Wearable device monitoring method based on data analysis

Abstract

The invention relates to the field of data analysis, in particular to a wearable device monitoring method based on data analysis, which comprises the following steps: periodically acquiring various target monitoring data of a target monitoring person, determining key analysis data, and obtaining a key monitoring video corresponding to each key analysis data; determining an analysis strategy of the corresponding key analysis data according to the abnormal coincidence coefficient; if the abnormal coincidence coefficient is greater than a preset abnormal coincidence coefficient, detecting a data change period of each type of regional data; if the abnormal coincidence coefficient is smaller than or equal to a preset abnormal coincidence coefficient, performing associated personnel search for the key monitoring video, and determining a video information tracing mode according to an interaction duration ratio of target monitoring personnel in the key monitoring video and the number of associated personnel; under the condition that information analysis is completed, early warning information of all key analysis data is sent to the user, and the effectiveness of the early warning information is improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a wearable device monitoring method based on data analysis. Background Art

[0002] Real-time monitoring is performed on the patient's various vital sign data to obtain the patient's abnormal physical data as timely as possible. However, the cause of the abnormal physical data cannot be effectively determined based on the acquired vital sign data alone. There are errors in judging the patient's status only through the vital sign data, and the reason why the patient is in an abnormal state cannot be effectively traced. Collaborative monitoring through the collected video can make an effective judgment on the patient's status, but the existing wearable device monitoring methods often only extract monitoring videos based on the moment corresponding to the abnormal state, and cannot guarantee the validity of the acquired monitoring video. Therefore, how to obtain a valid video segment based on the acquired data information and video information is a problem that needs to be urgently solved by technical personnel in this field.

[0003] Chinese patent publication number CN117936073A discloses a remote real-time online monitoring and management system for human health information, including a patient information acquisition module for acquiring medical information of patients; a wearable data acquisition module for being worn on patients to collect vital sign data; a primary warning module for identifying abnormal conditions of patients based on sensor data and generating primary alarm information; a warning correction module for correcting primary alarm information using a behavior pattern obtained from video data corresponding to wearable data acquired through video acquisition to obtain corrected alarm information; an alarm module for sending notifications to relevant personnel of the patients based on the corrected alarm information; and a suggestion module for matching emergency treatment plans based on the alarm information and sending them to patients and relevant personnel. However, the above scheme has the following problems: it fails to extract effective parts of the video information according to the actual scene in which the patient is located in the acquired video information, resulting in low effectiveness of the acquired video information, and further resulting in low accuracy of the judgment results of abnormal data. Summary of the invention

[0004] To this end, the present invention provides a wearable device monitoring method based on data analysis to overcome the problem in the prior art that the effective part of the video information is not extracted according to the actual scene in which the patient is located in the acquired video information, resulting in low effectiveness of the acquired video information, and further resulting in low accuracy of the judgment results of abnormal data.

[0005] To achieve the above object, the present invention provides a wearable device monitoring method based on data analysis, comprising:

[0006] Periodically collect various target monitoring data of target monitoring personnel, record the target monitoring data whose monitoring value is not within the corresponding preset data range or whose data change coefficient is greater than the preset data change coefficient as key analysis data, and obtain the key monitoring video corresponding to each key analysis data;

[0007] Determine the analysis strategy of the corresponding key analysis data according to the abnormal coincidence coefficient;

[0008] If the abnormal coincidence coefficient is greater than the preset abnormal coincidence coefficient, the data change cycle of each type of regional data is detected;

[0009] If the abnormal overlap coefficient is less than or equal to the preset abnormal overlap coefficient, a search for related persons is performed for the key monitoring video, and the video information tracing method is determined based on the interaction time ratio of the target monitoring personnel in the key monitoring video and the number of related persons;

[0010] The video information tracing method includes extracting video segments corresponding to each associated person in the key monitoring video and setting a warning priority coefficient, and dividing the key monitoring video and determining the video extraction method according to the historical abnormal repetition coefficient;

[0011] When information analysis is completed, early warning information of key analysis data will be sent to users.

[0012] Furthermore, under the key analysis conditions, the abnormal coincidence coefficients of various key analysis data of the target monitoring personnel are detected, and the analysis strategy of the corresponding key analysis data is determined according to the abnormal coincidence coefficients;

[0013] The anomaly coincidence coefficient of key analytical data is determined based on the reference anomaly differences of each monitoring personnel in the relevant area;

[0014] The key analysis condition is that key analysis data exists in the various target monitoring data of the target monitoring personnel.

[0015] Further, for any key analysis data, if the abnormal coincidence coefficient is greater than the preset abnormal coincidence coefficient, various types of regional data of the key analysis data are obtained to determine the data change cycle of the corresponding regional data;

[0016] The warning priority coefficient for each regional data is set according to the correlation of abnormal changes in each type of regional data.

[0017] Furthermore, for any key analysis data, if the abnormal overlap coefficient is less than or equal to the preset abnormal overlap coefficient, a search for related persons is performed for the key monitoring video corresponding to the key analysis data, and the interactive video segments corresponding to each related person in the key monitoring video are extracted, and the video information tracing method is determined according to the interaction time ratio of the target monitoring person in the key monitoring video and the number of related persons;

[0018] The associated personnel corresponding to the key monitoring video are determined according to the personnel correlation coefficient between each monitoring personnel and the target monitoring personnel during the video monitoring period, and the monitoring personnel whose personnel correlation coefficient is greater than the preset personnel correlation coefficient are recorded as associated personnel.

[0019] Furthermore, for a single key monitoring video, if the interaction time ratio is greater than the preset interaction time ratio or the number of associated persons is greater than the preset number of associated persons, the warning priority coefficient of the corresponding interaction video segment is set according to the interaction correlation coefficient between each interaction video segment and the corresponding key analysis data;

[0020] The warning priority coefficient and the mutual correlation coefficient are positively correlated.

[0021] Furthermore, for a single key monitoring video, if the interaction time ratio is less than or equal to the preset interaction time ratio and the number of associated persons is less than or equal to the preset number of associated persons, the key monitoring video is divided to obtain several video segments to be analyzed, and the historical abnormal repetition coefficients of the key analysis data corresponding to the video segments to be analyzed are detected to determine the video extraction strategy based on the historical abnormal repetition coefficients.

[0022] Furthermore, if the historical anomaly repetition coefficient is greater than the preset historical anomaly repetition coefficient, the warning priority coefficient is set according to the feature overlap of each video segment to be analyzed and the corresponding feature correlation coefficient;

[0023] The warning priority coefficient is positively correlated with the characteristic reference value.

[0024] Further, if the historical anomaly repetition coefficient is less than or equal to the preset historical anomaly repetition coefficient, the key reference frame of the key monitoring video is set according to the relevant moment of the key analysis data corresponding to the video segment to be analyzed, and the setting method is determined according to the distribution state of the key reference frame;

[0025] If there are key reference frames in a dense state, the adjacent to-be-analyzed video segment in which the key reference frames are in a dense state is recorded as a warning video segment, and the warning priority coefficient of the warning video segment is determined according to the number of key reference frames contained in the warning video segment;

[0026] The warning priority coefficient is positively correlated with the number of key reference frames.

[0027] Furthermore, behavioral features are extracted for the video segments to be analyzed corresponding to the key reference frames in a dispersed state, and a warning priority coefficient is set for the video segments to be analyzed according to the matching coefficient between each behavioral feature and the corresponding key reference frame;

[0028] The warning priority coefficient and the matching coefficient are positively correlated.

[0029] Furthermore, when the information analysis is completed, the warning information of each key analysis data is sent to the user according to the warning priority coefficient of the regional data and the video segment;

[0030] The information analysis completion condition is that all key analysis data have completed the setting of the warning priority coefficient of the regional data, or the corresponding key monitoring videos have completed the setting of the warning priority coefficient of the video segment.

[0031] Compared with the prior art, the beneficial effect of the present invention lies in that, in the technical scheme of the present invention, a targeted and effective information extraction method is selected according to the abnormal overlap coefficient of the key analysis data and the actual situation of the related personnel in the key monitoring video, so that the information extraction method is more in line with the actual monitoring scenario, thereby ensuring the effectiveness of the early warning information extracted from the regional data of the key analysis data and the collected video information, and avoiding the inefficiency of information transmission and abnormal status judgment of the target monitoring personnel due to the fact that the sent early warning information contains too much invalid information.

[0032] Furthermore, the present invention determines the corresponding analysis strategy according to the abnormal overlap coefficient of each key analysis data. When the abnormal overlap coefficient of a certain key analysis data is large, it indicates that there are many monitoring personnel in the relevant area of ​​the target monitoring personnel and have similar abnormal conditions in the key analysis data. Therefore, various data in the area where they are located are collected, and the regional data most relevant to the abnormal state of the data is selected for early warning according to the regional abnormal correlation. The present invention improves the effectiveness of the early warning information.

[0033] Furthermore, in the present invention, when the abnormal overlap coefficient of a certain key analysis data is small, it indicates that there is no or few monitoring personnel in the relevant area of ​​the target monitoring personnel with similar abnormal situations in the key analysis data. Therefore, a specific analysis is performed on the key monitoring video, and the video information tracing method is determined according to the proportion of interaction time of the target monitoring personnel in the key monitoring video and the number of related personnel, to ensure that the method of extracting valid video segments is more in line with the actual situation of the target monitoring personnel, thereby ensuring the validity of the extracted video segments.

[0034] Furthermore, in the present invention, when the proportion of interaction time is greater than the preset proportion of interaction time or the number of related persons is greater than the preset number of related persons, by analyzing the video segments corresponding to each related person in the key monitoring video, the warning priority coefficient of the corresponding video segment is set according to the time correlation coefficient and the behavior correlation coefficient. In the case that there are many interactions between the target monitored persons, the video segments corresponding to the related persons are analyzed to determine the video segments for priority warning, which can improve the efficiency of video analysis while ensuring the effectiveness of the video segments for priority warning.

[0035] Furthermore, in the present invention, when the interaction time ratio is less than or equal to the preset interaction time ratio and the number of associated persons is less than or equal to the preset number of associated persons, the video extraction strategy is determined according to the historical abnormal repetition coefficient of the key analysis data. When the historical abnormal repetition coefficient is large, that is, the abnormal state of this key analysis data occurs more frequently and has regularity, the warning priority coefficient of the video segment to be analyzed is set according to the feature overlap and the corresponding feature correlation coefficient. When the historical abnormal repetition coefficient is small, that is, there is no regularity in this key analysis data, it is set for each video segment to be analyzed according to the specific distribution of the key reference frames, so that the method of extracting valid video segments is more in line with the actual situation, while improving the efficiency of video analysis, the effectiveness of the video segments with priority warning is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a wearable device monitoring method based on data analysis of the present invention;

[0037] Figure 2 A flow chart of the present invention for determining an analysis strategy based on an abnormal coincidence coefficient;

[0038] Figure 3 It is a flow chart of the present invention for determining a video information tracing method according to the interaction time ratio of the target monitoring personnel in the key monitoring video and the number of associated personnel;

[0039] Figure 4 The present invention is a flow chart of determining a video extraction strategy based on a historical abnormal repetition coefficient. DETAILED DESCRIPTION

[0040] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0041] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0042] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0043] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] See also Figures 1 to 4 As shown, the present invention provides a wearable device monitoring method based on data analysis, comprising:

[0045] Periodically collect various target monitoring data of target monitoring personnel, record the target monitoring data whose monitoring value is not within the corresponding preset data range or whose data change coefficient is greater than the preset data change coefficient as key analysis data, and obtain the key monitoring video corresponding to each key analysis data;

[0046] Determine the analysis strategy of the corresponding key analysis data according to the abnormal coincidence coefficient;

[0047] If the abnormal coincidence coefficient is greater than the preset abnormal coincidence coefficient, the regional abnormal period of each type of regional data is detected;

[0048] If the abnormal overlap coefficient is less than or equal to the preset abnormal overlap coefficient, a search for related persons is performed for the key monitoring video, and the video information tracing method is determined based on the interaction time ratio of the target monitoring personnel in the key monitoring video and the number of related persons;

[0049] The video information tracing method includes extracting video segments corresponding to each associated person in the key monitoring video and setting a warning priority coefficient, and dividing the key monitoring video and determining the video extraction method according to the historical abnormal repetition coefficient;

[0050] When the information analysis is completed, a set of early warning information for each key analysis data is sent to the user.

[0051] The target monitoring personnel are monitoring personnel who are currently analyzing various data and video information. The monitoring personnel are personnel who use wearable devices to monitor the target monitoring data. The types of target monitoring data in the present invention include but are not limited to: blood pressure, heart rate, electrocardiogram, blood oxygen saturation, body temperature, heart rate variability, electromyographic signals, blood volume pulse waves and blood sugar. In addition, the wearable device used in the present invention needs to be able to obtain various regional data and monitoring video data of the location of the target monitoring personnel. The categories of regional data include but are not limited to temperature, air pressure and light intensity. The present invention does not specifically limit the model of the wearable device used. The user can adaptively set the specific model of the wearable device according to the actual scene needs. The selected wearable device can obtain the various target monitoring data, regional data and monitoring video data that the user needs to monitor.

[0052] The present invention applies several historical monitoring records, and any historical monitoring record records at least one monitoring record for the monitoring personnel's basic information (such as age, gender and medical history), the data variation coefficient of the target monitoring data, the difference value of the monitoring data, the abnormal coincidence coefficient, the personnel correlation coefficient, the historical repetition coefficient and the feature similarity, and each historical monitoring record corresponds to a qualified mark, which records whether the accuracy of the abnormal judgment result meets the user's requirements;

[0053] A cyclic data monitoring cycle is applied in the present invention, and the duration of the data monitoring cycle can be determined by the user. The higher the timeliness requirement of the user for the monitoring results of the target monitoring personnel, the shorter the duration of the data monitoring cycle. A data monitoring cycle duration is provided, and the duration of the data monitoring cycle is 10s. At the end of each data monitoring cycle, detection is performed on each target monitoring data to obtain a corresponding monitoring value, and the monitoring value is a value obtained by detecting the monitoring data of each target. In the present invention, any target monitoring data is provided with a corresponding preset data range, and the maximum value and the minimum value of the preset data range can be set by the user according to the reference record. The reference record is a historical monitoring record of a monitoring personnel with the same age, gender and medical history as the target monitoring personnel. For single-item target monitoring data, the maximum value of the monitoring value in the historical monitoring record without regional data and video segment extraction is recorded as the maximum value of the preset data range, and the minimum value of the monitoring value is recorded as the minimum value of the preset data range. How to set the preset data range is easy to understand for those skilled in the art and will not be elaborated here.

[0054] For any target monitoring data, the data variation coefficient is the sum of the monitoring data fluctuation value and the monitoring data difference value. The monitoring data difference value is the absolute value of the difference between the monitoring values ​​obtained in the current data detection period and the previous data detection period. The monitoring data fluctuation value = the sum of the absolute values ​​of the differences between each monitoring value and the average monitoring value within the fluctuation detection period / the number of times the monitoring data for the target item is detected within the fluctuation detection period. The average monitoring value is the average value of each monitoring data within the fluctuation detection period. The duration of the fluctuation detection period can be determined by the user according to the actual working scenario, and the user's monitoring results for the target monitoring personnel The higher the accuracy requirement, the larger the value of the duration of the fluctuation detection cycle. A value of the duration of the fluctuation detection cycle is provided, and the value of the duration of the fluctuation detection cycle is 5 minutes. The value of the preset data change coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical monitoring records. The higher the accuracy requirement of the user for the monitoring results of the target monitoring personnel, the smaller the value of the preset data change coefficient. A method for setting the value of the preset data change coefficient is provided, and the maximum value of the data change coefficient in the historical monitoring records without regional data and video segment extraction is recorded as the preset data change coefficient.

[0055] For a single key monitoring data, a key monitoring video is obtained according to a key abnormal moment. If the monitoring value is not within the corresponding preset data range, the moment when the monitoring value is detected is recorded as the key abnormal moment. If the data change coefficient is greater than the preset data change coefficient, the first moment when a monitoring data difference value greater than a preset monitoring data difference value is detected is recorded as the key abnormal moment. The key abnormal moment is set as the cutoff time of the key monitoring video, and the key monitoring video is obtained according to the preset video extraction time. The values ​​of the preset monitoring data difference value and the preset video extraction time can be determined by the user according to the actual working scenario. For example, the user can set them according to the historical monitoring records. The higher the user's accuracy requirements for the monitoring results of the target monitored personnel, the smaller the value of the preset monitoring data difference value and the larger the value of the preset video extraction time. A method for determining the preset monitoring data difference value is provided, and the maximum value of the monitoring data difference value in the historical monitoring records where the regional data and video segment extraction are not performed is recorded as the preset monitoring data difference value. A method for determining the preset video extraction time is provided, and the average value of the duration of each key monitoring video in the historical monitoring records that meet the user's accuracy requirements for the monitoring results of the target monitored personnel is recorded as the preset video extraction time.

[0056] Specifically, under the key analysis conditions, the abnormal coincidence coefficients of various key analysis data of the target monitoring personnel are detected, and the analysis strategy of the corresponding key analysis data is determined according to the abnormal coincidence coefficients;

[0057] The anomaly coincidence coefficient of key analytical data is determined based on the reference anomaly differences of each monitoring personnel in the relevant area;

[0058] The key analysis condition is that key analysis data exists in the various target monitoring data of the target monitoring personnel.

[0059] Among them, for any key analysis data, the abnormal overlap coefficient is the average value of the reference abnormal difference of each monitoring personnel in the relevant area. For a single monitoring personnel, the reference abnormal difference is the sum of the monitoring difference value and the product of the abnormal moment difference value and the corresponding influence coefficient. The monitoring difference value is the absolute value of the difference between the monitoring values ​​of the key analysis data of the monitoring personnel and the target monitoring personnel, and the duration difference value is the interval between the key abnormal moments of the key analysis data of the monitoring personnel and the target monitoring personnel. The relevant area is a set of locations of monitoring personnel in a building space whose regional data are consistent with those obtained by the target monitoring personnel.

[0060] Specifically, for any key analysis data, if the abnormal coincidence coefficient is greater than the preset abnormal coincidence coefficient, various regional data of the key analysis data are obtained to determine the data change cycle of the corresponding regional data;

[0061] The warning priority coefficient for each regional data is set according to the correlation of abnormal changes in each type of regional data.

[0062] The value of the preset abnormal coincidence coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical monitoring records, and a method for setting the value of the preset abnormal coincidence coefficient is provided. The historical monitoring records based on the regional data as the warning information are recorded as the coincidence coefficient reference records, and the minimum value of the preset abnormal coincidence coefficient in the coincidence coefficient reference records that meet the user's accuracy requirements for the monitoring results of the target monitoring personnel is recorded as the preset abnormal coincidence coefficient;

[0063] The present invention adopts a cyclic regional data monitoring cycle, and the duration of the regional data monitoring cycle can be determined by the user. The higher the user's requirements for the timeliness of the monitoring results of the target monitoring personnel, the shorter the duration of the regional data monitoring cycle. A duration of a regional data monitoring cycle is provided, and the regional data monitoring cycle is 1 minute. At the end of each regional data monitoring cycle, the values ​​of various types of regional data are detected. For any category of regional data, the starting time of the data change cycle is the time period corresponding to the key monitoring cycle, and the first time it is detected that the regional data difference value is greater than the preset regional data difference value. The regional data difference value is the absolute value of the difference between the current regional data detection cycle and the value obtained in the previous regional data detection cycle. The abnormal change correlation = the overlapping time of the data change cycle and the abnormal monitoring cycle / the duration of the key monitoring video.

[0064] Specifically, for any key analysis data, if the abnormal overlap coefficient is less than or equal to the preset abnormal overlap coefficient, a search for related persons is performed for the key monitoring video corresponding to the key analysis data, and the interactive video segments corresponding to each related person in the key monitoring video are extracted. The video information tracing method is determined based on the interaction time ratio of the target monitoring person in the key monitoring video and the number of related persons.

[0065] The associated personnel corresponding to the key monitoring video are determined according to the personnel correlation coefficient between each monitoring personnel and the target monitoring personnel during the video monitoring period, and the monitoring personnel whose personnel correlation coefficient is greater than the preset personnel correlation coefficient are recorded as associated personnel.

[0066] Wherein, the personnel association coefficient is determined according to the influencing parameters corresponding to the interaction characteristics between the monitoring personnel and the target monitoring personnel and the influencing parameters corresponding to the existing association relationship. The categories of the interaction characteristics include, but are not limited to, drug distribution, drug injection and food distribution. The categories of the association relationship include, but are not limited to, doctor-patient relationship and nursing relationship. The user can set the values ​​of the influencing parameters corresponding to the interaction characteristics and the association relationship according to the actual working scene. An interaction characteristic and an association relationship for determining the personnel association coefficient in the present invention are provided. The interaction characteristics include drug distribution, drug injection and food distribution. The association relationship includes doctor-patient relationship and nursing relationship. The values ​​of the influencing parameters corresponding to drug distribution, drug injection and food distribution are provided. The value of the influencing parameter corresponding to drug distribution is 0.3, the value of the influencing parameter corresponding to drug injection is 0.3, and the value of the influencing parameter corresponding to food distribution is 0.4. The values ​​of the influencing parameters corresponding to the doctor-patient relationship and the nursing relationship are provided. The value of the influencing parameter corresponding to the doctor-patient relationship is 0.5, and the value of the influencing parameter corresponding to the nursing relationship is 0.5;

[0067] The value of the preset personnel association coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical monitoring records. The higher the user's requirement on the accuracy of the monitoring results of the target monitored personnel, the larger the value of the preset personnel association coefficient. A method for determining the value of the preset personnel association coefficient is provided, and the average value of the personnel association coefficient of each related person in the historical monitoring records that meets the user's requirement on the accuracy of the monitoring results of the target monitored personnel is recorded as the preset personnel association coefficient; the video segment in the present invention is a partial video captured from the key monitoring video, and the interaction time ratio = the sum of the video durations corresponding to each interaction video segment / the video duration of the key monitoring video. For a single related person, the starting time of the corresponding interaction video segment is the time when the related person first appears in the key monitoring video, and the ending time of the interaction video is the time when the related person last appears. How to extract the interaction video segment for each related person is easy for technical personnel in this field to understand and will not be elaborated here.

[0068] Specifically, for a single key monitoring video, if the interaction time ratio is greater than the preset interaction time ratio or the number of associated persons is greater than the preset number of associated persons, the warning priority coefficient of the corresponding interactive video segment is set according to the interaction correlation coefficient between each interactive video segment and the corresponding key analysis data;

[0069] The warning priority coefficient and the mutual correlation coefficient are positively correlated.

[0070] Among them, the values ​​of the preset interaction time ratio and the preset number of associated personnel can be determined by the user according to the actual work scenario. For example, the user can set them according to the historical monitoring records, and a method for setting the preset interaction time ratio is provided. The historical monitoring records set according to the time correlation coefficient and the behavior correlation coefficient for the warning priority coefficient of the corresponding video segment are recorded as interaction reference records, and the minimum value of the interaction time ratio of each key monitoring video in the interaction reference records that meets the user's requirements for the accuracy of the monitoring results of the target monitored personnel is recorded as the preset interaction time ratio. A method for setting the preset number of associated personnel is provided, and the minimum value of the number of associated personnel in each key monitoring video in the interaction reference records that meets the user's requirements for the accuracy of the monitoring results of the target monitored personnel is recorded as the preset number of associated personnel;

[0071] The interaction correlation coefficient is the sum of the products of each relevant interaction behavior and the corresponding time matching coefficient. Behavioral features are extracted for each interactive video segment to determine the category of the interactive behavior. For a key analysis data, if the abnormal cause in its historical monitoring record includes a certain interactive behavior determined in the interactive video segment, the behavioral feature is recorded as a relevant interactive behavior; the time matching coefficient corresponding to each relevant interactive behavior is negatively correlated with the behavior time difference value, the behavior time difference value is the absolute value of the difference between the relevant interval duration and the reference interval duration, the relevant interval duration is the interval duration between the moment corresponding to the relevant interaction behavior and the key abnormal moment, and the reference interval duration is the average value of the interval duration between the moment corresponding to the relevant interaction behavior and the key abnormal moment in each historical monitoring record.

[0072] Specifically, for a single key monitoring video, if the interaction time ratio is less than or equal to the preset interaction time ratio and the number of associated persons is less than or equal to the preset number of associated persons, the key monitoring video is divided to obtain several video segments to be analyzed, and the historical abnormal repetition coefficient of the key analysis data corresponding to the video segments to be analyzed is tested to determine the video extraction strategy based on the historical abnormal repetition coefficient.

[0073] Among them, the key monitoring video is divided into several video segments to be analyzed with the same time length. The user can determine the number of video segments to be analyzed according to the actual work scenario. For example, the user can set it according to the historical monitoring records. The higher the user's requirements for the accuracy of the monitoring results of the target monitoring personnel, the larger the number of video segments to be analyzed. A value of the number of video segments to be analyzed is provided, and the value of the number of video segments to be analyzed is 10; for a single target monitoring data, the historical anomaly repetition coefficient = the number of times the target monitoring data has an anomaly / the total number of data monitoring cycles. If the target monitoring data has an anomaly, the target monitoring data is recorded as the key analysis data. The total number of data monitoring cycles is the number of data monitoring cycles that exist from the monitoring value of the target monitoring personnel for the first time obtaining the target monitoring data in the historical monitoring records to the current moment.

[0074] Specifically, if the historical anomaly repetition coefficient is greater than the preset historical anomaly repetition coefficient, the warning priority coefficient is set according to the feature overlap of each video segment to be analyzed and the corresponding feature correlation coefficient;

[0075] The warning priority coefficient is positively correlated with the characteristic reference value.

[0076] Among them, the value of the preset historical abnormal repetition coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical monitoring records, and a method for setting the value of the preset historical abnormal repetition coefficient is provided, and the historical monitoring records set according to the feature overlap degree and the corresponding feature correlation coefficient for the warning priority coefficient are recorded as repeated reference records, and the minimum value of the historical repetition coefficient in the repeated reference records that meets the user's accuracy requirements for the monitoring results of the target monitoring personnel is recorded as the preset historical abnormal repetition coefficient;

[0077] For a single key monitoring data, the historical monitoring record contains the video segments that are finally determined to be associated with the data anomaly when there is an anomaly each time, and records the corresponding anomaly reasons, and extracts the behavioral features of the target monitored personnel and their associated personnel. For a single video segment to be analyzed, the feature reference value is the sum of the products of the feature overlaps and the corresponding feature correlation coefficients. The feature overlap = the number of overlapping behavioral features / the number of behavioral features extracted from the video segment to be analyzed. The overlapping behavioral feature is a behavioral feature in the video segment to be analyzed whose feature similarity with any behavioral feature in any video segment associated with the data anomaly is greater than the preset feature similarity. How to extract behavioral features for video segments and how to determine the feature similarity between behavioral features are contents that are easy for technicians in this field to understand. The specific execution process is not limited here and will not be repeated here. The preset feature similarity The user can determine the value according to the actual working scenario. For example, the user can set it according to the historical monitoring records. The higher the user's requirement for the accuracy of the monitoring results of the target monitored personnel, the larger the value of the preset feature similarity. A method for determining the value of the preset feature similarity is provided, and the average value of the feature similarities of each overlapping behavior feature in the historical monitoring records that meets the user's requirement for the accuracy of the monitoring results of the target monitored personnel is recorded as the preset feature similarity; for a single feature overlap, it is determined according to the proportion of abnormal causes corresponding to the video segment that determines the feature overlap in the historical monitoring records. The feature correlation coefficient corresponding to the feature overlap is positively correlated with the proportion of abnormal causes in the historical monitoring records. The proportion of abnormal causes = the number of times the abnormal cause corresponding to the video segment that determines the feature overlap in each historical monitoring record appears / the number of times the target monitoring data corresponding to the video segment with the feature overlap is recorded as key analysis data.

[0078] Specifically, if the historical anomaly repetition coefficient is less than or equal to the preset historical anomaly repetition coefficient, the key reference frame of the key monitoring video is set according to the relevant moment of the key analysis data corresponding to the video segment to be analyzed, and the setting method is determined according to the distribution state of the key reference frame;

[0079] If there are key reference frames in a dense state, the adjacent to-be-analyzed video segment in which the key reference frames are in a dense state is recorded as a warning video segment, and the warning priority coefficient of the warning video segment is determined according to the number of key reference frames contained in the warning video segment;

[0080] The warning priority coefficient is positively correlated with the number of key reference frames.

[0081] Among them, for any key analysis data, the starting time of the video segment finally determined in each historical monitoring record is recorded as the relevant time, and the video frames corresponding to each relevant time in the key monitoring video corresponding to the key analysis data are recorded as key reference frames. The distribution state of the key reference frames is determined according to the interval time between each key reference frame and the adjacent key reference frame. The distribution state includes a dense state and a discrete state. If the interval time between the key reference frame and its adjacent key reference frame is less than or equal to the preset interval time, the key reference frame and its adjacent key reference frame are determined to be in a dense state. If the interval time between the key reference frame and its adjacent key reference frame is less than or equal to the preset interval time, the key reference frame is determined to be in a discrete state. For a single key reference frame, a key reference frame with no other key reference frames between it and the key reference frame is recorded as an adjacent key reference frame. The value of the preset interval time can be determined by the user according to the actual working scenario, and a value of the preset interval time is provided. The value of the preset interval time is 5% of the time of the key monitoring video where the key reference frame is located.

[0082] Specifically, behavior features are extracted for the video segments to be analyzed corresponding to the key reference frames in a dispersed state, and the warning priority coefficient of the video segments to be analyzed is set according to the matching coefficient between each behavior feature and the corresponding key reference frame;

[0083] The warning priority coefficient and the matching coefficient are positively correlated.

[0084] Among them, for a single video segment to be analyzed, the matching coefficient is the sum of the matching reference values ​​of the video segment to be analyzed and the video segments corresponding to each key reference frame. For the video segment corresponding to any key reference frame, the matching reference value = the number of overlapping behavioral features of the video segment to be analyzed / the number of behavioral features extracted from the video segment corresponding to the key reference frame.

[0085] Specifically, when the information analysis is completed, the warning information of each key analysis data is sent to the user according to the warning priority coefficient of the regional data and the video segment;

[0086] The information analysis completion condition is that all key analysis data have completed the setting of the warning priority coefficient of the regional data, or the corresponding key monitoring videos have completed the setting of the warning priority coefficient of the video segment.

[0087] Among them, the warning information is sent to the user according to the warning priority coefficient items of each regional data, each warning video segment and each video segment to be analyzed. The larger the warning priority coefficient of the regional data, the warning video segment and the video segment to be analyzed, the earlier it is sent to the user as a warning information.

[0088] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle 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 fall within the protection scope of the present invention.

[0089] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A wearable device monitoring method based on data analysis, characterized in that: include: Periodically collect various target monitoring data of target monitoring personnel, record the target monitoring data whose monitoring value is not within the corresponding preset data range or whose data change coefficient is greater than the preset data change coefficient as key analysis data, and obtain the key monitoring video corresponding to each key analysis data; Determine the analysis strategy of the corresponding key analysis data according to the abnormal coincidence coefficient; If the abnormal coincidence coefficient is greater than the preset abnormal coincidence coefficient, the data change cycle of each type of regional data is detected; If the abnormal overlap coefficient is less than or equal to the preset abnormal overlap coefficient, a search for related persons is performed for the key monitoring video, and the video information tracing method is determined based on the interaction time ratio of the target monitoring personnel in the key monitoring video and the number of related persons; The video information tracing method includes extracting video segments corresponding to each associated person in the key monitoring video and setting a warning priority coefficient, and dividing the key monitoring video and determining the video extraction method according to the historical abnormal repetition coefficient; When information analysis is completed, early warning information of key analysis data will be sent to users.

2. The wearable device monitoring method based on data analysis according to claim 1, characterized in that: Under key analysis conditions, detect the abnormal coincidence coefficients of key analysis data of target monitoring personnel, and determine the analysis strategy of the corresponding key analysis data according to the abnormal coincidence coefficients; The anomaly coincidence coefficient of key analytical data is determined based on the reference anomaly differences of each monitoring personnel in the relevant area; The key analysis condition is that key analysis data exists in the various target monitoring data of the target monitoring personnel.

3. The wearable device monitoring method based on data analysis according to claim 2, characterized in that: For any key analysis data, if the abnormal coincidence coefficient is greater than the preset abnormal coincidence coefficient, various regional data of the key analysis data are obtained to determine the data change cycle of the corresponding regional data; The warning priority coefficient for each regional data is set according to the correlation of abnormal changes in each type of regional data.

4. The wearable device monitoring method based on data analysis according to claim 3 is characterized in that: For any key analysis data, if the abnormal overlap coefficient is less than or equal to the preset abnormal overlap coefficient, the key monitoring video corresponding to the key analysis data is searched for related persons, and the interactive video segments corresponding to each related person in the key monitoring video are extracted. The video information tracing method is determined based on the interaction time ratio of the target monitoring person in the key monitoring video and the number of related persons; The associated personnel corresponding to the key monitoring video are determined according to the personnel correlation coefficient between each monitoring personnel and the target monitoring personnel during the video monitoring period, and the monitoring personnel whose personnel correlation coefficient is greater than the preset personnel correlation coefficient are recorded as associated personnel.

5. The wearable device monitoring method based on data analysis according to claim 4, characterized in that: For a single key monitoring video, if the interaction time ratio is greater than the preset interaction time ratio or the number of associated persons is greater than the preset number of associated persons, the warning priority coefficient of the corresponding interactive video segment is set according to the interaction correlation coefficient between each interactive video segment and the corresponding key analysis data; The warning priority coefficient and the mutual correlation coefficient are positively correlated.

6. The wearable device monitoring method based on data analysis according to claim 5, characterized in that: For a single key monitoring video, if the interaction time ratio is less than or equal to the preset interaction time ratio and the number of associated persons is less than or equal to the preset number of associated persons, the key monitoring video is divided to obtain several video segments to be analyzed, and the historical abnormal repetition coefficient of the key analysis data corresponding to the video segments to be analyzed is tested to determine the video extraction strategy based on the historical abnormal repetition coefficient.

7. The wearable device monitoring method based on data analysis according to claim 6, characterized in that: If the historical anomaly repetition coefficient is greater than the preset historical anomaly repetition coefficient, the warning priority coefficient is set according to the feature overlap of each video segment to be analyzed and the corresponding feature correlation coefficient; The warning priority coefficient is positively correlated with the characteristic reference value.

8. The wearable device monitoring method based on data analysis according to claim 7, characterized in that: If the historical anomaly repetition coefficient is less than or equal to the preset historical anomaly repetition coefficient, the key reference frame of the key monitoring video is set according to the relevant time of the key analysis data corresponding to the video segment to be analyzed, and the setting method is determined according to the distribution state of the key reference frame; If there are key reference frames in a dense state, the adjacent to-be-analyzed video segment in which the key reference frames are in a dense state is recorded as a warning video segment, and the warning priority coefficient of the warning video segment is determined according to the number of key reference frames contained in the warning video segment; The warning priority coefficient is positively correlated with the number of key reference frames.

9. The wearable device monitoring method based on data analysis according to claim 8, characterized in that: Behavior features are extracted for the video segments to be analyzed corresponding to the key reference frames in a dispersed state, and the warning priority coefficients of the video segments to be analyzed are set according to the matching coefficients of the behavior features and the corresponding key reference frames; The warning priority coefficient and the matching coefficient are positively correlated.

10. The wearable device monitoring method based on data analysis according to claim 9, characterized in that: When information analysis is completed, early warning information of each key analysis data is sent to users based on regional data and early warning priority coefficients of video segments; The information analysis completion condition is that all key analysis data have completed the setting of the warning priority coefficient of the regional data, or the corresponding key monitoring videos have completed the setting of the warning priority coefficient of the video segment.

Images