Instrument state judgment method and device, computer device and medium

Abstract

The present disclosure relates to the technical field of instrument information processing, and provides an instrument state judgment method and device, computer equipment and a medium. The method comprises the following steps: generating initial model parameters; sending an update instrument data processing model request to a model platform server; screening out target intermediate model information; obtaining a target instrument processing model; and generating instrument state information. Through the above steps, the present disclosure can screen out abnormal instruments without human detection, thereby improving detection efficiency and reducing labor costs.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of instrument information processing, and particularly relates to an instrument state judgment method and device, computer equipment and a medium. BACKGROUND

[0002] With the continuous progress of industrial instruments, industrial instruments are increasingly widely used. Abnormal state detection of the instrument is one of the important work of the enterprise. Since the existing instrument abnormal monitoring is mainly realized by periodic human detection, the detection efficiency is extremely low. SUMMARY

[0003] Therefore, the present disclosure provides an instrument state judgment method and device, computer equipment and a medium to solve the problem that the detection efficiency is extremely low due to the fact that the existing instrument abnormal monitoring is mainly realized by periodic human detection.

[0004] In a first aspect, an instrument state judgment method is provided. The method includes: in response to receiving an instruction to update an instrument processing model, generating initial model parameters based on a preset initial generation strategy; sending an update instrument data processing model request to a model platform server, wherein the update instrument data processing model request includes initial instrument data information and the initial model parameters; in response to receiving an intermediate model information set sent by the model platform server, screening target intermediate model information from the intermediate model information set based on a preset screening strategy, wherein the intermediate model information set includes at least one intermediate model information, and the intermediate model information includes intermediate model parameters; updating the intermediate model parameters of the target intermediate model information to the initial instrument processing model to obtain a target instrument processing model; and generating instrument state information based on the initial instrument data information and the target instrument processing model.

[0005] In a second aspect, an instrument state judgment device is provided. The device includes: an initial generation module configured to, in response to receiving an instruction to update an instrument processing model, generate initial model parameters based on a preset initial generation strategy; a sending module configured to send an update instrument data processing model request to a model platform server, wherein the update instrument data processing model request includes initial instrument data information and the initial model parameters; a screening module configured to, in response to receiving an intermediate model information set sent by the model platform server, screen target intermediate model information from the intermediate model information set based on a preset screening strategy, wherein the intermediate model information set includes at least one intermediate model information, and the intermediate model information includes intermediate model parameters; an updating module configured to update the intermediate model parameters of the target intermediate model information to the initial instrument processing model to obtain a target instrument processing model; and a state generation module configured to generate instrument state information based on the initial instrument data information and the target instrument processing model.

[0006] In a third aspect, the present disclosure provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0007] In a fourth aspect, the present disclosure provides a computer readable storage medium, which stores a computer program, wherein the computer program implements the steps of the above method when executed by a processor.

[0008] Compared with the prior art, the present disclosure has at least the following beneficial effects: by generating initial model parameters, sending an update instrument data processing model request to a model platform server, screening out target intermediate model information, obtaining a target instrument processing model, and generating instrument state information, the abnormal instrument can be screened out without human detection, which improves the detection efficiency and reduces the labor cost. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 is a joint learning architecture diagram of the present disclosure;

[0011] Figure 2 is a flow of the instrument state judgment method provided by the present disclosure Figure 1 ;

[0012] Figure 3 is a flow of the instrument state judgment method provided by the present disclosure Figure 2 ;

[0013] Figure 4 is a schematic diagram of the instrument state judgment device provided by the present disclosure;

[0014] Figure 5 is a schematic diagram of the computer device provided by the present disclosure. DETAILED DESCRIPTION

[0015] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

[0016] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0017] Joint learning refers to comprehensively utilizing multiple AI (Artificial Intelligence) technologies under the premise of ensuring data security and user privacy, jointly mining data value by multiple parties, and giving birth to new intelligent formats and modes based on joint modeling. Joint learning has at least the following characteristics:

[0018] (1) Participating nodes control the weak centralized joint training mode of self-owned data to ensure data privacy and security in the process of co-creating intelligence.

[0019] (2) In different application scenarios, AI algorithms, privacy protection calculations are used to screen and / or combine, and multiple model aggregation optimization strategies are established to obtain high-level and high-quality models.

[0020] (3) Based on multiple model aggregation optimization strategies, the performance of the joint learning engine is improved under the premise of ensuring data security and user privacy. The performance method can be to improve the overall performance of the joint learning engine by solving problems such as parallel computing architecture, information interaction in large-scale cross-domain networks, intelligent perception, and exception handling mechanism.

[0021] (4) Obtain the needs of multiple users in each scenario, determine the real contribution of each joint participant through a mutual trust mechanism, and distribute incentives.

[0022] Based on the above method, an AI technology ecosystem based on joint learning can be established to fully realize the value of industry data and promote the landing of vertical field scenarios.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] Figure 1 is a schematic diagram of a joint learning architecture according to an embodiment of the present disclosure. As shown in Figure 1 , the joint learning architecture can include a server (central node) 101 and a participating party 102, a participating party 103, and a participating party 104.

[0025] In the federated learning process, the basic model can be established by the server 101, and the server 101 sends the model to the participants 102, 103 and 104 which establish a communication connection with the server 101. The basic model can also be established by any participant and uploaded to the server 101, and the server 101 sends the model to other participants which establish a communication connection with the server 101. The participants 102, 103 and 104 construct the model according to the downloaded basic structure and model parameters, train the model using local data, obtain updated model parameters, and upload the updated model parameters to the server 101 in an encrypted manner. The server 101 aggregates the model parameters sent by the participants 102, 103 and 104, obtains global model parameters, and transmits the global model parameters back to the participants 102, 103 and 104. The participants 102, 103 and 104 iterate the respective models according to the received global model parameters until the model converges finally, thereby realizing the training of the model. In the federated learning process, the data uploaded by the participants 102, 103 and 104 is the model parameter, and the local data is not uploaded to the server 101, and all participants can share the final model parameters, so that common modeling can be realized on the basis of ensuring data privacy. It should be noted that the number of participants is not limited to three as described above, but can be set as needed, and the embodiments of the present disclosure do not limit this.

[0026] Figure 2 is a flowchart of the instrument state judgment method provided by the embodiments of the present disclosure. Figure 2 The instrument state judgment method can be executed by Figure 1 the server or the participant. As Figure 2 indicated, the instrument state judgment method includes:

[0027] S201, in response to receiving an update instrument processing model instruction, generating initial model parameters based on a preset initial generation strategy.

[0028] The instruction can refer to a command for a computer to perform an operation, which is composed of a series of binary codes. The update instrument processing model instruction can refer to an instruction for instructing the server 2 to update its instrument processing model. The instrument processing model can refer to a neural network model. The preset initial generation strategy can refer to a step or method for generating initial model parameters. The initial model parameters can refer to related parameters of the existing instrument processing model before receiving the update instrument processing model instruction.

[0029] S202, sending an update instrument data processing model request to a model platform server, wherein the update instrument data processing model request includes initial instrument data information and initial model parameters.

[0030] The request can refer to a command for the computer to perform an operation, and is composed of a series of binary codes. The request for updating the meter processing model can refer to a request for instructing the server 2 to update its meter processing model. The initial meter data information can refer to the collected relevant data related to the meter for predicting the data. The model platform server can refer to a server for managing various types of model information. The model platform server can issue an instruction to at least one training server, wherein the instruction includes the initial model parameter. The at least one training server first updates the initial model parameter to a local model, then trains locally based on local data, and feeds back at least one model parameter obtained by training to the model platform server, and then the model platform server can send the at least one model parameter to the server 2.

[0031] S203, in response to receiving the intermediate model information set sent by the model platform server, screening target intermediate model information from the intermediate model information set based on a preset screening strategy, wherein the intermediate model information set includes at least one intermediate model information, and the intermediate model information includes an intermediate model parameter.

[0032] The intermediate model information set can refer to a set composed of a plurality of intermediate model information. The intermediate model information can refer to the model parameter related information obtained by the model platform server. The intermediate model information can include an intermediate model parameter. The intermediate model parameter can refer to a model parameter in the model server platform.

[0033] S204, updating the intermediate model parameter of the target intermediate model information to the initial meter processing model to obtain a target meter processing model.

[0034] The target meter processing model can refer to the meter processing model obtained by updating the screened model parameter to the initial meter processing model.

[0035] S205, generating meter state information based on the initial meter data information and the target meter processing model.

[0036] The meter state information can refer to the relevant information of the meter state. As an example, the meter state information can be "normal" or "abnormal". In some other embodiments, the meter state information can also be "normal operation", "interrupted operation" or "abnormal operation", etc., which is set as needed, and is not specifically limited herein.

[0037] Generating an initial model parameter; sending a request for updating a meter data processing model to a model platform server; screening target intermediate model information; obtaining a target meter processing model; and generating meter state information can screen out abnormal meters without human detection, on the one hand improving the detection efficiency, and on the other hand reducing the labor cost.

[0038] In some embodiments, the initial generation strategy comprises: obtaining at least one test data set; training the initial meter processing model based on a preset training strategy, to obtain the initial model parameter.

[0039] The test data set can refer to a set of data compositions for training the model. It should be noted that the result of the test data set is known. The training strategy can refer to the method or steps for training the initial meter model.

[0040] In some embodiments, the training strategy comprises: training the initial meter processing model based on each of the at least one test data set, to generate at least one intermediate parameter and at least one intermediate evaluation value; selecting a target evaluation value from the at least one intermediate evaluation value; and determining the intermediate parameter corresponding to the target evaluation value as the initial model parameter.

[0041] The intermediate parameter can refer to the parameter vector of the initial meter processing model after training. The intermediate evaluation value can refer to the difference between the predicted value of the test data set after training and the actual value of the test data set. As an example, the predicted value of the test data set after training is 13, and the actual value of the test data set is 19, then the intermediate evaluation value is equal to 19-13=6. The intermediate evaluation value can also be in other forms, which are not specifically limited here. The target evaluation value can be the target evaluation value that best meets the requirements among the at least one intermediate evaluation value. As an example, the target evaluation value can be the value with the smallest value among the at least one intermediate evaluation value.

[0042] In some embodiments, the screening strategy comprises: obtaining initial identification information of the initial meter data information; step one: obtaining one of the at least one intermediate model information to obtain the target intermediate model information; step two: generating an identification difference value based on a preset calculation strategy, the initial identification information, and the intermediate identification information of the target intermediate model information; repeating steps one to two until each of the at least one intermediate model information is processed to obtain at least one identification difference value; selecting a target identification difference value from the at least one identification difference value, and determining the intermediate model information corresponding to the target identification difference value as the target intermediate model information.

[0043] The initial identification information can refer to some related information of the meter information. As an example, the initial identification information can include meter type information, meter usage time information, etc. The meter type information can refer to the value represented by different types of meters. As an example, the type value of meter A is 01, and the type value of meter B is 02. The preset calculation strategy can refer to the steps or methods for calculating the initial identification information and the intermediate identification information, which can be set as needed and are not specifically limited here. The target identification difference value can be the identification difference value with the smallest value among the at least one identification difference value.

[0044] In some embodiments, the computing strategy comprises: obtaining an identification information computing table, wherein the identification information computing table comprises a computing weight and a computing method of each sub-identification information; and generating an identification difference value based on the identification computing information table, the initial identification information, and the intermediate identification information of the target intermediate model information.

[0045] The identification computing information table can refer to the score rules and computing weights of each identification in the initial identification information. As an example, the identification computing information table can be as shown in the following table:

[0046]

[0047] The sub-identification information can refer to one of the identification information in the initial identification information. The computing weight can refer to the proportional coefficient of each sub-identification information computing formula, and the sum of the proportional coefficients of each sub-identification information computing formula is 1.

[0048] Substituting the initial identification information and the intermediate identification information of the target intermediate model information into the identification computing information table, the identification difference value can be obtained.

[0049] In some embodiments, based on the initial instrument data information and the target instrument processing model, the instrument state information is generated, comprising: a data interval threshold, an interval proportion threshold, a target count value, at least one target data bit, and a data bit proportion threshold, wherein the target count value is a natural number, and the initial value of the target count value is 0; the initial instrument data information is substituted into the target instrument processing model to obtain predicted instrument data information; based on each metadata in the initial instrument data information and the corresponding metadata in the predicted instrument data information, at least one metadata difference value is generated; step one: obtaining one of the at least one metadata difference value to obtain an intermediate metadata difference value; step two: when the intermediate metadata difference value is greater than the target threshold, the value of the target count value is incremented by one; steps one to two are repeatedly executed until each metadata difference value in the at least one metadata difference value is compared with the target threshold; based on the target count value and the number of metadata difference values in the at least one metadata difference value, an intermediate proportion value is generated; when the intermediate proportion value is not less than the interval proportion threshold, the generated interval result is set as abnormal; based on the data bit processing strategy, the at least one target data bit, and the data bit proportion threshold, a data bit result is generated; when the results of any one of the interval result and the data bit result are abnormal, the instrument state information is set as abnormal; when the results of any one of the interval result and the data bit result are abnormal, the instrument state information is set as normal.

[0050] The data interval threshold can refer to a data interval of a normal value of the instrument, and data not belonging to the data interval is abnormal data. The interval proportion threshold can refer to a limit value of a percentage of abnormal data in all data, and when the limit value is exceeded, the data of the instrument can have a serious abnormality. The target count value can refer to a technical unit for calculating an intermediate value, wherein the value range of the target count value can be a natural number. The target data bit can refer to at least one key data bit in the initial instrument data information. The key data bit can refer to data on the data bit that has a strong correlation with an abnormal state. The data bit proportion threshold can refer to a proportion limit value of the number of abnormal data in the target data bit and the number of all data in the target data bit, and when the limit value is exceeded, the data of the instrument can have a serious abnormality. The predicted instrument data information can refer to predicted information obtained by calculating the initial instrument data information by a model. The metadata can refer to a basic data unit in the initial instrument data information or the predicted instrument data information. The metadata difference value can refer to a difference value between the metadata in the initial instrument data information and the corresponding metadata in the predicted instrument data information, and the difference value is a non-negative number. The intermediate data difference value can refer to a selected metadata difference value. The interval result can refer to a result information of whether the overall data in the initial instrument data information is abnormal. The interval result can be "abnormal" or "normal". The data bit result can refer to a result information of whether the data in the data bit is abnormal. The data bit result can be "abnormal" or "normal".

[0051] In some embodiments, the data bit processing strategy includes: setting the target count value to 0; step one: obtaining one of the at least one target data bit to obtain a target data bit; step two: when the metadata difference value corresponding to the target data bit in the at least one metadata difference value is not less than the target threshold, increasing the target count value by one; repeating steps one and two until each metadata difference value in the at least one metadata difference value is compared with the target threshold; generating a data bit proportion value based on the target count value and the number of target data bits in the at least one target data bit; and setting the data bit result to abnormal when the data bit proportion value is not less than the interval proportion threshold.

[0052] The target data bit can refer to a data bit selected for calculation in the at least one target data bit. The data bit proportion value can refer to a proportion of the target count value and the number of target data bits in the at least one target data bit.

[0053] Figure 3 is a flowchart of a gas boiler instrument state judgment method provided by the embodiments of the present disclosure. Figure 3 The gas boiler instrument state judgment method of Figure 1 may be performed by a participant. As Figure 3 shown, the gas boiler instrument state judgment method includes:

[0054] S301, acquire at least one test data set.

[0055] S302, train the initial gas boiler instrument processing model based on each test data set in the at least one test data set, generate corresponding at least one intermediate parameter and at least one intermediate evaluation value.

[0056] S303, select a target evaluation value from the at least one intermediate evaluation value.

[0057] S304, determine the intermediate parameter corresponding to the target evaluation value as the initial model parameter.

[0058] S305, in response to receiving an instruction to update the gas boiler instrument processing model, generate the initial model parameter based on a preset initial generation strategy.

[0059] S306, send an update gas boiler instrument data processing model request to the model platform server, wherein the update gas boiler instrument data processing model request includes initial gas boiler instrument data information and initial model parameter.

[0060] S307, in response to receiving the intermediate model information set sent by the model platform server, select the target intermediate model information from the intermediate model information set based on a preset screening strategy, wherein the intermediate model information set includes two intermediate model information, and the intermediate model information includes intermediate model parameter.

[0061] S308, in response to receiving the intermediate model information set sent by the model platform server, acquire the two intermediate model information in the intermediate model information set.

[0062] S309, acquire one of the two intermediate model information, and obtain the target intermediate model information.

[0063] S310, generate an identification difference value based on the initial identification information and the intermediate identification information of the target intermediate model information.

[0064] S311, repeat S309 to S310 until each intermediate model information in the two intermediate model information is processed, and at least one identification difference value is obtained.

[0065] S312, select a target identification difference value from the at least one identification difference value, and determine the intermediate model information corresponding to the target identification difference value as the target intermediate model information.

[0066] S313, update the intermediate model parameter of the target intermediate model information to the initial gas boiler instrument processing model, and obtain the target gas boiler instrument processing model.

[0067] S314, generating the gas boiler instrument state information based on the initial gas boiler instrument data information and the target gas boiler instrument processing model.

[0068] All the optional technical solutions described above can be combined to form optional embodiments of the present application, which will not be described one by one here.

[0069] The following is an embodiment of the device of the present disclosure, which can be used to execute the method embodiments of the present disclosure. For details not disclosed in the device embodiments of the present disclosure, please refer to the method embodiments of the present disclosure.

[0070] Figure 4 is a schematic diagram of the instrument state judgment device provided by the embodiment of the present disclosure. As shown in Figure 4 The instrument state judgment device comprises:

[0071] The initial generation module 401 is configured to generate initial model parameters based on a preset initial generation strategy in response to receiving an update instrument processing model instruction;

[0072] The sending module 402 is configured to send an update instrument data processing model request to a model platform server, wherein the update instrument data processing model request comprises initial instrument data information and initial model parameters;

[0073] The screening module 403 is configured to screen target intermediate model information from the intermediate model information set based on a preset screening strategy in response to receiving the intermediate model information set sent by the model platform server, wherein the intermediate model information set comprises at least one intermediate model information, and the intermediate model information comprises intermediate model parameters;

[0074] The update module 404 is configured to update the intermediate model parameters of the target intermediate model information to the initial instrument processing model to obtain a target instrument processing model;

[0075] The state generation module 405 is configured to generate instrument state information based on initial instrument data information and a target instrument processing model.

[0076] In some embodiments, the initial generation strategy comprises: obtaining at least one test data set; training the initial instrument processing model based on a preset training strategy through the at least one test data set to obtain the initial model parameters.

[0077] In some embodiments, the training strategy comprises: training the initial instrument processing model based on each test data set in the at least one test data set to generate at least one corresponding intermediate parameter and at least one intermediate evaluation value; screening a target evaluation value from the at least one intermediate evaluation value; and determining the intermediate parameter corresponding to the target evaluation value as the initial model parameter.

[0078] In some embodiments, the screening strategy comprises: obtaining initial identification information of initial instrument data information; step one: obtaining one of the at least one intermediate model information to obtain target intermediate model information; step two: generating an identification difference value based on the preset calculation strategy, the initial identification information and the intermediate identification information of the target intermediate model information; repeating steps one and two until each intermediate model information in the at least one intermediate model information is processed to obtain at least one identification difference value; screening a target identification difference value from the at least one identification difference value, and determining the intermediate model information corresponding to the target identification difference value as the target intermediate model information.

[0079] In some embodiments, the calculation strategy comprises: obtaining an identification information calculation table, wherein the identification information calculation table comprises the calculation weight and the calculation method of each sub-identification information; generating an identification difference value based on the identification calculation information table, the initial identification information and the intermediate identification information of the target intermediate model information.

[0080] In some embodiments, the state generation module 405 of the instrument state judgment device is further configured to: a data interval threshold, an interval proportion threshold, a target count value, obtain at least one target data bit and a data bit proportion threshold, wherein the target count value is a natural number, and the initial value of the target count value is 0; substitute the initial instrument data information into the target instrument processing model to obtain predicted instrument data information; based on each metadata in the initial instrument data information and the corresponding metadata in the predicted instrument data information, generate at least one metadata difference value; step one: obtain one of the at least one metadata difference value to obtain an intermediate metadata difference value; step two: when the intermediate metadata difference value is greater than the target threshold, the value of the target count value is incremented by one; repeat steps one and two until each metadata difference value in the at least one metadata difference value is compared with the target threshold; generate an intermediate proportion value based on the target count value and the number of metadata difference values in the at least one metadata difference value; when the intermediate proportion value is not less than the interval proportion threshold, set the generated interval result as abnormal; generate a data bit result based on the data bit processing strategy, the at least one target data bit and the data bit proportion threshold; when the results of any one of the interval result and the data bit result are abnormal, set the instrument state information as abnormal; when the results of any one of the interval result and the data bit result are abnormal, set the instrument state information as normal.

[0081] In some embodiments, the data bit processing strategy comprises: setting a target count value to 0; step one: obtaining one of the at least one target data bit to obtain a target data bit; step two: when a metadata difference value corresponding to the target data bit in the at least one metadata difference value is not less than a target threshold, adding one to the target count value; repeating steps one and two until each metadata difference value in the at least one metadata difference value is compared with the target threshold; generating a data bit ratio value based on the target count value and a number of target data bits in the at least one target data bit; and setting a data bit result to be abnormal when the data bit ratio value is not less than an interval ratio threshold.

[0082] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0083] Figure 5 is a schematic diagram of a computer device 5 provided by the embodiments of the present disclosure. As shown in Figure 5 the computer device 5 of this embodiment includes a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. The processor 501 implements the steps in each of the above method embodiments when executing the computer program 503. Alternatively, the processor 501 implements the functions of each module / unit in each of the above device embodiments when executing the computer program 503.

[0084] By way of example, the computer program 503 can be divided into one or more modules / units, which are stored in the memory 502 and executed by the processor 501 to complete the present disclosure. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 503 in the computer device 5.

[0085] The computer device 5 can be a desktop computer, a notebook computer, a palm computer, and a cloud server computer device. The computer device 5 can include but is not limited to the processor 501 and the memory 502. Those skilled in the art can understand, Figure 5 that the computer device 5 is only an example and does not constitute a limitation on the computer device 5, and can include more or fewer components than those shown, or combine certain components, or different components, for example, the computer device can also include an input / output device, a network access device, a bus, etc.

[0086] The processor 501 can be a central processing unit (CPU), or other general purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic components, discrete hardware components, etc. The general purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0087] The memory 502 can be an internal storage unit of the computer device 5, for example, a hard disk or a memory of the computer device 5. The memory 502 can also be an external storage device of the computer device 5, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 502 can include both the internal storage unit and the external storage device of the computer device 5. The memory 502 is used to store computer programs and other programs and data required by the computer device. The memory 502 can also be used to temporarily store data that has been output or will be output.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0089] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0090] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present disclosure.

[0091] In the embodiments provided by the present disclosure, it should be understood that the disclosed apparatus / computer device and method can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely schematic, for example, the division of the modules or units is merely a logical function division, and there can be another division manner in actual implementation, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0092] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] In addition, each functional unit in each embodiment of the present disclosure can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0094] The integrated modules / units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program can include computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier signal and telecommunication signal.

[0095] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure.

Claims

1. An instrument state determination method, characterized by, The method comprises: in response to receiving the update instrument processing model instruction, generating initial instrument processing model parameters based on a preset initial generation strategy; sending an update instrument data processing model request to a model platform server, wherein the update instrument data processing model request comprises initial instrument data information and the initial instrument processing model parameters; in response to receiving the intermediate model information set sent by the model platform server, screening target intermediate model information from the intermediate model information set based on a preset screening strategy, wherein the intermediate model information set comprises at least one intermediate model information, and the intermediate model information comprises intermediate model parameters; updating the intermediate model parameters of the target intermediate model information to the initial instrument processing model to obtain a target instrument processing model; generating instrument state information based on the initial instrument data information and the target instrument processing model; the screening strategy comprises: obtaining initial identification information of the initial instrument data information; step one: obtaining one of the at least one intermediate model information to obtain target intermediate model information; step two: generating an identification difference value based on a preset calculation strategy, the initial identification information and the intermediate identification information of the target intermediate model information; repeating steps one to two until each intermediate model information in the at least one intermediate model information is processed to obtain at least one identification difference value; screening a target identification difference value from the at least one identification difference value, and determining the intermediate model information corresponding to the target identification difference value as the target intermediate model information.

2. The method of claim 1, wherein, The initial generation strategy comprises: obtaining at least one test data set; training the initial instrument processing model based on a preset training strategy through the at least one test data set to obtain initial instrument processing model parameters.

3. The method of claim 2, wherein, The training strategy comprises: training the initial instrument processing model based on each test data set in the at least one test data set to generate at least one intermediate parameter and at least one intermediate evaluation value corresponding to the initial instrument processing model; screening a target evaluation value from the at least one intermediate evaluation value; determining the intermediate parameter corresponding to the target evaluation value as the initial instrument processing model parameter.

4. The method of claim 1, wherein, The calculation strategy comprises: obtaining an identification information calculation table, wherein the identification information calculation table comprises the calculation weight and calculation method of each sub-identification information; generating the identification difference value based on the identification information calculation table, the initial identification information and the intermediate identification information of the target intermediate model information.

5. The method of claim 1, wherein, The instrument state information is generated based on the initial instrument data information and the target instrument processing model, comprising: obtaining at least one target data bit and data bit proportion threshold based on data interval threshold, interval proportion threshold and target count value, wherein the target count value is a natural number, and the initial value of the target count value is 0; substituting the initial instrument data information into the target instrument processing model to obtain predicted instrument data information; generating at least one metadata difference value based on each metadata in the initial instrument data information and the corresponding metadata in the predicted instrument data information; Step one: obtain one of the at least one metadata difference value, to obtain an intermediate metadata difference value; Step two: when the intermediate metadata difference value is greater than the target threshold value, add one to the value of the target count value; Repeat steps one to two until each of the at least one metadata difference value is compared with the target threshold value; Based on the target count value and the number of metadata difference values in the at least one metadata difference value, generate an intermediate ratio value; When the intermediate ratio value is not less than the interval ratio threshold value, set the generated interval result as abnormal; Based on the data bit processing strategy, the at least one target data bit and the data bit ratio threshold value, generate a data bit result; When the result of any one of the interval result and the data bit result is abnormal, set the instrument state information as abnormal; When the result of any one of the interval result and the data bit result is abnormal, set the instrument state information as normal.

6. The method of claim 5, wherein, The data bit processing strategy includes: Set the target count value to 0; Step one: obtain one of the at least one target data bit, to obtain a target data bit; Step two: when the metadata difference value corresponding to the target data bit in the at least one metadata difference value is not less than the target threshold value, add one to the target count value; Repeat steps one to two until each of the at least one metadata difference value is compared with the target threshold value; Based on the target count value and the number of target data bits in the at least one target data bit, generate a data bit ratio value; When the data bit ratio value is not less than the interval ratio threshold value, set the data bit result as abnormal.

7. An apparatus for determining the state of a meter, characterized by It includes: An initial generation module configured to generate an initial instrument processing model parameter based on a preset initial generation strategy in response to receiving an update instrument processing model instruction; A sending module configured to send an update instrument data processing model request to a model platform server, wherein the update instrument data processing model request includes initial instrument data information and the initial instrument processing model parameter; A screening module configured to screen out target intermediate model information from the intermediate model information set based on a preset screening strategy in response to receiving the intermediate model information set sent by the model platform server, wherein the intermediate model information set includes at least one intermediate model information, and the intermediate model information includes an intermediate model parameter; An update module configured to update the intermediate model parameter of the target intermediate model information to the initial instrument processing model to obtain a target instrument processing model; A state generation module configured to generate instrument state information based on the initial instrument data information and the target instrument processing model; The screening strategy includes: Obtain the initial identification information of the initial instrument data information; Step one: obtain one of the at least one intermediate model information, to obtain target intermediate model information; Step two: generate an identification difference value based on a preset calculation strategy, the initial identification information and the intermediate identification information of the target intermediate model information; Repeating the step one to step two until each of the at least one intermediate model information is processed, obtaining at least one identification difference value; Filtering a target identification difference value from the at least one identification difference value, and determining the intermediate model information corresponding to the target identification difference value as the target intermediate model information.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images