A method, device and electronic device for modeling based on fusion

Abstract

The embodiment of this specification provides a method for modeling based on fusion, which obtains multi-attribute state information collected by sensors of each device, normalizes each attribute state information, generates multiple state sequences, constructs a state set, calculates multi-target statistics between different state sequences using a preset target statistical value function, calculates similarity based on set boundary parameters, determines similar state sequences, fuses similar state sequences, adds the fused state sequence to the state set, removes the fused similar state sequence from the state set, and uses the state set to model. By fusing state information according to the state sequence, the processing of similar state information is reduced, the amount of data is reduced, and thus the model processing efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method, device and electronic device for modeling based on fusion. Background Art

[0002] In recent years, with the rapid development of micro-electromechanical system technology, wireless communication technology, and sensor technology, sensor networks have the advantages of fast construction and easy deployment. They can complete large-scale, multi-mode information collection and monitoring, and then use data intelligence technology to use the monitored data as a data set for modeling to build a model for analyzing the operating status of equipment. However, many medium and large industrial equipment have many types of sensors and a large number of sensors, which makes the modeling efficiency and model maintenance efficiency unsatisfactory, which greatly affects and restricts the application of data intelligence technology in the industrial field.

[0003] Therefore, it is necessary to provide a modeling method to improve the model processing efficiency. Summary of the invention

[0004] The embodiments of this specification provide a method, device and electronic device for modeling based on fusion, so as to improve the efficiency of model processing.

[0005] The embodiment of this specification provides a method for modeling based on fusion, including:

[0006] Obtain multi-attribute state information collected by sensors of each device, normalize each attribute state information, generate multiple state sequences, and construct a state set;

[0007] Constructing a data fusion model, and fusing the multiple state sequences through the data fusion model, including:

[0008] The preset target statistical value function is used to calculate the multi-target statistical values ​​between different state sequences, the similarity is calculated according to the set boundary parameters, similar state sequences are determined, and similar state sequences are merged;

[0009] The fused state sequence is added to the state set, and the fused similar state sequence is removed from the state set, and the state set is used for modeling.

[0010] Optionally, the calculating of multi-objective statistics between different state sequences by using a preset objective statistical value function includes:

[0011] Calculate the standard deviation, mean, median, and covariance of the corresponding parameters in different state sequences.

[0012] Optionally, the multi-attribute state information includes:

[0013] Health status information, communication status information and environmental conditions.

[0014] Optionally, each attribute status information is normalized, including:

[0015] The attribute state information is subtracted from the historical minimum value of the attribute, and the result is divided by the historical fluctuation range of the attribute to obtain normalized attribute state information.

[0016] Optionally, the fusing similar state sequences further includes:

[0017] Merge similar state sequences in different state sequences.

[0018] Optionally, fusing similar state sequences includes:

[0019] The data in one of the state sequences is adjusted according to the similarity, and the adjusted state sequence is used as the fused state sequence.

[0020] Optionally, it also includes:

[0021] Adjust boundary parameters based on preset modeling efficiency data.

[0022] The embodiment of this specification also provides a device for modeling based on fusion, including:

[0023] The state set module is used to obtain the multi-attribute state information collected by the sensors of each device, normalize the state information of each attribute, generate multiple state sequences, and construct a state set;

[0024] A fusion module constructs a data fusion model and fuses the multiple state sequences through the data fusion model, including:

[0025] The preset target statistical value function is used to calculate the multi-target statistical values ​​between different state sequences, the similarity is calculated according to the set boundary parameters, similar state sequences are determined, and similar state sequences are merged;

[0026] The state set module is also used to add the fused state sequence to the state set, remove the fused similar state sequence from the state set, and use the state set to model.

[0027] The embodiment of the present specification also provides an electronic device, wherein the electronic device includes:

[0028] processor; and,

[0029] A memory storing a computer executable program, wherein when the executable program is executed, the processor performs any one of the above methods.

[0030] An embodiment of the present specification also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0031] The various technical solutions provided in the embodiments of this specification obtain multi-attribute state information collected by sensors of each device, normalize each attribute state information, generate multiple state sequences, construct a state set, calculate the multi-target statistical value between different state sequences using a preset target statistical value function, calculate the similarity according to the set boundary parameters, determine similar state sequences, fuse similar state sequences, add the fused state sequence to the state set, remove the fused similar state sequence from the state set, and use the state set to model. By fusing the state information according to the state sequence, the processing of similar state information is reduced, the amount of data is reduced, and the model processing efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0033] Figure 1 A schematic diagram of the principle of a method for modeling based on fusion provided in an embodiment of this specification;

[0034] Figure 2 A schematic diagram of the structure of a device for modeling based on fusion provided in an embodiment of this specification;

[0035] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0036] Figure 4 A schematic diagram of a computer-readable medium provided for an embodiment of this specification. DETAILED DESCRIPTION

[0037] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in a variety of forms, and should not be construed as limiting the present invention to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, and is more convenient for fully conveying the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0038] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0039] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0040] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0041] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0042] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0043] Figure 1 A schematic diagram of a method for modeling based on fusion provided in an embodiment of this specification, the method may include:

[0044] S101: Obtain multi-attribute state information collected by sensors of each device, normalize each attribute state information, generate multiple state sequences, and construct a state set.

[0045] In this embodiment of the specification, the multi-attribute state information may include:

[0046] Health status information, communication status information and environmental conditions.

[0047] The status information may also include basic device information, behavior actions, and device parameters.

[0048] Among them, the status sensor data of the device can be defined and the signals of the device sensors can be preprocessed.

[0049] Specifically, it may include:

[0050] Obtain the device status sensor installed inside the device, obtain the data collected by the device, obtain the data collected by different sensors, and construct multi-attribute status information. Of course, invalid values ​​in the above-mentioned device status sensor data can be eliminated.

[0051] Then, the multi-attribute status information collected by the device at the same time is normalized, and the normalized results of each attribute status information are combined to generate a state sequence. The combination results of each device at the same time form a state sequence, the combination results of each device form multiple state sequences, and the combination results of each device at different times form multiple state sequences.

[0052] Among them, the normalized result = (current moment value - historical minimum value) / (historical maximum value - historical minimum value).

[0053] Therefore, in the embodiment of this specification, each attribute status information is normalized, including:

[0054] The attribute state information is subtracted from the historical minimum value of the attribute, and the result is divided by the historical fluctuation range of the attribute to obtain normalized attribute state information.

[0055] The normalized results are stored as arrays, matrix information, etc. according to preset rules, which is convenient for adoption and use by various models.

[0056] Preferably, data cleaning is performed before normalization according to actual conditions.

[0057] Among them, basic information may refer to nameplate information, which is used to quickly identify the device, including device model, device description, manufacturer, number of ports, hardware version, firmware version, software version, IP address, and MAC address;

[0058] Health status, including: power status, CPU status, software status, memory status, storage status and clock status;

[0059] Communication status includes: port status, optical power status, flow status and service status, etc.

[0060] Behavioral actions include: real-time recording and real-time monitoring of instruction information;

[0061] Environmental conditions include environmental types, such as severe conditions and normal conditions, and can also be specific physical environmental parameters.

[0062] The sensors of the equipment may include: online infrared thermal imagers, visible light video monitoring equipment, vibration measuring instruments, ultrasonic thickness gauges, portable hardness testers, gas detectors, motor fault diagnosis instruments, thermal measuring instruments, calibration measuring instruments and electrical measuring instruments, etc.

[0063] Establish multi-level operations for multiple types of data. For the multi-source data collection layer, data can be collected from multiple data sources; the data interface layer is connected to the multi-source data collection layer, and has multiple data interfaces corresponding to multiple data types, and uses the data interfaces of the corresponding data types to receive multi-source data; the big data fusion management layer separately stores the data received by the data interface layer, performs big data calculation and analysis, etc.

[0064] Preferably, the data interface layer includes a SQOOP interface for transmitting relational data, a JMS interface for transmitting real-time data streams, and an FTP interface for transmitting conventional data;

[0065] The big data fusion management layer includes data warehouse tool Hive, Hbase database, SQL big data query tool Impala and Hadoop resource manager YARN;

[0066] It also includes Spark Streaming, a large-scale streaming data processing framework, Spark R, a language package for using Apache Spark from R, MLlib, a machine learning algorithm library, Spark GraphX, and a Python programming environment for performing graph parallel computing.

[0067] Preferably, it also includes an open source algorithm library, such as a spatiotemporal geographic analysis module, an impact range analysis module, a graph computing analysis module, and a correlation relationship analysis module;

[0068] Preferably, the model access interface layer includes: Java database connection interface JDBC, used to execute SQL statements; open database connection ODBC, used to support SQL language; SparkSQL, used to realize the calculation of structured data; HUE interface, used to realize the development and debugging of Hadoop ecosystem.

[0069] The above multi-level operations enable equipment managers to flexibly and accurately process various types of signal data, and conveniently use existing statistical analysis tools to quickly build models and generate simple or complex analysis results.

[0070] S102: constructing a data fusion model, and fusing the multiple state sequences through the data fusion model, including:

[0071] The preset target statistical value function is used to calculate the multi-target statistical values ​​between different state sequences, the similarity is calculated according to the set boundary parameters, similar state sequences are determined, and similar state sequences are fused.

[0072] The data fusion model may be a modeling component analysis model (MCA), which is used to analyze and fuse the modeling components to output modeling components based on parameter association.

[0073] In the embodiment of the present specification, the method of calculating the multi-objective statistical values ​​between different state sequences by using a preset objective statistical value function includes:

[0074] Calculate the standard deviation, mean, median, and covariance of the corresponding parameters in different state sequences.

[0075] The specific implementation method is:

[0076] 1) Calculation of key statistical values ​​between sensor parameter data:

[0077] Define the function Statisticx(T1,T2),

[0078] Among them, the input T1 and T2 are any two sensor parameter value sequences, and the output is the set [std, avr, mdn, alpha, cov], where std is the standard deviation of the difference between the two parameter value sequences, avr is the mean of the difference between the two sequence values, mdn is the median of the difference between the two sequence values, and cov is the covariance of the difference between the two sequence values.

[0079] 2) Similarity calculation between sensor parameter data:

[0080] Define the function Similarity(P),

[0081] Where P is a sensor parameter ID, and the output is a set of sensor parameter IDs similar to it. The execution steps of Similarity(P) are as follows:

[0082] Set similarity boundary parameters: Delta_std, Delta_avr, Delta_mdn_L1, Delta_mdn_L2, Alpha_ratio. The default settings are:

[0083] Delta_std = 0.05;

[0084] Delta_avr = 0.05;

[0085] Delta_mdn_L1=0.1;

[0086] Delta_mdn_L2=0.5;

[0087] Alpha_ratio = 0.005;

[0088] Calculate a parameter similar to parameter P:

[0089] For parameter Q:

[0090] If std < Delta_std and avr < Delta_avr and mdn < Delta_mdn_L2 and cov[0,1] and cov[1,0] are both greater than 0 and alpha < (N_data * Alpha_ratio) between it and P, then Q is a similar parameter to P;

[0091] If std < Delta_std and avr < Delta_avr and mdn < Delta_mdn_L1 and cov[0,1] and cov[1,0] are both greater than 0 between it and P, then Q is a similar parameter to P;

[0092] If avr == 0 and cov[0,0], cov[0,1], cov[1,0], cov[1,1] are all 0 between it and P, then Q is a similar parameter to P.

[0093] In the embodiments of this specification, the fusion of similar state sequences further includes:

[0094] Fusing the similar state sequences in different state sequences.

[0095] In the embodiments of this specification, the fusion of similar state sequences includes:

[0096] Adjust the data in one of the state sequences according to the similarity, and use the adjusted state sequence as the fused state sequence.

[0097] In the embodiments of this specification, it further includes:

[0098] Adjust the boundary parameters according to the preset modeling efficiency data.

[0099] S103: Add the fused state sequence to the state set, remove the fused similar state sequences from the state set, and model using the state set.

[0100] By obtaining the multi-attribute state information collected by the sensors of each device, normalizing each attribute state information to generate multiple state sequences, constructing a state set, calculating the multi-objective statistical values between different state sequences using a preset target statistical value function, calculating the similarity according to the set boundary parameters, determining the similar state sequences, and fusing the similar state sequences, adding the fused state sequence to the state set, removing the fused similar state sequences from the state set, and modeling using the state set. By fusing the state information according to the state sequences, the processing of similar state information is reduced, the data volume is reduced, and thus the model processing efficiency is improved.

[0101] By using the acquired sensor data reflecting the historical operating status of the equipment, a smaller data set is obtained through the MCA model (for example, the original data contains data from N sensors, and after processing, data from M sensors is obtained, M<N), thereby greatly improving the efficiency of equipment status modeling (estimated to increase by 30% to 50%) and the performance of real-time application of the model.

[0102] Figure 2 A schematic diagram of a structure of a device for modeling based on fusion provided in an embodiment of this specification, the device may include:

[0103] The state set module 201 is used to obtain multi-attribute state information collected by sensors of each device, normalize each attribute state information, generate multiple state sequences, and construct a state set;

[0104] The fusion module 202 constructs a data fusion model and fuses the multiple state sequences through the data fusion model, including:

[0105] The preset target statistical value function is used to calculate the multi-target statistical values ​​between different state sequences, the similarity is calculated according to the set boundary parameters, similar state sequences are determined, and similar state sequences are merged;

[0106] The state set module 201 is also used to add the fused state sequence to the state set, remove the fused similar state sequence from the state set, and use the state set for modeling.

[0107] The device obtains multi-attribute state information collected by sensors of each device, normalizes each attribute state information, generates multiple state sequences, constructs a state set, calculates multi-target statistical values ​​between different state sequences using a preset target statistical value function, calculates similarity according to set boundary parameters, determines similar state sequences, fuses similar state sequences, adds the fused state sequence to the state set, removes the fused similar state sequence from the state set, and uses the state set to model. By fusing state information according to state sequences, the processing of similar state information is reduced, the amount of data is reduced, and thus the model processing efficiency is improved.

[0108] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0109] The following describes an electronic device embodiment of the present invention, which can be regarded as a specific physical implementation of the method and device embodiments of the present invention. The details described in the electronic device embodiment of the present invention should be regarded as a supplement to the above method or device embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above method or device embodiments.

[0110] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 3 The electronic device 300 according to the embodiment of the present invention is described. Figure 3 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0111] like Figure 3 As shown, the electronic device 300 is in the form of a general computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different system components (including the storage unit 320 and the processing unit 310), a display unit 340, etc.

[0112] The storage unit stores program codes, which can be executed by the processing unit 310, so that the processing unit 310 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 310 can perform the following steps: Figure 1 Steps shown.

[0113] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache memory unit 3202 , and may further include a read-only memory unit (ROM) 3203 .

[0114] The storage unit 320 may also include a program / utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0115] Bus 330 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0116] The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 300, and / or any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 through the bus 330. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0117] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: Figure 1 The method shown.

[0118] Figure 4 A schematic diagram of a computer-readable medium provided for an embodiment of this specification.

[0119] accomplish Figure 1The computer program of the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0120] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0121] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0122] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0123] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0124] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0125] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for modeling based on fusion, characterized in that: Including: Obtain multi-attribute status information collected by sensors of each device, normalize each attribute status information, generate multiple state sequences, and construct a state set; Construct a data fusion model, and fuse the multiple state sequences through the data fusion model, including: Use a preset target statistical value function to first calculate the standard deviation std, mean avr, median mdn, and covariance cov of the differences of corresponding parameters between different state sequences, and then set boundary parameters, where the boundary parameters include: Delta_std, Delta_avr, Delta_mdn_L1, Delta_mdn_L2, and Alpha_ratio; If the standard deviation std of different state sequences < Delta_std, and the mean avr < Delta_avr, and the median mdn < Delta_mdn_L2, and the covariance cov[0,1] > 0, cov[1,0] > 0, and alpha < (N_data * Alpha_ratio), then the state sequences are similar; If the standard deviation std of different state sequences < Delta_std, and the mean avr < Delta_avr, and the median mdn < Delta_mdn_L1, and the covariance cov[0,1] > 0, cov[1,0] > 0, then the state sequences are similar; If the mean avr of different state sequences = 0, and the covariance cov[0,0], cov[0,1], cov[1,0], and cov[1,1] are all equal to 0, then the state sequences are similar; And fuse the similar state sequences; Add the fused state sequences to the state set, remove the fused similar state sequences from the state set, and model using the state set.

2. The method according to claim 1, characterized in that The multi-attribute status information includes: Health status information, communication status information, and environmental conditions.

3. The method according to claim 1, characterized in that Normalize each attribute status information, including: Subtract the historical minimum value of the attribute from the attribute status information, and perform a division operation with the historical fluctuation range of the attribute to obtain the normalized attribute status information.

4. The method according to claim 1, characterized in that: The fusing of the similar state sequences further includes: Fuse the similar state sequences in different state sequences.

5. The method according to claim 1, characterized in that The fusing of the similar state sequences includes: Adjust the data in one of the state sequences according to the similarity degree, and use the adjusted state sequence as the fused state sequence.

6. The method according to claim 1, characterized in that Also included: Adjust the boundary parameters according to the preset modeling efficiency data.

7. A device for modeling based on fusion, characterized in that: Including: A state set module, used to obtain multi-attribute status information collected by sensors of each device, normalize each attribute status information, generate multiple state sequences, and construct a state set; A fusion module, which constructs a data fusion model and fuses the multiple state sequences through the data fusion model, including: First, calculate the standard deviation std, mean avr, median mdn, and covariance cov of the differences of the corresponding parameters between different state sequences using a preset target statistical value function, and then set boundary parameters, where the boundary parameters include: Delta_std, Delta_avr, Delta_mdn_L1, Delta_mdn_L2, and Alpha_ratio; If the standard deviation std of different state sequences < Delta_std, and the mean avr < Delta_avr, and the median mdn < Delta_mdn_L2, and the covariance cov[0,1] > 0, cov[1,0] > 0, and alpha < (N_data * Alpha_ratio), then the state sequences are similar; If the standard deviation std of different state sequences < Delta_std, and the mean avr < Delta_avr, and the median mdn < Delta_mdn_L1, and the covariance cov[0,1] > 0, cov[1,0] > 0, then the state sequences are similar; If the mean avr of different state sequences = 0, and the covariance cov[0,0], cov[0,1], cov[1,0], and cov[1,1] are all equal to 0, then the state sequences are similar; And fuse the similar state sequences; The state set module is further configured to add the fused state sequences to the state set, remove the similar state sequences to be fused from the state set, and model using the state set.

8. An electronic device, wherein: The electronic device includes: A processor; and, A memory storing a computer-executable program, where the executable program, when executed, causes the processor to execute the method according to any one of claims 1-6.

9. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and the one or more programs, when executed by the processor, implement the method according to any one of claims 1-6.

Images