Leakage point identification method and device, computer equipment, storage medium and program product
By performing Poisson verification of industrial chain data, the leakage points in the operating situation of the industrial chain are identified, which solves the problem of inaccurate identification of leakage points in the existing technology, and achieves more efficient and accurate identification of leakage points.
Patent Information
- Application Number
- CN202411570086.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2025-02-14
AI Technical Summary
The method of identifying the leakage points of the industrial chain operating situation in the prior art is not accurate enough.
By collecting industrial chain data and performing Poisson verification, the leakage points in the operating trend of the industrial chain are identified. Poisson verification uses statistical data to analyze the number of target events, actual frequency and expected frequency, determine the Poisson value and degree of offset, and then determine the rejection domain and missing point identification results.
It improves the accuracy of missing point recognition, can predict the operating trend of the industrial chain more effectively, simplifies the implementation process of the method, and improves the efficiency of missing point recognition.
Smart Images
Figure CN119442033A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of distributed storage technology, and in particular to a leakage identification method, device, computer equipment, storage medium and program product. Background Art
[0002] In the context of intelligent manufacturing, the world is competing to develop big data in the manufacturing industry. At present, industrial data accumulated in the R&D, design, production, management, sales and operation and maintenance services of enterprises are becoming the core driving force of intelligent manufacturing and are increasingly becoming the key engine for accelerating the development of the digital economy. Accurate collection, analysis and processing of industrial data are necessary means to ensure the stable operation of the industrial chain, and the identification of leakage points in the operation of the industrial chain is particularly important.
[0003] However, in related technologies, the method for identifying loopholes in the operation status of the industrial chain is not accurate. Summary of the invention
[0004] Based on this, it is necessary to provide a leakage identification method, device, computer equipment, storage medium and program product that can identify leakage points in the operation status of the industrial chain in the intelligent manufacturing industry in response to the above-mentioned technical problems.
[0005] In a first aspect, the present application provides a leak point identification method, comprising:
[0006] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0007] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0008] The leakage point identification method described in the above embodiment obtains leakage point identification results by collecting industrial chain data and performing Poisson check on the industrial chain data, wherein the industrial chain data includes data related to the operation status of the industrial chain. This method can identify leakage points in the operation status of the industrial chain, and then can predict the operation status of the industrial chain. Moreover, the above method performs leakage point identification by means of Poisson check, which provides a leakage point identification method and can also improve the accuracy of leakage point identification.
[0009] In one embodiment, performing a Poisson check on the industrial chain data to obtain a leak point identification result includes:
[0010] Performing statistical analysis on the industrial chain data to determine statistical data on the occurrence of target events in the industrial chain data; the statistical data includes the number of occurrences of the target event, the actual frequency, the expected frequency and the significance level;
[0011] A Poisson check is performed on the target event according to the statistical data to obtain a leakage point identification result.
[0012] The method described in the above embodiment can realize leakage point identification in the industrial chain based only on the statistical data of the target event, and the statistical data can be obtained by analyzing the industrial chain data, so the method is simple and easy to implement, which can improve the efficiency of leakage point identification; in addition, the above method realizes leakage point identification by means of Poisson check, which can improve the accuracy of leakage point identification.
[0013] In one embodiment, performing a Poisson check on the target event according to the statistical data to obtain a leak point identification result includes:
[0014] According to the number of occurrences, actual frequency and expected frequency of the target event, a Poisson check is performed on the target event to obtain a Poisson value and a degree of deviation of the target event;
[0015] Determining a rejection region according to the degree of deviation and significance level of the target event;
[0016] The leak point identification result is determined according to the rejection region and the Poisson value.
[0017] The method described in the above embodiment realizes missed point detection by setting a rejection domain and evaluating the relationship between the Poisson value corresponding to the target event and the rejection domain, thereby improving the accuracy of missed detection.
[0018] In one embodiment, performing a Poisson check on the target event according to the number of occurrences, the actual frequency, and the expected frequency of the target event to obtain the Poisson value and the degree of deviation of the target event includes:
[0019] Determine the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency;
[0020] The degree of deviation of the target event is determined according to the expected frequency and the actual frequency of occurrence of the target event.
[0021] The method described in the above embodiment counts the degree of deviation of the target event, estimates the distance between the target event and the expected value, and evaluates the degree of deviation of the target event based on the distance between the target event and the expected value, and then identifies whether the target event is a leakage event based on the degree of deviation of the target event, thereby improving a method for identifying leakage events by analyzing the degree of deviation of the target event.
[0022] In one embodiment, determining the leak point identification result according to the rejection region and the Poisson value includes:
[0023] If the Poisson value falls into the rejection region, the target event is determined to be a leak event;
[0024] If the Poisson value does not fall into the rejection region, the target event is determined to be a non-missing event.
[0025] The method described in the above embodiment provides a Poisson verification method assuming Poisson distribution by setting a rejection region, which can improve the efficiency and accuracy of Poisson verification, and further improve the efficiency and accuracy of leak detection.
[0026] In one embodiment, the method further comprises:
[0027] Preprocessing the industrial chain data to obtain processed industrial chain data; the preprocessing includes at least one of noise processing, consistency checking, data labeling, format conversion, redundancy processing, merging processing and missing value processing;
[0028] The Poisson check is performed on the industrial chain data to obtain a leak point identification result, including:
[0029] A Poisson check is performed on the processed industrial chain number to obtain a leak point identification result.
[0030] In the method described in the above embodiment, data preprocessing is very important in the above Poisson verification process, which can improve the quality and availability of data, reduce the complexity of data, and improve the efficiency and accuracy of data analysis and mining. Moreover, after data preprocessing, mathematical methods can be used to make different data features have different units and dimensions. Standardization can eliminate such dimensional differences, so that different features can be directly compared and calculated, so as to improve the accuracy of leak point identification based on the preprocessed data in the later stage.
[0031] In a second aspect, the present application also provides a leakage point identification device, comprising:
[0032] A collection module, used to collect industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0033] The identification module is used to perform Poisson check on the industrial chain data to obtain leakage point identification results.
[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0035] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0036] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0038] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0039] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0040] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0041] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0042] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0043] The above leakage point identification method, device, computer equipment, storage medium and program product obtain leakage point identification results by collecting industrial chain data and performing Poisson check on the industrial chain data, wherein the industrial chain data includes relevant data on the operation status of the industrial chain. This method can realize the identification of leakage points in the operation status of the industrial chain, and then can predict the operation status of the industrial chain. Moreover, the above method performs leakage point identification by means of Poisson check, which provides a leakage point identification method while also improving the accuracy of leakage point identification. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0045] Figure 1 A diagram showing an application environment of a leak point identification method in an embodiment;
[0046] Figure 2 One of the flowcharts of the leak point identification method in one embodiment;
[0047] Figure 3 The second flowchart of the leakage point identification method in one embodiment;
[0048] Figure 4The third flowchart of the leakage point identification method in one embodiment;
[0049] Figure 5 is a schematic diagram of a Poisson distribution curve in one embodiment;
[0050] Figure 6 The fourth flowchart of the leak point identification method in one embodiment;
[0051] Figure 7 FIG5 is a fifth flow chart of a leak point identification method in an embodiment;
[0052] Figure 8 A schematic diagram of the structure of a leak point identification system in one embodiment;
[0053] Fig. 9 A schematic diagram of the structure of a leakage point identification device in one embodiment;
[0054] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0056] At present, the world is competing to develop big data in the manufacturing industry under the background of intelligent manufacturing. At present, the industrial data accumulated in the links of enterprise R&D design, production and manufacturing, business management, sales and operation and maintenance services are becoming the core driving force of intelligent manufacturing and are increasingly becoming the key engine for accelerating the development of the digital economy.
[0057] The leakage point identification method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the collection device 102 can communicate with the computer device 104 in a wired or wireless manner. The collection device 102 includes multiple collection devices, each of which is used to collect various types of industrial chain data, for example, industrial chain data includes supply chain data, quality control data, process optimization data, energy management data, log data, industrial production data and industrial external data, etc., and various types of data can be collected using corresponding types of collection devices. Among them, the computer device 104 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The computer device 104 can also be a server, and it is an independent physical server, or it can be a server cluster or distributed system composed of multiple physical servers, or it can be a cloud server that provides cloud computing services.
[0058] In an exemplary embodiment, Figure 2 As shown, a leak point identification method is provided, which is applied to Figure 1 Taking the computer device in the example as an example, the method includes:
[0059] S201, collect industry chain data.
[0060] Among them, industrial chain data includes data related to the operation status of the industrial chain. Industrial chain data includes supply chain data, quality control data, process optimization data, energy management data, log data, industrial production data, external industry data and other data at different stages of the industrial chain.
[0061] In the present application embodiment, Figure 1As shown, one method is that various types of collection devices on the industrial chain can collect industrial chain data of each industrial chain stage in real time, and then various types of collection devices can transmit the collected data to computer equipment. After the computer equipment receives the data collected by various types of collection devices, it can process the industrial chain data, perform Poisson check, etc.; optionally, the computer equipment can also receive the data collected by various types of collection devices, store the received industrial chain data, and wait until a mechanism that triggers the processing and verification of the industrial chain data appears, the computer equipment processes the industrial chain data, performs Poisson check, etc.; optionally, the computer equipment can also actively obtain the corresponding type of industrial chain data from various types of collection devices when a mechanism that triggers the processing and verification of the industrial chain data appears, and process the industrial chain data, perform Poisson check, etc.
[0062] Optionally, when computer equipment collects various types of industrial chain data, it can access the data to the database. Common data transmission methods include text data import, data recognition scanning of paper documents, and data access through library tables / FTP / interfaces, etc. Attention should be paid to data quality and data format during data collection to ensure data accuracy and consistency. Data quality and data format can provide reference and support for subsequent data preprocessing.
[0063] S202, perform Poisson check on the industrial chain data to obtain leakage point identification results.
[0064] Among them, the leakage point identification result includes the existence of leakage point events in the operation status of the industrial chain, and includes the number of leakage point events; or, includes the absence of leakage point events in the operation status of the industrial chain.
[0065] In an embodiment of the present application, when the computer device collects industrial chain data based on the aforementioned steps, it can first determine the potential leakage events that may exist in the industrial chain operation situation corresponding to the current industrial chain data, and extract the relevant industrial chain data corresponding to various potential leakage events from the industrial chain data according to the type of potential leakage events to be detected, and perform a Poisson check on the relevant industrial chain data corresponding to each potential leakage event to obtain a Poisson check result for each potential leakage event, and then determine whether each potential leakage event is a real leakage based on the Poisson check result for each potential leakage event, thereby realizing leakage identification, and record the number of real leakage events to obtain a leakage identification result including the identified real leakage events and the number of leakage events.
[0066] The leakage point identification method described in the above embodiment obtains leakage point identification results by collecting industrial chain data and performing Poisson check on the industrial chain data, wherein the industrial chain data includes data related to the operation status of the industrial chain. This method can identify leakage points in the operation status of the industrial chain, and then can predict the operation status of the industrial chain. Moreover, the above method performs leakage point identification by means of Poisson check, which provides a leakage point identification method and can also improve the accuracy of leakage point identification.
[0067] In one embodiment, an implementation of the above S202 is provided, such as Figure 3 As shown, the above S202 "performs Poisson check on industrial chain data to obtain leakage point identification results" includes:
[0068] S301, performing statistical analysis on the industrial chain data to determine statistical data of target events in the industrial chain data.
[0069] Among them, the statistical data include the number of target event occurrences, actual frequency, expected frequency and significance level. The number of target event occurrences refers to the number of times the target event occurs in each observation, the actual frequency refers to the frequency of the number of target event occurrences in multiple observations, and the expected frequency refers to the theoretical frequency of the number of target event occurrences in multiple observations. The target event is any type of event to be analyzed in the operation status of the entire industrial chain, which is used to describe low-probability events. For example, the target event is a low-probability event that the state of the enterprise in the industrial chain changes and the complementary industrial chain cannot be formed; the target event can also be a low-probability event that an alarm occurs in the industrial chain within a quarter. The Poisson test is used to verify whether the probability of occurrence of such low-probability events is very low and very stable, and there is no influence relationship between the size of the frequency of occurrence.
[0070] In the embodiment of the present application, when the computer device obtains the industrial chain data related to the target event, the industrial chain data related to the target event can be statistically analyzed to determine the number of occurrences of the target event X(t) in the observation of the industrial chain operation situation within the preset time period t, and such observation is repeated m times to obtain the number of observations; for example, observation is made once every three days, a total of 5 times, and the number of occurrences of the target event A each time is X(t), and Ai={X(t)=i}{i=0,1,2,....,n} can be recorded as the event that the target event A occurs i times in one observation. The frequencies of A0, A1, ...., An in m observations are m0, m1, ...., mn respectively. For example, m1 represents the frequency of A1 in m observations, that is, the proportion of the occurrence of the target event A once in m observations. For example, assuming that the number of times the target event A appears once is 2 times and m is 10 times, the corresponding frequency is m1=2 / 10. It should be noted that the frequencies involved in the above process are actual frequencies; the expected frequencies can be determined based on a pre-set or theoretical Poisson distribution. The significance level is an evaluation parameter used to evaluate whether an event follows a Poisson distribution. Computer equipment can obtain the significance level based on empirical values, or determine the significance level based on a theoretical Poisson distribution.
[0071] S302, performing Poisson check on the target event according to the statistical data to obtain a leak point identification result.
[0072] In the embodiment of the present application, when the computer device obtains the statistical data of the occurrence of the target event, it can further determine whether the target event obeys the Poisson distribution by analyzing these statistical data and referring to the Poisson distribution principle. Since the Poisson distribution can test whether the probability of the event is very low and stable, and there is no influence relationship between the frequency of the target event, the leakage event can be accurately identified according to the result of whether it obeys the Poisson distribution; based on this, when the above-mentioned computer device determines that the target event obeys the Poisson distribution, it means that the target event is not a leakage event; if it is determined that the target event does not obey the Poisson distribution, it means that the target event is a leakage event, so as to realize the identification or detection of leakage events. It should be noted that the above process is a method for the computer device to identify the target event. According to this method, the computer device can identify all the events that may exist in the operation situation of the entire industrial chain as target events in turn, so as to determine the number of real leakage events and real leakage events included in the operation situation of the entire industrial chain.
[0073] The method described in the above embodiment can realize leakage point identification in the industrial chain based only on the statistical data of the target event, and the statistical data can be obtained by analyzing the industrial chain data, so the method is simple and easy to implement, which can improve the efficiency of leakage point identification; in addition, the above method realizes leakage point identification by means of Poisson check, which can improve the accuracy of leakage point identification.
[0074] In one embodiment, an implementation of the above S302 is provided, that is, the above S302 "performs a Poisson check on the target event according to the statistical data to obtain a leak point identification result", such as Figure 4 As shown, including:
[0075] S401, performing a Poisson check on the target event according to the number of occurrences of the target event, the actual frequency and the expected frequency, to obtain the Poisson value and the degree of deviation of the target event.
[0076] In an embodiment of the present application, the computer device can calculate the Poisson value of the target event based on the number of occurrences of the target event and the actual frequency, and determine the degree of deviation of the target event based on the expected frequency and the actual frequency of the target event. Exemplary explanation: The computer device can first assume that the target event obeys the Poisson distribution, that is, when the observation is repeated m times, only a finite number of different values can be observed. The hypothesis we need to test is whether the number of occurrences of the target event (marked by X(t)) obeys the Poisson distribution (marked by P(λ)), where P is an unknown parameter. The hypothesis to be tested X(t) ~ p(λ) is converted into the following hypothesis (see equation (1)):
[0077] (1);
[0078] Where λ is an unknown parameter that can be determined using maximum likelihood estimation, for example, see equation (2);
[0079] (2);
[0080] Among them, Ai represents the event that the target event A occurs i times; Pi represents the Poisson value; X(t) represents the number of times the target event A occurs; m represents the number of observations, i represents the number of times; mi represents the actual frequency of the target event. Substituting the maximum likelihood estimate of λ and λ^ into the above relationship (1), the Poisson value Pi of the target event can be estimated.
[0081] When the computer device obtains the expected frequency and actual frequency of the target event, the deviation degree of the target event can be calculated based on the expected frequency and the actual frequency. Specifically, it can be calculated using the following relationship (3):
[0082] (3);
[0083] in, It indicates the degree of deviation of the target event and also the chi-square value of the occurrence of the target event; Indicates the actual frequency of the target event; represents the Poisson value of the target event; Indicates the expected frequency. It represents the maximum number of times the target event Ai occurs in m observations.
[0084] S402: Determine a rejection region according to the deviation degree and significance level of the target event.
[0085] In the embodiment of the present application, when the computer device obtains the deviation degree and significance level of the target event, the rejection region W can be determined using the following relationship (4):
[0086] (4);
[0087] in, represents the rejection region; Indicates the degree of deviation of the target event; represents the significance level; It represents the maximum number of times the target event Ai occurs in m observations.
[0088] S403, determining the leak point identification result according to the rejection region and the Poisson value.
[0089] Among them, the rejection region is used to evaluate whether the target event follows the Poisson distribution.
[0090] In the embodiment of the present application, when the computer device determines the rejection domain, it can determine whether the target event is a leak event based on the Poisson value of the target event and the relationship between the Poisson value and the rejection domain. Specifically, the computer device can determine whether the Poisson value of the target event is located in the rejection domain. If it is determined that the Poisson value is located in the rejection domain, the target event is determined to be a leak event; if it is determined that the Poisson value is not located in the rejection domain, the target event is determined to be a non-leak event. It should be noted that the embodiment of the present application only illustrates the leak identification process of the target event, and the leak identification process for other events is the same, except that the rejection domains corresponding to different events can be different or the same.
[0091] Optionally, the rejection region can be determined by the following equation (5) in addition to the equation (4) above:
[0092] (5);
[0093] in, represents the significance level; represents the Poisson value of the target event. For example, to test the null hypothesis, if the Poisson value of the target event is , indicating that it is not significant, then the null hypothesis cannot be rejected at this time, and the statistical data of the target event follows the Poisson distribution. , indicating that it is significant, then the original hypothesis is rejected and the statistical data of the target event does not obey the Poisson distribution.
[0094] Exemplarily, by executing the above Poisson check method, the following Poisson check table 1 can be obtained:
[0095] Poisson test table 1
[0096]
[0097] Optionally, when the computer device verifies and determines that the target event follows a Poisson distribution, a Poisson distribution curve can be generated according to the Poisson distribution or statistical data of the target event, and an expected Poisson distribution curve can be generated according to the expected Poisson distribution or expected data (e.g., expected frequency), and the two curves can be displayed on the current display interface of the computer device, see Figure 5 As shown, the user can analyze the target event through the curve. It should be noted that only the Poisson distribution curve corresponding to the target event is shown here. When the computer device calculates the Poisson distribution curves of multiple events, the Poisson distribution curves of all events in the operation status of the entire industrial chain can be displayed on the display interface, so that the user can evaluate the risk level of the operation status of the entire industrial chain by observing the Poisson distribution curves of all events.
[0098] The method described in the above embodiment provides a Poisson verification method assuming Poisson distribution by setting a rejection region, which can improve the efficiency and accuracy of Poisson verification, and further improve the efficiency and accuracy of leak detection.
[0099] In one embodiment, a method for preprocessing industrial chain data is also provided, namely Figure 2 The method described in the embodiment, such as Figure 6 As shown, the method includes:
[0100] S203, pre-processing the industrial chain data to obtain processed industrial chain data.
[0101] Among them, preprocessing includes at least one of noise processing, consistency check, data labeling, format conversion, redundancy processing, merging processing and missing value processing. Missing value processing is used to identify and process missing values in data, such as filling, deleting or interpolating. Noise processing is used to smooth data to eliminate noise or outliers. Data deduplication is used to delete or merge duplicate data rows or columns. Data consistency check is used to ensure the correctness of data format, spelling and logic. Merging processing is used to integrate data from different sources into a unified data set. Redundancy processing is used to deal with redundancy and conflict, such as deleting or integrating redundant data, and resolving conflicts and inconsistencies between data. Feature encoding is used to convert non-numeric data (such as categorical data) into numerical data. Feature scaling is used to scale data to the same scale through methods such as standardization and normalization. Data labeling is used to assign appropriate labels to each data item in the data set, that is, to make clear classifications of the data.
[0102] In the embodiment of the present application, the computer device can adopt any one of the above-mentioned preprocessing methods, or adopt multiple preprocessing methods to preprocess the industrial chain data according to actual processing requirements to obtain processed industrial chain data.
[0103] Correspondingly, when the computer device executes the above S202, the specific execution steps are: performing Poisson check on the processed industrial chain number to obtain the leakage point identification result. This step is basically consistent with the above step S202, and the detailed process can be found in the above content, which will not be repeated here.
[0104] In the method described in the embodiment of the present application, data preprocessing is very important in the above-mentioned Poisson verification process, which can improve the quality and availability of data, reduce the complexity of data, and improve the efficiency and accuracy of data analysis and mining. Moreover, after data preprocessing, mathematical methods can be used to make different data features have different units and dimensions. Standardization processing can eliminate such dimensional differences, so that different features can be directly compared and calculated, so as to improve the accuracy of leak point identification based on preprocessed data in the later stage.
[0105] Based on all the above embodiments, a leak point identification method is also provided. Figure 7 As shown, the method includes:
[0106] S501, collect industry chain data.
[0107] S502, pre-processing the industrial chain data to obtain processed industrial chain data.
[0108] S503, performing statistical analysis on the industrial chain data to determine statistical data of target events in the industrial chain data.
[0109] S504, determining the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency; and determining the degree of deviation of the target event according to the expected frequency and the actual frequency of occurrence of the target event.
[0110] S505, determine the rejection region according to the deviation degree and significance level of the target event. If the Poisson value is in the rejection region, execute step S506; if the Poisson value is not in the rejection region, execute step S507.
[0111] S506: Determine that the target event is a leak event.
[0112] S507, determining that the target event is not a leak event.
[0113] The above steps are all explained in the previous instructions. Please refer to the previous instructions for details and will not be repeated here.
[0114] In one embodiment, based on all the above methods, a leak point identification system is also provided. Figure 8 As shown, the leak point identification system includes a collection device and a processing device, wherein the collection device includes multiple collection devices, and the processing device includes a data preprocessing module and a verification module; the collection device is used to perform the above Figure 2 The steps of S201 in the embodiment are the same as those of S201. For details, please refer to the description of S201 above, which will not be repeated here. The data preprocessing module is used to execute the above Figure 6 The specific steps of step S203 in the embodiment are consistent with those of step S203. For details, please refer to the description of step S203 above, which will not be repeated here. The verification module is used to execute the above Figure 2 Step S202 in the embodiment, and Figure 3-Figure 6 For details of the verification method involved in the embodiment, please refer to the above Figure 3-Figure 6 The description of the embodiments is not repeated here.
[0115] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0116] Based on the same inventive concept, the embodiment of the present application also provides a leak point identification device for implementing the leak point identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more leak point identification device embodiments provided below can refer to the limitations of the leak point identification method above, and will not be repeated here.
[0117] In one embodiment, Fig. 9 As shown, a leakage point identification device is provided, comprising:
[0118] The collection module 11 is used to collect industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain.
[0119] The identification module is used to perform Poisson check on the industrial chain data to obtain leakage point identification results.
[0120] In one embodiment, the identification module includes:
[0121] An analysis unit, used to perform statistical analysis on the industrial chain data to determine statistical data of target events in the industrial chain data; the statistical data includes the number of occurrences of the target event, the actual frequency, the expected frequency and the significance level;
[0122] The identification unit is used to perform a Poisson check on the target event according to the statistical data to obtain a leakage point identification result.
[0123] In one embodiment, the identification unit includes:
[0124] A check subunit, configured to perform a Poisson check on the target event according to the number of occurrences, the actual frequency and the expected frequency of the target event, to obtain a Poisson value and a degree of deviation of the target event;
[0125] Determine a subunit, used to determine a rejection region according to the deviation degree and significance level of the target event;
[0126] The identification subunit is used to determine the leakage point identification result according to the rejection region and the Poisson value.
[0127] In one embodiment, the above-mentioned verification subunit is specifically used to determine the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency; determine the degree of deviation of the target event according to the expected frequency and the actual frequency of occurrence of the target event.
[0128] In one embodiment, the identification subunit is specifically used to determine that the target event is a leak event when the Poisson value is located in the rejection domain; and to determine that the target event is not a leak event when the Poisson value is not located in the rejection domain.
[0129] In one embodiment, the leakage point identification device further includes:
[0130] A preprocessing module, used to preprocess the industrial chain data to obtain processed industrial chain data; the preprocessing includes at least one of noise processing, consistency checking, data labeling, format conversion, redundancy processing, merging processing and missing value processing, data deduplication, feature encoding, and feature scaling;
[0131] Correspondingly, the above-mentioned identification module is specifically used to perform Poisson check on the processed industrial chain number to obtain a leakage point identification result.
[0132] Each module in the above leakage point identification device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.
[0133] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a leakage point identification method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0134] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0135] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0136] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0137] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0138] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0139] Performing statistical analysis on the industrial chain data to determine statistical data on the occurrence of target events in the industrial chain data; the statistical data includes the number of occurrences of the target event, the actual frequency, the expected frequency and the significance level;
[0140] A Poisson check is performed on the target event according to the statistical data to obtain a leakage point identification result.
[0141] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0142] According to the number of occurrences, actual frequency and expected frequency of the target event, a Poisson check is performed on the target event to obtain a Poisson value and a degree of deviation of the target event;
[0143] Determining a rejection region according to the degree of deviation and significance level of the target event;
[0144] The leak point identification result is determined according to the rejection region and the Poisson value.
[0145] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0146] Determine the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency;
[0147] The degree of deviation of the target event is determined according to the expected frequency and the actual frequency of occurrence of the target event.
[0148] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0149] If the Poisson value is located in the rejection region, the target event is determined to be a leakage event;
[0150] If the Poisson value is not located in the rejection region, it is determined that the target event is not a leak event.
[0151] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0152] Preprocessing the industrial chain data to obtain processed industrial chain data; the preprocessing includes at least one of noise processing, consistency checking, data labeling, format conversion, redundancy processing, merging processing and missing value processing, data deduplication, feature encoding, and feature scaling;
[0153] A Poisson check is performed on the processed industrial chain number to obtain a leak point identification result.
[0154] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0155] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0156] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0158] Performing statistical analysis on the industrial chain data to determine statistical data on the occurrence of target events in the industrial chain data; the statistical data includes the number of occurrences of the target event, the actual frequency, the expected frequency and the significance level;
[0159] A Poisson check is performed on the target event according to the statistical data to obtain a leakage point identification result.
[0160] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0161] According to the number of occurrences, actual frequency and expected frequency of the target event, a Poisson check is performed on the target event to obtain a Poisson value and a degree of deviation of the target event;
[0162] Determining a rejection region according to the degree of deviation and significance level of the target event;
[0163] The leak point identification result is determined according to the rejection region and the Poisson value.
[0164] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0165] Determine the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency;
[0166] The degree of deviation of the target event is determined according to the expected frequency and the actual frequency of occurrence of the target event.
[0167] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0168] If the Poisson value is located in the rejection region, the target event is determined to be a leakage event;
[0169] If the Poisson value is not located in the rejection region, it is determined that the target event is not a leak event.
[0170] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0171] Preprocessing the industrial chain data to obtain processed industrial chain data; the preprocessing includes at least one of noise processing, consistency checking, data labeling, format conversion, redundancy processing, merging processing and missing value processing, data deduplication, feature encoding, and feature scaling;
[0172] A Poisson check is performed on the processed industrial chain number to obtain a leak point identification result.
[0173] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0174] Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain;
[0175] A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
[0176] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0177] Performing statistical analysis on the industrial chain data to determine statistical data on the occurrence of target events in the industrial chain data; the statistical data includes the number of occurrences of the target event, the actual frequency, the expected frequency and the significance level;
[0178] A Poisson check is performed on the target event according to the statistical data to obtain a leakage point identification result.
[0179] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0180] According to the number of occurrences, actual frequency and expected frequency of the target event, a Poisson check is performed on the target event to obtain a Poisson value and a degree of deviation of the target event;
[0181] Determining a rejection region according to the degree of deviation and significance level of the target event;
[0182] The leak point identification result is determined according to the rejection region and the Poisson value.
[0183] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0184] Determine the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency;
[0185] The degree of deviation of the target event is determined according to the expected frequency and the actual frequency of occurrence of the target event.
[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0187] If the Poisson value is located in the rejection region, the target event is determined to be a leakage event;
[0188] If the Poisson value is not located in the rejection region, it is determined that the target event is not a leak event.
[0189] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0190] Preprocessing the industrial chain data to obtain processed industrial chain data; the preprocessing includes at least one of noise processing, consistency checking, data labeling, format conversion, redundancy processing, merging processing and missing value processing, data deduplication, feature encoding, and feature scaling;
[0191] A Poisson check is performed on the processed industrial chain number to obtain a leak point identification result.
[0192] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0193] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0194] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A leak point identification method, characterized in that: The method comprises: Collecting industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain; A Poisson check is performed on the industrial chain data to obtain a leak point identification result.
2. The method according to claim 1, characterized in that The Poisson check is performed on the industrial chain data to obtain a leak point identification result, including: Performing statistical analysis on the industrial chain data to determine statistical data on the occurrence of target events in the industrial chain data; the statistical data includes the number of occurrences of the target event, the actual frequency, the expected frequency and the significance level; A Poisson check is performed on the target event according to the statistical data to obtain a leakage point identification result.
3. The method according to claim 2, characterized in that The performing Poisson check on the target event according to the statistical data to obtain a leak point identification result includes: According to the number of occurrences, actual frequency and expected frequency of the target event, a Poisson check is performed on the target event to obtain a Poisson value and a degree of deviation of the target event; Determining a rejection region according to the degree of deviation and significance level of the target event; The leak point identification result is determined according to the rejection region and the Poisson value.
4. The method according to claim 3, characterized in that The step of performing a Poisson check on the target event according to the number of occurrences, the actual frequency, and the expected frequency of the target event to obtain a Poisson value and a degree of deviation of the target event includes: Determine the Poisson value of the target event according to the number of occurrences of the target event and the actual frequency; The degree of deviation of the target event is determined according to the expected frequency and the actual frequency of occurrence of the target event.
5. The method according to claim 3, characterized in that: The step of determining the leak point identification result according to the rejection region and the Poisson value includes: If the Poisson value is located in the rejection region, the target event is determined to be a leakage event; If the Poisson value is not located in the rejection region, it is determined that the target event is not a leak event.
6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Preprocessing the industrial chain data to obtain processed industrial chain data; the preprocessing includes at least one of noise processing, consistency checking, data labeling, format conversion, redundancy processing, merging processing and missing value processing, data deduplication, feature encoding, and feature scaling; The Poisson check is performed on the industrial chain data to obtain a leak point identification result, including: A Poisson check is performed on the processed industrial chain number to obtain a leak point identification result.
7. A leak point identification device, characterized in that: The device comprises: A collection module, used to collect industrial chain data; the industrial chain data includes data related to the operation status of the industrial chain; The identification module is used to perform Poisson check on the industrial chain data to obtain leakage point identification results.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.