A multi-scenario guidance content management system

Abstract

The application relates to the field of guide content management, in particular to a multi-scene guide content management system which comprises a guide screen, an interactive sensing module, a guide screen detection module, a content management module and a decision analysis module. The application collects interactive sensing parameters of a target guide screen in a historical period, analyzes the interactive sensing values based on the interactive sensing parameters, and determines whether to start the guide screen detection module based on the interactive sensing values; determines whether to start the edge cache adjustment submodule based on the interference index; determines whether to start the coding adjustment submodule under the condition of determining not to start the edge cache adjustment submodule; determines whether to start the decision analysis module based on the interactive degradation index; and determines whether to start the microphone adjustment submodule or the backlight partition adjustment submodule based on the interactive degradation index. The application improves the interactive efficiency of the guide content management system in different scenes.

Description

Technical Field

[0001] This invention relates to the field of wayfinding content management, and more particularly to a multi-scenario wayfinding content management system. Background Technology

[0002] With the integration of intelligent interactive technology and the Internet of Things (IoT), multi-scenario systems have been widely applied in public places such as shopping malls, transportation hubs, hospitals, and government service halls to provide information inquiry, route guidance, and self-service. Existing systems typically integrate touchscreens, voice interaction, and content distribution functions, but face the following problems in actual deployment: First, touch interaction is susceptible to environmental interference, leading to abnormal responses; voice interaction suffers from reduced signal-to-noise ratio in noisy environments, and both lack a collaborative diagnostic mechanism. Second, content distribution relies on CDN caching, but the caching strategy is fixed and cannot be dynamically adjusted based on network link fluctuations and interaction quality, resulting in decreased cache hit rate and delayed content updates. Third, the system experiences performance degradation after prolonged operation, but existing technologies lack the ability to analyze the correlation between touch, voice, and display power consumption, making it impossible to pinpoint the root cause and perform layered repairs. Furthermore, issues such as packet loss due to retransmission in wireless projection scenarios and the linkage between near-field sensing and display refresh rate for energy saving have not yet been effectively resolved.

[0003] Chinese Patent Publication No. CN119094544A discloses a smart LED digital content management system and method, comprising the following steps: Step 1, using distributed content distribution technology through a content management module to automatically distribute digital content to various display devices; Step 2, a central control module imports, edits, and publishes content in various media formats through the content management module; Step 3, using a content update module to utilize high-bandwidth networks and fast caching technology for real-time updates and publication of digital content; and using a scheduling module to utilize intelligent scheduling algorithms to dynamically adjust the displayed content based on time, location, and audience interest factors; Step 4, using a redundancy module to utilize backup servers and backup networks to ensure continued system operation in the event of a main device or network failure; Step 5, using a fault detection module to deploy system monitoring tools to monitor the server and network status in real time and detect abnormalities; and using a recovery module to utilize automatic recovery scripts to automatically attempt to repair problems when faults are detected.

[0004] However, existing technologies only achieve basic content distribution and fault recovery, without collaborative perception and layered diagnosis of multimodal touch and voice interaction, and cannot distinguish between network fluctuations and system overload defects; CDN caching strategies are fixed and cannot dynamically adapt to load and environmental interference; there is a lack of quantitative assessment of interaction degradation, and it is impossible to accurately match voice pickup and power consumption optimization strategies, resulting in insufficient adaptability and operational stability in multiple scenarios. Summary of the Invention

[0005] To address this, the present invention provides a multi-scenario wayfinding content management system to overcome the problem in the prior art that, when the intelligent wayfinding system is applied in different scenarios, the loading delay of cached content caused by network link status fluctuations leads to the inability to write updated content in a timely manner and the degradation of interactive performance, resulting in the inability to adaptively adjust voice wake-up sensitivity and display power consumption, thus causing low operational stability of the multi-scenario wayfinding content management system.

[0006] To achieve the above objectives, the present invention provides a multi-scene navigation content management system, comprising: The guide screen integrates a touch sensor, microphone array, near field sensor, display panel and wireless communication circuit; The interactive sensing module is used to collect interactive sensing parameters of the target guide screen within a historical period, analyze the interactive sensing values ​​based on the interactive sensing parameters, and determine whether to activate the guide screen detection module based on the interactive sensing values; wherein, the interactive sensing parameters include the touch response time of the guide screen, the voice signal-to-noise ratio, and the content distribution delay time. The guide screen detection module is used to determine whether to activate the edge buffer adjustment submodule or the encoding adjustment submodule based on the interference index. The content management module is used to determine whether to activate the decision analysis module based on the interaction degradation index; The decision analysis module is used to determine whether to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index.

[0007] Furthermore, the interactive sensing module also includes: The interaction perception analysis submodule is used to determine the interaction perception value based on the touch response time, voice signal-to-noise ratio and content distribution delay. An interactive perception detection submodule is used to determine whether to activate the guide screen detection module based on the interactive perception value; wherein, the condition for activating the guide screen detection module is that the interactive perception value is greater than the interactive perception threshold.

[0008] Furthermore, the guide screen detection module also includes: The interference index determination submodule is used to determine the interference index based on the impedance fluctuation rate of the touch electrode, the ambient reverberation energy ratio, and the number of interactions within a preset time. A cache state detection submodule is used to determine whether to activate the edge cache adjustment submodule or the encoding adjustment submodule based on the interference index; wherein, the condition for activating the edge cache adjustment submodule is that the interference index is less than or equal to the interference index threshold; and the condition for activating the encoding adjustment submodule is that the interference index is greater than the interference index threshold.

[0009] Furthermore, the guide screen detection module also includes: The edge cache adjustment submodule is used to determine the edge cache adjustment index based on the noise spectral density and the accuracy of touch commands, and to determine the adjustment range of the CDN edge node content prefetch depth based on the edge cache adjustment index. The re-detection submodule is used to determine whether to start the encoding adjustment submodule if the adjustment range of the CDN edge node content prefetch depth has been determined and the interference index is still less than or equal to the interference index threshold after re-detection.

[0010] Furthermore, the edge cache adjustment submodule also includes: The content chunking unit is used to determine the content adjustment index based on the timestamp dispersion of the cached content and the duration of user interaction, and to determine the adjustment range of the content chunk size for a single prefetch request of the CDN edge node, provided that the adjustment range of the content prefetch depth of the CDN edge node has been determined. The content aggregation unit is used to merge several consecutive content chunk requests into a single batch prefetch request based on the aggregation degree of the chunk requests, provided that the adjustment range of the content chunk size of the single prefetch request for the determined CDN edge node is completed.

[0011] Furthermore, the guide screen detection module also includes: The coding adjustment submodule is used to determine the adjustment range of the wireless projection coding complexity of the guide screen based on channel utilization, packet loss rate and RSSI volatility. The keyframe recovery submodule is used to determine the adjustment range of the number of times key frames are repeatedly sent based on the number of consecutively successfully decoded non-key frames, after completing the adjustment range of the wireless projection encoding complexity of the guide screen, until it is restored to the initial value.

[0012] Furthermore, the content management module also includes: The degradation index calculation submodule is used to determine the interaction degradation index based on the accuracy of the semantic parsing of the interaction command and the power consumption of the guide screen, under the condition that the adjustment range of the repeated transmission number of the determined key frame is completed and the interaction sensing value is still greater than the interaction sensing threshold. An interaction detection submodule is used to determine whether to control the decision analysis module to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index. The condition for determining whether to control the decision analysis module to activate the microphone adjustment submodule is that the interaction degradation index is less than or equal to the interaction degradation index threshold. The condition for determining whether to control the decision analysis module to activate the backlight zone adjustment submodule is that the interaction degradation index is greater than the interaction degradation index threshold.

[0013] Furthermore, the decision analysis module also includes: The microphone adjustment submodule is used to determine the speech engine optimization index based on the accuracy of intent slot filling and the echo cancellation residual ratio of the microphone array, and to determine the adjustment range of the target azimuth angle of the beamforming pointing angle of the microphone array based on the speech engine optimization index. The pointing angle calibration submodule is used to periodically calibrate the beamforming pointing angle based on the consistency of the speech arrival time difference of the distributed microphones, provided that the adjustment range of the target azimuth angle of the beamforming pointing angle of the determined microphone array has been completed.

[0014] Furthermore, the decision analysis module also includes: The backlight zone adjustment submodule is used to determine the sleep energy saving index based on the touch scanning frequency and the interval duration of near field sensing triggering, and to determine the adjustment range of the number of local backlight zones of the guide screen based on the sleep energy saving index, under the condition that the target azimuth angle of the beamforming pointing angle of the microphone array is adjusted. The partition boundary adjustment submodule is used to determine the adjustment range of the number of local backlight partitions of the guide screen based on the boundary detection results of static and dynamic areas in the image, after completing the adjustment range of the number of local backlight partitions of the guide screen.

[0015] Furthermore, the partition boundary adjustment submodule also includes: The backlight adjustment unit is used to determine the brightness adjustment index based on the ambient light intensity and screen brightness, and to determine the adjustment range of the backlight duty cycle of the non-interactive area of ​​the guide screen based on the brightness adjustment index, under the condition that the adjustment range of the number of partitions of the determined static area and dynamic area is completed. The gaze tracking correction unit is used to dynamically adjust the division boundary of the non-interactive area based on the user's gaze focus position detected by the near-field sensing sensor, provided that the backlight duty cycle of the non-interactive area of ​​the determined guide screen has been adjusted.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a multi-scenario wayfinding content management system, including a wayfinding screen, an interaction sensing module, a wayfinding screen detection module, a content management module, and a decision analysis module. The wayfinding screen integrates a touch sensor, a microphone array, a near-field sensor, a display panel, and a wireless communication circuit. The interaction sensing module collects interaction sensing parameters of the target wayfinding screen within a historical period, analyzes the interaction sensing values ​​based on these parameters, and determines whether to activate the wayfinding screen detection module based on the interaction sensing values. The wayfinding screen detection module determines whether to activate the edge cache adjustment submodule or the encoding adjustment submodule based on the interference index. The content management module determines whether to activate the decision analysis module based on the interaction degradation index. The decision analysis module determines whether to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index. This invention overcomes the problem of low operational stability in existing intelligent wayfinding systems when applied in different scenarios. This is caused by network link fluctuations leading to delayed cached content loading, resulting in untimely writing of updated content and degraded interactive performance. Consequently, voice wake-up sensitivity and display power consumption cannot be adaptively adjusted.

[0017] In particular, this invention integrates a touch sensor, microphone array, near-field sensor, display panel, and wireless communication circuit into a single hardware unit for the wayfinding screen. This unit can simultaneously collect user touch signals, voice commands, human proximity status, and gaze focus information to complete interactive data collection, content display, and network data transmission. This reduces data collection delays and status synchronization errors caused by the dispersion of peripheral devices, and improves the stability of the wayfinding screen in long-term operation under different scenarios, thereby enhancing the adaptability of the hardware for multi-scenario wayfinding content management systems.

[0018] In particular, this invention collects the interactive sensing parameters of the target wayfinding screen within a historical period through the interactive sensing module, analyzes the interactive sensing values ​​based on the interactive sensing parameters, and determines whether to activate the wayfinding screen detection module based on the interactive sensing values. This enables the detection of the wayfinding screen's operating status, improves the system's adaptability to complex environments and load changes, and thus enhances the accuracy of the multi-scenario wayfinding content management system in detecting the wayfinding screen's operating status.

[0019] In particular, the present invention uses the guidance screen detection module to determine whether to activate the edge cache adjustment submodule or the encoding adjustment submodule based on the interference index, and in the case of termination of operation, uses the content management module to determine whether to activate the decision analysis module based on the interaction degradation index. This allows the collaborative degradation parameters of touch and voice multimodal interaction to be incorporated into the detection mechanism, triggering deep detection when the system interaction performance significantly declines, thereby improving the efficiency of fault detection in the multi-scenario guidance content management system.

[0020] In particular, the present invention uses a decision analysis module to determine whether to activate the microphone adjustment submodule based on the interaction degradation index. If it is determined that the microphone adjustment submodule should not be activated, then the backlight zone adjustment submodule should be activated. This can optimize the sound pickup direction when the voice recognition quality deteriorates and reduce the backlight load when the power consumption is high, thereby improving the recognition accuracy of the interactive commands of the multi-scene guide content management system. Attached Figure Description

[0021] Figure 1 This is a structural block diagram of the multi-scene navigation content management system according to an embodiment of the present invention; Figure 2 This is a logic diagram illustrating how the guide screen detection module is activated based on interactive sensing values, according to an embodiment of the present invention. Figure 3 This is a logic diagram illustrating how the edge cache adjustment submodule is activated based on the interference index in an embodiment of the present invention. Figure 4 This is a logic diagram illustrating the process of determining whether to activate the decision analysis module based on the interaction degradation index in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0023] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0024] It should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connected" should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral connection; it can refer to a mechanical connection or an electrical connection; it can refer to a direct connection or an indirect connection through an intermediate medium; it can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0025] Please see Figure 1 As shown, this is a structural block diagram of a multi-scene wayfinding content management system according to an embodiment of the present invention. The present invention provides a multi-scene wayfinding content management system, including: The guide screen integrates a touch sensor, microphone array, near field sensor, display panel and wireless communication circuit; An interactive sensing module, connected to the guide screen, is used to collect interactive sensing parameters of the target guide screen within a historical period, analyze interactive sensing values ​​based on the interactive sensing parameters, and determine whether to activate the guide screen detection module based on the interactive sensing values; wherein, the interactive sensing parameters include the touch response time of the guide screen, the voice signal-to-noise ratio, and the content distribution delay time; The guide screen detection module is connected to both the guide screen and the interaction sensing module, and is used to determine whether to activate the edge buffer adjustment submodule or the encoding adjustment submodule based on the interference index; wherein, the interference index is determined based on the impedance fluctuation rate of the touch electrode, the ambient reverberation energy ratio and the number of interactions within a preset time. A content management module, which is connected to the guide screen and the guide screen detection module respectively, is used to determine whether to start the decision analysis module based on the interaction degradation index; wherein, the interaction degradation index is determined based on the accuracy of the semantic parsing of the interaction command and the power consumption of the guide screen; The decision analysis module, which is connected to the content management module, is used to determine whether to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index.

[0026] In this embodiment, the touch sensor is a capacitive multi-touch sensing chip, used to collect touch signals through an ITO conductive layer attached to the surface of the display panel. The microphone array is a 4-microphone linear distributed pickup submodule, used to collect ambient voice and user command signals through MEMS microphones. The near-field sensing sensor is a millimeter-wave and infrared composite proximity sensor, used to detect user distance and gaze focus by emitting and receiving reflected waves. The display panel is an LCD partial backlight partitioned screen, used to control the brightness of partitions through an LED driver chip and display directional content. The wireless communication circuit is a Wi-Fi 6 and 4G dual-mode communication module, used to interact with CDN nodes and backend servers through TCP and IP protocols.

[0027] This invention provides a multi-scene wayfinding content management system. Through a wayfinding screen, a touch sensor, microphone array, near-field sensor, display panel, and wireless communication circuit are integrated. An interaction sensing module collects interaction sensing parameters of the target wayfinding screen over a historical period, analyzes the interaction sensing values ​​based on these parameters, and determines whether to activate the wayfinding screen detection module based on the interaction sensing values. The wayfinding screen detection module determines whether to activate an edge buffer adjustment submodule or an encoding adjustment submodule based on an interference index. A content management module determines whether to activate a decision analysis module based on an interaction degradation index. The decision analysis module determines whether to activate a microphone adjustment submodule or a backlight zone adjustment submodule based on the interaction degradation index, thereby improving the interaction efficiency of the multi-scene wayfinding content management system in different scenarios.

[0028] Please see Figure 2 As shown, this is a logic diagram for determining whether to activate the guide screen detection module based on interactive sensing values ​​in an embodiment of the present invention. The interactive sensing module in this embodiment of the present invention further includes: The interaction perception analysis submodule is used to determine the interaction perception value based on the touch response time, voice signal-to-noise ratio and content distribution delay time, so as to detect the interaction response efficiency of the guide screen. The larger the interaction perception value, the worse the overall interaction response efficiency of the system and the higher the timing match between user operation and system feedback. The smaller the interaction perception value, the better the overall interaction response efficiency of the system and the higher the timing match between user operation and system feedback. An interaction perception detection submodule, which is connected to the interaction perception parsing submodule, is used to determine whether to activate the guide screen detection module based on the interaction perception value; wherein, the condition for activating the guide screen detection module is that the interaction perception value is greater than the interaction perception threshold.

[0029] Specifically, the interaction-aware parsing submodule also includes: The touch response deviation ratio calculation unit includes several touch controllers and capacitive touch detection chips deployed on the wayfinding screen. It determines the touch response duration of the wayfinding screen based on the interval between the user touching the display panel and the generation of touch coordinates from the effective touch signal. It also determines the touch response deviation ratio based on the ratio of the touch response duration to a touch response duration threshold, thereby detecting the delay in touch sensing on the wayfinding screen. A larger touch response deviation ratio results in a longer touch signal recognition cycle and a slower system feedback speed; a smaller touch response deviation ratio results in a shorter touch signal recognition cycle and a faster system feedback speed. The signal-to-noise ratio (SNR) calculation unit, which is a voice activity detection chip built into the microphone array, is used to determine the voice SNR of the guide screen based on the ratio of the effective voice signal intensity of the user to the ambient noise signal intensity collected by the microphone array of the guide screen. It also determines the SNR based on the ratio of the voice SNR threshold to the SNR to detect the sound pickup quality of the guide screen microphone array. The larger the SNR, the greater the ambient background noise and the higher the misjudgment rate of speech recognition. The smaller the SNR, the smaller the ambient background noise and the lower the misjudgment rate of speech recognition. The latency deviation ratio calculation unit, which is part of the network protocol stack, is used to determine the content distribution latency of the guide screen based on the interval between the content request initiated by the guide screen and the arrival of the first byte of data on the guide screen. It also determines the latency deviation ratio based on the ratio of the content distribution latency to a latency threshold, in order to detect the system's content loading efficiency. A larger latency deviation ratio indicates that network link bandwidth contention leads to a longer arrival time for the first byte, resulting in poorer real-time content display. Conversely, a smaller latency deviation ratio indicates a shorter arrival time for the first byte, resulting in better real-time content display. The interaction perception determination unit is used to determine the interaction perception value based on the sum of the touch response deviation ratio, the signal-to-noise ratio, and the delay deviation ratio.

[0030] In this embodiment, the touch response duration threshold is determined based on the upper limit boundary value that ensures the vast majority of interactive operations are perceived as instantaneous responses by users, based on the statistical distribution of touch response duration of the guide screen under standard operating conditions within a historical period; the signal-to-noise ratio threshold is determined based on the lower limit boundary value that ensures the speech activity detection algorithm can stably distinguish effective speech from background noise, based on the statistical distribution of speech signal-to-noise ratio of the guide screen in various typical scenarios within a historical period; the latency threshold is determined based on the upper limit boundary value that ensures continuous content playback without stuttering or idling within the statistical distribution of content distribution latency of the guide screen under baseline network conditions within a historical period; and the interaction sensing threshold is determined based on the statistical value representing the upper limit of normal fluctuations within the distribution of interaction sensing values ​​of the guide screen during normal operation in typical deployment scenarios within a historical period.

[0031] This invention, through an interactive sensing module, comprehensively detects the user's interaction response efficiency with the wayfinding screen based on touch response time, voice signal-to-noise ratio, and content distribution delay. In scenarios where wayfinding screens are deployed in densely populated transportation hubs with complex wireless signals, increased environmental electromagnetic interference prolongs the touch signal recognition cycle, increased environmental noise reduces the voice signal-to-noise ratio, and concurrent requests from multiple users intensify network bandwidth competition, leading to a longer arrival time of the first byte. All three deviations tend to increase simultaneously, resulting in a larger interactive sensing value. At the same time, an adaptive interactive sensing threshold is set according to the usage habits of users in different locations, thereby improving the operational stability and adaptability of the multi-scenario wayfinding content management system to different deployment scenarios.

[0032] Please see Figure 3 As shown, this is a logic diagram for determining whether to activate the edge cache adjustment submodule based on the interference index in an embodiment of the present invention. The guide screen detection module in this embodiment of the present invention further includes: The interference index determination submodule is used to determine the interference index based on the impedance fluctuation rate of the touch electrodes, the environmental reverberation energy ratio, and the number of interactions within a preset time period, in order to detect the degree of influence of the guide screen load on the interactive perception effect. The larger the interference index, the greater the degree of interference of the environment and system load on the integrity of the interactive perception signal, indicating that the system load is higher. The heat generated by dense interactions and signal crosstalk cause the touch and voice quality to deteriorate simultaneously. It is necessary to prioritize adjusting the encoding parameters to reduce the bandwidth occupation of wireless projection. The smaller the interference index, the smaller the degree of interference of the environment and system load on the integrity of the interactive perception signal, indicating that the external physical environment has less interference on touch and voice. The interaction lag is mainly due to the untimely content retrieval caused by network link status fluctuations. A cache state detection submodule, connected to the interference index determination submodule, is used to determine whether to activate the edge cache adjustment submodule or the encoding adjustment submodule based on the interference index; wherein, the condition for activating the edge cache adjustment submodule is that the interference index is less than or equal to the interference index threshold; the condition for activating the encoding adjustment submodule is that the interference index is greater than the interference index threshold.

[0033] Specifically, the interference index determination submodule further includes: The impedance fluctuation deviation ratio calculation unit is an impedance measurement circuit of the touch controller deployed inside the guide screen. It is used to determine the impedance fluctuation rate of the touch electrode based on the difference between the real-time impedance value of the touch electrode of the guide screen and the reference impedance value per unit time, and to determine the impedance fluctuation deviation ratio based on the ratio of the impedance fluctuation rate to the impedance fluctuation rate threshold, so as to detect the fluctuation degree of the touch electrode of the guide screen. The larger the impedance fluctuation deviation ratio, the greater the reference impedance deviation caused by temperature drift of the touch electrode, and the greater the risk of false alarm and missed touch signal of the system. The smaller the impedance fluctuation deviation ratio, the smaller the reference impedance deviation caused by temperature drift of the touch electrode, and the lower the risk of false alarm and missed touch signal of the system. The reverberation energy deviation ratio calculation unit is used to determine the environmental reverberation energy ratio based on the ratio of the sum of the energy of the sound sources in the space where the guide screen is located after multi-path reflection delay to the direct sound energy, and to determine the reverberation energy deviation ratio based on the ratio of the environmental reverberation energy ratio to the environmental reverberation energy ratio threshold, so as to detect the clarity of the microphone array in recognizing the user's voice. The larger the reverberation energy deviation ratio, the more times the direct sound energy of the voice command is reflected, and the lower the voice clarity. The smaller the reverberation energy deviation ratio, the fewer times the direct sound energy of the voice command is reflected, and the higher the voice clarity. The interaction deviation ratio calculation unit is used to determine the number of interactions within a preset time period based on the total number of valid touch events and valid voice commands collected by the guide screen within the preset time period, and to determine the interaction deviation ratio based on the ratio of the number of interactions to the interaction number threshold, so as to detect the load level of the guide screen. The larger the interaction deviation ratio, the higher the frequency of user operation on the guide screen within the preset time period, and the greater the system load; the smaller the interaction deviation ratio, the lower the frequency of user operation on the guide screen within the preset time period, and the smaller the system load. The interference index determination unit is used to determine the interference index based on the sum of the impedance fluctuation deviation ratio, the reverberation energy deviation ratio, and the interaction deviation ratio.

[0034] In this embodiment, the impedance fluctuation rate threshold is determined based on the statistical value representing the upper limit of normal fluctuation in the statistical distribution of the touch electrode impedance fluctuation rate of the guide screen under standard temperature and humidity environment within a historical period; the environmental reverberation energy ratio threshold is determined based on the statistical value representing the upper limit of normal reverberation in the statistical distribution of the reverberation energy ratio of the guide screen under standard acoustic environment within a historical period; the interaction number threshold is determined based on the statistical value representing the upper limit of normal interaction amount in the statistical distribution of the number of effective interactions of the guide screen within a preset time in typical interaction scenarios within a historical period; and the interference index threshold is determined based on the statistical value representing the upper limit of normal fluctuation in the interference index distribution of the guide screen under normal operation in multiple scenarios within a historical period.

[0035] Specifically, the guide screen detection module also includes: The edge cache adjustment submodule is used to determine the edge cache adjustment index based on the noise spectral density and the accuracy of touch commands, and to determine the adjustment range of the CDN edge node content prefetching depth based on the edge cache adjustment index, so as to release cache space to accommodate updated content. The larger the edge cache adjustment index, the more significant the interference of environmental noise on voice interaction or the more obvious the deviation of touch command parsing, and the greater the probability of new content being written to the cache. The smaller the edge cache adjustment index, the better the sound pickup effect and touch recognition accuracy of the guide screen, and the more sufficient the amount of content fetched by the system in a single operation. The edge cache adjustment submodule further includes: The content chunking unit, which is built into the edge cache adjustment submodule, is used to determine the adjustment range of the content chunk size of a single prefetch request in the CDN edge node based on the content adjustment index determined by the timestamp dispersion of the cached content and the duration of user interaction, after adjusting the content prefetch depth of the CDN edge node, so as to determine the reduction ratio of the content chunk size of a single prefetch. The content aggregation unit, which is built into the edge cache adjustment submodule and connected to the content segmentation unit, is used to merge multiple consecutive content segmentation requests into a batch prefetch request based on the aggregation degree of the segmentation requests, under the condition that the size of the single prefetch content segment is adjusted, so as to merge two or more consecutive segmentation requests into a batch prefetch request. The content aggregation unit further includes: The aggregation degree acquisition sub-unit is a request count statistics table built into the system. It is used to determine the aggregation degree of the block requests based on the ratio of the number of continuous content block requests that are merged into a batch prefetch request within a preset time period to the total number of block requests in the window, so as to detect the system's request content aggregation effect. The higher the aggregation degree, the higher the efficiency of request merging, and the better the problem of the surge in the number of requests caused by excessively fine blocks is suppressed. The lower the aggregation degree, the lower the efficiency of request merging. The re-detection submodule, which is connected to the edge cache adjustment submodule, is used to determine to start the encoding adjustment submodule if the CDN edge node content prefetching depth has been adjusted and the interference index is still less than or equal to the interference index threshold after re-detection. The encoding adjustment submodule, which is connected to the edge buffer adjustment submodule, is used to determine the adjustment range of the wireless projection encoding complexity of the guide screen based on the channel utilization, packet loss rate and RSSI fluctuation rate, so as to reduce the probability of data transmission failure and the resource consumption of data retransmission. The keyframe recovery submodule, which is connected to the encoding adjustment submodule, is used to determine the adjustment range of the number of repeated transmissions of keyframes based on the number of consecutively successfully decoded non-keyframes, after completing the adjustment of the wireless projection encoding complexity of the guide screen, until it is restored to the initial value, so as to ensure that the decoding end can still complete the image reconstruction through redundant reception when keyframes are lost.

[0036] Specifically, the edge cache adjustment submodule also includes: The noise deviation ratio calculation unit, which is a microphone array deployed on the guide screen, is used to determine the noise spectral density based on the ambient noise power within a unit bandwidth, and to determine the noise deviation ratio based on the ratio of the noise spectral density threshold to the noise spectral density, so as to detect the degree of interference of background noise on the user's voice commands. The larger the noise deviation ratio, the denser the energy distribution of ambient noise in the frequency domain, and the more severe the masking of the effective voice band; the smaller the noise deviation ratio, the more dispersed the energy distribution of ambient noise in the frequency domain, and the less severe the masking of the effective voice band. The touch accuracy deviation ratio calculation unit, which is a touch sensing chip built into the guide screen, is used to determine the accuracy of touch commands based on the proportion of touch events successfully parsed into valid commands within a preset time period, and to determine the touch accuracy deviation ratio based on the ratio of the touch command accuracy to the accuracy threshold, so as to detect the accuracy of the system in parsing commands. The larger the touch accuracy deviation ratio, the lower the proportion of touch events successfully parsed into valid commands, and the worse the reliability of the system's correct response to user click operations. The smaller the touch accuracy deviation ratio, the higher the hit matching degree between touch coordinates and interactive area, and the higher the success rate of touch command parsing. The cache adjustment index determination unit determines the edge cache adjustment index based on the product of the noise deviation ratio and the touch accuracy deviation ratio, so as to adjust the prefetch depth of the cached content. The larger the edge cache adjustment index, the more fully the storage space is released and the higher the probability of new content being written to the cache. The smaller the edge cache adjustment index, the less storage space is released and the lower the probability of new content being written to the cache. The edge cache adjustment unit is used to determine the reduction in the content prefetch depth of CDN edge nodes based on the ratio of the content adjustment index to the content adjustment index threshold.

[0037] In this embodiment, the noise spectral density threshold is determined based on the statistical value of the ambient noise power spectral density of the guide screen under standard acoustic conditions within a historical period; the accuracy threshold is determined based on the statistical value of the touch command parsing accuracy of the guide screen under interference-free conditions within a historical period; and the content adjustment index threshold is determined based on the statistical value representing the upper limit of normal fluctuation in the edge cache adjustment index distribution corresponding to the guide screen when the cache hit rate is in a stable range within a historical period.

[0038] Specifically, the content segmentation unit further includes: The time dispersion ratio calculation unit is used to determine the timestamp dispersion of cached content based on the standard deviation between the last update timestamps of all cached entries in the CDN edge nodes, and to determine the time dispersion ratio based on the ratio of the timestamp dispersion of cached content to the timestamp dispersion threshold, so as to detect the time consistency of cached content. The larger the time dispersion ratio, the larger the update time difference of different cached content, and the higher the probability that the system will hit expired content when the user requests it; the smaller the time dispersion ratio, the smaller the update time difference of different cached content, and the lower the probability that the system will hit expired content when the user requests it. The interaction delay deviation ratio calculation unit is used to determine the user interaction interval duration based on the average difference between the timestamps of adjacent events within a preset duration, and to determine the interaction delay deviation ratio based on the ratio of the user interaction interval duration to a user interaction interval duration threshold, so as to detect the system load status under different operation frequencies; the larger the interaction delay deviation ratio, the lower the user interaction frequency and the smaller the system load; the smaller the interaction delay deviation ratio, the higher the user interaction frequency and the larger the system load. The content adjustment index determination unit is used to determine the content adjustment index based on the sum of the time discrepancy ratio and the interaction delay ratio.

[0039] In this embodiment, the timestamp dispersion threshold is determined based on the statistical value of the timestamp dispersion of the CDN edge node cached content at a stable update frequency within a historical period; the user interaction interval duration threshold is determined based on the statistical value of the time interval between adjacent valid events on the guide screen under typical interaction scenarios within a historical period.

[0040] Specifically, the content aggregation unit further includes: The aggregation degree acquisition subunit is used to determine the aggregation degree of the chunked requests based on the ratio of the number of continuous content chunked requests that are merged into a batch prefetch request within a preset time period to the total number of chunked requests in the window, so as to detect the request aggregation effect of the system under different chunking strategies. The higher the aggregation degree, the higher the efficiency of request merging, and the better the problem of the surge in the number of requests caused by excessive chunking is suppressed. The lower the aggregation degree, the lower the efficiency of request merging.

[0041] Specifically, the encoding adjustment subunit further includes: The channel utilization deviation ratio calculation unit determines the channel utilization rate based on the ratio of the actual data transmission time to the total available time on the wireless communication channel, and determines the channel utilization deviation ratio based on the ratio of the channel utilization rate to the channel utilization threshold, in order to detect the sufficiency of the system's network bandwidth. The larger the channel utilization deviation ratio, the closer the wireless communication channel is to saturation, the tighter the available bandwidth, and the longer the data transmission queuing time; the smaller the channel deviation ratio, the more abundant the channel idle resources. The packet loss rate deviation ratio calculation unit is used to determine the packet loss rate based on the ratio of the number of data packets sent by the transmitter that were not correctly acknowledged by the receiver to the total number of packets sent per unit time, and to determine the packet loss rate deviation ratio based on the ratio of the packet loss rate threshold to the packet loss rate, so as to detect the transmission reliability of the system network link. The larger the packet loss rate deviation ratio, the worse the stability of the wireless transmission link, the higher the proportion of data packets that are dropped or damaged during transmission, and the more frequent the retransmission requests triggered by the receiver. The smaller the packet loss rate deviation ratio, the higher the proportion of data packets that successfully reach the receiver. The volatility deviation ratio calculation unit, which is a wireless network interface controller built into the system, is used to determine the RSSI volatility based on the ratio of the standard deviation to the average value of the received signal strength indication value within a preset time period, and to determine the volatility deviation ratio based on the ratio of the RSSI volatility threshold to the RSSI volatility, so as to detect the stability of the network channel of the system. The larger the volatility deviation ratio, the more obvious the quality fluctuation of the wireless link, and the worse the stability of the continuous decoding of the guide screen. The smaller the volatility deviation ratio, the more stable the signal strength, the more stable the wireless channel state, and the better the stability of the continuous decoding of the guide screen. The complexity index determination unit is used to determine the coding complexity index based on the sum of the channel utilization deviation ratio, the packet loss rate deviation ratio, and the volatility deviation ratio. The encoding adjustment unit is used to determine the wireless screen projection encoding complexity based on the ratio of the encoding complexity index to the encoding complexity index threshold.

[0042] In this embodiment, the channel utilization threshold is determined based on the channel utilization statistics of the guide screen under stable wireless communication conditions within a historical period; the packet loss rate threshold is determined based on the packet loss rate statistics of the guide screen under reliable wireless transmission conditions within a historical period; the RSSI volatility threshold is determined based on the received signal strength indication volatility statistics of the guide screen under a stable signal environment within a historical period; and the coding complexity index threshold is determined based on the statistical value representing the upper limit of normal volatility in the coding complexity index distribution corresponding to the guide screen when the wireless projection screen plays continuously and smoothly within a historical period.

[0043] In this embodiment of the invention, the coding adjustment submodule is activated by the guide screen detection module when the interference index increases. Based on the channel utilization, packet loss rate and signal fluctuation, the wireless projection coding complexity is adjusted in a coordinated manner. This can dynamically adapt to the real-time changes in wireless link quality, thereby improving the continuity of screen transmission in the multi-scenario guide content management system.

[0044] Please see Figure 4 As shown, this is a logic diagram for determining whether to activate the decision analysis module based on the interaction degradation index in an embodiment of the present invention. The content management module in this embodiment of the present invention further includes: The degradation index calculation submodule is used to determine the interaction degradation index based on the accuracy of semantic parsing of the interaction command and the power consumption of the guide screen, under the condition that the complexity of the wireless projection encoding of the guide screen has been adjusted and the interaction sensing value is still greater than the interaction sensing threshold, so as to match the corresponding adjustment method. The larger the interaction degradation index, the greater the deviation of the speech recognition engine in understanding the semantics of the user command, indicating that the overall power consumption of the system has increased. It is necessary to reduce the display load first to release the power budget, and the backlight zone adjustment submodule needs to be activated. The smaller the interaction degradation index, the smaller the deviation of the speech recognition engine in understanding the semantics of the user command, indicating that the decline in the interaction performance of the guide screen is mainly due to insufficient sound pickup quality, rather than excessive overall system power consumption, and the microphone adjustment submodule needs to be activated. An interaction detection submodule, connected to the degradation index calculation submodule, is used to determine whether to control the decision analysis module to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index. The condition for controlling the decision analysis module to activate the microphone adjustment submodule is that the interaction degradation index is less than or equal to an interaction degradation index threshold; the condition for controlling the decision analysis module to activate the backlight zone adjustment submodule is that the interaction degradation index is greater than the interaction degradation index threshold.

[0045] Specifically, the degradation index calculation submodule also includes: The semantic deviation ratio calculation unit, which is a speech recognition engine built into the guide screen, is used to determine the accuracy of semantic parsing based on the proportion of user voice commands correctly converted into semantic representations with slot annotations within a preset time period, and to determine the semantic deviation ratio based on the ratio of the accuracy threshold to the accuracy of semantic parsing, so as to detect the accuracy of the system's understanding of voice commands. The larger the semantic deviation ratio, the greater the deviation of the speech recognition engine in understanding the semantics of user commands, and the worse the smoothness of system interaction; the smaller the semantic deviation ratio, the smaller the deviation of the speech recognition engine in understanding the semantics of user commands, and the better the smoothness of system interaction. The power consumption deviation ratio calculation unit is a power monitoring circuit built into the wayfinding screen. It is used to determine the power consumption of the wayfinding screen based on the average power of the wayfinding screen within a preset time period, and to determine the power consumption deviation ratio based on the ratio of power consumption to power consumption threshold, so as to detect the operating energy consumption of the wayfinding screen. The larger the power consumption deviation ratio, the higher the power consumption of the wayfinding screen and the greater the heat dissipation pressure of the system. The smaller the power consumption deviation ratio, the lower the power consumption of the wayfinding screen and the less the heat dissipation pressure of the system. The degradation index determination unit is used to determine the interaction degradation index based on the sum of the semantic deviation ratio and the power consumption deviation ratio.

[0046] In this embodiment, the accuracy threshold is determined based on the statistical value of the accuracy of the semantic parsing of voice commands on the wayfinding screen in a standard interactive environment within a historical period; the power consumption threshold is determined based on the statistical value of the total average power consumption of the wayfinding screen under typical operating conditions within a historical period.

[0047] This invention determines the interaction degradation index based on the accuracy of semantic parsing of interactive commands and the power consumption of the wayfinding screen through the content management module. When the wayfinding screen runs under high-load interactive scenarios for a long time, the accumulation of background processes in the system leads to an increase in processor utilization. At the same time, the speech recognition engine needs to call a larger-scale decoding network to cope with complex semantics. Both of these factors jointly increase the overall power consumption of the device. Furthermore, the competition for processor resources causes the response timing of semantic parsing to deviate, limiting the decoding depth and thus reducing the accuracy. The deviation ratio of the two factors tends to increase simultaneously. In addition, the interaction degradation index determines whether to control the decision analysis module to start the microphone adjustment submodule or the backlight zone adjustment submodule, thereby improving the execution efficiency of the multi-scenario wayfinding content management system in automatically adjusting when the interaction deteriorates.

[0048] Specifically, the decision analysis module also includes: The microphone adjustment submodule is used to determine the speech engine optimization index based on the accuracy of intent slot filling and the echo cancellation residual ratio of the microphone array, and to determine the adjustment range of the target azimuth angle of the beamforming pointing angle of the microphone array based on the speech engine optimization index, so as to reduce the interference of the environment on the microphone array. The larger the speech engine optimization index, the greater the interference of the signal quality acquired by the microphone array on semantic understanding, and the lower the accuracy of the system in recognizing voice commands. The smaller the speech engine optimization index, the less the interference of the signal quality acquired by the microphone array on semantic understanding, and the higher the accuracy of the system in recognizing voice commands. The pointing angle calibration submodule, which is connected to the microphone adjustment submodule, is used to periodically calibrate the beamforming pointing angle based on the consistency of the voice arrival time difference of the distributed microphones, under the condition that the target azimuth angle of the beamforming pointing angle of the microphone array has been adjusted, so as to reduce the cumulative error of beam pointing. The pointing angle calibration submodule further includes: The speech consistency acquisition unit determines the consistency of the speech arrival time difference of the distributed microphones based on the standard deviation of the deviation between the speech arrival time difference measured within a preset time period and the reference arrival time of the microphone in the initial calibration state. This is to detect the degree of deviation in the acquisition of speech from different directions by the microphone array. The smaller the consistency, the greater the perceptual deviation of the sound source direction between different microphone pairs, the greater the calibration error of the beamforming pointing angle, and the lower the accuracy of the system in recognizing speech commands. Conversely, the greater the consistency, the smaller the calibration error of the beamforming pointing angle, and the higher the accuracy of the system in recognizing speech commands. The pointing angle calibration unit is used to determine whether to re-determine the delay compensation amount of the microphone array to correct the beam pointing based on the speech arrival time difference of adjacent microphones within a preset time period and the speech arrival time difference; wherein, the condition for determining to re-determine the delay compensation amount of the microphone array is that the speech arrival time difference is greater than a preset speech arrival time difference threshold, indicating that there is a deviation in the beam pointing.

[0049] Specifically, the microphone adjustment submodule also includes: The intent deviation ratio calculation unit, which is a pre-stored intent template in the system, is used to determine the intent slot filling accuracy based on the ratio of the number of intent categories and slots correctly extracted from the speech recognition text within a preset time period to the total number of intent categories and slots in the speech recognition text. It also determines the intent deviation ratio based on the ratio of the intent slot filling accuracy threshold to the intent slot filling accuracy, thereby detecting the semantic completeness of the voice command. A larger intent deviation ratio indicates a lower proportion of correctly extracted intent categories and key slots in the speech recognition text, resulting in poorer semantic completeness of the user command and a greater deviation in the system's interpretation of the user's query target and operational intent. Conversely, a smaller intent deviation ratio indicates higher reliability of semantic understanding and a smaller deviation in the system's interpretation of the user's query target and operational intent. The slots include the query target, starting location, and destination. The echo cancellation deviation ratio calculation unit is used to determine the echo cancellation residual ratio of the microphone array based on the ratio of the remaining signal energy after echo cancellation algorithm processing to the original acquired speech signal energy, and to determine the echo cancellation deviation ratio based on the ratio of the echo cancellation residual ratio to the echo cancellation residual ratio threshold, so as to detect the echo suppression effect of the system. The larger the echo cancellation deviation ratio, the worse the suppression effect of the adaptive filter on the speaker reference signal, and the greater the interference of residual echo on user voice commands. The smaller the echo cancellation deviation ratio, the better the suppression effect of the adaptive filter on the speaker reference signal, and the less the interference of residual echo on user voice commands. The optimization index determination unit is used to determine the speech engine optimization index based on the sum of the intent deviation ratio and the echo cancellation deviation ratio. The azimuth adjustment unit is used to determine the adjustment range of the target azimuth angle of the microphone array beamforming pointing angle based on the ratio of the voice engine optimization index to the voice engine optimization index threshold.

[0050] In this embodiment, the accuracy threshold for intent slot filling is determined based on the statistical minimum value representing the lower limit of normal fluctuation in the statistical distribution of intent slot filling accuracy of the guide screen in a standard interactive environment within a historical period; the echo cancellation residue ratio threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the statistical distribution of residual signal energy after echo cancellation processing of the guide screen in a standard acoustic environment within a historical period; and the voice engine optimization index threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the voice engine optimization index distribution of the guide screen in a standard acoustic environment within a historical period.

[0051] In this embodiment of the invention, the decision analysis module determines the voice engine optimization index based on the accuracy of intent slot filling and the echo cancellation residue ratio of the microphone array, and determines the adjustment range of the target azimuth angle of the beamforming pointing angle of the microphone array based on the voice engine optimization index, thereby improving the accuracy of the multi-scene wayfinding content management system in adaptive adjustment of voice pickup pointing in dynamic sound source scenarios.

[0052] Specifically, the decision analysis module also includes: A backlight zone adjustment submodule, which is connected to the microphone adjustment submodule, is used to determine the sleep energy saving index based on the touch scanning frequency and the interval duration of near field sensing triggering, under the condition of completing the target azimuth angle of adjusting the beamforming pointing angle of the microphone array, and to determine the adjustment range of the number of local backlight zones of the guide screen based on the sleep energy saving index, so as to reduce the computing load of the digital signal processor of the guide screen. The partition boundary adjustment submodule, which is connected to the backlight partition adjustment submodule, is used to improve the edge clarity of moving objects in the guide screen by maintaining the reduced number of partitions in the static area and restoring the default number of partitions in the dynamic area, based on the boundary detection results of the static and dynamic areas in the screen, after adjusting the number of local backlight partitions.

[0053] Specifically, the backlight zone adjustment submodule also includes: The touch scan deviation ratio calculation unit is used to determine the touch scanning frequency of the guide screen based on the number of times the touch controller scans the touch sensor and reports the coordinate position per unit time, and to determine the touch scan deviation ratio based on the ratio of the touch scan frequency threshold to the touch scan frequency, so as to detect the touch time resolution of the system. The larger the touch scan deviation ratio, the higher the touch detection time resolution, the more resources the touch controller consumes per unit time, and the higher the system's operating power consumption. The smaller the touch scan deviation ratio, the lower the touch detection time resolution, and the lower the system's operating power consumption. The sensing trigger deviation ratio calculation unit is used to determine the near-field sensing trigger interval of the guide screen based on the interval between two adjacent near-field sensing sensors detecting the user's approach to the guide screen, and to determine the sensing trigger deviation ratio based on the ratio of the near-field sensing trigger interval to the near-field sensing trigger interval threshold, so as to detect the user's interaction time. The larger the sensing trigger deviation ratio, the longer the user stays in front of the guide screen for continuous interaction, and the greater the power consumption of the system to maintain high display quality. The smaller the sensing trigger deviation ratio, the shorter the user stays in front of the guide screen for continuous interaction, and the lower the power consumption of the system to maintain high display quality. The sleep energy saving index determination unit is used to determine the sleep energy saving index based on the sum of the touch scan deviation ratio and the sensor trigger deviation ratio; The backlight zone adjustment unit is used to determine the reduction range of the number of local backlight zones of the guide screen based on the ratio of the sleep energy saving index to the sleep energy saving index threshold.

[0054] In this embodiment, the touch scanning frequency threshold is determined based on the statistical minimum value representing the lower limit of normal fluctuation in the statistical distribution of touch scanning frequency of the guide screen under standard interactive conditions within a historical period; the near-field sensing trigger interval duration threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the statistical distribution of near-field sensing trigger interval duration of the guide screen under continuous interactive scenarios within a historical period; and the sleep energy saving index threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the statistical distribution of sleep energy saving index of the guide screen under low load standby state within a historical period.

[0055] Specifically, the partition boundary adjustment submodule also includes: The boundary detection unit is used to determine the boundary detection results of static and dynamic areas in the picture based on the difference value of consecutive frames in the video frame buffer, so as to distinguish the static picture area and dynamic picture area of ​​the display panel. The larger the proportion of static area in the detection result, the more fixed content in the picture, the better the energy saving effect of reducing the number of backlight partitions in that area and the smaller the visual impact. The smaller the proportion of static area in the detection result, the worse the energy saving effect of reducing the number of backlight partitions in that area. A partition adjustment unit is used to determine the adjustment range of the number of partitions in static and dynamic areas based on the boundary detection results of static and dynamic areas in the image. Specifically, it maintains the number of backlight partitions and the corresponding backlight duty cycle in the static areas; adjusts the number of backlight partitions in the dynamic areas to the initial number of grid partitions; and determines the buffer band width between the static and dynamic areas based on a predetermined pixel width to increase the display quality of the dynamic areas, reduce the power consumption of the static areas, and eliminate brightness jumps through the buffer band. Preferably, the predetermined width is set based on the spatial smoothing length required for brightness transition between the dynamic and static areas.

[0056] Specifically, the partition boundary adjustment submodule also includes: The backlight adjustment unit is used to determine the brightness adjustment index based on the ambient light intensity and screen brightness, and to determine the adjustment range of the backlight duty cycle of the non-interactive area of ​​the guide screen based on the brightness adjustment index, so as to reduce the backlight duty cycle of the non-interactive area in the guide screen to soften the brightness transition boundary and save power consumption. A gaze tracking correction unit, which is connected to the backlight adjustment unit, is used to dynamically adjust the division boundary of the non-interactive area based on the user's gaze focus position detected by the near field sensor, after adjusting the backlight duty cycle of the non-interactive area, so as to ensure that the area the user is looking at is always identified as the interactive area and maintain the brightness of the area. The gaze tracking correction unit further includes: The coordinate positioning subunit includes a near-field sensing sensor built into the guide screen, which employs an infrared binocular camera to determine the gaze point coordinates of the display panel based on the three-dimensional spatial coordinates of the user's binocular vision. Simultaneously, a circular interactive hot zone with a preset radius is generated centered on the gaze point coordinates. All backlight zones within the circular interactive hot zone are marked as interactive areas, and zones outside the circular interactive hot zone are marked as non-interactive areas, in order to identify the area of ​​the user's field of vision mapped onto the guide screen. The preset radius is set based on the minimum value of the statistical value of the effective gaze area diameter on the screen corresponding to the central fovea of ​​the user's monocular field of vision. The interaction range reduction subunit is used to linearly reduce the radius of the circular interaction hot zone when the displacement of the gaze point coordinates is less than the preset pixel width for two or more consecutive times, so as to limit the high brightness area within the user's line of sight more precisely and reduce the backlight energy consumption of the non-interactive area; wherein, the preset pixel width is set based on the maximum value of the pixel spacing corresponding to the spatial frequency at which the human eye is not sensitive to the screen brightness jump at normal viewing distance. The interaction range expansion subunit is used to linearly expand the radius of the circular interaction hot zone when the gaze point coordinate displacement is greater than the preset pixel width, so as to improve the backlight duty cycle of the user's gaze focus area. The deep energy-saving subunit is used to determine that the user has left if the near-field sensing sensor does not detect the user's face or eyes for ten or more consecutive times. It then restores the full screen to the low backlight duty cycle state of the non-interactive area, and at the same time, the guide screen enters the deep energy-saving mode to reduce the overall energy consumption of the system.

[0057] Specifically, the backlight adjustment unit further includes: An ambient light intensity deviation ratio calculation subunit includes several ambient light sensors integrated on the bezel of the wayfinding screen display panel. These sensors are used to determine the ambient light intensity based on the visible light intensity of the environment in which the wayfinding screen is located, and to determine the ambient light intensity deviation ratio based on the ratio of the ambient light intensity to an ambient light intensity threshold, so as to detect the brightness of the environment in which the system is located. The larger the ambient light intensity deviation ratio, the brighter the ambient light, and the higher the brightness and contrast required for the content of the wayfinding screen. The smaller the ambient light intensity deviation ratio, the darker the ambient light, and the lower the brightness and contrast required for the content of the wayfinding screen. The screen brightness deviation ratio calculation subunit is a backlight pulse width modulation duty cycle register built into the system. It is used to determine the screen brightness of the guide screen based on the average brightness level currently output by the guide screen display panel, and to determine the screen brightness deviation ratio based on the ratio of the screen brightness to the screen brightness threshold, so as to detect the operating power consumption of the guide screen. The larger the screen brightness deviation ratio, the brighter the display panel and the greater the power consumption of the guide screen; the smaller the screen brightness deviation ratio, the less power consumption of the guide screen. The brightness adjustment index determination subunit is used to determine the brightness adjustment index based on the product of the ambient light intensity deviation ratio and the screen brightness deviation ratio. The backlight duty cycle adjustment subunit is used to determine the reduction range of the backlight duty cycle in the non-interactive area of ​​the guide screen based on the ratio of the brightness adjustment index to the brightness adjustment index threshold.

[0058] In this embodiment, the ambient light intensity threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the statistical distribution of ambient light intensity of the wayfinding screen under typical indoor lighting conditions within a historical period; the screen brightness threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the statistical distribution of screen brightness of the wayfinding screen under standard display conditions within a historical period; and the brightness adjustment index threshold is determined based on the statistical maximum value representing the upper limit of normal fluctuation in the statistical distribution of brightness adjustment index of the wayfinding screen under typical ambient light intensity and screen brightness combination conditions within a historical period.

[0059] This invention, through a partition boundary adjustment submodule, determines the reduction range of the backlight duty cycle in non-interactive areas based on ambient light intensity and screen brightness, thereby reducing backlight energy consumption in non-interactive areas. Simultaneously, by dynamically adjusting the boundaries of interactive hot zones, it ensures that the user's gaze area always maintains high brightness, thus improving the display stability of the multi-scene guide content management system in dynamic interactive scenarios.

[0060] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A multi-scene navigation content management system, characterized in that, include: The guide screen integrates a touch sensor, microphone array, near field sensor, display panel and wireless communication circuit; The interactive sensing module is used to collect interactive sensing parameters of the target guide screen within a historical period, analyze the interactive sensing values ​​based on the interactive sensing parameters, and determine whether to activate the guide screen detection module based on the interactive sensing values; wherein, the interactive sensing parameters include the touch response time of the guide screen, the voice signal-to-noise ratio, and the content distribution delay time. The guide screen detection module is used to determine whether to activate the edge buffer adjustment submodule or the encoding adjustment submodule based on the interference index. The content management module is used to determine whether to activate the decision analysis module based on the interaction degradation index; The decision analysis module is used to determine whether to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index.

2. The multi-scene navigation content management system according to claim 1, characterized in that, The interactive sensing module also includes: The interaction perception analysis submodule is used to determine the interaction perception value based on the touch response time, voice signal-to-noise ratio and content distribution delay. An interactive perception detection submodule is used to determine whether to activate the guide screen detection module based on the interactive perception value; wherein, the condition for activating the guide screen detection module is that the interactive perception value is greater than the interactive perception threshold.

3. The multi-scene navigation content management system according to claim 2, characterized in that, The guide screen detection module also includes: The interference index determination submodule is used to determine the interference index based on the impedance fluctuation rate of the touch electrode, the ambient reverberation energy ratio, and the number of interactions within a preset time. A cache state detection submodule is used to determine whether to activate the edge cache adjustment submodule or the encoding adjustment submodule based on the interference index; wherein, the condition for activating the edge cache adjustment submodule is that the interference index is less than or equal to the interference index threshold; and the condition for activating the encoding adjustment submodule is that the interference index is greater than the interference index threshold.

4. The multi-scene navigation content management system according to claim 3, characterized in that, The guide screen detection module also includes: The edge cache adjustment submodule is used to determine the edge cache adjustment index based on the noise spectral density and the accuracy of touch commands, and to determine the adjustment range of the CDN edge node content prefetch depth based on the edge cache adjustment index. The re-detection submodule is used to determine whether to start the encoding adjustment submodule if the adjustment range of the CDN edge node content prefetch depth has been determined and the interference index is still less than or equal to the interference index threshold after re-detection.

5. The multi-scene navigation content management system according to claim 4, characterized in that, The edge cache adjustment submodule also includes: The content chunking unit is used to determine the content adjustment index based on the timestamp dispersion of the cached content and the duration of user interaction, and to determine the adjustment range of the content chunk size for a single prefetch request of the CDN edge node, provided that the adjustment range of the content prefetch depth of the CDN edge node has been determined. The content aggregation unit is used to merge several consecutive content chunk requests into a single batch prefetch request based on the aggregation degree of the chunk requests, provided that the adjustment range of the content chunk size of the single prefetch request for the determined CDN edge node is completed.

6. The multi-scene navigation content management system according to claim 4, characterized in that, The guide screen detection module also includes: The coding adjustment submodule is used to determine the adjustment range of the wireless projection coding complexity of the guide screen based on channel utilization, packet loss rate and RSSI volatility. The keyframe recovery submodule is used to determine the adjustment range of the number of times key frames are repeatedly sent based on the number of consecutively successfully decoded non-key frames, after completing the adjustment range of the wireless projection encoding complexity of the guide screen, until it is restored to the initial value.

7. The multi-scene navigation content management system according to claim 6, characterized in that, The content management module also includes: The degradation index calculation submodule is used to determine the interaction degradation index based on the accuracy of the semantic parsing of the interaction command and the power consumption of the guide screen, under the condition that the adjustment range of the repeated transmission number of the determined key frame is completed and the interaction sensing value is still greater than the interaction sensing threshold. An interaction detection submodule is used to determine whether to control the decision analysis module to activate the microphone adjustment submodule or the backlight zone adjustment submodule based on the interaction degradation index. The condition for determining whether to control the decision analysis module to activate the microphone adjustment submodule is that the interaction degradation index is less than or equal to the interaction degradation index threshold. The condition for determining whether to control the decision analysis module to activate the backlight zone adjustment submodule is that the interaction degradation index is greater than the interaction degradation index threshold.

8. The multi-scene navigation content management system according to claim 7, characterized in that, The decision analysis module also includes: The microphone adjustment submodule is used to determine the speech engine optimization index based on the accuracy of intent slot filling and the echo cancellation residual ratio of the microphone array, and to determine the adjustment range of the target azimuth angle of the beamforming pointing angle of the microphone array based on the speech engine optimization index. The pointing angle calibration submodule is used to periodically calibrate the beamforming pointing angle based on the consistency of the speech arrival time difference of the distributed microphones, provided that the adjustment range of the target azimuth angle of the beamforming pointing angle of the determined microphone array has been completed.

9. The multi-scene navigation content management system according to claim 7, characterized in that, The decision analysis module also includes: The backlight zone adjustment submodule is used to determine the sleep energy saving index based on the touch scanning frequency and the interval duration of near field sensing triggering, and to determine the adjustment range of the number of local backlight zones of the guide screen based on the sleep energy saving index, under the condition that the target azimuth angle of the beamforming pointing angle of the microphone array is adjusted. The partition boundary adjustment submodule is used to determine the adjustment range of the number of local backlight partitions of the guide screen based on the boundary detection results of static and dynamic areas in the image, after completing the adjustment range of the number of local backlight partitions of the guide screen.

10. The multi-scene navigation content management system according to claim 9, characterized in that, The partition boundary adjustment submodule also includes: The backlight adjustment unit is used to determine the brightness adjustment index based on the ambient light intensity and screen brightness, and to determine the adjustment range of the backlight duty cycle of the non-interactive area of ​​the guide screen based on the brightness adjustment index, under the condition that the adjustment range of the number of partitions of the determined static area and dynamic area is completed. The gaze tracking correction unit is used to dynamically adjust the division boundary of the non-interactive area based on the user's gaze focus position detected by the near-field sensing sensor, provided that the backlight duty cycle of the non-interactive area of ​​the determined guide screen has been adjusted.

Images