A data monitoring method and system based on image recognition

Abstract

The present invention is applicable to the technical field of image recognition and translation task scheduling, and provides a data monitoring method and system based on image recognition, the method comprising: when it is determined that a target translator has a specific device switching behavior, obtaining the original scheduling priority value, historical translation records and current image fragment of the target translator, and determining the type of the current translation task. The present invention constructs a dynamic correction mechanism for translator scheduling priorities for device switching scenarios by introducing two behavior adjustment factors, namely the device adaptation index and the translation input index. Compared with the traditional method that only relies on static scoring or single state evaluation, the present invention can simultaneously perceive the long-term adaptation trend of translators in cross-device tasks and the immediate entry efficiency of current tasks, thereby improving the accuracy and robustness of scheduling judgments.

Description

Technical Field

[0001] The present invention belongs to the technical field of image recognition and translation task scheduling, and in particular relates to a data monitoring method and system based on image recognition. Background Art

[0002] Existing translation task allocation systems typically use fixed scheduling strategies or static scoring mechanisms to assign tasks to translators. These systems often prioritize tasks based on factors such as translators' language orientation, historical evaluation scores, and task completion rates, thereby achieving automated task matching. However, existing methods generally lack the ability to perceive the translator's current state and are unable to determine whether they are in a suitable working state for immediate task access. This is particularly true in multi-terminal environments, where the system cannot effectively determine whether the translator has fully adapted to the current device, potentially leading to a state discrepancy between scheduling and execution.

[0003] Meanwhile, while some technologies attempt to incorporate real-time video monitoring or behavior recognition modules to capture translators' online status or simple behavioral changes, these approaches often remain limited to crude identification of "whether they are on duty" or "whether they are active." They fail to establish dynamic evaluation models based on deeper characteristics such as behavioral evolution trends and task entry efficiency. They also fail to establish systematic behavioral analysis mechanisms for "device switching," a key disruptive factor commonly found in remote or multi-client collaborative translation tasks. Consequently, existing technologies suffer from significant perception blind spots and scheduling delays when addressing complex work scenarios such as translators frequently working across platforms and experiencing uncertain access status. Summary of the Invention

[0004] The purpose of the present invention is to provide a data monitoring method and system based on image recognition, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a data monitoring method based on image recognition, the method comprising:

[0006] When it is determined that the target translator has a specific device switching behavior, the original scheduling priority value, historical translation records, and current image fragment of the target translator are obtained, and the type of the current translation task is determined;

[0007] Based on the current image segment, perform image recognition processing on the target translator and generate its current behavior label;

[0008] Filter out several related translation segments from historical translation records based on the type of the current translation task, the current behavior tag, and the specific device switching behavior;

[0009] Based on historical translation records, the device adaptation index of the target translator in each associated translation segment is extracted, and a first adjustment factor is calculated based on the time series change trend of the device adaptation index;

[0010] Performing an intelligent evaluation on each associated translation segment to generate a corresponding translation input index, obtaining a preset benchmark index, and calculating a second adjustment factor based on the difference between each translation input index and the preset benchmark index;

[0011] Based on the first adjustment factor and the second adjustment factor, the original scheduling priority value is comprehensively modified.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the steps of extracting the device adaptation index of the target translator in each associated translation segment based on historical translation records, and calculating and generating the first adjustment factor based on the time series change trend of the device adaptation index include:

[0013] Parse historical translation records and extract image behavior segments within a preset period of time after the target translator completes a specific device switching behavior in each associated translation segment;

[0014] Image recognition technology is used to analyze behavioral fragments in images, extracting behavioral parameters such as facial orientation, lip movement rhythm, posture stability, and eye movement trajectory. The convergence degree of each behavioral parameter within a preset time period is calculated to generate a corresponding behavioral stability score. The weighted fusion of each stability score is then used to generate a device adaptation index.

[0015] A time series is constructed based on the device adaptation indexes corresponding to several associated translation segments, and the average slope of the time series is used as the first adjustment factor.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the steps of intelligently evaluating each associated translation segment, generating a corresponding translation input index, obtaining a preset benchmark index, and calculating a second adjustment factor based on a difference between each translation input index and the preset benchmark index include:

[0017] Analyze each relevant translation segment and monitor the target translator's behavior at the beginning of the translation task. Identify the behavioral changes from task initiation to stable translation state, measure the duration required for translation focus, and generate a corresponding translation engagement index based on this duration.

[0018] Obtaining a preset benchmark index, wherein the preset benchmark index refers to an average time invested based on statistics of a number of high-quality translation behavior segments;

[0019] The deviation magnitude of each translation input index compared to a preset benchmark index is calculated, and the average value of all the deviation magnitudes is used as the second adjustment factor.

[0020] As a further limitation of the technical solution of the embodiment of the present invention, the step of comprehensively correcting the original scheduling priority value based on the first adjustment factor and the second adjustment factor includes:

[0021] Retrieving a preset priority value correction formula, and combining the first adjustment factor and the second adjustment factor to perform a weighted correction on the original scheduling priority value to obtain a corrected scheduling priority value;

[0022] The corrected scheduling priority value is applied to the task allocation process of the target translator to optimize the scheduling order or task matching decision of the target translator.

[0023] As a further limitation of the technical solution of the embodiment of the present invention, the priority value correction formula is: ,in Refers to the revised scheduling priority value, Refers to the original scheduling priority value, refers to the first adjustment factor, i.e. the average slope of the time series, Refers to the adjustment weight of the first adjustment factor, Refers to the total number of associated translation segments, Refers to the The translation input index corresponding to the associated translation segments, Refers to the preset benchmark index, refers to the second adjustment factor, which is the average of all deviation amplitudes, refers to the adjustment weight of the second adjustment factor, and and Both are greater than 0.

[0024] As a further limitation of the technical solution of an embodiment of the present invention, a data monitoring system based on image recognition includes: a data acquisition module, a label setting module, a data screening module, a first adjustment factor determination module, a second adjustment factor determination module, and a priority value correction module, wherein:

[0025] A data acquisition module is used to obtain the original scheduling priority value, historical translation records, and current image segment of the target translator when it is determined that the target translator has a specific device switching behavior, and to determine the type of the current translation task;

[0026] The label setting module is used to perform image recognition processing on the target translator based on the current image segment and generate its current behavior label;

[0027] The data filtering module is used to filter out several related translation segments from historical translation records based on the type of the current translation task, the current behavior label, and the specific device switching behavior;

[0028] A first adjustment factor determination module is configured to extract the device adaptation index of the target translator in each associated translation segment based on historical translation records, and calculate and generate a first adjustment factor based on a time series change trend of the device adaptation index;

[0029] a second adjustment factor determination module, configured to intelligently evaluate each associated translation segment, generate a corresponding translation input index, obtain a preset benchmark index, and calculate a second adjustment factor based on the difference between each translation input index and the preset benchmark index;

[0030] The priority value correction module is used to comprehensively correct the original scheduling priority value based on the first adjustment factor and the second adjustment factor.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the first adjustment factor determination module specifically includes:

[0032] An image segment extraction unit is used to parse historical translation records and extract image behavior segments within a preset period of time after the target translator completes a specific device switching behavior in each associated translation segment;

[0033] The device adaptation index generation unit is used to analyze the image behavior fragments based on image recognition technology, extract behavioral parameters such as facial orientation, lip movement rhythm, posture stability, and eye movement trajectory, calculate the degree of convergence of each behavioral parameter within a preset time period, generate a corresponding behavioral stability score, and weightedly fuse each stability score to generate the device adaptation index;

[0034] The average slope calculation unit is used to construct a time series based on the device adaptation indexes corresponding to the multiple associated translation segments, and use the average slope of the time series as a first adjustment factor.

[0035] As a further limitation of the technical solution of the embodiment of the present invention, the second adjustment factor determination module specifically includes:

[0036] A translation engagement index generation unit is used to analyze each associated translation segment, monitor the target translator's behavior at the beginning of the translation task, identify the behavioral changes from task initiation to entering a stable translation state, and measure the duration required for the translator to reach a state of translation focus. Based on this duration, a corresponding translation engagement index is generated.

[0037] A preset benchmark index obtaining unit, configured to obtain a preset benchmark index, wherein the preset benchmark index refers to an average time invested based on statistics of a number of high-quality translation behavior segments;

[0038] The deviation amplitude calculation unit is used to calculate the deviation amplitude of each translation input index compared with a preset benchmark index, and use the average value of all deviation amplitudes as the second adjustment factor.

[0039] As a further limitation of the technical solution of the embodiment of the present invention, the priority value correction module specifically includes:

[0040] a priority value correction unit, configured to retrieve a preset priority value correction formula, and perform weighted correction on the original scheduling priority value in combination with the first adjustment factor and the second adjustment factor to obtain a corrected scheduling priority value;

[0041] The modified priority value application unit is used to apply the modified scheduling priority value to the task allocation process of the target translator, so as to optimize the scheduling order or task matching decision of the target translator.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the priority value correction formula is:

[0043] ,in Refers to the revised scheduling priority value, Refers to the original scheduling priority value, refers to the first adjustment factor, i.e. the average slope of the time series, Refers to the adjustment weight of the first adjustment factor, Refers to the total number of associated translation segments, Refers to the The translation input index corresponding to the associated translation segments, Refers to the preset benchmark index, refers to the second adjustment factor, which is the average of all deviation amplitudes, refers to the adjustment weight of the second adjustment factor, and and Both are greater than 0.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention introduces two behavioral adjustment factors, the device adaptation index and the translation input index, to construct a dynamic correction mechanism for interpreter scheduling priorities for device switching scenarios. Compared with the traditional method that relies only on static scoring or single state evaluation, the present invention can simultaneously perceive the interpreter's long-term adaptation trend in cross-device tasks and the immediate access efficiency of the current task, thereby improving the accuracy and robustness of scheduling judgments. This mechanism is suitable for translation task allocation in a multi-terminal collaborative environment, and can effectively avoid behavioral instability or response delays caused by device switching, improve the intelligence level of system scheduling and the rationality of interpreter matching, and has obvious practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0047] Figure 2 A flowchart of generating a first adjustment factor in the method provided in an embodiment of the present invention;

[0048] Figure 3 A flow chart of generating a second adjustment factor in the method provided in an embodiment of the present invention;

[0049] Figure 4 A flowchart of correcting the original scheduling priority value in the method provided in an embodiment of the present invention;

[0050] Figure 5 An application architecture diagram of the system provided by an embodiment of the present invention;

[0051] Figure 6 A structural block diagram of a first adjustment factor determination module in a system provided by an embodiment of the present invention;

[0052] Figure 7 A structural block diagram of a second adjustment factor determination module in a system provided by an embodiment of the present invention;

[0053] Figure 8 This is a structural block diagram of a priority value correction module in a system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0056] Specifically, a data monitoring method based on image recognition includes the following steps:

[0057] Step S100 : When it is determined that the target translator has a specific device switching behavior, the original scheduling priority value, historical translation records, and current image segment of the target translator are obtained, and the type of the current translation task is determined.

[0058] In this embodiment of the present invention, this solution is applicable to a scheduling scenario involving multiple interpreters and dynamic task allocation. Typically, this system is used in remote or multi-platform translation environments, where multiple interpreters are on standby, awaiting new translation tasks. Each interpreter may be using a different terminal device (e.g., desktop, laptop, tablet, mobile device, etc.). The system needs to dynamically assess the interpreter's suitability based on their actual status and historical performance, and optimize interpreter scheduling priorities accordingly to achieve optimal matching of interpreters to positions.

[0059] Device-specific switching behavior refers to the behavior of a target interpreter switching from one translation terminal device to another within a short period of time, such as switching from a mobile device to a desktop terminal, or from an offline simultaneous interpretation system to a remote video platform. Because changes in the device environment often affect interpreters' operational fluency, behavioral rhythm, and task adaptability, incorporating this behavior recognition mechanism into scheduling decisions can effectively avoid assigning tasks to interpreters who have not yet fully adapted or whose operations are unstable, thereby improving translation quality and system scheduling reliability.

[0060] The original scheduling priority value is the system's default reference ranking criteria for translators currently without assigned tasks. This value is typically derived through statistical scoring within existing translation platform management systems, intelligent scheduling systems, or task matching modules. For example, a preliminary assessment can be conducted based on factors such as the translator's language compatibility, historical completion rate, average response time, and feedback quality score, generating an initial priority score. These metrics are already in use within existing remote translation service platforms and possess a strong practical feasibility and engineering foundation.

[0061] Historical translation records are a collection of data generated by the target translator during past tasks. They typically include the translator's task number, task type, time of participation, device environment, behavioral trajectory (e.g., image frame sequence), engagement performance data (e.g., time from task start to focus), and device adaptation performance (e.g., operational stability after switching devices). This fundamental data serves as the basis for behavioral modeling and trend extraction, and is the primary source for the subsequent extraction of the Device Adaptation Index and Translation Engagement Index.

[0062] The current image segment originates from the image acquisition device on the target interpreter's current terminal, typically consisting of a sequence of video frames captured by a camera module. While the interpreter is waiting for a task assignment, the system periodically captures the interpreter's image data. Upon recognizing a device switch, the system captures a sequence of continuous image frames over a specific period (e.g., 30 to 60 seconds after the switch) as input for subsequent image recognition processing and behavioral feature extraction.

[0063] The type of the current translation task can be determined by the scheduling platform based on the task source information. It usually includes classification information such as task subject, language direction, business type (such as legal, medical, technical, conference, etc.), task duration or urgency. This type of metadata is generally provided by the task initiator or user interface when the task is generated or connected to the system. It falls within the scope of task description information already available on the existing platform and can be used as one of the contextual conditions for scheduling decisions.

[0064] Furthermore, the data monitoring method based on image recognition further includes the following steps:

[0065] Step S200 : Based on the current image segment, image recognition processing is performed on the target translator to generate a current behavior label.

[0066] In this embodiment of the present invention, the core objective of step S200 is to perform image recognition analysis on the target translator based on the current image segment, and thereby determine the translator's current working status, thereby matching the target translator with a behavior label with a semantic description for subsequent label comparison with historical translation segments and behavior trend assessment.

[0067] This step primarily relies on existing image and gesture recognition technologies. The system uses a camera to capture the target interpreter's current image segment—that is, video frame data within a time window after a specific device switch. Using pose estimation algorithms (such as OpenPose and MediaPipe), the system extracts key parameters, including facial orientation, eye movement direction, head rotation angle, mouth opening and closing, and changes in shoulder and hand position. Further, characteristic metrics such as motion duration, frequency, and amplitude are extracted from the image frame sequence.

[0068] Based on these characteristics, the system can determine whether the target translator is currently in a stable and still state, frequently moving, turning his head to talk, eating, or looking down for a long time, and match the corresponding behavior tags accordingly. Behavior tags may include but are not limited to the following categories:

[0069] "Sitting still and focused", "Non-interactive state", "Eating", "Walking", "Not concentrating", "Communicating with others", "Adjusting the device", "Frequent hand movements", "Stay away from the device", etc.

[0070] These labels are generated based on trained classification rules or lightweight behavior classification models, constructed using supervised learning from existing image samples. The labels themselves are not used to infer the translator's translation quality; instead, they serve as semantic representations of behavioral characteristics, serving as matching criteria for subsequent historical behavior screening. This ensures a high degree of similarity between historical segments and the current translator's state, helping to generate more valuable references for device adaptation and translation effort indices.

[0071] Furthermore, the data monitoring method based on image recognition further includes the following steps:

[0072] Step S300 : Filtering a number of related translation segments from historical translation records based on the type of the current translation task, the current behavior tag, and the specific device switching behavior.

[0073] In an embodiment of the present invention, the purpose of step S300 is to filter out several related translation segments that match the current context from the target translator's historical translation records, and use them as the data basis for the subsequent calculation of the device adaptation index and the translation input index, so as to improve the pertinence and effectiveness of the behavior trend assessment.

[0074] The specific screening process includes the following aspects:

[0075] First, the system determines the semantic category of the current translation task, such as legal, medical, conference, or technical. This task type, provided by the task metadata, serves as a preliminary screening criterion, removing historical translation fragments that clearly do not match the current task type.

[0076] Next, the system uses the current behavior tag identified in step S200 as a second-level filtering criterion. The system extracts all translation segments from the historical translation history that share the same behavior tag at the initial stage of the task entry. For example, if the current tag is "concentrated meditation," only segments with the same tag at the beginning of the task are retained to ensure comparable behavior states.

[0077] Furthermore, the system combines the currently identified specific device switching behaviors, such as "switching from mobile to desktop" or "switching from offline to remote platforms," ​​to further restrict historical translation records to only include translation segments whose device switching type matches the current one. Device switching behaviors can be matched against device change records in task access logs or historical behavior records, ensuring structural consistency in the filtered results regarding device adaptability.

[0078] Finally, based on the three conditions of task type matching, consistent behavior labels, and matching device switching types, the system selects multiple translation segments that meet the conditions from the historical translation records as associated translation segments, and sorts and numbers them according to chronological order or task quality level, providing input data for the calculation of the device adaptation index and translation input index in subsequent steps.

[0079] Through the above-mentioned screening mechanism, the system can ensure that the extracted historical behavior samples are highly similar to the actual status of the current translator, thereby improving the accuracy of behavior trend modeling and the reference value of priority correction.

[0080] Furthermore, the data monitoring method based on image recognition further includes the following steps:

[0081] Step S400 : extracting the device adaptation index of the target translator in each associated translation segment based on historical translation records, and calculating and generating a first adjustment factor according to a time series variation trend of the device adaptation index.

[0082] Specifically, Figure 2 A flow chart for generating a first adjustment factor is shown.

[0083] The process of extracting the device adaptation index of the target translator in each associated translation segment based on historical translation records and calculating and generating the first adjustment factor according to the time series change trend of the device adaptation index specifically includes the following steps:

[0084] Step S401: parsing historical translation records to extract image behavior segments within a preset time period after the target translator completes a specific device switching behavior in each associated translation segment;

[0085] Step S402: Analyze the image behavior fragments based on image recognition technology to extract behavioral parameters such as facial orientation, lip movement rhythm, posture stability, and eye movement trajectory. The convergence degree of each behavioral parameter within a preset time period is calculated to generate a corresponding behavioral stability score. The weighted fusion of each stability score is then used to generate a device adaptation index.

[0086] Step S403 : constructing a time series based on the device adaptation indices corresponding to the plurality of associated translation segments, and using the average slope of the time series as a first adjustment factor.

[0087] In this embodiment of the present invention, step S402 uses image recognition technology to analyze the image behavior segments and extract multiple behavioral parameters of the target interpreter during a preset period after switching to a specific device. These behavioral parameters, including facial orientation, lip movement rhythm, posture stability, and eye movement trajectory, can be extracted using existing image pose estimation and feature tracking algorithms, such as those based on OpenPose, MediaPipe, or other deep learning-based skeletal keypoint detection models. By continuously analyzing key areas of the video frame, such as the head, eyes, mouth, and shoulders, the system identifies facial deflection angles, mouth opening and closing frequency, fluctuations in upper body posture, and changes in eye gaze.

[0088] Over a set time period, the system constructs a parameter sequence for each behavioral parameter and calculates stability indicators for this sequence, such as amplitude of change, frequency of fluctuation, and the difference between maximum and minimum values, to determine whether it exhibits a trend from fluctuation to stability. The system uses this to determine the degree of convergence for each parameter type—that is, whether the behavior after a device switch tends to stabilize within a short period of time. After assigning a stability score to each parameter, the system then combines these scores according to preset weights to generate a device adaptability index that comprehensively represents the interpreter's adaptability under the current device switching scenario.

[0089] In step S403, the system chronologically arranges the device adaptation indices generated for the aforementioned multiple related translation segments to construct a time series of device adaptation indices. This time series can reflect whether there are clear trends in the translator's adaptation performance after completing device switching across different historical tasks. The system then performs a linear fit on this time series, obtaining the average slope of the fitted line as the first adjustment factor.

[0090] The core rationale for using the average slope as the first adjustment factor is that it quantifies the evolving trends in an interpreter's device adaptability. A positive slope indicates a gradual improvement in the interpreter's performance during device switching, indicating an increasing adaptability trend; a negative slope indicates a decrease in adaptability; and a slope close to zero indicates stable adaptability. This allows the system to dynamically perceive the target interpreter's adaptability across multiple device switching tasks, providing a quantifiable, trend-driven basis for revising the priority value.

[0091] Furthermore, the data monitoring method based on image recognition further includes the following steps:

[0092] Step S500 , performing intelligent evaluation on each associated translation segment, generating a corresponding translation input index, obtaining a preset benchmark index, and calculating a second adjustment factor based on the difference between each translation input index and the preset benchmark index.

[0093] Specifically, Figure 3 A flow chart for generating a second adjustment factor is shown.

[0094] The intelligent evaluation of each associated translation segment to generate a corresponding translation input index, obtaining a preset benchmark index, and calculating a second adjustment factor based on the difference between each translation input index and the preset benchmark index specifically includes the following steps:

[0095] Step S501: parse each associated translation segment, monitor the target translator's behavior at the start of the translation task, identify the behavioral changes from task initiation to stable translation state, measure the duration required for the translator to reach a state of translation focus, and generate a corresponding translation engagement index based on the duration.

[0096] Step S502: Obtaining a preset benchmark index, wherein the preset benchmark index refers to an average time invested based on statistics of a number of high-quality translation behavior segments;

[0097] Step S503 : Calculate the deviation of each translation input index from a preset benchmark index, and use the average of all deviations as a second adjustment factor.

[0098] In this embodiment of the present invention, in step S501, the system continuously monitors the image behavior sequences of the associated translation segments to identify the behavioral changes experienced by the target translator from the start of the task to the stable translation state. Specifically, the system uses image recognition technology to analyze the consecutive image frames after the translation task begins, extracting key motion features of the head, face, eyes, mouth, shoulders, and other areas, including whether the facial orientation is stable, whether the eyes are focused on the screen, whether the mouth opens and closes regularly, and whether the upper body is still.

[0099] During behavioral monitoring, the system sets a set of behavioral stability thresholds to identify the starting point when the interpreter's behavior gradually shifts from unstable to stable. For example, facial deviation angles continuously fall below a set range, mouth rhythms maintain a fixed frequency, and gaze remains continuously focused on the screen area. When these behavioral parameters simultaneously meet the stability requirements for the first time in an image sequence, the system defines that point as the decision node for entering a stable translation state. It then calculates the time from the start of the task to this point, representing the duration required for the interpreter to complete the transition to this state.

[0100] This duration, after normalization, can be directly used as a translation investment index. To enhance the indicator's sensitivity, the system can also incorporate a weighting mechanism to weight factors such as the amplitude and frequency of state fluctuations at different stages, or the smoothness of the entry path, thereby generating a more recognizable investment performance value.

[0101] In step S502, the system obtains a preset benchmark index. This benchmark value is derived from a set of historically high-quality translation activity segments. These high-quality segments are derived from the behavioral process data of other translators with high performance scores while translating the same type of task (i.e., the same task type). These translators are typically characterized by fast response times, stable behavioral engagement, and good task completion evaluations, thus serving as a reference template for assessing the current translator's engagement level. By calculating the average duration from task initiation to focus in this set of high-quality segments, the system obtains a preset benchmark index for comparison.

[0102] The second adjustment factor reflects the overall deviation between the target translator's current state and the high-performance reference behavior. A positive value indicates that the translator typically spends more time entering the translation state than the high-quality reference translator, resulting in a slower task response speed. A negative value indicates that the translator is able to enter a focused state more quickly and has a higher level of engagement efficiency. By quantifying and averaging these deviations, we can effectively measure the target translator's recent overall engagement performance across different tasks, providing an objective basis for adjusting scheduling priorities downward or upward, making task allocation strategies more robust and data-driven.

[0103] Furthermore, the data monitoring method based on image recognition further includes the following steps:

[0104] Step S600 : comprehensively modifying the original scheduling priority value based on the first adjustment factor and the second adjustment factor.

[0105] Specifically, Figure 4 A flow chart for modifying the original scheduling priority value is shown.

[0106] The comprehensive correction of the original scheduling priority value based on the first adjustment factor and the second adjustment factor specifically includes the following steps:

[0107] Step S601: Retrieve a preset priority value correction formula, and perform weighted correction on the original scheduling priority value in combination with the first adjustment factor and the second adjustment factor to obtain a corrected scheduling priority value;

[0108] Step S602 : Applying the modified scheduling priority value to the task allocation process of the target translator to optimize the scheduling order or task matching decision of the target translator.

[0109] The priority value correction formula is: ,in Refers to the revised scheduling priority value, Refers to the original scheduling priority value, refers to the first adjustment factor, i.e. the average slope of the time series, Refers to the adjustment weight of the first adjustment factor, Refers to the total number of associated translation segments, Refers to the The translation input index corresponding to the associated translation segments, Refers to the preset benchmark index, refers to the second adjustment factor, which is the average of all deviation amplitudes, refers to the adjustment weight of the second adjustment factor, and and Both are greater than 0.

[0110] In this embodiment of the present invention, the first and second adjustment factors are designed to jointly modify the scheduling priority value, offering significant technical advantages and application value. While the behavioral dimensions they measure do not overlap, they are highly correlated in the specific context of "device switching." They can collaboratively reflect an interpreter's true adaptability from both a behavioral trend and real-time status perspective, thereby building a more complete, stable, and dynamically responsive scheduling optimization mechanism.

[0111] First, the first adjustment factor reflects the changing trend of the translator's adaptability in multiple historical device switching scenarios. Its essence is to construct a time series through the device adaptation index and calculate its average slope to determine whether the target translator's performance in similar device migration tasks is gradually stabilizing, improving, or deteriorating. This trend factor based on historical series can reveal the impact of device switching on the translator's long-term behavioral state. For example, for some translators, frequent switching from mobile terminals to desktop terminals may form a stable adaptation path, which is manifested by a gradual increase in the adaptation index; while other translators may have repeated adjustment periods after each switch, which is manifested by large fluctuations or even a decline in the adaptation index. The introduction of this factor allows the system to not only focus on current performance during scheduling, but also to identify in advance whether the translator has the ability to work stably across devices, thereby reducing task interruptions or quality fluctuations caused by scheduling errors.

[0112] Secondly, the second adjustment factor is to evaluate the "entry speed" required by the translator in the current translation task, from the start of the task to the complete entry into the stable translation state. This factor calculates the deviation of the translator's input in different tasks by comparing it with the average input time extracted from a group of high-quality translation samples. It does not rely on long-term historical trends, but focuses more on the state responsiveness of the "early stage of the current task". It is an important indicator to measure the efficiency of the translator's immediate input. After switching devices, translators often need a certain amount of time to readapt to the technical environment such as the terminal interface, voice input, and auditory feedback. Therefore, this factor is extremely critical for judging whether the translator has completed the state transition.

[0113] These two factors were chosen as the basis for scheduling adjustments because "device switching" inherently exhibits two key characteristics: first, it involves a certain degree of reconfiguration of the operating environment, causing short-term disruptions to interpreter behavior; second, this disruption manifests itself as localized response delays within each task, but can also accumulate over long periods of time, forming habitual effects. Therefore, relying solely on a single perspective is insufficient to fully reflect an interpreter's scheduling adaptability. Relying solely on historical trends (the first adjustment factor) might overlook the immediate risk of a degraded interpreter's performance after completing a high-intensity task prior to a task. Relying solely on current performance (the second adjustment factor) might overlook the interpreter's overall stability in adapting to the device, leading to frequent scheduling errors. Therefore, combining these two factors creates a dual validation logic: "long-term behavioral trends + current performance." This balances trend prediction with real-time status response during scheduling, effectively improving the reliability and contextual adaptability of scheduling behavior.

[0114] Furthermore, this dual-factor mechanism is not only applicable to interpreter task scheduling scenarios but also possesses high versatility in other intelligent dispatching systems involving multiple terminals and multiple task switching, with scalable applications in a variety of fields, including remote collaboration, virtual customer service, and cross-device human-computer interaction. This demonstrates that the dual-factor joint scheduling and correction mechanism proposed in this invention is particularly well-suited to the unique context of "device switching," offering significant advantages in terms of deep behavioral understanding, system response efficiency, and algorithm stability.

[0115] The correction formula proposed in this invention uses a linear weighted exponential correction model, which is intuitive, adjustable, and computationally inexpensive. It is particularly suitable for embedded scheduling scenarios and real-time system applications. However, this invention is not limited to this linear structure. Depending on actual application requirements, the following alternative or expanded forms can also be designed:

[0116] For example, based on the proportion normalization process, the exponential smoothing function or piecewise nonlinear mapping method can be used to improve the robustness to extreme values; in the case of preference for "trend driven" or "efficiency first", a weight adaptive adjustment mechanism can also be designed, that is, and Dynamic updates can be made based on historical performance; a threshold control mechanism can also be introduced, ensuring that corrections are triggered only when the adjustment factor exceeds a set critical value, thus avoiding frequent adjustments during fluctuations. Furthermore, if the system supports deep model embedding, neural networks or regression models can be used to learn priority correction functions based on multi-dimensional behavioral data, enabling more complex nonlinear dynamic allocation logic.

[0117] Further, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0118] In another preferred embodiment of the present invention, a data monitoring system based on image recognition includes:

[0119] The data acquisition module 100 is used to acquire the original scheduling priority value, historical translation records and current image segment of the target translator when it is determined that the target translator has a specific device switching behavior, and determine the type of the current translation task.

[0120] Furthermore, the data monitoring system based on image recognition also includes:

[0121] The label setting module 200 is used to perform image recognition processing on the target translator based on the current image segment and generate the current behavior label of the target translator.

[0122] Furthermore, the data monitoring system based on image recognition also includes:

[0123] The data screening module 300 is used to screen out a number of related translation segments from historical translation records according to the type of the current translation task, the current behavior tag, and the specific device switching behavior.

[0124] Furthermore, the data monitoring system based on image recognition also includes:

[0125] The first adjustment factor determination module 400 is configured to extract the device adaptation index of the target translator in each associated translation segment based on historical translation records, and calculate and generate a first adjustment factor according to a time series variation trend of the device adaptation index.

[0126] Specifically, Figure 6 FIG. 4 is a structural block diagram of a first adjustment factor determination module 400 in a system provided by an embodiment of the present invention.

[0127] In a preferred embodiment of the present invention, the first adjustment factor determination module 400 specifically includes:

[0128] The image segment extraction unit 401 is used to parse the historical translation records and extract the image behavior segments within a preset time period after the target translator completes the specific device switching behavior in each associated translation segment;

[0129] Device Adaptation Index Generating Unit 402 is configured to analyze the image behavior segments based on image recognition technology, extract behavioral parameters such as facial orientation, lip movement rhythm, posture stability, and eye movement trajectory, calculate the degree of convergence of each behavioral parameter within a preset time period, generate a corresponding behavioral stability score, and weightedly fuse each stability score to generate the device adaptation index.

[0130] The average slope calculation unit 403 is configured to construct a time series based on the device adaptation indices corresponding to the plurality of associated translation segments, and use the average slope of the time series as a first adjustment factor.

[0131] Furthermore, the data monitoring system based on image recognition also includes:

[0132] The second adjustment factor determination module 500 is configured to intelligently evaluate each associated translation segment, generate a corresponding translation input index, obtain a preset benchmark index, and calculate a second adjustment factor based on the difference between each translation input index and the preset benchmark index.

[0133] Specifically, Figure 7 FIG. 5 is a structural block diagram of a second adjustment factor determination module 500 in a system provided by an embodiment of the present invention.

[0134] In a preferred embodiment of the present invention, the second adjustment factor determination module 500 specifically includes:

[0135] The translation engagement index generating unit 501 is configured to analyze each associated translation segment, monitor the target translator's behavior at the initial stage of the translation task, identify the behavioral changes from task initiation to stable translation state, measure the duration required for the translator to reach the translation focus state, and generate a corresponding translation engagement index based on the duration;

[0136] A preset benchmark index obtaining unit 502 is configured to obtain a preset benchmark index, wherein the preset benchmark index refers to an average time invested based on statistics of a number of high-quality translation behavior segments;

[0137] The deviation amplitude calculation unit 503 is configured to calculate the deviation amplitude of each translation input index compared to a preset reference index, and use the average value of all the deviation amplitudes as the second adjustment factor.

[0138] Furthermore, the data monitoring system based on image recognition also includes:

[0139] The priority value correction module 600 is configured to perform comprehensive correction on the original scheduling priority value based on the first adjustment factor and the second adjustment factor.

[0140] Specifically, Figure 8 FIG. 6 is a structural block diagram of a priority value correction module 600 in a system provided by an embodiment of the present invention.

[0141] In a preferred embodiment of the present invention, the priority value correction module 600 specifically includes:

[0142] The priority value correction unit 601 is used to call a preset priority value correction formula and perform weighted correction on the original scheduling priority value in combination with the first adjustment factor and the second adjustment factor to obtain a corrected scheduling priority value;

[0143] The modified priority value application unit 602 is configured to apply the modified scheduling priority value to the task allocation process of the target translator, so as to optimize the scheduling order or task matching decision of the target translator.

[0144] The priority value correction formula is: ,in Refers to the revised scheduling priority value, Refers to the original scheduling priority value, refers to the first adjustment factor, i.e. the average slope of the time series, Refers to the adjustment weight of the first adjustment factor, Refers to the total number of associated translation segments, Refers to the The translation input index corresponding to the associated translation segments, Refers to the preset benchmark index, refers to the second adjustment factor, which is the average of all deviation amplitudes, refers to the adjustment weight of the second adjustment factor, and and Both are greater than 0.

[0145] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0146] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0147] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0148] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data monitoring method based on image recognition, characterized in that: The method comprises: When it is determined that the target translator has a specific device switching behavior, the original scheduling priority value, historical translation records, and current image fragment of the target translator are obtained, and the type of the current translation task is determined; Based on the current image segment, perform image recognition processing on the target translator and generate its current behavior label; Filter out several related translation segments from historical translation records based on the type of the current translation task, the current behavior tag, and the specific device switching behavior; Based on historical translation records, the device adaptation index of the target translator in each associated translation segment is extracted, and a first adjustment factor is calculated based on the time series change trend of the device adaptation index; Performing an intelligent evaluation on each associated translation segment to generate a corresponding translation input index, obtaining a preset benchmark index, and calculating a second adjustment factor based on the difference between each translation input index and the preset benchmark index; Based on the first adjustment factor and the second adjustment factor, the original scheduling priority value is comprehensively modified.

2. The data monitoring method based on image recognition according to claim 1, characterized in that: The steps of extracting the device adaptation index of the target translator in each associated translation segment based on historical translation records and calculating and generating a first adjustment factor according to a time series trend of the device adaptation index include: Parse historical translation records and extract image behavior segments within a preset period of time after the target translator completes a specific device switching behavior in each associated translation segment; Image recognition technology is used to analyze behavioral fragments in images, extracting behavioral parameters such as facial orientation, lip movement rhythm, posture stability, and eye movement trajectory. The convergence degree of each behavioral parameter within a preset time period is calculated to generate a corresponding behavioral stability score. The weighted fusion of each stability score is then used to generate a device adaptation index. A time series is constructed based on the device adaptation indexes corresponding to several associated translation segments, and the average slope of the time series is used as the first adjustment factor.

3. The data monitoring method based on image recognition according to claim 2, characterized in that: The steps of intelligently evaluating each associated translation segment, generating a corresponding translation input index, obtaining a preset benchmark index, and calculating a second adjustment factor based on the difference between each translation input index and the preset benchmark index include: Analyze each relevant translation segment and monitor the target translator's behavior at the beginning of the translation task. Identify the behavioral changes from task initiation to stable translation state, measure the duration required for translation focus, and generate a corresponding translation engagement index based on this duration. Obtaining a preset benchmark index, wherein the preset benchmark index refers to an average time invested based on statistics of a number of high-quality translation behavior segments; The deviation magnitude of each translation input index compared to a preset benchmark index is calculated, and the average value of all the deviation magnitudes is used as the second adjustment factor.

4. The data monitoring method based on image recognition according to claim 3, characterized in that: The step of comprehensively correcting the original scheduling priority value based on the first adjustment factor and the second adjustment factor includes: Retrieving a preset priority value correction formula, and combining the first adjustment factor and the second adjustment factor to perform a weighted correction on the original scheduling priority value to obtain a corrected scheduling priority value; The corrected scheduling priority value is applied to the task allocation process of the target translator to optimize the scheduling order or task matching decision of the target translator.

5. The data monitoring method based on image recognition according to claim 4, characterized in that: The priority value correction formula is: ,in Refers to the revised scheduling priority value, Refers to the original scheduling priority value, refers to the first adjustment factor, i.e. the average slope of the time series, Refers to the adjustment weight of the first adjustment factor, Refers to the total number of associated translation segments, Refers to the The translation input index corresponding to the associated translation segments, Refers to the preset benchmark index, refers to the second adjustment factor, which is the average of all deviation amplitudes, refers to the adjustment weight of the second adjustment factor, and and Both are greater than 0.

6. A data monitoring system based on image recognition, characterized in that: The system includes: a data acquisition module, a label setting module, a data screening module, a first adjustment factor determination module, a second adjustment factor determination module, and a priority value correction module, wherein: A data acquisition module is used to obtain the original scheduling priority value, historical translation records, and current image segment of the target translator when it is determined that the target translator has a specific device switching behavior, and to determine the type of the current translation task; The label setting module is used to perform image recognition processing on the target translator based on the current image segment and generate its current behavior label; The data filtering module is used to filter out several related translation segments from historical translation records based on the type of the current translation task, the current behavior label, and the specific device switching behavior; A first adjustment factor determination module is configured to extract the device adaptation index of the target translator in each associated translation segment based on historical translation records, and calculate and generate a first adjustment factor based on a time series change trend of the device adaptation index; a second adjustment factor determination module, configured to intelligently evaluate each associated translation segment, generate a corresponding translation input index, obtain a preset benchmark index, and calculate a second adjustment factor based on the difference between each translation input index and the preset benchmark index; The priority value correction module is used to comprehensively correct the original scheduling priority value based on the first adjustment factor and the second adjustment factor.

7. The data monitoring system based on image recognition according to claim 6, characterized in that: The first adjustment factor determination module specifically includes: An image segment extraction unit is used to parse historical translation records and extract image behavior segments within a preset time period after the target translator completes a specific device switching behavior in each associated translation segment; The device adaptation index generation unit is used to analyze the image behavior fragments based on image recognition technology, extract behavioral parameters such as facial orientation, lip movement rhythm, posture stability, and eye movement trajectory, calculate the degree of convergence of each behavioral parameter within a preset time period, generate a corresponding behavioral stability score, and weightedly fuse each stability score to generate the device adaptation index; The average slope calculation unit is used to construct a time series based on the device adaptation indexes corresponding to the multiple associated translation segments, and use the average slope of the time series as a first adjustment factor.

8. The data monitoring system based on image recognition according to claim 7, characterized in that: The second adjustment factor determination module specifically includes: A translation engagement index generation unit is used to analyze each associated translation segment, monitor the target translator's behavior at the beginning of the translation task, identify the behavioral changes from task initiation to entering a stable translation state, and measure the duration required for the translator to reach a state of translation focus. Based on this duration, a corresponding translation engagement index is generated. A preset benchmark index obtaining unit, configured to obtain a preset benchmark index, wherein the preset benchmark index refers to an average time invested based on statistics of a number of high-quality translation behavior segments; The deviation amplitude calculation unit is used to calculate the deviation amplitude of each translation input index compared with a preset benchmark index, and use the average value of all deviation amplitudes as the second adjustment factor.

9. The data monitoring system based on image recognition according to claim 8, characterized in that: The priority value correction module specifically includes: a priority value correction unit, configured to retrieve a preset priority value correction formula, and perform weighted correction on the original scheduling priority value in combination with the first adjustment factor and the second adjustment factor to obtain a corrected scheduling priority value; The modified priority value application unit is used to apply the modified scheduling priority value to the task allocation process of the target translator, so as to optimize the scheduling order or task matching decision of the target translator.

10. The data monitoring system based on image recognition according to claim 9, characterized in that: The priority value correction formula is: ,in Refers to the revised scheduling priority value, Refers to the original scheduling priority value, refers to the first adjustment factor, i.e. the average slope of the time series, Refers to the adjustment weight of the first adjustment factor, Refers to the total number of associated translation segments, Refers to the The translation input index corresponding to the associated translation segments, Refers to the preset benchmark index, refers to the second adjustment factor, which is the average of all deviation amplitudes, refers to the adjustment weight of the second adjustment factor, and and Both are greater than 0.

Images