Potential fault judgment method and system for intelligent meeting place

Abstract

The embodiment of the invention provides a potential fault judgment method and system for an intelligent meeting place, and belongs to the technical field of operation and maintenance of the intelligent meeting place. The judgment method comprises the following steps: acquiring sensing data of a meeting place in a preset time period; calculating a deviation difference between the sensing data and a preset sensor data model; whether the deviation difference is larger than or equal to a preset deviation threshold value or not is judged; when it is judged that the deviation difference is larger than or equal to the deviation threshold value, standardization operation is conducted on the sensing data; calculating the sensing data after the standardization operation and carrying out similarity matching operation; and determining a potential fault of the current meeting place according to a result of the similarity matching operation. According to the judgment method and system, a two-time judgment mode is combined, on one hand, invalid matching judgment is avoided, and on the other hand, the multi-dimension diagnosis process of the sensing data is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance of intelligent conference venues, and in particular to a potential fault judgment method and system for intelligent conference venues. Background Art

[0002] In the current operation and management of smart venues, the application of sensor technology has become very common, and they play an important role in monitoring the environment and ensuring safety. These sensor networks cover every corner of the venue and monitor various indicators such as temperature, humidity, smoke, gas concentration, etc. in real time. However, although the application of sensor technology has brought convenience and progress to venue management, the existing monitoring system has a series of problems that cannot be ignored.

[0003] In general, existing monitoring systems often rely on the value of a single sensor to determine abnormal situations. Although this method has achieved preliminary automated monitoring, the logic is relatively simple and lacks a comprehensive judgment mechanism. For example, when a smoke sensor detects an abnormal reading, the system may directly judge it as a fire hazard and issue an alarm without considering other possibilities, such as a large number of smokers nearby or the normal operation of the kitchen. In this case, the system cannot distinguish whether it is a real fire or an increase in smoke caused by other reasons, resulting in a false alarm.

[0004] False alarms not only cause unnecessary panic and confusion, but also reduce people's trust in system alarms and affect the efficiency of emergency response. In addition to false alarms, this single judgment logic may also lead to missed alarms. If a sensor fails to detect a real danger due to a malfunction or improper sensitivity setting, the system will be unable to respond, which is particularly dangerous when an emergency such as an initial fire is discovered.

[0005] Furthermore, due to the reliance on data from a single sensor, existing systems have limitations in handling complex situations. In actual venue environments, various factors are often intertwined, and a simple single indicator is difficult to fully and accurately reflect the on-site situation. This limitation not only affects the accuracy of monitoring, but also reduces the efficiency and quality of security management. Summary of the invention

[0006] The purpose of the embodiments of the present invention is to provide a potential fault judgment method and system for an intelligent conference room, wherein the judgment method and system can improve the monitoring efficiency of the intelligent conference room for potential faults.

[0007] In order to achieve the above object, an embodiment of the present invention provides a potential fault judgment method for a smart venue, comprising:

[0008] Obtain sensor data of the venue within a preset time period;

[0009] Calculating the deviation between the sensor data and a preset sensor data model;

[0010] Determining whether the deviation difference is greater than or equal to a preset deviation threshold;

[0011] In the case where it is determined that the deviation difference is greater than or equal to the deviation threshold, performing a normalization operation on the sensing data;

[0012] Calculate the sensor data after the normalization operation to perform similarity matching operation;

[0013] A potential fault of the current venue is determined according to the result of the similarity matching operation.

[0014] Optionally, obtaining sensor data of the venue within a preset time period includes:

[0015] Preset a plurality of sensors in the venue, wherein the sensors include at least one of a temperature sensor, a light intensity sensor, a humidity sensor, a power consumption sensor, and a gas sensor;

[0016] Receiving sampling values ​​of the sensor at a plurality of predetermined sampling moments;

[0017] A sensing data matrix is ​​constructed according to the sampling values.

[0018] Optionally, calculating the deviation between the sensor data and a preset sensor data model includes:

[0019] The deviation difference is calculated according to formula (1) to formula (4),

[0020]

[0021] Δs ij =δ|s ij -s min |,s ij min , (2)

[0022] Δs ij =ε|s ij -s max |,s ij >s max , (3)

[0023] Δs ij =0,s min ≤s ij ≤s max , (4)

[0024] Where L is the deviation, m is the number of sensor categories, n is the number of sensors in one category, Δs ij ​represents the deviation value of the jth sensor of the i-th category, δ and ε are the preset influencing factors, and 2δ<ε, s ij is the sampling value of the jth sensor of the i-th category.

[0025] Optionally, performing a standardization operation on the sensor data includes:

[0026] Constructing a value fluctuation range of each type of sensor in the sensor data;

[0027] Dividing the numerical fluctuation interval into a plurality of interval segments;

[0028] Numbering the interval segments;

[0029] A number corresponding to each sampling value in the sensor data is determined according to the interval segment and the number.

[0030] Optionally, the numerical fluctuation interval is divided into a plurality of interval segments, including:

[0031] The length of the interval segment is determined according to formula (5) and formula (6):

[0032]

[0033] D=∑d i , (6)

[0034] Among them, d i is the length of the i-th interval segment, Δd is the reference length value, and D is the total length of the numerical fluctuation interval.

[0035] Optionally, calculating the sensor data after the normalization operation to perform a similarity matching operation includes:

[0036] respectively calculating the similarity between the sensor data after the normalization operation and each fault matrix;

[0037] Determine whether a similarity difference between the maximum value and the second maximum value of the similarity is greater than or equal to a preset similarity threshold;

[0038] When it is determined that the similarity difference is greater than or equal to the similarity threshold, the fault type corresponding to the fault matrix with the greatest similarity is taken as a result of similarity matching.

[0039] Optionally, calculating the sensor data after the normalization operation to perform a similarity matching operation includes:

[0040] When it is determined that the similarity difference is less than the similarity threshold, the similarity difference between each two adjacent similarities is calculated in order according to the principle of similarity from large to small;

[0041] Starting from the maximum similarity, selecting the fault matrices corresponding to the similarity differences that are continuously smaller than the similarity threshold;

[0042] The fault type corresponding to the selected fault matrix is ​​taken as the result of similarity matching.

[0043] Optionally, respectively calculating the similarity between the sensor data after the normalization operation and each fault matrix includes:

[0044] The similarity is calculated according to formula (7):

[0045]

[0046] Wherein, S is the similarity, is the jth sampling value of the i-th sensor in the sensor data after the normalization operation, is the j-th element of the i-th row in the fault matrix c, m represents the number of sensor categories, and n represents the number of sensors in one category.

[0047] On the other hand, an embodiment of the present invention further provides a potential fault judgment system for a smart venue, wherein the judgment system includes a processor, and the processor is configured to execute any of the judgment methods described above.

[0048] Through the above technical solution, the embodiment of the present invention provides a potential fault judgment method and system for a smart venue, which determines whether the sensor data has diagnostic value by setting the deviation difference, and realizes the diagnosis process of the sensor by similarity calculation. Compared with the prior art, the judgment method and system provided by the present invention combines two judgment methods, which, on the one hand, avoids invalid matching judgments, and on the other hand, realizes the diagnosis process of multiple dimensions of sensor data.

[0049] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0051] Figure 1 is a flow chart of a potential fault determination method for a smart venue according to an embodiment of the present invention;

[0052] Figure 2 is one of the schematic diagrams of a conference venue according to an embodiment of the present invention;

[0053] Figure 3 is a second schematic diagram of a conference venue according to an embodiment of the present invention;

[0054] Figure 4 is a flow chart of a method of standardized operation according to one embodiment of the present invention;

[0055] Figure 5 is a flowchart of a method for similarity matching operation according to one embodiment of the present invention. DETAILED DESCRIPTION

[0056] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0057] like Figure 1 FIG. 1 is a flow chart of a potential fault determination method for a smart conference room according to an embodiment of the present invention. Figure 1 The determination method may include the following steps:

[0058] In step S10, sensor data of the venue within a preset time period is obtained;

[0059] In step S11, the deviation difference between the sensor data and the preset sensor data model is calculated;

[0060] In step S12, it is determined whether the deviation difference is greater than or equal to a preset deviation threshold;

[0061] In step S13, when it is determined that the deviation difference is greater than or equal to the deviation threshold, a normalization operation is performed on the sensor data;

[0062] In step S14, the sensor data after the normalization operation is calculated to perform a similarity matching operation;

[0063] In step S15, the potential fault of the current venue is determined according to the result of the similarity matching operation.

[0064] In this Figure 1 In the judgment method shown, step S10 can be used to obtain sensor data of the venue within a preset time period. The sensor data can be obtained by sampling multiple sensors preset in the venue. The venue can be a variety of structural forms known to those skilled in the art. In one example of the present invention, the venue can be, for example, Figure 2 and / or Figure 3As shown. The specific type of the sensor may include but is not limited to temperature sensors, light intensity sensors, humidity sensors, power consumption sensors, gas sensors and other sensor types known to those skilled in the art. The sensor data may be directly received from the sensor at a plurality of predetermined sampling moments. In addition, in order to facilitate the processing of the sensor data, the step S10 may also construct a sensor data matrix based on the received sampling values. Further, the sensor data matrix may be, for example, represented by the following formula (8):

[0065]

[0066] Among them, S is the sensor data matrix, s 11 、s 1n 、s ij 、s m1 and mn is the sampling value.

[0067] Step S11 can be used to calculate the deviation between the sensor data and the preset sensor data model. The deviation can be used to evaluate whether the current sensor data needs further diagnosis. Since the subsequent diagnostic algorithm is relatively complex, if each sensor data matrix needs to be diagnosed, it will cause a large load pressure on the server. Therefore, in this embodiment, the deviation can be set to avoid invalid activation of the diagnostic algorithm. For the deviation, although it can be a variety of forms known to those skilled in the art. However, in one example of the present invention, considering that the deviation itself needs to be combined with data from multiple sensors, and the data of each sensor itself, the degree of influence on whether diagnosis is needed is different in the two cases of being below a reasonable range and above a reasonable range. In this example, the step S11 can be to use the following formulas (1) to (4) to calculate the deviation,

[0068]

[0069] Δs ij =δ|s ij -s min |,s ij min , (2)

[0070] Δs ij =ε|s ij -s max |,s ij >s max , (3)

[0071] Δs ij =0,s min ≤s ij ≤s max , (4)​

[0072] Where L is the deviation, , represents the number of sensor categories, m represents the number of sensors in one category, and Δs ij represents the deviation value of the jth sensor of the i-th category, δ and ε are the preset influencing factors, and 2δ<ε, s ij is the sampling value of the jth sensor of the i-th category.

[0073] Step S12 can be used to determine whether the deviation difference is greater than or equal to a preset deviation threshold. If it is greater than the deviation threshold, it means that the sensor data has further diagnostic value, so steps S13 to S15 can be executed for further diagnosis. Otherwise, the group of sensor data is filtered to reduce the load on the server.

[0074] Step S13 can be used to perform a standardization operation on the sensor output. The specific method of the standardization operation can be various forms known to those skilled in the art. Considering that the sampling values ​​of each sensor in the sensor data have different dimensions, different ranges of readings, and different fluctuation ranges, in one example of the present invention, it can be adopted as follows Figure 4 The standardization operation is performed by the method shown in

[0075] In step S20, a value fluctuation range of each type of sensor in the sensor data is constructed;

[0076] In step S21, the value fluctuation interval is divided into a plurality of interval segments;

[0077] In step S22, the interval segments are numbered;

[0078] In step S23, the number corresponding to each sampling value in the sensor data is determined according to the interval segment and the number.

[0079] In this Figure 4 In the method shown, step S20 can be used to construct a value fluctuation range for each type of sensor in the sensor data. The value fluctuation range can be used to represent the possible fluctuation range of the conventional measurement value of the sensor (it can be between the maximum range and the minimum range, or it can be a reasonable value range of the pre-defined sensor).

[0080] Step S21 can be used to divide the value fluctuation interval into multiple intervals. However, if the value fluctuation interval is directly divided into multiple intervals, it will be difficult to distinguish the characteristic values, that is, the characteristic values ​​are likely to fall into the same interval after division. Therefore, in an example of the present invention, step S21 can be determined according to formula (5) and formula (6).

[0081]

[0082] D=∑d i , (6)

[0083] Among them, d i is the length of the i-th interval segment, Δd is the reference length value, and D is the total length of the numerical fluctuation interval.

[0084] Step S22 may be used to number the intervals. The specific method of numbering may be various forms known to those skilled in the art. For example, the numbering method may be, for example, starting from the lower limit of the interval and increasing the value upwards in sequence. Specifically, the numbering sequence may be, for example, 0.1 to 0.9.

[0085] Step S14 may be used to calculate the sensor data after the normalization operation to perform a similarity matching operation. In this embodiment, the similarity matching operation may be in various forms known to those skilled in the art. In one example of the present invention, the similarity matching operation may include: Figure 5 The method shown in Figure 5 In the similarity matching operation, the similarity matching operation may include the following steps:

[0086] In step S30, the similarity between the normalized sensor data and each fault matrix is ​​calculated. Further, the similarity can be calculated according to formula (7):

[0087]

[0088] Among them, S is the similarity, is the jth sampling value of the i-th sensor in the sensor data after the normalization operation, is the j-th element of the i-th row in the fault matrix c, m represents the number of sensor categories, and n represents the number of sensors in one category.

[0089] In step S31, it is determined whether the similarity difference between the maximum value and the second maximum value of the similarity is greater than or equal to a preset similarity threshold;

[0090] In step S32, when it is determined that the similarity difference is greater than or equal to the similarity threshold, the fault type corresponding to the fault matrix with the greatest similarity is taken as the result of similarity matching;

[0091] In step S33, when it is determined that the similarity difference is less than the similarity threshold, the similarity difference between every two adjacent similarities is calculated in order according to the principle of similarity from large to small;

[0092] In step S34, starting from the maximum similarity, the fault matrices corresponding to the similarity differences that are continuously smaller than the similarity threshold are selected;

[0093] In step S35, the fault type corresponding to the selected fault matrix is ​​taken as the result of similarity matching.

[0094] On the other hand, an embodiment of the present invention further provides a potential fault judgment system for a smart venue, the judgment system comprising a processor, the processor being configured to execute any of the judgment methods described above. Specifically, the judgment method may include the following steps:

[0095] In step S10, sensor data of the venue within a preset time period is obtained;

[0096] In step S11, the deviation difference between the sensor data and the preset sensor data model is calculated;

[0097] In step S12, it is determined whether the deviation difference is greater than or equal to a preset deviation threshold;

[0098] In step S13, when it is determined that the deviation difference is greater than or equal to the deviation threshold, a normalization operation is performed on the sensor data;

[0099] In step S14, the sensor data after the normalization operation is calculated to perform a similarity matching operation;

[0100] In step S15, the potential fault of the current venue is determined according to the result of the similarity matching operation.

[0101] In this Figure 1 In the judgment method shown, step S10 can be used to obtain sensor data of the venue within a preset time period. The sensor data can be obtained by sampling multiple sensors preset in the venue. The venue can be a variety of structural forms known to those skilled in the art. In one example of the present invention, the venue can be, for example, Figure 2 and / or Figure 3 As shown. The specific type of the sensor may include but is not limited to temperature sensors, light intensity sensors, humidity sensors, power consumption sensors, gas sensors and other sensor types known to those skilled in the art. The sensor data may be directly received from the sensor at a plurality of predetermined sampling moments. In addition, in order to facilitate the processing of the sensor data, the step S10 may also construct a sensor data matrix based on the received sampling values. Further, the sensor data matrix may be, for example, represented by the following formula (8):

[0102]

[0103] Among them, S is the sensor data matrix, s 11 、s 1n 、s ij 、sm1 and mn is the sampling value.

[0104] Step S11 can be used to calculate the deviation between the sensor data and the preset sensor data model. The deviation can be used to evaluate whether the current sensor data needs further diagnosis. Since the subsequent diagnostic algorithm is relatively complex, if each sensor data matrix needs to be diagnosed, it will cause a large load pressure on the server. Therefore, in this embodiment, the deviation can be set to avoid invalid activation of the diagnostic algorithm. For the deviation, although it can be a variety of forms known to those skilled in the art. However, in one example of the present invention, considering that the deviation itself needs to be combined with data from multiple sensors, and the data of each sensor itself, the degree of influence on whether diagnosis is needed is different in the two cases of being below a reasonable range and above a reasonable range. In this example, the step S11 can be to use the following formulas (1) to (4) to calculate the deviation,

[0105]

[0106] Δs ij =δ|s ij -s min |,s ij min , (2)

[0107] Δs ij =s|s ij -s max |,s ij >s max , (3)

[0108] Δs ij =0,s min ≤s ij ≤s max , (4)

[0109] Where L is the deviation, m is the number of sensor categories, n is the number of sensors in one category, Δs ij represents the deviation value of the jth sensor of the i-th category, δ and ε are the preset influencing factors, and 2δ<ε, s ij is the sampling value of the jth sensor of the i-th category.

[0110] Step S12 can be used to determine whether the deviation difference is greater than or equal to a preset deviation threshold. If it is greater than the deviation threshold, it means that the sensor data has further diagnostic value, so steps S13 to S15 can be executed for further diagnosis. Otherwise, the group of sensor data is filtered to reduce the load on the server. ​

[0111] Step S13 can be used to perform a standardization operation on the sensor output. The specific method of the standardization operation can be various forms known to those skilled in the art. Considering that the sampling values ​​of each sensor in the sensor data have different dimensions, different ranges of readings, and different fluctuation ranges, in one example of the present invention, it can be adopted as follows Figure 4 The standardization operation is performed by the method shown in

[0112] In step S20, a value fluctuation range of each type of sensor in the sensor data is constructed;

[0113] In step S21, the value fluctuation interval is divided into a plurality of interval segments;

[0114] In step S22, the interval segments are numbered;

[0115] In step S23, the number corresponding to each sampling value in the sensor data is determined according to the interval segment and the number.

[0116] In this Figure 4 In the method shown, step S20 can be used to construct a value fluctuation range for each type of sensor in the sensor data. The value fluctuation range can be used to represent the possible fluctuation range of the conventional measurement value of the sensor (it can be between the maximum range and the minimum range, or it can be a reasonable value range of the pre-defined sensor).

[0117] Step S21 can be used to divide the value fluctuation interval into multiple intervals. However, if the value fluctuation interval is directly divided into multiple intervals, it will be difficult to distinguish the characteristic values, that is, the characteristic values ​​are likely to fall into the same interval after division. Therefore, in an example of the present invention, step S21 can be determined according to formula (5) and formula (6).

[0118]

[0119] D=∑d i , (6)

[0120] Among them, d i is the length of the i-th interval segment, Δd is the reference length value, and D is the total length of the numerical fluctuation interval.

[0121] Step S22 may be used to number the intervals. The specific method of numbering may be various forms known to those skilled in the art. For example, the numbering method may be, for example, starting from the lower limit of the interval and increasing the value upwards in sequence. Specifically, the numbering sequence may be, for example, 0.1 to 0.9.

[0122] Step S14 may be used to calculate the sensor data after the normalization operation to perform a similarity matching operation. In this embodiment, the similarity matching operation may be in various forms known to those skilled in the art. In one example of the present invention, the similarity matching operation may include: Figure 5 The method shown in Figure 5 In the similarity matching operation, the similarity matching operation may include the following steps:

[0123] In step S30, the similarity between the normalized sensor data and each fault matrix is ​​calculated. Further, the similarity can be calculated according to formula (7):

[0124]

[0125] Among them, S is the similarity, is the jth sampling value of the i-th sensor in the sensor data after the normalization operation, is the j-th element of the i-th row in the fault matrix c, m represents the number of sensor categories, and n represents the number of sensors in one category.

[0126] In step S31, it is determined whether the similarity difference between the maximum value and the second maximum value of the similarity is greater than or equal to a preset similarity threshold;

[0127] In step S32, when it is determined that the similarity difference is greater than or equal to the similarity threshold, the fault type corresponding to the fault matrix with the greatest similarity is taken as the result of similarity matching;

[0128] In step S33, when it is determined that the similarity difference is less than the similarity threshold, the similarity difference between every two adjacent similarities is calculated in order according to the principle of similarity from large to small;

[0129] In step S34, starting from the maximum similarity, the fault matrices corresponding to the similarity differences that are continuously smaller than the similarity threshold are selected;

[0130] In step S35, the fault type corresponding to the selected fault matrix is ​​taken as the result of similarity matching.

[0131] Through the above technical solution, the embodiment of the present invention provides a potential fault judgment method and system for a smart venue, which determines whether the sensor data has diagnostic value by setting the deviation difference, and realizes the diagnosis process of the sensor by similarity calculation. Compared with the prior art, the judgment method and system provided by the present invention combines two judgment methods, which, on the one hand, avoids invalid matching judgments, and on the other hand, realizes the diagnosis process of multiple dimensions of sensor data.

[0132] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0136] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0137] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0138] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0139] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0140] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A potential fault judgment method for a smart venue, characterized in that: The determination method comprises: Obtain sensor data of the venue within a preset time period; Calculating the deviation between the sensor data and a preset sensor data model; Determining whether the deviation difference is greater than or equal to a preset deviation threshold; In the case where it is determined that the deviation difference is greater than or equal to the deviation threshold, performing a normalization operation on the sensing data; Calculate the sensor data after the normalization operation to perform similarity matching operation; The potential fault of the current venue is determined according to the result of the similarity matching operation.

2. The determination method according to claim 1, characterized in that: Obtain sensor data of the venue within a preset time period, including: Preset a plurality of sensors in the venue, wherein the sensors include at least one of a temperature sensor, a light intensity sensor, a humidity sensor, a power consumption sensor, and a gas sensor; Receiving sampling values ​​of the sensor at a plurality of predetermined sampling moments; A sensing data matrix is ​​constructed according to the sampling values.

3. The determination method according to claim 1, characterized in that: Calculating the deviation between the sensor data and a preset sensor data model includes: The deviation difference is calculated according to formula (1) to formula (4), Δs ij =δ|s ij -s min |,s ij <s min , (2) Δs ij =ε|s ij -s max |,s ij >s max , (3) Δs ij =0,s min ≤s ij ≤s max , (4) Where L is the deviation, m is the number of sensor categories, n is the number of sensors in one category, Δs ij represents the deviation value of the jth sensor of the i-th category, δ and ε are the preset influencing factors, and 2δ<ε, s ij is the sampling value of the jth sensor of the i-th category.

4. The determination method according to claim 1, characterized in that: The sensor data is subjected to a standardization operation, including: Constructing a value fluctuation range of each type of sensor in the sensor data; Dividing the numerical fluctuation interval into a plurality of interval segments; Numbering the interval segments; A number corresponding to each sampling value in the sensor data is determined according to the interval segment and the number.

5. The determination method according to claim 4, characterized in that: The numerical fluctuation interval is divided into a plurality of interval segments, including: The length of the interval segment is determined according to formula (5) and formula (6): D=∑d i , (6) Among them, d i is the length of the i-th interval segment, Δd is the reference length value, and D is the total length of the numerical fluctuation interval.

6. The determination method according to claim 1, characterized in that: Calculate the sensor data after the normalization operation to perform similarity matching operations, including: respectively calculating the similarity between the sensor data after the normalization operation and each fault matrix; Determine whether a similarity difference between the maximum value and the second maximum value of the similarity is greater than or equal to a preset similarity threshold; When it is determined that the similarity difference is greater than or equal to the similarity threshold, the fault type corresponding to the fault matrix with the greatest similarity is taken as a result of similarity matching.

7. The determination method according to claim 6, characterized in that: Calculate the sensor data after the normalization operation to perform similarity matching operations, including: When it is determined that the similarity difference is less than the similarity threshold, the similarity difference between each two adjacent similarities is calculated in order according to the principle of similarity from large to small; Starting from the maximum similarity, selecting the fault matrices corresponding to the similarity differences that are continuously smaller than the similarity threshold; The fault type corresponding to the selected fault matrix is ​​taken as the result of similarity matching.

8. The determination method according to claim 6, characterized in that: The similarity between the sensor data after the normalization operation and each fault matrix is ​​calculated respectively, including: The similarity is calculated according to formula (7): Wherein, S is the similarity, is the jth sampling value of the i-th sensor in the sensor data after the normalization operation, is the j-th element of the i-th row in the fault matrix c, m represents the number of sensor categories, and n represents the number of sensors in one category.

9. A potential fault judgment system for a smart venue, characterized in that: The judgment system comprises a processor, and the processor is configured to execute the judgment method according to any one of claims 1 to 8.

Images