Outdoor screen hot spot monitoring method and system based on multi-source parameters
By segmenting and diagnosing multi-source parameters of outdoor screens, the problem of early warning lag in traditional hot spot monitoring methods has been solved, enabling timely early warning and risk elimination of hot spots and improving the service life of outdoor screens.
Patent Information
- Application Number
- CN202511026156.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-24
- Publication Date
- 2025-11-07
AI Technical Summary
Traditional hot spot monitoring methods are unable to fully reflect the causes of hot spots and cannot achieve dynamic and continuous monitoring, resulting in delayed hot spot warnings and affecting the service life and safety of outdoor screens.
By monitoring the temperature of key parts of outdoor screens, using multi-source parameter segmentation and diagnostic models, the risk of hot spots is diagnosed in different areas, and a dual diagnostic model is constructed for early warning.
It improves the early warning efficiency of hot spots, eliminates potential risks in a timely manner, and extends the service life of outdoor screens.
Smart Images
Figure CN120908563A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application relates to the technical field of outdoor screen monitoring, in particular to an outdoor screen hot spot monitoring method and system based on multiple source parameters. BACKGROUND
[0002] During a long time of operation, an outdoor display screen is prone to form a local overheating area, i.e., a hot spot, due to factors such as environmental temperature changes, uneven heat dissipation, driving current fluctuations or pixel point aging. The hot spot not only causes display color difference and brightness attenuation, but also accelerates device aging and even causes safety hazards.
[0003] Traditional hot spot monitoring methods mostly rely on infrared temperature measurement or temperature sensors, and can only obtain surface temperature data, which is difficult to comprehensively reflect the causes of hot spots. Dynamic and continuous monitoring cannot be achieved, resulting in delayed hot spot early warning. SUMMARY
[0004] The application aims to solve the above technical problems, and provides an outdoor screen hot spot monitoring method and system based on multiple source parameters, which aims to improve the hot spot diagnosis and early warning efficiency of the outdoor screen and improve the service life of the outdoor screen.
[0005] Some embodiments of the application monitor the temperature of the key parts of the outdoor screen, timely warn the abnormal operation state of the outdoor screen, and diagnose the hot spot risk of the outdoor screen by segmenting the outdoor screen and collecting multiple source monitoring data, thereby improving the early warning efficiency of the hot spot of the outdoor screen and timely eliminating potential hot spot risks.
[0006] In some embodiments of the application, the monitoring sub-regions with hot spots are segmented again to timely locate the positions of the hot spots of the outdoor screen, and a double diagnosis model is constructed by processing the sub-regions with hot spots to timely warn potential hot spot risks and improve the operation life of the outdoor screen.
[0007] Some embodiments of the application provide an outdoor screen hot spot monitoring method based on multiple source parameters, which comprises: obtaining an operation temperature parameter of the outdoor screen, and setting a first cutting strategy according to the operation temperature parameter; setting multiple monitoring sub-regions according to the first cutting strategy, and generating diagnosis data packets of the monitoring sub-regions according to auxiliary monitoring data; generating hot spot risk values of the monitoring sub-regions according to all the diagnosis data packets, and judging whether to generate a warning instruction according to all the hot spot risk values.
[0008] In some embodiments of the application, when the first cutting strategy is set according to the operation temperature parameter, it comprises: a plurality of monitoring points are preset; Obtaining the operating temperature parameters of each monitoring point, and generating the operating value of each monitoring point; Generating a segmentation evaluation value c according to all operating values; c=[ βi*Y1(i)*(s i -s') 2 ]; Wherein, θ1 is the number of monitoring points; β i is the weight factor of the i th monitoring point; s i is the operating value of the i th monitoring point; s' is the preset operating value threshold; Y1(i) is the selection coefficient; if (s i -s')>0, Y1(i)=0; if (s i -s')<0, Y1(i)=1; According to the segmentation evaluation value c, a first cutting strategy is set, and the first cutting strategy includes the area of a single monitoring sub-region.
[0009] In some embodiments of the application, when generating the diagnostic data package of each monitoring sub-region, the following steps are included: Establishing a monitoring sub-region sequence A, A=(a1, a2…a i …a n ), wherein a i is the i th monitoring sub-region; n is the number of monitoring sub-regions; Obtaining auxiliary monitoring data; According to the monitoring sub-region sequence A, a i is set as the target sub-region; Based on the segmentation model, the associated monitoring data of the target sub-region in the auxiliary monitoring data is extracted; Based on the time sequence model, the associated monitoring data of the target sub-region is preprocessed, and the diagnostic data package of the target sub-region is generated according to the preprocessing result; Generating the diagnostic data package of each monitoring sub-region in turn.
[0010] In some embodiments of the application, when generating the hot spot risk value of each monitoring sub-region, the following steps are included: According to the monitoring sub-region sequence A, a i is set as the sub-region to be diagnosed; Obtaining the diagnostic data package of the sub-region to be diagnosed; Establishing a plurality of diagnostic time nodes according to the diagnostic data package; Establishing a diagnostic time node sequence T, T=(t1, t2…t i …t m ), wherein t i is the i th diagnostic time node based on time sequence; m is the number of diagnostic time nodes; generate an abnormal risk value of each diagnosis time node; establish an abnormal risk value sequence P, P=(p1, p2…p i …p m ), wherein p i is an abnormal risk value of the i-th diagnosis time node; m is the number of diagnosis time nodes; generate a hot spot risk value f of the target sub-region according to all the abnormal risk values; f=[ η i *v i ]; wherein θ2 is the number of risk characteristic indexes; η i is the influence factor of the i-th risk characteristic index; v i is the reference value of the i-th risk characteristic index based on the abnormal risk value sequence P; generate the hot spot risk value of each monitoring sub-region in sequence; establish a hot spot risk value sequence F, F=(f1, f2…f i …f n ), wherein f i is the hot spot risk value of the i-th monitoring sub-region.
[0011] In some embodiments of the present application, when generating the abnormal risk value of each diagnosis time node, the following steps are included: set t i as the target time node according to the diagnosis time node sequence T in sequence; generate the abnormal risk value p of the target time node; p=e1*Q1*[ µ i *Y2(i)*(d i -d' 1i )]+e2*Q2*[ µ i *Y3(i)*(d i -d' 2i )]; wherein e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; is the number of data categories; µ i is the influence factor of the i-th data category; d i is the real-time reference value of the i-th data category at the target time node; d' 1i is the safety threshold of the i-th data category; d' 2i is the real-time reference value of the i-th data category at the last diagnosis time node of the target time node; Y2(i) is a selection coefficient; if (d i -d'1i If (d i -d' 1i <0, Y2(i) = 0; Y3(i) is a selection coefficient; if (d i -d' 2i >0, Y3(i) = 1; if (d i -d' 2i <0, Y3(i) = 0; The abnormal risk values of each diagnostic time node are sequentially generated.
[0012] In some embodiments of the present application, when determining whether to generate a warning instruction according to all hot spot risk values, the following is included: A first hot spot risk value threshold F1 and a second hot spot risk value threshold F2 are preset, and F1 < F2; If f i > F2, the i-th monitoring sub-region is set as a risk sub-region, and a first-level warning instruction of the risk sub-region is generated; If F1 < f i < F2, the i-th monitoring sub-region is set as an abnormal sub-region, and a second-level diagnostic strategy of the abnormal sub-region is generated; If f i < F1, the i-th monitoring sub-region is set as a normal sub-region.
[0013] In some embodiments of the present application, the first-level warning instruction includes: A target risk sub-region is sequentially selected according to all risk sub-regions; A second-level segmentation strategy of the target risk sub-region is set; A plurality of hot spot sub-regions are established in the target risk sub-region according to the second-level segmentation strategy; Second-level diagnostic packages of each hot spot sub-region are sequentially generated; A hot spot diagnostic result of the target risk sub-region is generated according to all second-level diagnostic packages.
[0014] In some embodiments of the present application, the second-level diagnostic strategy includes: All monitoring sub-regions are aggregated according to the monitoring sub-region sequence A; An association model is generated according to the aggregation result; A target abnormal sub-region is sequentially selected according to all abnormal sub-regions; Environment similarity values of the target abnormal sub-region and each risk sub-region are generated according to the association model; An auxiliary diagnostic model of the target abnormal sub-region is generated according to all environment similarity values; A plurality of second-level sub-regions are established in the target abnormal sub-region according to the auxiliary diagnostic model; generating the early warning evaluation value of each secondary sub-region in sequence; determining whether to generate the secondary early warning instruction of each secondary sub-region according to the early warning evaluation value.
[0015] In some embodiments of the present application, when determining whether to generate the secondary early warning instruction of each secondary sub-region, the following steps are included: establishing a secondary sub-region sequence W; W=(w1,w2…wn1) i …wn1 n1 ), wherein w i is the i-th secondary sub-region in the target abnormal sub-region; n1 is the number of secondary sub-regions in the target abnormal sub-region; setting an auxiliary diagnosis period; setting w i as the target secondary sub-region in sequence; obtaining the feedback data packet of the target secondary sub-region in the auxiliary diagnosis period, and generating the early warning evaluation value h according to the feedback data packet; h=[ µ i *k i ]; wherein, is the number of data categories; µ i is the influence factor of the i-th data category; k i is the similarity value of the i-th data category generated according to the auxiliary diagnosis model and the feedback data packet; presetting an early warning evaluation value threshold H1; if h>H1, generating the secondary early warning instruction of the target secondary sub-region.
[0016] In some embodiments of the present application, an outdoor screen hot spot monitoring system based on multiple source parameters is provided, which comprises: a central control unit, configured to obtain the running temperature parameter of the outdoor screen; The central control unit is further configured to set a first cutting strategy according to the running temperature parameter; a monitoring unit comprising a plurality of monitoring sub-modules; The monitoring unit is configured to collect the running temperature parameter and auxiliary monitoring data of the outdoor screen; The central control unit comprises: a first processing module, configured to set a plurality of monitoring sub-regions according to the first cutting strategy; a second processing module, configured to generate a diagnosis data packet of each monitoring sub-region according to the auxiliary monitoring data; a first diagnosis module, configured to generate a hot spot risk value of each monitoring sub-region according to all diagnosis data packets, and determine whether to generate an early warning instruction according to all hot spot risk values.
[0017] Compared with the prior art, the outdoor screen hot spot monitoring method and system based on multiple source parameters has the beneficial effects that: By monitoring the temperature of the key parts of the outdoor screen, the abnormal operation state of the outdoor screen is timely warned, and by segmenting the outdoor screen and collecting multiple source monitoring data, the hot spot risk of the outdoor screen is diagnosed in different regions, thereby improving the early warning efficiency of the hot spot of the outdoor screen and timely eliminating the potential hot spot risk.
[0018] By twice segmenting the monitoring sub-regions with hot spots, the positions of each hot spot of the outdoor screen are timely located, and by processing the sub-regions with hot spots, a double diagnosis model is constructed to timely warn the potential hot spot risk and improve the operation life of the outdoor screen. BRIEF DESCRIPTION OF DRAWINGS
[0019] Figure 1 is a flowchart of the outdoor screen hot spot monitoring method based on multiple source parameters in the embodiments of the present application. DETAILED DESCRIPTION
[0020] The specific embodiments of the present application will be further described in detail below in conjunction with the drawings and examples. The following examples are used to illustrate the present application, but are not used to limit the scope of the present application.
[0021] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements indicated must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.
[0022] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more.
[0023] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connection" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.
[0024] As Figure 1 shown, the application embodiment of the application preferably comprises a multi-source parameter-based outdoor screen hot spot monitoring method, which comprises: S101: Obtain the running temperature parameter of the outdoor screen, and set a first cutting strategy according to the running temperature parameter; S102: Set a plurality of monitoring sub-regions according to the first cutting strategy, and generate a diagnosis data packet for each monitoring sub-region according to auxiliary monitoring data; S013: Generate a hot spot risk value for each monitoring sub-region according to all diagnosis data packets, and judge whether to generate a warning instruction according to all hot spot risk values.
[0025] Specifically, according to the device parameters of the outdoor screen, a plurality of monitoring sub-modules (preferably temperature sensors) are deployed on the back of the display screen, so as to collect the temperature of each key area (module, power supply, driving circuit accessory) on the back of the screen body, and generate corresponding running temperature parameters.
[0026] Specifically, when setting the first cutting strategy according to the running temperature parameter, it comprises: preset a plurality of monitoring points; obtain the running temperature parameter of each monitoring point, and generate the running value of each monitoring point; generate a segmentation evaluation value c according to all running values; c=[ βi*Y1(i)*(s i -s') 2 ]; Wherein, θ1 is the number of monitoring points; β i is the weight factor of the i-th monitoring point; s i is the running value of the i-th monitoring point; s' is the preset running value threshold; Y1(i) is the selection coefficient; if (s i -s')>0, Y1(i)=0; if (s i -s')<0, Y1(i)=1; set the first cutting strategy according to the segmentation evaluation value c, which includes the area of a single monitoring sub-region in the first cutting strategy.
[0027] Specifically, the larger the segmentation evaluation value is, the greater the probability of abnormal running state of the current outdoor screen is, and the smaller the area of the corresponding single monitoring sub-region is, thereby improving the diagnosis efficiency of the hot spot on the outdoor screen.
[0028] Specifically, each key area on the back of the screen body is set as a monitoring point, wherein the weight factor of each monitoring point is set according to the importance of its corresponding key area to the outdoor screen, and the greater the importance is, the greater the corresponding weight factor is.
[0029] Specifically, the operating value is set based on the difference between the temperature value collected at the monitoring point and the normal temperature value of that monitoring point. The smaller the difference, the larger the corresponding operating value, indicating that the monitoring point is less likely to be in an abnormal operating state.
[0030] Specifically, the operating value threshold can be set based on historical parameters. When the operating value of a monitoring point is lower than the operating value threshold, it indicates that the operating status of the monitoring point is abnormal.
[0031] It is understood that in the above embodiments, by monitoring the temperature of key parts of the outdoor screen, early warnings can be issued in a timely manner for abnormal operating conditions of the outdoor screen, and the area of a single monitoring sub-region can be dynamically adjusted according to the degree of abnormality, thereby reducing monitoring costs and improving the efficiency of early warning and diagnosis of hot spots on the outdoor screen.
[0032] In a preferred embodiment of this application, generating diagnostic data packets for each monitoring sub-region includes: Establish a monitoring sub-region sequence A, A=(a1, a2…a…) i …a n ), where a i Let n be the i-th monitoring sub-region; n is the number of monitoring sub-regions. Obtain auxiliary monitoring data; Based on the monitoring sub-region sequence A, a is set sequentially. i For the target sub-region; Based on the segmentation model, correlated monitoring data of the target sub-region is extracted from the auxiliary monitoring data; Preprocessing of associated monitoring data of the target sub-region based on time series model, and generating diagnostic data package of the target sub-region based on the preprocessing results; Diagnostic data packets for each monitoring sub-region are generated sequentially.
[0033] Specifically, the outdoor screen is divided according to the area of a single monitoring sub-region, and a monitoring sub-region sequence is established based on the division results.
[0034] Specifically, the segmentation model can process all the collected auxiliary monitoring data according to the location of each monitoring sub-region, thereby extracting the auxiliary monitoring data belonging to the target sub-region and setting it as the associated monitoring data of the target sub-region.
[0035] Specifically, the auxiliary monitoring data includes, but is not limited to, visual images (capturing display images of the display screen under certain conditions by deploying high-definition industrial cameras in front of or on the side of the screen, deploying a miniature infrared thermal imager on the back of the screen to obtain a local thermal distribution image), environmental data (collecting environmental temperature, humidity, light intensity, wind speed and other data in real time by installing an environmental monitoring unit around the display screen), and electrical parameters (input voltage, working current, power and other data of the display module or unit) and other multi-source data.
[0036] Specifically, the time sequence model can align different categories of monitoring data in the time dimension to generate corresponding diagnostic data packets.
[0037] Specifically, when generating the hot spot risk value of each monitoring sub-region, it includes: According to the monitoring sub-region sequence A, a is set in turn i for the to-be-diagnosed sub-region; obtain the diagnostic data packet of the to-be-diagnosed sub-region; establish a plurality of diagnostic time nodes according to the diagnostic data packet; establish a diagnostic time node sequence T, T=(t1, t2…t i …t m ), wherein t i is the i-th diagnostic time node based on time sequence; m is the number of diagnostic time nodes; generate an abnormal risk value for each diagnostic time node; establish an abnormal risk value sequence P, P=(p1, p2…p i …p m ), wherein p i is the i-th diagnostic time node abnormal risk value; m is the number of diagnostic time nodes; generate a hot spot risk value f of the target sub-region according to all abnormal risk values; f=[ η i *v i ]; wherein θ2 is the number of risk characteristic indexes; η i is the i-th risk characteristic index influence factor; vi is the reference value of the i-th risk characteristic index based on the abnormal risk value sequence P; generate a hot spot risk value for each monitoring sub-region in turn; establish a hot spot risk value sequence F, F=(f1, f2…f i …f n ), wherein f i is the i-th monitoring sub-region hot spot risk value.
[0038] Specifically, the greater the abnormal evaluation value, the higher the possibility of abnormal operation state in the corresponding diagnosis time node sub-region.
[0039] Specifically, the risk feature indicators include but are not limited to the number of abnormal evaluation values exceeding the abnormal evaluation value threshold, the average abnormal evaluation value, the change trend of the abnormal evaluation value, and the like. By quantifying each risk feature indicator, the diagnosis accuracy of the hot spot risk of the sub-region to be diagnosed is improved.
[0040] Specifically, the time interval between the two adjacent diagnosis time nodes is set according to the data amount in the diagnosis data packet. The greater the data amount, the greater the corresponding time interval, and the randomness of the selected point is improved.
[0041] Specifically, when generating the abnormal risk value of each diagnosis time node, it includes: According to the diagnosis time node sequence T, t i is set in turn; Generate the abnormal risk value p of the target time node; p = e1*Q1*[ µ i *Y2(i)*(d i -d' 1i )] + e2*Q2*[ µ i *Y3(i)*(d i -d' 2i )]; Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; is the number of data categories; µ i is the influence factor of the i-th data category; d i is the real-time reference value of the i-th data category at the target time node; d' 1i is the safety threshold of the i-th data category; d' 2i is the real-time reference value of the i-th data category at the last diagnosis time node of the target time node; Y2(i) is a selection coefficient; if (d i -d' 1i )>0, Y2(i)=1; if (d i -d' 1i )<0, Y2(i)=0; Y3(i) is a selection coefficient; if (d i -d' 2i )>0, Y3(i)=1; if (d i -d' 2i )<0, Y3(i)=0; The abnormal risk values of each diagnosis time node are generated in sequence.
[0042] Specifically, the data categories are all data categories in the auxiliary monitoring data, and the safety threshold of each data category is generated by analyzing historical data.
[0043] Specifically, by quantifying each data category, a real-time reference value of each data category is generated, and the greater the reference value, the greater the deviation between the actual running value and the safe running value of the current data category.
[0044] Specifically, the influence factor corresponding to each data category and hot spot risk is set according to the correlation degree, and the greater the correlation degree, the greater the corresponding influence factor.
[0045] Specifically, by presetting the first fixed coefficient and the second fixed coefficient, all parameters in the model are normalized, so that each parameter in the model is in the same value range.
[0046] It can be understood that in the above embodiment, the multi-source data of the to-be-diagnosed sub-region is screened, and all multi-source data is analyzed based on time sequence processing, thereby improving the early warning efficiency of the outdoor screen hot spot and timely eliminating potential hot spot risks.
[0047] In the preferred embodiment of the present application, when determining whether to generate a warning instruction according to all hot spot risk values, the following steps are included: A first hot spot risk value threshold F1 and a second hot spot risk value threshold F2 are preset, and F1 < F2; If f i F2, the i-th monitoring sub-region is set as a risk sub-region, and a first-level warning instruction of the risk sub-region is generated; If F1 < f i F2, the i-th monitoring sub-region is set as an abnormal sub-region, and a second-level diagnosis strategy of the abnormal sub-region is generated; If f i F1, the i-th monitoring sub-region is set as a normal sub-region.
[0048] Specifically, the first hot spot risk value threshold and the second hot spot risk value threshold can be set according to historical parameters.
[0049] Specifically, there is a hot spot in the risk sub-region, and there may be a hot spot in the abnormal sub-region.
[0050] Specifically, the first-level warning instruction includes: Selecting a target risk sub-region in sequence according to all risk sub-regions; Setting a second-level segmentation strategy for the target risk sub-region; According to the secondary segmentation strategy, multiple hot spot sub-regions are established in the target risk sub-region; The secondary diagnosis packages of the respective hot spot sub-regions are generated in sequence; The hot spot diagnosis result of the target risk sub-region is generated according to all the secondary diagnosis packages.
[0051] Specifically, according to historical data analysis, the area of the historical maximum hot spot is generated, the target risk sub-region is segmented according to the area, and multiple hot spot sub-regions are generated according to the segmentation result, wherein the area of each hot spot sub-region is not greater than the area of the historical maximum hot spot.
[0052] Specifically, by analyzing each hot spot sub-region, the hot spot in the target risk sub-region is located, and the hot spot diagnosis result is generated according to the location result.
[0053] In the preferred embodiment of the present application, the secondary diagnosis strategy includes: The aggregation processing is performed on all the monitoring sub-regions according to the monitoring sub-region sequence A; The correlation model is generated according to the aggregation result; The target abnormal sub-region is selected in sequence according to all the abnormal sub-regions; The environmental similarity values of the target abnormal sub-region and each risk sub-region are generated according to the correlation model; The auxiliary diagnosis model of the target abnormal sub-region is generated according to all the environmental similarity values; Multiple secondary sub-regions are established in the target abnormal sub-region according to the auxiliary diagnosis model; The early warning evaluation values of the respective secondary sub-regions are generated in sequence; It is determined whether to generate the secondary early warning instruction of each secondary sub-region according to the early warning evaluation values.
[0054] Specifically, by analyzing the environmental parameters of the target abnormal sub-region and each risk sub-region, the corresponding environmental similarity values are generated, and the auxiliary diagnosis model is constructed according to the risk sub-region with the maximum environmental similarity value, and the auxiliary diagnosis model is the simulation running model of the risk sub-region.
[0055] Specifically, when it is determined whether to generate the secondary early warning instruction of each secondary sub-region, it includes: The secondary sub-region sequence W is established; W=(w1,w2…wn1) i …wn1 n1 ), wherein w i is the i-th secondary sub-region in the target abnormal sub-region; n1 is the number of secondary sub-regions in the target abnormal sub-region; The auxiliary diagnosis period is set; w i is the target secondary sub-region; obtaining a feedback data packet of the target secondary sub-region in an auxiliary diagnosis cycle, and generating an early warning evaluation value h according to the feedback data packet; h=[ µ i *k i ]; wherein, is the number of data categories; µ i is an influence factor of the i-th data category; k i is a similarity value of the i-th data category generated according to the auxiliary diagnosis model and the feedback data packet; a preset early warning evaluation value threshold H1; if h>H1, generating a secondary early warning instruction of the target secondary sub-region.
[0056] Specifically, the target abnormal sub-region is processed according to a secondary segmentation strategy of a risk sub-region corresponding to the auxiliary diagnosis model.
[0057] Specifically, the greater the early warning evaluation value, the greater the possibility of the existence of hot spot risk in the secondary sub-region.
[0058] Specifically, the secondary early warning instruction indicates that the secondary sub-region has hot spot risk and needs to be repaired in time.
[0059] It can be understood that in the above embodiments, the monitoring sub-region with hot spot is twice segmented to timely locate the positions of each hot spot of the outdoor screen, and the sub-region with hot spot is processed to construct a double diagnosis model to timely warn the potential hot spot risk and improve the operation life of the outdoor screen.
[0060] Based on any one of the preferred embodiments of the outdoor screen hot spot monitoring method based on multiple source parameters, another preferred embodiment of the outdoor screen hot spot monitoring method based on multiple source parameters is provided in the preferred embodiment, which comprises: a central control unit configured to obtain an operation temperature parameter of the outdoor screen; the central control unit is further configured to set a first cutting strategy according to the operation temperature parameter; a monitoring unit comprising a plurality of monitoring sub-modules; the monitoring unit is configured to collect the operation temperature parameter and auxiliary monitoring data of the outdoor screen; the central control unit comprises: a first processing module configured to set a plurality of monitoring sub-regions according to the first cutting strategy; a second processing module configured to generate a diagnosis data packet of each monitoring sub-region according to the auxiliary monitoring data; a first diagnosis module configured to generate a hot spot risk value of each monitoring sub-region according to all diagnosis data packets, and to determine whether to generate an early warning instruction according to all hot spot risk values.
[0061] According to the first concept of the present application, by monitoring the temperature of the key parts of the outdoor screen, the abnormal operation state of the outdoor screen is warned in time, and by segmenting the outdoor screen and collecting multi-source monitoring data, the thermal spot risk of the outdoor screen is diagnosed, the warning efficiency of the thermal spot of the outdoor screen is improved, and the potential thermal spot risk is excluded in time.
[0062] According to the second concept of the present application, by twice segmenting the monitoring sub-area with thermal spots, the positions of each thermal spot of the outdoor screen are located in time, and by processing the sub-area with thermal spots, a double diagnosis model is constructed, the potential thermal spot risk is warned in time, and the operation life of the outdoor screen is improved.
[0063] The above is only the preferred embodiment of the present application, it should be pointed out that for ordinary skilled in the art, without departing from the technical principles of the present application, a number of improvements and replacements can be made, these improvements and replacements should also be considered as the protection scope of the present application.
Claims
1. A method for outdoor screen hot spot monitoring based on multi-source parameters, characterized in that, The application comprises the following steps: acquiring the operating temperature parameter of the outdoor screen and setting a first cutting strategy according to the operating temperature parameter; setting a plurality of monitoring sub-regions according to the first cutting strategy, and generating a diagnosis data packet of each monitoring sub-region according to auxiliary monitoring data; generating a hot spot risk value of each monitoring sub-region according to all diagnosis data packets, and judging whether to generate a warning instruction according to all hot spot risk values.
2. The multi-source parameter based outdoor screen hot spot monitoring method of claim 1, wherein, When setting the first cutting strategy according to the operating temperature parameter, the application comprises the following steps: presetting a plurality of monitoring points; acquiring the operating temperature parameter of each monitoring point and generating an operating value of each monitoring point; generating a segmentation evaluation value c according to all operating values; c=[ βi*Y1(i)*(s i -s') 2 ]; Wherein θ1 is the number of monitoring points; β i is the weight factor of the ith monitoring point; s i is the operating value of the ith monitoring point; s' is a preset operating value threshold; Y1(i) is a selection coefficient; if (s i -s') > 0, Y1(i) = 0; if (s i -s') < 0, Y1(i) = 1; setting the first cutting strategy according to the segmentation evaluation value c, wherein the first cutting strategy comprises the area of a single monitoring sub-region.
3. The multi-source parameter based outdoor screen hot spot monitoring method of claim 2, wherein, When generating the diagnosis data packet of each monitoring sub-region, the application comprises the following steps: Establish a monitoring sub-region sequence A, A=(a1, a2…a…) i …a n ), where a i Let n be the i-th monitoring sub-region; n is the number of monitoring sub-regions. acquiring auxiliary monitoring data; According to the monitoring sub-region sequence A, a is set in turn i Target sub-region; extracting associated monitoring data of a target sub-region in the auxiliary monitoring data based on a segmentation model; preprocessing the associated monitoring data of the target sub-region based on a time sequence model, and generating a diagnosis data packet of the target sub-region according to the preprocessing result; generating the diagnosis data packet of each monitoring sub-region in turn.
4. The multi-source parameter based outdoor screen hot spot monitoring method of claim 3, wherein, When generating the hot spot risk value of each monitoring sub-region, the application comprises the following steps: According to the monitoring sub-region sequence A, a is set in turn i To be diagnosed sub-region; acquiring the diagnosis data packet of a to-be-diagnosed sub-region; establishing a plurality of diagnosis time nodes according to the diagnosis data packet; A time node series T for diagnosis is established, T=(t1, t2…t i …t m ), wherein t i is the i-th time node for diagnosis based on time series; and m is the number of time nodes for diagnosis. generating an abnormal risk value of each diagnosis time node; Establish an abnormal risk value sequence P, P=(p1, p2…p i …p m ), where p i Let be the abnormal risk value at the i-th diagnostic time point; m is the number of diagnostic time points; generating a hot spot risk value f of the target sub-region according to all abnormal risk values; f=[ η i *v i ]; wherein θ2 is the number of risk characteristic indicators; η i is the impact factor of the i-th risk characteristic indicator; vi is the reference value of the i-th risk characteristic indicator based on the abnormal risk value sequence P; generating the hot spot risk value of each monitoring sub-region in turn. A series of hot spot risk values F, F = (f1, f2…f i …f n ), is established, where f i is the hot spot risk value of the i-th monitoring sub-region.
5. The multi-source parameter based outdoor screen hot spot monitoring method of claim 4, wherein, When generating the abnormal risk value of each diagnosis time node, the application comprises the following steps: According to the diagnosis time node sequence T, t is set in turn i Target time node; generating an abnormal risk value p of a target time node; p=e1*Q1*[ µ i *Y2(i)*(d i -d' 1i )]+e2*Q2*[ µ i *Y3(i)*(d i -d' 2i )]; wherein e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; and Q2 is a preset second fixed coefficient; is the number of data categories; µ i is an influence factor of the ith data category; d i is a real-time reference value of the ith data category at a target time node; d' 1i is a safety threshold of the ith data category; d' 2i is a real-time reference value of the ith data category at a last diagnosis time node of the target time node; Y2(i) is a selection coefficient; if (d i -d' 1i )>0, Y2(i)=1; if (d i -d' 1i )<0, Y2(i)=0; Y3(i) is a selection coefficient; if (d i -d' 2i )>0, Y3(i)=1; if (d i -d' 2i )<0, Y3(i)=0; generating the abnormal risk value of each diagnosis time node in turn.
6. The multi-source parameter based outdoor screen hot spot monitoring method of claim 4, wherein, When judging whether to generate a warning instruction according to all hot spot risk values, the application comprises the following steps: presetting a first hot spot risk value threshold F1 and a second hot spot risk value threshold F2, and F1 < F2; If f i F2, set the i-th monitoring sub-region as a risk sub-region, and generate a first-level warning instruction of the risk sub-region; If F1 < f i F2, set the i-th monitoring sub-region as an abnormal sub-region, and generate a secondary diagnosis strategy for the abnormal sub-region. If f i <F1, set the i-th monitoring sub-region as a normal sub-region.
7. The multi-source parameter based outdoor screen hot spot monitoring method of claim 6, wherein, the first warning instruction comprises the following steps: selecting a target risk sub-region in turn according to all risk sub-regions; setting a second segmentation strategy of the target risk sub-region; establishing a plurality of hot spot sub-regions in the target risk sub-region according to the second segmentation strategy; generating a second diagnosis packet of each hot spot sub-region in turn; generating a hot spot diagnosis result of the target risk sub-region according to all second diagnosis packets.
8. The multi-source parameter based outdoor screen hot spot monitoring method of claim 7, wherein, The second diagnosis strategy comprises the following steps: aggregating all monitoring sub-regions according to a monitoring sub-region sequence A; generating an associated model according to the aggregation result; selecting a target abnormal sub-region in turn according to all abnormal sub-regions; generating an environmental similarity value of the target abnormal sub-region and each risk sub-region according to the associated model; generating an auxiliary diagnosis model of the target abnormal sub-region according to all environmental similarity values; establishing a plurality of second sub-regions in the target abnormal sub-region according to the auxiliary diagnosis model; generating a warning evaluation value of each second sub-region in turn; judging whether to generate a second warning instruction of each second sub-region according to the warning evaluation value.
9. The multi-source parameter based outdoor screen hot spot monitoring method of claim 8, wherein, When judging whether to generate a second warning instruction of each second sub-region, the application comprises the following steps: establishing a second sub-region sequence W; W = (w1, w2…wn), wherein w i …w n1 ), wherein w i is the i-th secondary sub-region within the target abnormal sub-region; n1 is the number of secondary sub-regions within the target abnormal sub-region; setting an auxiliary diagnosis period; w is set in turn i targeting a secondary sub-region; acquiring a feedback data packet of the target second sub-region in the auxiliary diagnosis period, and generating a warning evaluation value h according to the feedback data packet; h=[ µ i *k i ]; wherein, is the number of data categories; µ i is the impact factor of the i-th data category; k i is the similarity value of the i-th data category generated according to the auxiliary diagnosis model and the feedback data packet; presetting a warning evaluation value threshold H1; If h > H1, a secondary early warning instruction of the target secondary sub-region is generated.
10. A multi-source parameter based outdoor screen hot spot monitoring system, adopting the multi-source parameter based outdoor screen hot spot monitoring method according to any one of claims 1-9, characterized in that, The method comprises the steps of: The central control unit is configured to acquire an operating temperature parameter of the outdoor screen. The central control unit is further configured to set a first cutting strategy according to the operating temperature parameter. The monitoring unit comprises a plurality of monitoring sub-modules. The monitoring unit is configured to collect the operating temperature parameter and auxiliary monitoring data of the outdoor screen. The central control unit comprises: A first processing module configured to set a plurality of monitoring sub-regions according to the first cutting strategy. A second processing module configured to generate a diagnosis data packet of each monitoring sub-region according to the auxiliary monitoring data. A first diagnosis module configured to generate a hot spot risk value of each monitoring sub-region according to all the diagnosis data packets, and determine whether to generate a warning instruction according to all the hot spot risk values.