A method, system, computer device and storage medium for reasoning about alarm position

Abstract

The present invention provides a method for reasoning the location of an alarm, comprising the steps of: using preset screening conditions to preliminarily screen a source set of alarm locations from different alarm sources; calculating the probability matrix of each alarm location corresponding to the source set according to the source set of the alarm location to obtain a reference source of the alarm location; calculating the probability of an inference value of the alarm location based on the reference source of the alarm location and historical real alarm data; solving the maximum probability of the inference value of the alarm location, thereby obtaining the inference value of the alarm location. The present invention defines a high accuracy condition, selects several reference locations from the alarm sources that meet the high accuracy condition, and infers the optimal alarm location through a given objective function.

Description

Technical Field

[0001] The present invention relates to the field of fire fighting technology, and in particular to an alarm position reasoning method, system, computer equipment and storage medium. Background Art

[0002] Common alarm information mostly comes from landline or mobile phone alarms, IoT sensing device alarms and SMS alarms, however, the case location information contained in these alarm messages is often inaccurate, which brings great inconvenience to fire rescue. It not only consumes a lot of time, manpower and material resources, but also misses the best rescue time, which can easily cause a lot of property losses and casualties.

[0003] Currently, there are two ways to obtain the location information of an emergency: one is to obtain the positioning information of landline or mobile phone, or the location information provided by the person who reported the incident. This information is often very different from the specific location of the actual incident. Other location information comes from the location information provided by the alarm of the Internet of Things sensing device, or the GPS information provided by the SMS alarm. This type of information is usually accurate and reliable. When a fire occurs, it is often accompanied by alarm information from different sources. The various information are mixed, which brings great inconvenience to firefighting and rescue.

[0004] Therefore, a method is needed to quickly infer and locate the actual location of a case from police information from various sources. Summary of the invention

[0005] The purpose of the present invention is to provide a police situation location reasoning method, system, computer equipment and storage medium, which can quickly infer and locate the actual location of the case from police situation information from various sources.

[0006] The technical solution provided by the present invention is as follows:

[0007] The present invention provides a method for reasoning about a warning position, comprising the steps of:

[0008] Use preset screening conditions to preliminarily screen the source set of alarm locations from different alarm sources;

[0009] According to the source set of the alarm position, a probability matrix corresponding to each alarm position in the source set is calculated to obtain a reference source of the alarm position;

[0010] Calculate the probability of the alarm position inference value based on the reference source of the alarm position and the historical real alarm data;

[0011] The maximum probability of the inference value of the alarm position is solved to obtain the inference value of the alarm position.

[0012] In some embodiments, before using the preset screening conditions to preliminarily screen the source set of the alarm location from different alarm sources, the method further includes:

[0013] Define the preset filter conditions as:

[0014]

[0015] Among them, D j is the alarm location of the jth alarm source; E(D j ) is the mean; Var(D j ) is the variance; ε1,ε2, are all positive real numbers.

[0016] In some embodiments, the use of preset screening conditions to preliminarily screen the source set of alarm locations from different alarm sources specifically includes:

[0017] Based on the preset screening conditions, the source set of the alarm location is obtained, specifically:

[0018]

[0019] Among them, S base is the source set of the alarm location; j is different alarm sources.

[0020] In some embodiments, the calculating of the probability matrix of each alarm location corresponding to the source set of the alarm location to obtain the reference source of the alarm location specifically includes:

[0021] Based on the source set of the alarm location, define the set S(n):

[0022]

[0023] Where n is a natural number less than or equal to j; p j (0) is the probability value that the alarm position corresponding to the j alarm source is the correct position; p k (0) is the probability value that the alarm location corresponding to the k alarm source is the correct location;

[0024] According to the probability value of each alarm source in the set S(n), the reference source of the alarm location is obtained.

[0025] In some embodiments, the calculating the probability of the alarm position inference value based on the reference source of the alarm position and the historical real alarm data specifically includes:

[0026] For the historical real alarm data z m , compute the solution to the optimization problem:

[0027]

[0028]

[0029] Introducing the actual parameter λ m , m=1,2,…,M; if the optimization problem has a solution, the solution of the optimization problem is defined as the effective position superposition parameter, recorded as

[0030] According to the effective position superposition parameters Constitute a statistical distribution, set as the sample value of the random variable L, with P L (·), p L (·) represent the probability distribution function and density function of the random variable L respectively;

[0031] Among them, the probability of the alarm position inference value is P{D1=s 1r ,D2=s 2r ,…,D l =s lr ,…,D J =s Jr}.

[0032] In some embodiments, solving the maximum probability of the alarm position inference value, thereby obtaining the inference value of the alarm position, specifically includes:

[0033] The alarm location is:

[0034] The difference between the alarm position and the alarm position of each reference source is:

[0035]

[0036] Among them, at all current alarm source locations , select as a reference source;

[0037] Based on the probability of the alarm position inference value of the reference source, the objective function of the optimization problem is calculated as:

[0038]

[0039] Assume that the solution to the optimization problem is:

[0040]

[0041] Then the inference value of the alarm position is:

[0042]

[0043] In some embodiments, a warning location reasoning system is also provided, including:

[0044] A screening module, used to preliminarily screen a source set of alarm locations from different alarm sources using preset screening conditions;

[0045] A first calculation module is used to calculate the probability matrix of each alarm position corresponding to the source set according to the source set of the alarm position, so as to obtain the reference source of the alarm position;

[0046] A second calculation module is used to calculate the probability of the alarm position inference value based on the reference source of the alarm position and the historical real alarm data;

[0047] The acquisition module is used to solve the maximum probability of the alarm position inference value, so as to obtain the inference value of the alarm position.

[0048] In some embodiments, a preset module is further included, specifically used for:

[0049] The default filter conditions are:

[0050]

[0051] Among them, D j is the alarm location of the jth alarm source; E(D j ) is the mean; Var(D j ) is the variance; ε1,ε2, are all positive real numbers;

[0052] Based on the preset screening conditions, the source set of the alarm location is obtained, specifically:

[0053]

[0054] Among them, S base is the source set of the alarm location; j is different alarm sources.

[0055] A computer device comprising:

[0056] A memory for storing running programs;

[0057] The processor is used to execute the running program stored in the memory to implement the operations performed by the alarm location reasoning method.

[0058] A storage medium stores at least one instruction, which is loaded and executed by a processor to implement the operations performed by the alarm location reasoning method.

[0059] The present invention provides a method, system, computer device and storage medium for reasoning about the location of an alarm, which have at least the following technical effects:

[0060] The present invention provides a combined position reasoning method, defines a high accuracy condition, selects several reference positions from alarm sources that meet the high accuracy condition, and infers the optimal alarm position through a given objective function. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The preferred implementation scheme will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present solution.

[0062] Figure 1 It is a flowchart of a method for reasoning the location of an alarm situation according to an embodiment of the present invention;

[0063] Figure 2 is a schematic diagram of a method for reasoning the location of an alarm situation according to an embodiment of the present invention;

[0064] Figure 3 is a schematic diagram of a warning situation location reasoning device according to an embodiment of the present invention;

[0065] Figure 4 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0067] In order to simplify the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0068] The present invention provides a method for reasoning about a warning position, comprising the steps of:

[0069] S101 uses preset screening conditions to preliminarily screen the source set of alarm locations from different alarm sources.

[0070] For example, for a new alarm, there may be alarm information (location information) from several different sources. The current location information of the alarm is obtained from landline or mobile phone positioning information, or location information provided by the person who reported the alarm, or location information provided by an Internet of Things sensing device alarm, or GPS information provided by a text message alarm.

[0071] In this embodiment, by pre-setting filtering conditions, the locations of different sources are filtered with high accuracy, and several inference reference sources are selected in the filtering set. By maximizing the objective function, a reliable location information can be inferred, providing strong technical support for firefighting and rescue operations, and effectively improving the efficiency of firefighting and rescue.

[0072] S102 calculates the probability matrix of each alarm location corresponding to the source set according to the source set of the alarm location, so as to obtain the reference source of the alarm location.

[0073] For a new alarm situation, the alarm locations of J different sources are represented as The difference between any two positions is expressed as Where j, l = 1, 2, ..., J. From this definition, we know that s jl =s lj , and when j = l, s jl =0.

[0074] Let’s consider two aspects:

[0075] 1. Considering the jth alarm source, its alarm location A j The probability that it is the correct position is p j (s jj )=p j (0), other alarm source locations The exact probability is p j (s jl ).

[0076] 2. From the alarm location Consider the location of each alarm source from the location The difference value is s jl ,s jl The value in the probability density function of each alarm source is p j (s jl ).

[0077] From this, we can get the probability table of alarm source and alarm location

[0078]

[0079] In the above table, the jth row represents the probability density function p of the jth alarm source.j (·) At each alarm location The value on the lth column represents the lth alarm position In the probability density function p of each alarm source j Obviously, the value of the cell in the jth row and jth column on the diagonal of the table is p j (0).

[0080] S103 calculates the probability of the alarm location inference value based on the reference source of the alarm location and the historical real alarm data.

[0081] S104 solves the maximum probability of the alarm position inference value, thereby obtaining the inference value of the alarm position.

[0082] The present invention provides a combined position reasoning method, defines a high accuracy condition, selects several reference positions from the alarm sources that meet the high accuracy condition, and infers the optimal alarm position through a given objective function.

[0083] In one embodiment, before using the preset screening conditions to preliminarily screen the source set of the alarm location from different alarm sources, the method further includes:

[0084] Define the preset filter conditions as:

[0085]

[0086] Among them, E(D j ) is the mean; Var(D j ) is the variance; ε1,ε2, are all positive real numbers.

[0087] In one embodiment, the use of preset screening conditions to preliminarily screen the source set of alarm locations from different alarm sources specifically includes:

[0088] Based on the preset screening conditions, the source set of the alarm location is obtained, specifically:

[0089]

[0090] Among them, S base is the source set of the alarm location; j is different alarm sources.

[0091] In one embodiment, the calculating of the probability matrix of each alarm location corresponding to the source set of the alarm location to obtain the reference source of the alarm location specifically includes:

[0092] Based on the source set of the alarm location, define the set S(n):

[0093]

[0094] Where n is a natural number less than or equal to j; p j (0) is the probability value that the alarm position corresponding to the j alarm source is the correct position; p k (0) is the probability value that the alarm location corresponding to the k alarm source is the correct location;

[0095] According to the probability value of each alarm source in the set S(n), the reference source of the alarm location is obtained.

[0096] In one embodiment, the calculating the probability of the alarm position inference value based on the reference source of the alarm position and the historical real alarm data specifically includes:

[0097] For the historical real alarm data z m , compute the solution to the optimization problem:

[0098]

[0099]

[0100] Introducing the actual parameter λ m , m=1,2,…,M; if the optimization problem has a solution, the solution of the optimization problem is defined as the effective position superposition parameter, recorded as

[0101] According to the effective position superposition parameters Constitute a statistical distribution, set as the sample value of the random variable L, with P L (·), p L (·) represent the probability distribution function and density function of the random variable L respectively;

[0102] Among them, the probability of the alarm position inference value is P{D1=s 1r ,D2=s 2r ,…,D l =s lr ,…,D J =s Jr}.

[0103] In one embodiment, solving the maximum probability of the alarm position inference value, thereby obtaining the inference value of the alarm position, specifically includes:

[0104] The alarm location is:

[0105] The difference between the alarm position and the alarm position of each reference source is:

[0106]

[0107] Among them, at all current alarm source locations , select as a reference source;

[0108] Based on the probability of the alarm position inference value of the reference source, the objective function of the optimization problem is calculated as:

[0109]

[0110] Assume that the solution to the optimization problem is:

[0111]

[0112] Then the inference value of the alarm position is:

[0113]

[0114] In one embodiment, the present invention provides a method for reasoning about a warning location, specifically comprising:

[0115] For a new alarm situation, the alarm locations of J different sources are represented as The difference between any two positions is expressed as Where j, l = 1, 2, ..., J. From this definition, we know that s jl =s lj , and when j = l, s jl =0.

[0116] Exemplarily, two aspects are considered below:

[0117] 3. Considering the jth alarm source, its alarm location A j The probability that it is the correct position is p j (s jj )=p j (0), other alarm source locations The exact probability is p j (s jl ).

[0118] 4. From the alarm location Consider the location of each alarm source from the location The difference value is s jl ,s jl The value in the probability density function of each alarm source is p j (s jl ).

[0119] From this, we can get the probability table of alarm source and alarm location

[0120]

[0121]

[0122] In the above table, the jth row represents the probability density function p of the jth alarm source. j (·) At each alarm location The value on the lth column represents the lth alarm position In the probability density function p of each alarm source j Obviously, the value of the cell in the jth row and jth column on the diagonal of the table is p j (0).

[0123] The combined position reasoning method in this embodiment specifically includes:

[0124] 1. Alarm location reference source selection.

[0125] All positions must meet high accuracy conditions.

[0126] The high accuracy conditions are defined as follows:

[0127]

[0128] In the above formula, ε1, ε2, are all positive real numbers. The location accuracy of the jth alarm source can be obtained by the mean E(D j ) and variance Var(D j ) Comprehensive measurement. Mean E(D j ) is smaller and the variance Var(D j ) is smaller, the more accurate the location of the alarm source is; the mean E(D j ) is larger and the variance Var(D j ) is smaller, the greater the systematic deviation of the location of the alarm source; the mean E(D j ) is larger and the variance Var(D j ) is larger, the lower the accuracy of the alarm location is.

[0129] Among them, the set of alarm sources that meet the high accuracy condition is denoted as S base ,Right now:

[0130]

[0131] Define the following set S(n), where n is a natural number not greater than J, including:

[0132]

[0133]

[0134] …

[0135]

[0136] From the above definition, we can see that the alarm source p in S(1) j (0) value, which is all S base The alarm source in p j (0) the largest value; the alarm source p in S(2) j (0) value, which is all S base The alarm source in p j (0) is the second largest value; similarly, the alarm source p in S(n) is j (0) value, which is all S base The alarm source in p j The reference source for position reasoning is selected from S(1), S(2), …, S(n).

[0137] The following is an exemplary method for selecting a reference source for alarm location reasoning. Consider selecting two reference sources for reasoning in total. If there are two alarm sources in S(1), then these two are directly selected; if there is only one alarm source in S(1), then this alarm source is selected and an alarm source in S(2) is selected at the same time. The two reference sources for alarm location reasoning are respectively denoted as Introducing the actual parameter λ m , where m = 1, 2, ..., M. For all historical real alarm data z m , find the solution to the following optimization problem:

[0138]

[0139]

[0140] If the above optimization problem has a solution, then its solution defines the effective position superposition parameter, denoted as All valid position overlay parameters Constitute a statistical distribution, set as the sample value of the random variable L, with P L (·), p L (·) represent the probability distribution function and density function of the random variable L respectively.

[0141] 2. Position reasoning.

[0142] As mentioned above, at all current alarm source locations , select As a reference source for inference, the inference address is represented as The difference between the inferred address and the location of each alarm source is:

[0143]

[0144] Among them, the probability of the alarm position inference value is: P{D1=s 1r ,D2=s 2r ,…,D l =s lr ,…,D J =s Jr}.

[0145] The probability of the inference value of the alarm location is calculated as follows:

[0146]

[0147] When the probability of the above alarm location inference value is the largest, its corresponding λ value and It can be used as the inference address. Therefore, the objective function of the optimization problem is:

[0148]

[0149] Assume that the solution to the above optimization problem is λ opt :

[0150]

[0151] Then the inference value of the alarm position is

[0152]

[0153] Among them, the entire police situation location reasoning flow chart is as follows Figure 2 As shown, a method for reasoning the location of an alarm provided in this embodiment includes:

[0154] S201 Alarm location source collection.

[0155] S202 obtains an alarm source set S that meets high accuracy conditions base .

[0156] S203 Calculate the alarm position probability matrix p j (0).

[0157] S204 alarm location reasoning reference source.

[0158] S205 calculates the optimal solution of the joint probability.

[0159] S206 Calculate the alarm position inference value.

[0160] In this embodiment, the following contents may also be included:

[0161] Prerequisites:

[0162] Alarm sources are independent of each other.

[0163] When considering the problem of multiple alarm sources, different alarm sources detect the same alarm situation through different and independent perception methods.

[0164] For example, the alarm person observes the fire flame and smoke conditions and reports the alarm based on his / her subjective understanding and judgment; the smoke sensor reports the alarm based on the smoke excitation signal received; the thermal sensing device reports the alarm based on the temperature change signal. Different alarm sources discover and report the alarm according to independent working mechanisms.

[0165] In this case, the covariance term Cov(D j ,D l )=0, which is a reasonable simplification of the problem. However, if different alarm sources obtain alarm addresses based on the calculation method of mutual correlation and mutual influence, the covariance term Cov(D j ,D l ) is not 0, in which case the model needs to be adjusted.

[0166] High accuracy conditions:

[0167] The above formula (1) defines the high accuracy condition of the alarm source.

[0168] Among them, E(D l )≤ε1 requires that the mean of the difference between the alarm position and the actual alarm position is less than a certain threshold ε1. If this condition is not met, it means that the mean of the difference is too large and the accuracy is too low.

[0169] Var(D l )≤ε2 requires that the variance of the difference between the alarm location and the actual alarm location is less than a certain threshold ε2. If this condition is not met, even if the alarm source meets E(D l )≤ε1, which also shows that the accuracy of this source is not stable enough and is prone to large errors.

[0170] The alarm source data must be sufficient and the proportion of all alarm data must be higher than a certain threshold. If it is lower than this threshold, even if the alarm source meets E(D l )≤ε1,Var(D l )≤ε2. It may also be that the alarm data from this source is not sufficient and the error is not reflected in the historical alarm location statistics.

[0171] At the same time, E(D l )≤ε1,Var(D l )≤ε2,E(D l )≤ε1, The source of the alarm.

[0172] On the one hand, it shows that the locations of these sources are not much different from the actual alarm locations in a statistical sense. On the other hand, it also shows that the data is sufficient and more stable and reliable. Therefore, the accuracy of these alarm sources is relatively high.

[0173] Valid position parameter stacking:

[0174] The alarm location inference reference source is selected from S(1), S(2), …, S(n). There are 2 times in total. The optimization problem defined by formulas (4) and (5) is used for all historical real alarm data z m A series of effective position superposition parameters are obtained

[0175] It should be noted that since formula (5) requires that the difference between the inferred position value and the true position value must be less than a certain threshold θ, if the effective position superposition parameter The small number indicates that the optimization problems defined by formulas (4) and (5) have few solutions.

[0176] To solve this problem, we can consider strengthening the high accuracy condition and select smaller ε1, ε2 and larger Threshold.

[0177] But if you still can't get more valid position superposition parameters This means that the accuracy of all current alarm sources is not high.

[0178] In this case, even if the inference position can be obtained according to formulas (9) and (10), However, the accuracy of the inferred position cannot be guaranteed. The number is an important factor in objectively measuring the effectiveness and accuracy of the locations of all current alarm sources.

[0179] This embodiment screens the locations of different sources with high accuracy, selects several inference reference sources in the screening set, and infers reliable location information by maximizing the objective function, thereby providing strong technical support for firefighting and rescue operations and effectively improving the efficiency of firefighting and rescue.

[0180] In one embodiment, Figure 3As shown, the present invention also provides a warning position reasoning system, comprising:

[0181] The screening module 101 is used to preliminarily screen the source set of the alarm location from different alarm sources by using preset screening conditions.

[0182] The first calculation module 102 is used to calculate the probability matrix of each alarm location corresponding to the source set according to the source set of the alarm location, so as to obtain the reference source of the alarm location.

[0183] The second calculation module 103 is used to calculate the probability of the alarm position inference value based on the reference source of the alarm position and the historical real alarm data.

[0184] The acquisition module 104 is used to solve the maximum probability of the alarm position inference value, so as to obtain the inference value of the alarm position.

[0185] In one embodiment, a preset module is further included, which is specifically used to:

[0186] The default filter conditions are:

[0187]

[0188] Among them, E(D j ) is the mean; Var(D j ) is the variance; ε1,ε2, are all positive real numbers.

[0189] Based on the preset screening conditions, the source set of the alarm location is obtained, specifically:

[0190]

[0191] Among them, S base is the source set of the alarm location; j is different alarm sources.

[0192] In addition, if Figure 4 As shown, the present invention also provides a computer device, including a memory 100 and a processor 200, the memory 100 is used to store running programs, and the processor 200 is used to execute the running programs stored in the memory to implement the operations performed by the alarm location inference method described in any of the embodiments.

[0193] Specifically, the computer device may further include a communication interface 300 , a communication bus 400 and an input / output interface 500 , wherein the processor 200 , the memory 100 , the input / output interface 500 and the communication interface 300 communicate with each other via the communication bus 400 .

[0194] The communication bus 400 is a circuit that connects the elements described and realizes transmission between these elements. For example, the processor 200 receives commands from other elements through the communication bus 400, decrypts the received commands, and performs calculations or data processing according to the decrypted commands. The memory 100 may include program modules, such as kernels, middleware, application programming interfaces (APIs) and applications. The program modules may be composed of software, firmware or hardware, or at least two of them. The input / output interface 500 forwards commands or data entered by the user through input and output devices (such as sensors, keyboards, touch screens). The communication interface 300 connects the computer device to other network devices, user devices, and networks. For example, the communication interface 300 can be connected to the network by wire or wireless to connect to other external network devices or user devices. Wireless communication may include at least one of the following: wireless fidelity (WiFi), Bluetooth (BT), near field communication technology (NFC), global satellite positioning system (GPS) and cellular communication, etc. Wired communication may include at least one of the following: Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), RS-232, etc. The network may be a telecommunication network and a communication network. The communication network may be a computer network, the Internet, the Internet of Things, or a telephone network. The computer device may be connected to the network via the communication interface 300, and the protocol used by the computer device and other network devices for communication may be supported by at least one of an application, an application programming interface (API), a middleware, a kernel, and a communication interface.

[0195] In addition, the present invention also provides a storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by the processor to implement the operation performed by the alarm location reasoning method described in any of the embodiments. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a read-only compact disk (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device. They can be implemented with program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0196] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

Claims

1. A method for reasoning about the location of an alarm, characterized in that: Includes steps: Use preset screening conditions to preliminarily screen the source set of alarm locations from different alarm sources; According to the source set of the alarm position, a probability matrix corresponding to each alarm position in the source set is calculated to obtain a reference source of the alarm position; Based on the reference source of the alarm position and the historical real alarm data, the probability of the alarm position inference value is calculated, specifically including: for the historical real alarm data Compute the solution to an optimization problem: Among them, θ is the threshold; the real parameter λ is introduced m , m=1,2,…,M; if the optimization problem has a solution, the solution of the optimization problem is defined as the effective position superposition parameter, recorded as The reference source for location reasoning is According to the effective position superposition parameters Constitute a statistical distribution, set as the sample value of the random variable L, with P L (·), p L (·) represent the probability distribution function and density function of the random variable L respectively; Among them, the probability of the alarm position inference value is P{D1=s 1r ,D2=s 2r ,…,D l =s lr ,…,D J =s Jr }; Solving the maximum probability of the alarm position inference value, thereby obtaining the inference value of the alarm position, specifically including: The difference between the inferred alarm position and the alarm position of each reference source is: Among them, at all current alarm source locations , select As a reference source; the inferred alarm position is expressed as Based on the probability of the alarm position inference value of the reference source, the objective function of the optimization problem is calculated as: Assume that the solution to the optimization problem is: Then the inference value of the alarm position is:

2. A method for reasoning the location of an alarm according to claim 1, characterized in that: Before the method of using the preset screening conditions to preliminarily screen the source set of the alarm location from different alarm sources, it also includes: Define the preset filter conditions as: Among them, D j is the alarm location of the jth alarm source; E(D j ) is the mean; Var(D j ) is the variance; ε1,ε2, are all positive real numbers.

3. A method for reasoning about the location of an alarm situation according to claim 2, characterized in that: The preset screening conditions are used to preliminarily screen the source set of the alarm location from different alarm sources, specifically including: Based on the preset screening conditions, the source set of the alarm location is obtained, specifically: Among them, S base is the source set of the alarm location; j is different alarm sources.

4. A method for reasoning about the location of an alarm situation according to claim 3, characterized in that: The step of calculating the probability matrix of each alarm position corresponding to the source set of the alarm position to obtain the reference source of the alarm position specifically includes: Based on the source set of the alarm location, define the set S(n): Where n is a natural number less than or equal to J; p j (0) is the probability value that the alarm position corresponding to the j alarm source is the correct position; p k (0) is the probability value that the alarm location corresponding to the k alarm source is the correct location; According to the probability value of each alarm source in the set S(n), the reference source of the alarm location is obtained.

5. A warning location reasoning system, characterized in that: A method for reasoning about the location of an alarm situation as claimed in any one of claims 1 to 4 is applied, comprising: A screening module, used to preliminarily screen a source set of alarm locations from different alarm sources using preset screening conditions; A first calculation module is used to calculate the probability matrix of each alarm position corresponding to the source set according to the source set of the alarm position, so as to obtain the reference source of the alarm position; The second calculation module is used to calculate the probability of the alarm position inference value based on the reference source of the alarm position and the historical real alarm data; specifically including: for the historical real alarm data Compute the solution to an optimization problem: Introducing the actual parameter λ m , m=1,2,…,M; if the optimization problem has a solution, the solution of the optimization problem is defined as the effective position superposition parameter, recorded as The reference source for location reasoning is According to the effective position superposition parameters Constitute a statistical distribution, set as the sample value of the random variable L, with P L (·), p L (·) represent the probability distribution function and density function of the random variable L respectively; Among them, the probability of the alarm position inference value is P{D1=s 1r ,D2=s 2r ,…,D l =s lr ,…,D J =s Jr }; The acquisition module is used to solve the maximum probability of the alarm position inference value, so as to obtain the inference value of the alarm position, which specifically includes: The alarm location is: The difference between the alarm position and the alarm position of each reference source is: Among them, at all current alarm source locations , select as a reference source; Based on the probability of the alarm position inference value of the reference source, the objective function of the optimization problem is calculated as: Assume that the solution to the optimization problem is: Then the inference value of the alarm position is:

6. The alarm location reasoning system according to claim 5, characterized in that: Also includes preset modules specifically for: The default filter conditions are: Among them, D j is the alarm location of the jth alarm source; E(D j ) is the mean; Var(D j ) is the variance; ε1,ε2, are all positive real numbers; Based on the preset screening conditions, the source set of the alarm location is obtained, specifically: Among them, S base is the source set of the alarm location; j is different alarm sources.

7. A computer device, characterized in that: include: A memory for storing running programs; The processor is used to execute the running program stored in the memory to implement the operations performed by the alarm location reasoning method as described in any one of claims 1 to 4.

8. A storage medium, characterized in that: The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the operations performed by the alarm location reasoning method as described in any one of claims 1 to 4.

Images