Device data cleaning method and device, computer device and medium

Abstract

The present disclosure relates to the technical field of device data processing, and provides a device data cleaning method and device, a computer device and a medium. The method comprises the following steps: sending an update device data processing model request to a model platform server; screening target intermediate model information from the intermediate model information set based on a preset screening strategy; and generating target device data information based on the target intermediate model information and the initial device data information. The present disclosure can greatly improve the efficiency of data cleaning through the above steps.

Description

Technical Field

[0001] This disclosure relates to the field of equipment data processing technology, and in particular to equipment data cleaning methods, apparatus, computer equipment and media. Background Technology

[0002] With the development of industrial instruments and computers, the demand for equipment data is increasing. Existing...

[0003] Data cleaning methods typically involve acquiring data and then performing complex mathematical operations to clean it. However, when dealing with large amounts of data, the extremely high complexity of these mathematical operations makes data cleaning very inefficient. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, apparatus, computer equipment, and medium for cleaning device data, in order to solve the problem that the efficiency of data cleaning is extremely low when dealing with large amounts of data due to the extremely high complexity of mathematical operations.

[0005] A first aspect of this disclosure provides a device data cleaning method, comprising: in response to receiving an instruction to update a device processing model, sending an update device data processing model request to a model platform server, wherein the update device data processing model request includes initial device data information; in response to receiving an intermediate model information set sent by the model platform server, filtering target intermediate model information from the intermediate model information set based on a preset filtering strategy, wherein the intermediate model information set includes at least one intermediate model information (the intermediate model information includes intermediate model parameters); and generating target device data information based on the target intermediate model information and the initial device data information.

[0006] A second aspect of this disclosure provides a device data cleaning apparatus, comprising: a sending module configured to send an update device data processing model request to a model platform server in response to receiving an update device processing model instruction, wherein the update device data processing model request includes initial device data information; a filtering module configured to filter target intermediate model information from the intermediate model information set based on a preset filtering strategy in response to receiving an intermediate model information set sent by the model platform server, wherein the intermediate model information set includes at least one intermediate model information (the intermediate model information includes intermediate model parameters); and a generation module configured to generate target device data information based on the target intermediate model information and the initial device data information.

[0007] A third aspect of this disclosure provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0008] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0009] The beneficial effects of this disclosure embodiment compared with the prior art include at least the following: by sending an update device data processing model request to the model platform server; filtering target intermediate model information from the intermediate model information set based on a preset filtering strategy; and generating target device data information based on the target intermediate model information and the initial device data information, the efficiency of data cleaning can be greatly improved. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of a joint learning architecture according to an embodiment of this disclosure;

[0012] Figure 2 This is a flowchart of a device data cleaning method provided in an embodiment of this disclosure. Figure 1 ;

[0013] Figure 3 This is a flowchart of another device data cleaning method provided in this disclosure embodiment. Figure 2 ;

[0014] Figure 4 This is a block diagram of a device data cleaning apparatus provided in an embodiment of this disclosure;

[0015] Figure 5 This is a schematic diagram of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0016] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0017] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] Federation learning refers to the comprehensive utilization of multiple AI (Artificial Intelligence) technologies, under the premise of ensuring data security and user privacy, to collaboratively explore the value of data and foster new intelligent business forms and models based on joint modeling. Federation learning has at least the following characteristics:

[0019] (1) Participating nodes control their own data in a weakly centralized joint training mode to ensure data privacy and security in the process of co-creating intelligence.

[0020] (2) In different application scenarios, various model aggregation optimization strategies are established by using screening and / or combination of AI algorithms and privacy-preserving computing to obtain high-level and high-quality models.

[0021] (3) Under the premise of ensuring data security and user privacy, based on multiple model aggregation optimization strategies, obtain methods to improve the performance of the federated learning engine. The performance methods can be improved by solving problems such as parallel computing architecture, information interaction under large-scale cross-domain networks, intelligent perception, and anomaly handling mechanisms.

[0022] (4) Obtain the needs of multiple users in various scenarios, determine the true contribution of each joint participant through a mutual trust mechanism, and allocate incentives accordingly.

[0023] Based on the above approach, an AI technology ecosystem based on collaborative learning can be established, fully leveraging the value of industry data and promoting the implementation of scenarios in vertical fields.

[0024] This disclosure will now be described in detail with reference to the accompanying drawings.

[0025] Figure 1 This is a schematic diagram of a joint learning architecture according to an embodiment of this disclosure. Figure 1 As shown, the architecture of joint learning may include a server (central node) 101 and participants 102, 103 and 104.

[0026] In the joint learning process, a basic model can be established through server 101, which then sends this model to participants 102, 103, and 104 with whom it has established a communication connection. Alternatively, any participant can establish the basic model and upload it to server 101, which then sends it to other participants with whom it has established a communication connection. Participants 102, 103, and 104 construct models based on the downloaded basic structure and model parameters, train the models using local data, obtain updated model parameters, and encrypt and upload these updated model parameters to server 101. Server 101 aggregates the model parameters sent by participants 102, 103, and 104 to obtain global model parameters, which are then transmitted back to participants 102, 103, and 104. Participants 102, 103, and 104 iterate on their respective models based on the received global model parameters until the models converge, thus achieving model training. During the collaborative learning process, the data uploaded by participants 102, 103, and 104 are model parameters. Local data is not uploaded to server 101, and all participants can share the final model parameters. Therefore, collaborative modeling can be achieved while ensuring data privacy. It should be noted that the number of participants is not limited to the three mentioned above, but can be set as needed. This embodiment of the disclosure does not impose any restrictions on this.

[0027] Figure 2 This is a flowchart of a device data cleaning method provided in an embodiment of this disclosure. Figure 2 Equipment data cleaning methods can be developed by Figure 1 The participating parties execute it. For example... Figure 2 As shown, the data cleaning method for this device includes:

[0028] S201, in response to receiving the instruction to update the device processing model, a request to update the device data processing model is sent to the model platform server, wherein the request to update the device data processing model includes initial device data information.

[0029] An instruction can refer to a command that a computer uses to perform a certain operation, consisting of a string of binary digits. An "update device processing model" instruction can refer to an instruction used to instruct server 2 to update its device processing model. The device processing model can refer to a neural network model. A preset initial generation strategy can refer to the steps or methods for generating initial model parameters. Initial model parameters can refer to the relevant parameters of the existing device processing model before receiving the "update device processing model" instruction.

[0030] A request can refer to a command from a computer to perform a certain operation, consisting of a string of binary digits. An update device processing model request can refer to a request instructing server 2 to update its device processing model. Initial device data information can refer to relevant data collected related to the device used for prediction data. A model platform server can refer to a server used to manage various types of model information. This model platform server can issue instructions to at least one training server, where the instructions include initial model parameters. The at least one training server first updates the initial model parameters to its local model, then trains locally based on local data, and feeds back the at least one model parameter obtained from the training to the model platform server. Subsequently, the model platform server can send the at least one model parameter to server 2.

[0031] S202, in response to receiving the intermediate model information set sent by the model platform server, the target intermediate model information is filtered out from the intermediate model information set based on a preset filtering strategy, wherein the intermediate model information set includes at least one intermediate model information.

[0032] An intermediate model information set can refer to a collection of multiple intermediate model information sets. Intermediate model information can refer to information related to model parameters obtained by the model platform server. This intermediate model information can include intermediate model parameters. An intermediate model parameter can refer to a model parameter within the model server platform.

[0033] S203, Based on the target intermediate model information and the initial device data information, generate the target device data information.

[0034] The target device data information can refer to the data information after data cleaning.

[0035] According to the technical solution provided in this disclosure, by sending an update device data processing model request to the model platform server; filtering target intermediate model information from the intermediate model information set based on a preset filtering strategy; and generating target device data information based on the target intermediate model information and the initial device data information, the efficiency of data cleaning can be greatly improved.

[0036] In some embodiments, the filtering strategy includes: obtaining initial identification information of initial device data information; step one: obtaining one of the intermediate model information from at least one intermediate model information to obtain target intermediate model information; step two: generating an identification difference 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; filtering out the target identification difference from the at least one identification difference, and determining the intermediate model information corresponding to the target identification difference as the target intermediate model information.

[0037] Initial identification information can refer to some relevant information about the device. For example, this initial identification information may include device type information, device usage time information, etc. Device type information can refer to the values ​​represented by different device types. For example, device A has a type value of 01, and device B has a type value of 02. The preset calculation strategy can refer to the steps or methods for calculating the initial and intermediate identification information, and can be set as needed; no specific restrictions are imposed here. The target identification difference can be the smallest identification difference among the at least one identification difference.

[0038] In some embodiments, the calculation strategy includes: obtaining an identification information calculation table, wherein the identification information calculation table includes the calculation weight and calculation method of each sub-identification information; and generating an identification difference based on the identification calculation information table, the initial identification information, and the intermediate identification information of the target intermediate model information.

[0039] The identifier mapping table can refer to the scoring rules and calculation weights of each identifier in the initial identifier information. As an example, this identifier information calculation table can be shown below:

[0040]

[0041] Here, sub-identifier information can refer to one of the identifier information in the initial identifier information. The calculation weight can refer to the proportional coefficient of the calculation formula for each sub-identifier information, and the sum of the proportional coefficients of the calculation formula for each sub-identifier information is 1.

[0042] By substituting the intermediate identification information of the initial identification information and the target intermediate model information into the identification calculation information table, the identification difference can be obtained.

[0043] In some embodiments, the sub-identification information includes: device model information, usage time information, and data volume information.

[0044] Equipment model information refers to the specific model of the equipment. Since different models of the same category of equipment can differ significantly, using equipment model information as sub-identifier information provides higher accuracy. Usage time information refers to the time the equipment has been used. Processing volume scale information refers to different levels of the amount of data in the initial identification information; this level can be manually set. As a specific embodiment, an identifier mapping table using equipment model information, usage time information, and processing volume scale information as sub-identifier information can be as follows:

[0045]

[0046] In some embodiments, generating target device data information based on target intermediate model information and initial device data information includes: updating intermediate model parameters of the target intermediate model information to the initial device processing model and then to the target device processing model; importing the initial device data information into the target device processing model to generate predicted device data information; and generating target device data information based on the initial device data information and predicted device data information.

[0047] Predictive device data information refers to the predictive information obtained after training with initial device data information. Predictive device data information can indicate the target range of the data within a certain range, but it is not precise. Therefore, it is necessary to combine the predictive device data information with the initial device data information, remove outlier data, and generate target device data information.

[0048] In some embodiments, generating target device data information based on initial device data information and predicted device data information includes: obtaining a target threshold; generating at least one metadata difference based on each metadata in the initial device data information and the corresponding metadata in the predicted device data information; step one: obtaining one of the metadata differences among the at least one metadata difference to obtain an intermediate metadata difference; step two: in response to determining that the intermediate metadata difference is greater than the target threshold, replacing the metadata in the predicted device data information corresponding to the intermediate metadata difference with the metadata in the initial device data information corresponding to the intermediate metadata difference; step three: deleting the intermediate metadata difference from the at least one metadata difference; repeating steps one to three until each metadata difference among the at least one metadata difference is compared with the target threshold; and determining the initial device data information as the target device data information.

[0049] The target threshold refers to the limited range of the difference between the metadata in the initial equipment data and the corresponding metadata in the predicted equipment data. When this difference is not less than this limited range, the data is considered abnormal and requires processing. Metadata refers to the basic data unit in the initial or predicted equipment data. The metadata difference refers to the difference between the metadata in the initial instrument data and the corresponding metadata in the predicted instrument data; this difference is a non-negative number. The intermediate data difference refers to the selected metadata difference.

[0050] In some embodiments, generating at least one metadata difference based on each metadata in the initial device data information and the corresponding metadata in the predicted device data information includes: Step 1: Obtaining one of the unmarked metadata in the initial device data information to obtain initial metadata; Step 2: Obtaining the metadata in the predicted device data information corresponding to the intermediate metadata to obtain predicted metadata; Step 3: Generating a metadata difference based on the initial metadata and the predicted metadata; Step 4: Marking the intermediate metadata as used; Repeating steps 1 to 3 until each metadata in the initial device data information is marked as used to obtain at least one metadata difference.

[0051] Initial metadata can refer to one of the metadata elements in the initial device data information. Predictive metadata can refer to one of the metadata elements in the predictive device data information.

[0052] Figure 3 This is a flowchart of a boiler equipment data cleaning method provided in an embodiment of this disclosure. Figure 3 The data cleaning method for boiler equipment can be performed by the participating parties. For example... Figure 3 As shown, the data cleaning method for this boiler equipment includes:

[0053] S301: In response to receiving the instruction to update the boiler equipment processing model, a request to update the boiler equipment data processing model is sent to the model platform server, wherein the request to update the boiler equipment data processing model includes the initial boiler equipment data information.

[0054] S302: In response to receiving the intermediate model information set sent by the model platform server, obtain the initial identification information of the initial boiler equipment data information, wherein the intermediate model information set includes two intermediate model information.

[0055] S303: Obtain one of the two intermediate model information to get the target intermediate model information.

[0056] S304: Obtain the identification information calculation table, wherein the identification information calculation table includes the calculation weight and calculation method of each sub-identification information.

[0057] S305: Generate an identification difference based on the intermediate identification information of the identification calculation information table, the initial identification information, and the target intermediate model information.

[0058] S306: Repeat S303 to S305 until each of the two intermediate model information is processed to obtain at least one identification difference.

[0059] S307: Select the target identifier difference from at least one identifier difference, and determine the intermediate model information corresponding to the target identifier difference as the target intermediate model information.

[0060] S308: Update the intermediate model parameters of the target intermediate model information to the initial boiler equipment processing model, and then to the target boiler equipment processing model.

[0061] S309: Import the initial boiler equipment data into the target boiler equipment processing model to generate predicted boiler equipment data.

[0062] S310: Obtain the target threshold.

[0063] S311: Generate at least one metadata difference based on each metadata in the initial boiler equipment data information and the corresponding metadata in the predicted boiler equipment data information.

[0064] S312: Obtain one of the metadata differences from at least one metadata difference to obtain an intermediate metadata difference.

[0065] S313: In response to determining that the intermediate metadata difference is greater than the target threshold, the metadata corresponding to the intermediate metadata difference in the predicted boiler equipment data information is replaced with the metadata corresponding to the intermediate metadata difference in the initial boiler equipment data information.

[0066] S314: Delete intermediate metadata differences from at least one metadata difference.

[0067] S315: Repeat S312 to S314 until each of the metadata differences in at least one metadata difference is compared with the target threshold.

[0068] S316: Determine the initial boiler equipment data information as the target boiler equipment data information.

[0069] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0070] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0071] Figure 4 This is a schematic diagram of the device data cleaning apparatus provided in an embodiment of this disclosure. Figure 4 As shown, the data cleaning device of this equipment includes:

[0072] The sending module 401 is configured to send an update device data processing model request to the model platform server in response to receiving an update device processing model instruction, wherein the update device data processing model request includes initial device data information;

[0073] The filtering module 402 is configured to, in response to receiving an intermediate model information set sent by the model platform server, filter out target intermediate model information from the intermediate model information set based on a preset filtering strategy, wherein the intermediate model information set includes at least one intermediate model information (the intermediate model information includes intermediate model parameters).

[0074] The generation module 403 is configured to generate target device data information based on the target intermediate model information and the initial device data information.

[0075] According to the technical solution provided in this disclosure, by sending an update device data processing model request to the model platform server; filtering target intermediate model information from the intermediate model information set based on a preset filtering strategy; and generating target device data information based on the target intermediate model information and the initial device data information, the efficiency of data cleaning can be greatly improved.

[0076] In some embodiments, the filtering strategy includes: obtaining initial identification information of initial device data information; step one: obtaining one of the intermediate model information from at least one intermediate model information to obtain target intermediate model information; step two: generating an identification difference 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; filtering out the target identification difference from the at least one identification difference, and determining the intermediate model information corresponding to the target identification difference as the target intermediate model information.

[0077] In some embodiments, the calculation strategy includes: obtaining an identification information calculation table, wherein the identification information calculation table includes the calculation weight and calculation method of each sub-identification information; and generating an identification difference based on the identification calculation information table, the initial identification information, and the intermediate identification information of the target intermediate model information.

[0078] In some embodiments, the sub-identification information includes: device model information, usage time information, and data processing volume information. In some embodiments, the filtering module 402 of the device data cleaning device is further configured to: update the intermediate model parameters of the target intermediate model information to the initial device processing model and then to the target device processing model; import the initial device data information into the target device processing model to generate predicted device data information; and generate target device data information based on the initial device data information and the predicted device data information.

[0079] In some embodiments, generating target device data information based on initial device data information and predicted device data information includes: obtaining a target threshold; generating at least one metadata difference based on each metadata in the initial device data information and the corresponding metadata in the predicted device data information; step one: obtaining one of the metadata differences among the at least one metadata difference to obtain an intermediate metadata difference; step two: in response to determining that the intermediate metadata difference is greater than the target threshold, replacing the metadata in the predicted device data information corresponding to the intermediate metadata difference with the metadata in the initial device data information corresponding to the intermediate metadata difference; step three: deleting the intermediate metadata difference from the at least one metadata difference; repeating steps one to three until each metadata difference among the at least one metadata difference is compared with the target threshold; and determining the initial device data information as the target device data information.

[0080] In some embodiments, generating at least one metadata difference based on each metadata in the initial device data information and the corresponding metadata in the predicted device data information includes: Step 1: Obtaining one of the unmarked metadata in the initial device data information to obtain initial metadata; Step 2: Obtaining the metadata in the predicted device data information corresponding to the intermediate metadata to obtain predicted metadata; Step 3: Generating a metadata difference based on the initial metadata and the predicted metadata; Step 4: Marking the intermediate metadata as used; Repeating steps 1 to 3 until each metadata in the initial device data information is marked as used to obtain at least one metadata difference.

[0081] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0082] Figure 5 This is a schematic diagram of a computer device 500 provided in an embodiment of this disclosure. Figure 5 As shown, the computer device 500 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. When the processor 501 executes the computer program 503, it implements the steps in the various method embodiments described above. Alternatively, when the processor 501 executes the computer program 503, it implements the functions of each module / unit in the various device embodiments described above.

[0083] For example, computer program 503 may be divided into one or more modules / units, which are stored in memory 502 and executed by processor 501 to perform the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 503 in computer device 500.

[0084] Computer device 500 can be a desktop computer, laptop, handheld computer, cloud server, or other similar computer device. Computer device 500 may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will understand that... Figure 5 This is merely an example of computer device 500 and does not constitute a limitation on computer device 500. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer device may also include input / output devices, network access devices, buses, etc.

[0085] Processor 501 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0086] The memory 502 can be an internal storage unit of the computer device 500, such as a hard disk or RAM of the computer device 500. The memory 502 can also be an external storage device of the computer device 500, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device 500. Furthermore, the memory 502 can include both internal and external storage units of the computer device 500. 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.

[0087] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0088] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0089] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 this disclosure.

[0090] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0091] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0092] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0093] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in a computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0094] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. A device data processing method, characterized in that, The method includes: In response to receiving an instruction to update the device processing model, an update device data processing model request is sent to the model platform server, wherein the update device data processing model request includes initial device data information; In response to receiving an intermediate model information set sent by the model platform server, target intermediate model information is filtered from the intermediate model information set based on a preset filtering strategy, wherein the intermediate model information set includes at least one intermediate model information. Based on the target intermediate model information and the initial device data information, target device data information is generated; The screening strategy includes: Acquire the initial identification information of the initial device data information; Step 1: Obtain one of the intermediate model information from the at least one intermediate model information to obtain the target intermediate model information; Step 2: Based on the preset calculation strategy, the initial identification information, and the intermediate identification information of the target intermediate model information, generate the identification difference; Repeat steps one to two until each of the at least one intermediate model information is processed to obtain at least one identifier difference; Target identifier difference is selected from the at least one identifier difference, and the intermediate model information corresponding to the target identifier difference is determined as the target intermediate model information; The calculation strategy includes: Obtain an identification information calculation table, wherein the identification information calculation table includes the calculation weight and calculation method of each sub-identification information; The identifier difference is generated based on the identifier information calculation table, the initial identifier information, and the intermediate identifier information of the target intermediate model information; The step of generating target device data information based on the target intermediate model information and the initial device data information includes: Update the intermediate model parameters of the target intermediate model information to the initial device processing model, and then to the target device processing model; The initial device data information is imported into the target device processing model to generate predicted device data information; Based on the initial device data and the predicted device data, target device data is generated; Based on the initial device data information and the predicted device data information, target device data information is generated, including: Obtain the target threshold; Based on each metadata in the initial device data information and the corresponding metadata in the predicted device data information, at least one metadata difference is generated; Step 1: Obtain one of the at least one metadata difference values ​​to obtain the intermediate metadata difference value; Step 2: In response to determining that the intermediate metadata difference is greater than the target threshold, replace the metadata in the prediction device data information corresponding to the intermediate metadata difference with the metadata in the initial device data information corresponding to the intermediate metadata difference; Step 3: Delete the intermediate metadata difference from the at least one metadata difference; Repeat steps one through three until each of the at least one metadata difference is compared with the target threshold. The initial device data information is determined as the target device data information.

2. The method according to claim 1, characterized in that, The sub-identifier information includes: Equipment model information, usage time information, and data processing volume information.

3. The method according to claim 1, characterized in that, The step of generating at least one metadata difference based on each metadata in the initial device data information and the corresponding metadata in the predicted device data information includes: Step 1: Obtain one of the untagged metadata elements from the initial device data information to obtain the initial metadata; Step 2: Obtain the metadata corresponding to the intermediate metadata from the prediction device data information to obtain the prediction metadata; Step 3: Generate metadata difference based on the initial metadata and the predicted metadata; Step 4: Mark the intermediate metadata as used; Repeat steps one through three until each metadata in the initial device data information is marked as used, thus obtaining the at least one metadata difference.

4. A device for cleaning equipment data, wherein the device employs the method described in any one of claims 1-3, characterized in that, The device includes: The sending module is configured to send an update device data processing model request to the model platform server in response to receiving an update device processing model instruction, wherein the update device data processing model request includes initial device data information; The filtering module is configured to, in response to receiving an intermediate model information set sent by the model platform server, filter out target intermediate model information from the intermediate model information set based on a preset filtering strategy, wherein the intermediate model information set includes at least one intermediate model information, and the intermediate model information includes intermediate model parameters. The generation module is configured to generate target device data information based on the target intermediate model information and the initial device data information.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 3.

Images