, this posture change may be attributed to temperature rather than lighting. These rules can be trained and optimized based on expert knowledge, machine learning models, or historical data.

[0087] Finally, the removed facial expression features and body posture features are compared with preset satisfaction expression and posture patterns to infer the user's satisfaction with the current lighting condition. The preset satisfaction expression and posture patterns are established based on extensive user data and psychological research; for example, a relaxed sitting posture and a smiling expression are usually associated with satisfaction, while a tense body and a frown may be associated with dissatisfaction. Through comparison, the user's level of satisfaction with the current lighting condition can be quantified.

[0088] This application's solution, by introducing and integrating multi-dimensional contextual information (such as ambient noise intensity, voice content, workstation temperature and humidity, and user health data), enables a more comprehensive understanding of the user's current state. It is precisely through the monitoring and identification of these non-lighting factors that the system can effectively identify and eliminate the influence of non-lighting factors on facial expression or body posture characteristics according to preset interference exclusion rules. This elimination of interference factors ensures that subsequent inferences about user satisfaction are based on facial and posture changes directly related to the lighting condition, thereby avoiding misjudgments caused by other external factors.

[0089] Through the above technical solution, this application can significantly improve the accuracy of inferring user satisfaction with the current lighting status based on facial expressions and body posture. Compared to traditional methods that rely solely on facial expressions and posture, this application comprehensively considers and eliminates interference from non-lighting factors such as environmental noise, user communication status, and physical discomfort. This avoids misjudging user discomfort or emotions caused by other reasons as dissatisfaction with lighting, thus enabling the system to obtain more realistic and reliable user satisfaction feedback. This more accurate satisfaction feedback can guide the lighting adjustment system to make more refined lighting adjustments that better meet the actual needs of users, thereby improving the user experience and the level of intelligence in environmental design.

[0090] In some preferred embodiments, a specific example is given below. Assume a user is working at a workstation. The system acquires facial and body posture images of the user through cameras deployed in the lighting area. Simultaneously, a microphone detects high ambient noise levels, and a voice recognition module identifies that the user is engaged in a conference call. Temperature and humidity sensors show that the workstation temperature and humidity are within normal ranges. At this time, the user may exhibit a frowning expression and a slightly tense sitting posture.

[0091] Reference Figure 4 The first embodiment of the present invention provides an interactive system for adjusting ambient lighting, comprising: The data acquisition unit is used to receive lighting adjustment commands issued by the user. The processing unit is used to obtain the user's task intent based on the lighting adjustment command; when there is a conflict between the task intents, the conflicting task intents are processed and the lighting target is obtained. The execution end is used to execute the lighting target.

[0092] It should be noted that the environmental design lighting adjustment interaction system provided in this embodiment of the invention uses all the process steps of the environmental design lighting adjustment interaction method of the above embodiment. The working principle and beneficial effect of the two correspond one-to-one, so they will not be described again.

[0093] This invention also provides a terminal device. The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps described in the various embodiments of the environmental design lighting adjustment interaction method, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above system embodiments.

[0094] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0095] The terminal device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of terminal devices and do not constitute a limitation on the terminal device. It may include more or fewer components than described above, or a combination of certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0096] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0097] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0098] Wherein, if the modules / units integrated in the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0099] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0100] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. An environmental design lighting adjustment interaction method, characterized by, The method comprises: receiving a lighting adjustment instruction issued by a user; obtaining a task intention of the user based on the lighting adjustment instruction; when the task intentions conflict, processing the conflicting task intentions to obtain a lighting target; and executing the lighting target.

2. The environmental design lighting regulation interaction method according to claim 1, wherein, The method further comprises: calculating a comprehensive priority of the conflicting task intentions; identifying a highest-priority task intention and a second-highest-priority task intention according to the comprehensive priority and calculating a priority difference; presetting a priority elasticity interval threshold; when the priority difference is less than or equal to the priority elasticity interval threshold, maintaining a current lighting state; when the priority of the highest-priority task intention is continuously higher than those of other task intentions and the priority difference is continuously greater than the priority elasticity interval threshold, or a user forced switching instruction is received, releasing the current lighting state.

3. The environmental design lighting regulation interaction method according to claim 2, wherein, The method further comprises: obtaining identity information of the user, the identity information comprising a user role level and a permission weight; determining a weight factor of the user role according to the user role level and the permission weight; and performing weighted calculation on the weight factor and a basic priority of the task intention, a time context weight, an activity type context weight, a user quantity, and an intention intensity weight to obtain the comprehensive priority.

4. The environmental design lighting regulation interaction method according to claim 1, wherein, The method further comprises: mapping the lighting adjustment instruction to a preset task scene according to a preset digital context mapping rule set; if the mapping fails, obtaining a window title or a document name of an active application and performing keyword matching; when the matching succeeds, inferring the task intention of the user according to the keyword; and when the matching fails, sending a query to the user to obtain the task intention of the user.

5. The environmental design lighting regulation interaction method according to claim 2, wherein, The method further comprises: recording a maintenance time of the current lighting state; periodically evaluating a matching degree between the current lighting state and ideal lighting parameters of the conflicting task intentions; when the matching degree is lower than a preset matching degree threshold and the maintenance time exceeds a preset maximum maintenance duration, sending a query to the user to obtain a confirmation instruction of whether the user needs to adjust the current lighting state; and if the user needs to adjust the current lighting state, releasing the current lighting state.

6. The environmental design lighting regulation interaction method according to claim 5, wherein, The periodic evaluation of the matching degree between the current lighting state and the ideal lighting parameter of the conflicting task intention comprises: obtaining the brightness, color temperature and directivity parameter of the current lighting state; obtaining the ideal lighting parameter of the conflicting task intention, which comprises ideal brightness, ideal color temperature and ideal directivity parameter; calculating the brightness deviation, color temperature deviation and directivity deviation of the current lighting state and the conflicting task intention respectively; performing weighted summation on the brightness deviation, color temperature deviation and directivity deviation to obtain a weighted deviation; performing nonlinear mapping on the weighted deviation to obtain the matching degree of the conflicting task intention; and performing weighted averaging on the matching degree to obtain the overall matching degree.

7. The environmental design lighting regulation interaction method according to claim 6, characterized in that, The obtaining of the ideal lighting parameter of the conflicting task intention, which comprises ideal brightness, ideal color temperature and ideal directivity parameter, comprises: obtaining the task intention of the user and obtaining the preset ideal lighting parameter corresponding to the task intention; obtaining the satisfaction feedback of the user on the current lighting state; and adjusting the preset ideal lighting parameter according to the satisfaction feedback to obtain the ideal lighting parameter.

8. The environmental design lighting regulation interaction method according to claim 7, characterized in that, The obtaining of the satisfaction feedback of the user on the current lighting state comprises: monitoring the keyboard input frequency and mouse movement frequency of the user on the personal computing device of the user through the agent program deployed on the personal computing device; determining that the user is in an inactive state when the keyboard input frequency and the mouse movement frequency are continuously lower than a preset activity threshold; determining that the user is in an active state when the keyboard input frequency and the mouse movement frequency are continuously higher than the preset activity threshold; providing a satisfaction score slider or an emoji selection through an application interface on the personal computing device when the user is in the active state to obtain the satisfaction degree expressed by the user through active clicking or dragging; and analyzing the facial expression or body posture of the user by combining image recognition technology through the camera deployed in the lighting area when the user is in the inactive state to infer the satisfaction degree of the user on the current lighting state.

9. The environmental design lighting regulation interaction method according to claim 8, wherein, The analysis of the facial expression or body posture of the user to infer the satisfaction degree of the user on the current lighting state comprises: obtaining the facial key points and body key points of the user, and extracting facial expression features and body posture features; monitoring environmental noise intensity and speech content to identify whether the user is communicating; monitoring the temperature and humidity of the work station of the user to determine whether the user has physical discomfort; fusing the facial expression features, the body posture features, the environmental noise intensity, the speech content and the user health data; identifying and removing the influence of non-lighting factors on the facial expression features or the body posture features according to a preset interference factor exclusion rule; and comparing the facial expression features and the body posture features after removal with preset satisfaction expression patterns and posture patterns to infer the satisfaction degree of the user on the current lighting state.

10. An ambient design lighting adjustment interaction system, characterized by, The system comprises: a collection end configured to receive a lighting adjustment instruction issued by a user; a processing end configured to acquire a task intention of the user based on the lighting adjustment instruction; when the task intention is in conflict, the conflicting task intention is processed to acquire a lighting target; and an execution end configured to execute the lighting target.

Images