Equipment checking method and device, computer equipment, storage medium and computer program product
Through the analysis and feature extraction of wireless radio frequency identification tag information, combined with pre-training models, the problem of low accuracy of traditional manual inventory IT equipment is solved, and high-accuracy automated equipment inventory is achieved.
Patent Information
- Application Number
- CN202411715638.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-27
- Publication Date
- 2025-02-25
AI Technical Summary
Traditional manual inventory of IT equipment has subjective factors and is prone to errors, resulting in low accuracy of equipment inventory.
By obtaining the wireless radio frequency identification tag information of the device to be counted, the feature extraction is performed after analysis and preprocessing, and inputting it to the pre-trained device inventory result prediction model to obtain the status change information of the device.
It improves the accuracy of equipment inventory, avoids subjective errors in manual inventory, and realizes an automated and uninterrupted equipment inventory process.
Smart Images
Figure CN119514569A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a device inventory method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art
[0002] As enterprises become more information-based, IT (Information Technology) asset management has become a key link in ensuring business continuity and cost optimization. In order to ensure the normal operation of IT equipment, it is essential to inventory IT equipment.
[0003] In traditional technology, manual inventory is generally used in the process of equipment inventory; however, this manual inventory method has subjective factors and is prone to errors, resulting in low accuracy of equipment inventory. Summary of the invention
[0004] Based on this, it is necessary to provide a device inventory method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of device inventory in response to the above technical problems.
[0005] In a first aspect, the present application provides a device inventory method, comprising:
[0006] Acquire tag information of the device to be counted; the tag information is obtained by identifying a radio frequency identification tag set on the device to be counted;
[0007] Parsing the tag information to obtain current status information of the device to be counted, and acquiring historical status information of the device to be counted;
[0008] Preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted;
[0009] Performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information;
[0010] The first feature vector and the second feature vector are input into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as a target device inventory result corresponding to the device to be inventoried.
[0011] In one of the embodiments, the pre-processed current state information includes a plurality of sub-state information;
[0012] The performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information includes:
[0013] Performing feature extraction processing on the plurality of sub-state information respectively to obtain sub-feature vectors corresponding to the plurality of sub-state information;
[0014] A concatenation order of the plurality of sub-state information is obtained, and sub-feature vectors corresponding to the plurality of sub-state information are concatenated according to the concatenation order to obtain the first feature vector.
[0015] In one embodiment, the performing feature extraction processing on the plurality of sub-state information respectively to obtain sub-feature vectors corresponding to the plurality of sub-state information includes:
[0016] Identify target data types corresponding to the plurality of sub-state information;
[0017] According to the target data type, query the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the multiple sub-state information;
[0018] The target feature extraction model is used to perform feature extraction processing on the plurality of sub-state information respectively to obtain sub-feature vectors corresponding to the plurality of sub-state information.
[0019] In one embodiment, the parsing of the tag information to obtain the current status information of the device to be counted includes:
[0020] Parsing the tag information to obtain parsed information of the device to be counted;
[0021] Inputting each of the analysis information into a pre-trained entropy value prediction model to obtain the entropy value of each of the analysis information;
[0022] Determining the importance of each piece of parsed information according to the entropy value of each piece of parsed information;
[0023] From each of the analysis information, the analysis information whose importance is greater than a preset importance is screened out as the current state information.
[0024] In one embodiment, before obtaining the tag information of the device to be counted, the method further includes:
[0025] Receiving a device inventory task sent by a terminal, and determining a target device type corresponding to the device inventory task;
[0026] The device type of the candidate device is obtained, and the candidate device whose device type meets the target device type is screened out from the candidate devices as the device to be counted.
[0027] In one embodiment, the pre-trained equipment inventory result prediction model is trained in the following manner:
[0028] Get sample tag information of sample equipment;
[0029] Parsing the sample tag information to obtain current sample status information of the sample device and acquiring historical sample status information of the sample device;
[0030] Preprocessing the current sample state information and the historical sample state information respectively to obtain the preprocessed current sample state information and the preprocessed historical sample state information of the sample device;
[0031] Performing feature extraction processing on the preprocessed current sample state information and the preprocessed historical sample state information respectively to obtain a first sample feature vector corresponding to the preprocessed current sample state information and a second sample feature vector corresponding to the preprocessed historical sample state information;
[0032] Inputting the first sample feature vector and the second sample feature vector into a device inventory result prediction model to be trained, and obtaining state change information corresponding to the sample device as a predicted device inventory result corresponding to the sample device;
[0033] The actual device inventory result corresponding to the sample device is obtained, and according to the difference between the predicted device inventory result and the actual device inventory result, the device inventory result prediction model to be trained is iteratively trained to obtain the pre-trained device inventory result prediction model.
[0034] In a second aspect, the present application also provides a device inventory apparatus, comprising:
[0035] An information acquisition module is used to acquire tag information of the device to be counted; the tag information is obtained by identifying a wireless radio frequency identification tag set on the device to be counted;
[0036] A status acquisition module is used to parse the tag information to obtain the current status information of the device to be counted and to obtain the historical status information of the device to be counted;
[0037] An information processing module, used to pre-process the current state information and the historical state information respectively, to obtain the pre-processed current state information and the pre-processed historical state information of the device to be counted;
[0038] A feature extraction module, used to perform feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively, to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information;
[0039] The result prediction module is used to input the first feature vector and the second feature vector into a pre-trained device inventory result prediction model to obtain the state change information corresponding to the device to be inventoried as the target device inventory result corresponding to the device to be inventoried.
[0040] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0041] Acquire tag information of the device to be counted; the tag information is obtained by identifying a radio frequency identification tag set on the device to be counted;
[0042] Parsing the tag information to obtain current status information of the device to be counted, and acquiring historical status information of the device to be counted;
[0043] Preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted;
[0044] Performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information;
[0045] The first feature vector and the second feature vector are input into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as a target device inventory result corresponding to the device to be inventoried.
[0046] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0047] Acquire tag information of the device to be counted; the tag information is obtained by identifying a radio frequency identification tag set on the device to be counted;
[0048] Parsing the tag information to obtain current status information of the device to be counted, and acquiring historical status information of the device to be counted;
[0049] Preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted;
[0050] Performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information;
[0051] The first feature vector and the second feature vector are input into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as a target device inventory result corresponding to the device to be inventoried.
[0052] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0053] Acquire tag information of the device to be counted; the tag information is obtained by identifying a radio frequency identification tag set on the device to be counted;
[0054] Parsing the tag information to obtain current status information of the device to be counted, and acquiring historical status information of the device to be counted;
[0055] Preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted;
[0056] Performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information;
[0057] The first feature vector and the second feature vector are input into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as a target device inventory result corresponding to the device to be inventoried.
[0058] The above-mentioned equipment inventory method, apparatus, computer equipment, storage medium and computer program product first perform identification processing on the wireless radio frequency identification tag set on the equipment to be inventoried to obtain the tag information of the equipment to be inventoried, then parse the tag information to obtain the current state information of the equipment to be inventoried, and obtain the historical state information of the equipment to be inventoried, then pre-process the current state information and the historical state information respectively to obtain the pre-processed current state information and the pre-processed historical state information of the equipment to be inventoried, then perform feature extraction processing on the pre-processed current state information and the pre-processed historical state information respectively to obtain the first feature vector corresponding to the pre-processed current state information and the second feature vector corresponding to the pre-processed historical state information, finally, the first feature vector and the second feature vector are input into a pre-trained equipment inventory result prediction model to obtain the state change information corresponding to the equipment to be inventoried as the target equipment inventory result corresponding to the equipment to be inventoried. In this way, in the process of taking inventory of equipment, after the label information of the equipment to be counted is obtained, a series of processing steps such as parsing, preprocessing and feature extraction are performed, and finally with the help of a pre-trained equipment inventory result prediction model, a comprehensive and in-depth understanding of the state changes of the equipment to be counted can be achieved, and then the inventory results of the target equipment corresponding to the equipment to be counted can be accurately determined, which is conducive to improving the accuracy of the equipment inventory; moreover, the entire process does not require human intervention, avoiding the subjective factors in the manual inventory method, which is prone to errors and leads to the defect of low accuracy of the equipment inventory, thereby improving the accuracy of the equipment inventory. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0060] Figure 1 A schematic diagram of a flow chart of a device inventory method in one embodiment;
[0061] Figure 2 A schematic flow chart of a device inventory method in another embodiment;
[0062] Figure 3 A schematic diagram of a system architecture of an IT asset intelligent inventory method based on RFID technology in one embodiment;
[0063] Figure 4 A schematic diagram of a process of an IT asset intelligent inventory method based on RFID technology in one embodiment;
[0064] Figure 5 It is a structural block diagram of a device inventory counting apparatus in one embodiment;
[0065] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0066] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0068] In an exemplary embodiment, Figure 1 As shown, a device inventory method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones and tablet computers; the server can be implemented as an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:
[0069] Step S101, obtaining tag information of the device to be counted; the tag information is obtained by identifying the wireless radio frequency identification tag set on the device to be counted.
[0070] Among them, the equipment to be counted refers to the IT equipment that needs to be counted (also called IT assets, such as servers, computers, printers, etc.).
[0071] The tag information is used to represent the information set in the wireless radio frequency identification tag of the device to be counted, including key information such as the unique identification, type, and location of the device to be counted.
[0072] The radio frequency identification tag refers to a radio frequency identification (RFID) tag.
[0073] Exemplarily, in response to a device inventory instruction for the device to be inventoryed, the server receives tag information of the device to be inventoryed sent by a handheld or fixed RFID reader / writer via a wireless network, wherein the wireless network includes communication methods such as Wi-Fi (Wireless Fidelity) and Bluetooth.
[0074] It should be noted that the handheld or fixed RFID reader / writer scans the area where the device to be counted is located to obtain the tag information of the device to be counted.
[0075] Step S102: parse the tag information to obtain current status information of the device to be counted, and obtain historical status information of the device to be counted.
[0076] The current status information refers to the status information of the device to be counted at the current time (such as location information, operation information, performance information, etc.).
[0077] The historical status information refers to the status information of the device to be counted at a historical time.
[0078] Exemplarily, the server parses the tag information to obtain the status information of the device to be counted at the current time as the current status information of the device to be counted; then, the server obtains the status information of the device to be counted at the current time through the database in the asset management system as the historical status information of the device to be counted.
[0079] Step S103, preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted.
[0080] The pre-processed current state information refers to the current state information after pre-processing.
[0081] The pre-processed historical status information refers to the historical status information after pre-processing.
[0082] Exemplarily, the server uses data processing technology to perform pre-processing such as cleaning, fusion, and conversion on the current state information and the historical state information, respectively, to inventory the pre-processed current state information and the pre-processed historical state information of the device.
[0083] Step S104 , performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively, to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information.
[0084] The first eigenvector refers to the eigenvector corresponding to the current state information after preprocessing.
[0085] The second eigenvector refers to the eigenvector corresponding to the historical state information after preprocessing.
[0086] Exemplarily, the server inputs the preprocessed current state information into the feature extraction model for feature extraction processing, and obtains a feature vector corresponding to the preprocessed current state information as the first feature vector; then, the server inputs the preprocessed historical state information into the feature extraction model for feature extraction processing, and obtains a feature vector corresponding to the preprocessed historical state information as the second feature vector.
[0087] Step S105, inputting the first feature vector and the second feature vector into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as the target device inventory result corresponding to the device to be inventoried.
[0088] Among them, the equipment inventory result prediction model refers to a network model that can use the first eigenvector and the second eigenvector to obtain the state change information corresponding to the equipment to be inventoried, such as a recurrent neural network model, a convolutional neural network model, etc.
[0089] The state change information is used to indicate the difference between the current state information after preprocessing and the historical state information after preprocessing.
[0090] The target device inventory result is used to represent the comprehensive device inventory status of the device to be inventoried.
[0091] Exemplarily, the server inputs the first feature vector and the second feature vector into a pre-trained device inventory result prediction model to obtain distance information (such as Euclidean distance) between the first feature vector and the second feature vector as state change information corresponding to the device to be inventoried; then, the server obtains the device identification (such as the device name) corresponding to the device to be inventoried, and combines the state change information and the device identification corresponding to the device to be inventoried in a preset manner to obtain the target device inventory result corresponding to the device to be inventoried.
[0092] In the above-mentioned device inventory method, the wireless radio frequency identification tag set on the device to be inventoried is first identified and processed to obtain the tag information of the device to be inventoried, and then the tag information is parsed and processed to obtain the current state information of the device to be inventoried, and the historical state information of the device to be inventoried is obtained. Then, the current state information and the historical state information are preprocessed respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be inventoried. Then, feature extraction processing is performed on the preprocessed current state information and the preprocessed historical state information respectively to obtain the first feature vector corresponding to the preprocessed current state information and the second feature vector corresponding to the preprocessed historical state information. Finally, the first feature vector and the second feature vector are input into a pre-trained device inventory result prediction model to obtain the state change information corresponding to the device to be inventoried as the target device inventory result corresponding to the device to be inventoried. In this way, in the process of taking inventory of equipment, after the label information of the equipment to be counted is obtained, a series of processing steps such as parsing, preprocessing and feature extraction are performed, and finally with the help of a pre-trained equipment inventory result prediction model, a comprehensive and in-depth understanding of the state changes of the equipment to be counted can be achieved, and then the inventory results of the target equipment corresponding to the equipment to be counted can be accurately determined, which is conducive to improving the accuracy of the equipment inventory; moreover, the entire process does not require human intervention, avoiding the subjective factors in the manual inventory method, which is prone to errors and leads to the defect of low accuracy of the equipment inventory, thereby improving the accuracy of the equipment inventory.
[0093] In an exemplary embodiment, the pre-processed current state information includes a plurality of sub-state information.
[0094] Then, the above step S104, respectively performs feature extraction processing on the preprocessed current state information and the preprocessed historical state information to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information, specifically includes the following contents: respectively perform feature extraction processing on multiple sub-state information to obtain sub-feature vectors corresponding to the multiple sub-state information; obtain the splicing order of the multiple sub-state information, and according to the splicing order, perform splicing processing on the sub-feature vectors corresponding to the multiple sub-state information to obtain the first feature vector.
[0095] The sub-state information refers to part of the state information in the current state information after preprocessing, such as location information, operation information or performance information.
[0096] The sub-feature vector refers to the feature vector corresponding to the sub-state information.
[0097] The splicing order is used to indicate the order information of the sub-state information during the splicing process.
[0098] Exemplarily, the server inputs the multiple sub-state information in the current state information after preprocessing into the feature extraction model for feature extraction processing, and obtains sub-feature vectors corresponding to the multiple sub-state information; then, the server determines the splicing order of the multiple sub-state information according to the position information of each sub-state information in the current state information after preprocessing; then, the server splices the sub-feature vectors corresponding to the multiple sub-state information according to the splicing order, and obtains the spliced sub-feature vector as the first feature vector.
[0099] In this embodiment, by performing feature extraction processing on multiple sub-state information in the current state information after preprocessing, the unique features contained in each sub-state information can be deeply explored; multiple sub-feature vectors are spliced in a specific splicing order to obtain a first feature vector, thereby organically integrating the features extracted from each sub-state information, which is beneficial to improving the accuracy of determining the first feature vector.
[0100] In an exemplary embodiment, feature extraction processing is performed on multiple sub-state information respectively to obtain sub-feature vectors corresponding to the multiple sub-state information, which specifically includes the following contents: identifying the target data type corresponding to the multiple sub-state information; according to the target data type, querying the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the multiple sub-state information; through the target feature extraction model, feature extraction processing is performed on the multiple sub-state information respectively to obtain the sub-feature vectors corresponding to the multiple sub-state information.
[0101] The target data type refers to the data type corresponding to the sub-state information, such as numerical data, text data, etc.
[0102] The correspondence between the data type and the feature extraction model is used to represent the association information between the data type and the feature extraction model. For example, data type A corresponds to feature extraction model a, data type B corresponds to feature extraction model b, and data type C corresponds to feature extraction model c.
[0103] The target feature extraction model refers to the feature extraction model corresponding to the sub-state information.
[0104] Exemplarily, the server performs integrity check processing on multiple sub-state information to obtain integrity check results corresponding to the multiple sub-state information; then, when the integrity check results indicate that the multiple sub-state information have passed, the server identifies the target data types corresponding to the multiple sub-state information; then, the server queries the correspondence between the data type and the feature extraction model based on the target data type, and obtains the feature extraction model corresponding to the target data type of the multiple sub-state information as the target data type corresponding to the multiple sub-state information; then, the server inputs the multiple sub-state information into the target feature extraction model, and performs feature extraction processing on the multiple sub-state information respectively through the target feature extraction model to obtain sub-feature vectors corresponding to the multiple sub-state information.
[0105] In this embodiment, by first identifying the target data type corresponding to multiple sub-state information, and then determining the target feature extraction model based on the correspondence between the data type and the feature extraction model, it can ensure that the extraction model that best suits the data characteristics of each sub-state information is selected, thereby accurately mining the key features contained therein, which is conducive to improving the accuracy of determining the sub-feature vectors corresponding to multiple sub-state information.
[0106] In an exemplary embodiment, the above step S102, in which the tag information is parsed to obtain the current status information of the device to be counted, specifically includes the following contents: parsing the tag information to obtain the parsed information of the device to be counted; inputting each parsed information into a pre-trained entropy value prediction model to obtain the entropy value of each parsed information; determining the importance of each parsed information according to the entropy value of each parsed information; and screening out the parsed information having an importance greater than a preset importance from each parsed information as the current status information.
[0107] The parsed information refers to the information obtained by parsing the tag information.
[0108] The entropy value prediction model refers to a network model that can utilize various analytical information to obtain the entropy value corresponding to each analytical information.
[0109] Among them, the entropy value is used to indicate the complexity of each parsed information.
[0110] The importance is used to indicate the importance of each piece of analysis information.
[0111] The preset importance refers to a preset importance threshold, such as 80%. It should be noted that the preset importance depends on the situation.
[0112] Exemplarily, the server obtains format information corresponding to the tag information (such as binary encoding format, structured data format, etc.), and queries the correspondence between the format information and the parsing method to obtain the target parsing method corresponding to the tag information; then, the server parses the tag information according to the target parsing method to obtain the parsing information of the device to be inventoried; then, the server inputs each parsing information into a pre-trained entropy value prediction model, and obtains the entropy value of each parsing information through the pre-trained entropy value prediction model; then, the server queries the correspondence between the entropy value and the importance according to the entropy value of each parsing information, and obtains the importance of each parsing information; then, the server screens out the parsing information whose importance is greater than the preset importance from each parsing information, and uses the parsing information as the current state information.
[0113] In this embodiment, information with an importance greater than the threshold is filtered out from all the analyzed information as the current status information, which is equivalent to accurately filtering a large amount of analyzed information, avoiding interference from a large amount of secondary or irrelevant information, and is conducive to quickly and accurately understanding the actual operation status of the equipment, thereby improving the accuracy of determining the current status information.
[0114] In an exemplary embodiment, the above step S101, before obtaining the tag information of the device to be counted, specifically includes the following contents: receiving the device inventory task sent by the terminal, and determining the target device type corresponding to the device inventory task; obtaining the device type of the candidate device, and screening out the candidate device whose device type meets the target device type from each candidate device as the device to be counted.
[0115] Among them, the equipment inventory task refers to the task information related to the equipment inventory.
[0116] The target device type refers to the device type involved in the device inventory task.
[0117] Among them, device types include computer devices (such as desktop computers, laptops), storage devices (such as hard drives, network attached storage), network devices (such as routers, switches) and input and output devices (such as keyboards, mice), etc.
[0118] Exemplarily, the server establishes a network path with the terminal, and receives a device inventory task sent by the terminal through the network path; then, the server determines the device type involved in the device inventory task as the target device type; then, the server obtains the device type of the candidate device, and from each candidate device, screens out the candidate devices whose device type meets the target device type, and uses these candidate devices as devices to be inventoried.
[0119] In this embodiment, by receiving the device inventory task sent by the terminal and clarifying the corresponding target device type, the inventory work can be accurately focused on candidate devices that meet the target device type, thereby effectively avoiding redundant operations on devices that are not related to the inventory task, which is beneficial to improving the overall efficiency of the device inventory.
[0120] In an exemplary embodiment, the device inventory method provided by the present application also includes a training step of a pre-trained device inventory result prediction model, which specifically includes the following contents: obtaining sample label information of a sample device; parsing the sample label information to obtain current sample status information of the sample device, and obtaining historical sample status information of the sample device; preprocessing the current sample status information and the historical sample status information respectively to obtain preprocessed current sample status information and preprocessed historical sample status information of the sample device; performing feature extraction processing on the preprocessed current sample status information and the preprocessed historical sample status information respectively to obtain a first sample feature vector corresponding to the preprocessed current sample status information, and a second sample feature vector corresponding to the preprocessed historical sample status information; inputting the first sample feature vector and the second sample feature vector into the device inventory result prediction model to be trained to obtain state change information corresponding to the sample device as the predicted device inventory result corresponding to the sample device; obtaining the actual device inventory result corresponding to the sample device, and iteratively training the device inventory result prediction model to be trained according to the difference between the predicted device inventory result and the actual device inventory result to obtain a pre-trained device inventory result prediction model.
[0121] The sample device refers to the device used to train the device inventory result prediction model to be trained.
[0122] The sample label information refers to the label information of the sample device.
[0123] The current sample status information refers to the current status information of the sample device.
[0124] The historical sample status information refers to the historical status information of the sample device.
[0125] The current sample state information after preprocessing refers to the current sample state information after preprocessing.
[0126] The pre-processed historical sample status information refers to the historical sample status information after pre-processing.
[0127] The first sample feature vector refers to the feature vector corresponding to the current sample state information after preprocessing.
[0128] Among them, the second sample feature vector is a feature vector corresponding to the historical sample state information after preprocessing.
[0129] The predicted equipment inventory result refers to the predicted value corresponding to the equipment inventory result of the sample equipment.
[0130] The actual device inventory result refers to the actual value corresponding to the device inventory result of the sample device.
[0131] Exemplarily, in response to a model training instruction for a device inventory result prediction model to be trained, the server obtains sample label information of a sample device from a database; then, the server parses the sample label information to obtain current sample status information of the sample device, and obtains historical sample status information of the sample device; then, the server preprocesses the current sample status information and the historical sample status information respectively to obtain preprocessed current sample status information and preprocessed historical sample status information of the sample device; then, the server performs feature extraction processing on the preprocessed current sample status information and the preprocessed historical sample status information respectively to obtain a first sample feature vector corresponding to the preprocessed current sample status information, and a second sample feature vector corresponding to the preprocessed historical sample status information; then, The server inputs the first sample feature vector and the second sample feature vector into the device inventory result prediction model to be trained, and obtains the state change information corresponding to the sample device as the predicted device inventory result corresponding to the sample device; then, the server obtains the actual device inventory result corresponding to the sample device, and obtains the loss value according to the difference between the predicted device inventory result and the actual device inventory result; then, the server adjusts the model parameters of the device inventory result prediction model to be trained according to the loss value; then, the server re-trains the device inventory result prediction model after the model parameters are adjusted until the loss value obtained by the trained device inventory result prediction model is less than the loss value threshold, then stops training, and uses the trained device inventory result prediction model as the pre-trained device inventory result prediction model.
[0132] In this embodiment, by pre-training the equipment inventory result prediction model, it is convenient to predict the state change information corresponding to the equipment to be inventoried after obtaining the first eigenvector and the second eigenvector in actual application; moreover, the equipment inventory result prediction model receives new data in each round of iteration, and performs internal improvements and optimizations on the model, so as to make predictions more effectively, which is beneficial to improving the prediction accuracy of the equipment inventory result prediction model.
[0133] In an exemplary embodiment, Figure 2 As shown, another device inventory method is provided, which is described by taking the method applied to a server as an example, and includes the following steps:
[0134] Step S201: receiving a device inventory task sent by a terminal, and determining a target device type corresponding to the device inventory task.
[0135] Step S202, obtaining the device types of the candidate devices, and screening out the candidate devices whose device types meet the target device type from the candidate devices as the devices to be counted.
[0136] Step S203, obtaining tag information of the device to be counted; the tag information is obtained by identifying the wireless radio frequency identification tag set on the device to be counted.
[0137] Step S204, parsing the tag information to obtain parsed information of the device to be counted; inputting each parsed information into a pre-trained entropy value prediction model to obtain an entropy value of each parsed information.
[0138] Step S205, determining the importance of each piece of parsed information according to the entropy value of each piece of parsed information; and selecting parsed information with an importance greater than a preset importance from each piece of parsed information as the current state information.
[0139] Step S206, obtaining historical status information of the device to be counted.
[0140] Step S207, preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted.
[0141] Step S208 , performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information.
[0142] Step S209: input the first feature vector and the second feature vector into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as the target device inventory result corresponding to the device to be inventoried.
[0143] In the above-mentioned device inventory method, in the process of taking inventory of the equipment, after the label information of the equipment to be inventoried is obtained, a series of processing steps such as parsing, preprocessing and feature extraction are performed, and finally with the help of a pre-trained equipment inventory result prediction model, a comprehensive and in-depth understanding of the state changes of the equipment to be inventoried can be achieved, and then the target equipment inventory results corresponding to the equipment to be inventoried can be accurately determined, which is conducive to improving the accuracy of the equipment inventory; moreover, the entire process does not require human intervention, avoiding the subjective factors in the manual inventory method, which is prone to errors and leads to the defect of low accuracy of the equipment inventory, thereby improving the accuracy of the equipment inventory.
[0144] In an exemplary embodiment, in order to more clearly illustrate the device inventory method provided in the embodiment of the present application, the device inventory method is specifically described below with a specific embodiment. Figure 3 As shown, the present application also provides an intelligent inventory method for IT assets based on RFID technology. In the process of inventorying the equipment, a handheld or fixed RFID reader is used to scan the area where the asset is located, read the information in the RFID tag installed on the asset, and transmit the read tag information to the server or data processing center through a wireless network. The server or data processing center parses the received data, extracts detailed information about the asset, and compares the parsed data with the database in the asset management system, updates the latest status information of the asset, and generates a detailed asset inventory report based on the processed data, including an asset list, location distribution, status statistics, etc., and displays the current status and location information of the asset in real time through the system interface or mobile application for management personnel to view. Specifically including the following:
[0145] 1. Overview of this embodiment:
[0146] This embodiment uses RFID (radio frequency identification) technology, combined with data processing, network communication and intelligent algorithms, to build an efficient and accurate IT asset inventory system. The system can automatically identify and record IT asset information with RFID tags, and realize rapid inventory, real-time monitoring and intelligent management of assets.
[0147] 2. Data flow and processing:
[0148] (1) Data generation:
[0149] RFID tag installation: First, install RFID tags for all IT assets (such as servers, computers, printers, etc.), which store key information such as the asset's unique identification, type, and location.
[0150] RFID reader scanning: Use a handheld or fixed RFID reader to scan the area where the asset is located and read the information in the RFID tag.
[0151] (2) Data processing:
[0152] Data collection: The RFID reader transmits the read tag information to the server or data processing center via a wireless network (such as Wi-Fi, Bluetooth, etc.).
[0153] Data parsing: The server or data processing center parses the received data and extracts detailed information about the asset, such as asset number, type, location, etc.
[0154] Data comparison and update: Compare the parsed data with the database in the asset management system and update the latest status information of the assets, such as location changes, status changes, etc.
[0155] (3) Data output:
[0156] Inventory report: Generate a detailed asset inventory report based on the processed data, including asset list, location distribution, status statistics, etc.
[0157] Real-time monitoring: Through the system interface or mobile application, the current status and location information of the assets are displayed in real time for managers to view.
[0158] 3. Execution subject and timing:
[0159] RFID tags: installed on assets by asset managers as the source of data generation.
[0160] RFID reader: held by inventory personnel or fixed in a specific location, responsible for scanning RFID tags and collecting data.
[0161] Server / data processing center: responsible for receiving, parsing, comparing and updating data, as well as generating inventory reports and real-time monitoring interface.
[0162] In terms of timing, the RFID tag is first installed and initialized, then the inventory personnel use the RFID reader to scan, and the scanned data is transmitted to the server in real time for processing. Finally, an inventory report and a real-time monitoring interface are generated for management personnel to view.
[0163] 4. Application scenarios:
[0164] This embodiment is applicable to a variety of application scenarios, including but not limited to:
[0165] Enterprise IT asset management: quickly take inventory of IT assets such as servers, computers, printers, etc. within the enterprise to ensure the accuracy and timeliness of asset information.
[0166] Library book management: Books are identified through RFID tags to achieve rapid inventory, borrowing and return management.
[0167] Warehouse goods management: Set RFID tags for each item in the warehouse to achieve rapid inventory, warehousing, outbound and inventory management of goods.
[0168] 5. Modular description:
[0169] (1) RFID tag module:
[0170] Function: Store key information such as the unique identification, type, and location of assets.
[0171] Relationship: Interact with the RFID reader module through radio frequency signals.
[0172] (2) RFID reader / writer module:
[0173] Function: Scan RFID tags, collect information from the tags, and transmit it to the server via wireless network.
[0174] Relationship: interact with the RFID tag module through radio frequency signals and transmit data with the server module through wireless networks.
[0175] (3) Server / data processing center module:
[0176] Function: Receive data transmitted by RFID readers, parse, compare and update, generate inventory reports and real-time monitoring interface.
[0177] Relationship: Transmit data with the RFID reader module through the wireless network and interact with the asset management system database.
[0178] (4) Asset management system module:
[0179] Function: Store detailed information of assets and provide data query, update and management functions.
[0180] Relationship: Interact with the server / data processing center module to provide data support for inventory reports and real-time monitoring interfaces.
[0181] 6. System architecture and interaction process:
[0182] like Figure 4 As shown in the figure, the system adopts C / S (Client / Server) architecture, with the RFID reader as the client and the server / data processing center as the server. The RFID reader communicates with the server through a wireless network to transmit the scanned RFID tag information. After receiving the data, the server performs parsing, comparison and update operations, and stores the processing results in the asset management system database. At the same time, the server is also responsible for generating inventory reports and real-time monitoring interfaces for management personnel to view and manage.
[0183] In the above-mentioned embodiment, during the process of taking inventory of equipment, after obtaining the label information of the equipment to be counted, a series of processing steps including parsing, preprocessing and feature extraction are performed, and finally a pre-trained equipment inventory result prediction model is used to comprehensively and deeply understand the state changes of the equipment to be counted, and then the target equipment inventory result corresponding to the equipment to be counted can be accurately determined, which is conducive to improving the accuracy of the equipment inventory; moreover, the whole process does not require manual intervention, thus avoiding the defects of low accuracy of equipment inventory caused by subjective factors and prone to errors in manual inventory, thereby improving the accuracy of equipment inventory. Meanwhile, the traditional IT asset inventory relies on manual verification one by one, which is not only time-consuming and labor-intensive, but also inefficient. However, the present embodiment can quickly read the information of multiple asset tags through RFID technology, significantly shortening the inventory time; the RFID handheld reader can instantly read multiple tags within a certain range, greatly improving the inventory speed; the traditional inventory method is easily affected by human factors, such as negligence, misreading, etc., resulting in inaccurate inventory results. RFID technology automatically identifies the target object through wireless radio frequency signals, reducing the probability of human errors, thereby ensuring the accuracy of the inventory results; in addition, the RFID system can update asset information in real time, further improving the timeliness and accuracy of the data; by integrating multiple systems such as asset management system and RFID system to form a complete automated inventory solution, the present patent can significantly reduce the operating costs of enterprises; automated inventory reduces dependence on manual labor and reduces labor costs; at the same time, it reduces additional losses and costs caused by inventory errors; the existing RFID system may have problems of inconsistent standards and poor compatibility; the present embodiment improves the compatibility and scalability of the system by optimizing the system design and algorithm, so that it can adapt to the asset management needs of different enterprises and different scenarios.
[0184] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0185] Based on the same inventive concept, the embodiment of the present application also provides a device inventory device for implementing the device inventory method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more device inventory device embodiments provided below can refer to the limitations of the device inventory method above, and will not be repeated here.
[0186] In an exemplary embodiment, Figure 5 As shown, a device inventory apparatus is provided, including: an information acquisition module 501, a state acquisition module 502, an information processing module 503, a feature extraction module 504 and a result prediction module 505, wherein:
[0187] The information acquisition module 501 is used to acquire tag information of the device to be counted; the tag information is obtained by identifying the wireless radio frequency identification tag set on the device to be counted.
[0188] The status acquisition module 502 is used to parse the tag information to obtain the current status information of the device to be counted and to obtain the historical status information of the device to be counted.
[0189] The information processing module 503 is used to pre-process the current state information and the historical state information respectively to obtain the pre-processed current state information and the pre-processed historical state information of the device to be counted.
[0190] The feature extraction module 504 is used to perform feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information.
[0191] The result prediction module 505 is used to input the first feature vector and the second feature vector into a pre-trained device inventory result prediction model to obtain the state change information corresponding to the device to be inventoried as the target device inventory result corresponding to the device to be inventoried.
[0192] In an exemplary embodiment, the feature extraction module 504 is also used to perform feature extraction processing on multiple sub-state information respectively to obtain sub-feature vectors corresponding to the multiple sub-state information; obtain the splicing order of the multiple sub-state information, and splice the sub-feature vectors corresponding to the multiple sub-state information according to the splicing order to obtain the first feature vector.
[0193] In an exemplary embodiment, the feature extraction module 504 is also used to identify the target data type corresponding to multiple sub-state information; based on the target data type, query the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the multiple sub-state information; through the target feature extraction model, perform feature extraction processing on the multiple sub-state information respectively to obtain sub-feature vectors corresponding to the multiple sub-state information.
[0194] In an exemplary embodiment, the state acquisition module 502 is also used to parse the tag information to obtain the parsed information of the device to be inventoryed; input each parsed information into a pre-trained entropy value prediction model to obtain the entropy value of each parsed information; determine the importance of each parsed information according to the entropy value of each parsed information; and filter out the parsed information whose importance is greater than the preset importance from each parsed information as the current state information.
[0195] In an exemplary embodiment, the device inventory apparatus also includes a device screening module for receiving a device inventory task sent by a terminal and determining a target device type corresponding to the device inventory task; obtaining a device type of a candidate device, and screening out a candidate device whose device type meets the target device type from each candidate device as a device to be inventoried.
[0196] In an exemplary embodiment, the equipment inventory device also includes a model training module, which is used to obtain sample label information of the sample equipment; parse the sample label information to obtain the current sample status information of the sample equipment, and obtain the historical sample status information of the sample equipment; preprocess the current sample status information and the historical sample status information respectively to obtain the preprocessed current sample status information and the preprocessed historical sample status information of the sample equipment; perform feature extraction processing on the preprocessed current sample status information and the preprocessed historical sample status information respectively to obtain a first sample feature vector corresponding to the preprocessed current sample status information, and a second sample feature vector corresponding to the preprocessed historical sample status information; input the first sample feature vector and the second sample feature vector into the equipment inventory result prediction model to be trained to obtain the state change information corresponding to the sample equipment as the predicted equipment inventory result corresponding to the sample equipment; obtain the actual equipment inventory result corresponding to the sample equipment, and iteratively train the equipment inventory result prediction model to be trained according to the difference between the predicted equipment inventory result and the actual equipment inventory result to obtain a pre-trained equipment inventory result prediction model.
[0197] Each module in the above-mentioned device inventory device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0198] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as current status information and historical status information. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a device inventory method is implemented.
[0199] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0200] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0201] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0202] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0203] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0204] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0205] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A device inventory method, characterized in that: The method comprises: Acquire tag information of the device to be counted; the tag information is obtained by identifying a radio frequency identification tag set on the device to be counted; Parsing the tag information to obtain current status information of the device to be counted, and acquiring historical status information of the device to be counted; Preprocessing the current state information and the historical state information respectively to obtain the preprocessed current state information and the preprocessed historical state information of the device to be counted; Performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information; The first feature vector and the second feature vector are input into a pre-trained device inventory result prediction model to obtain state change information corresponding to the device to be inventoried as a target device inventory result corresponding to the device to be inventoried.
2. The method according to claim 1, characterized in that: The pre-processed current state information includes a plurality of sub-state information; The performing feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information includes: Performing feature extraction processing on the plurality of sub-state information respectively to obtain sub-feature vectors corresponding to the plurality of sub-state information; A concatenation order of the plurality of sub-state information is obtained, and sub-feature vectors corresponding to the plurality of sub-state information are concatenated according to the concatenation order to obtain the first feature vector.
3. The method according to claim 2, characterized in that The performing feature extraction processing on the plurality of sub-state information respectively to obtain sub-feature vectors corresponding to the plurality of sub-state information includes: Identify target data types corresponding to the plurality of sub-state information; According to the target data type, query the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the multiple sub-state information; The target feature extraction model is used to perform feature extraction processing on the plurality of sub-state information respectively to obtain sub-feature vectors corresponding to the plurality of sub-state information.
4. The method according to claim 1, characterized in that The parsing of the tag information to obtain the current status information of the device to be counted includes: Parsing the tag information to obtain parsed information of the device to be counted; Inputting each of the analysis information into a pre-trained entropy value prediction model to obtain the entropy value of each of the analysis information; Determining the importance of each piece of parsed information according to the entropy value of each piece of parsed information; From each of the analysis information, the analysis information whose importance is greater than a preset importance is screened out as the current state information.
5. The method according to claim 1, characterized in that Before obtaining the tag information of the device to be counted, the following steps are also required: Receiving a device inventory task sent by a terminal, and determining a target device type corresponding to the device inventory task; The device type of the candidate device is obtained, and the candidate device whose device type meets the target device type is screened out from the candidate devices as the device to be counted.
6. The method according to any one of claims 1 to 5, characterized in that: The pre-trained equipment inventory result prediction model is trained in the following way: Get sample tag information of sample equipment; Parsing the sample tag information to obtain current sample status information of the sample device and acquiring historical sample status information of the sample device; Preprocessing the current sample state information and the historical sample state information respectively to obtain the preprocessed current sample state information and the preprocessed historical sample state information of the sample device; Performing feature extraction processing on the preprocessed current sample state information and the preprocessed historical sample state information respectively to obtain a first sample feature vector corresponding to the preprocessed current sample state information and a second sample feature vector corresponding to the preprocessed historical sample state information; Inputting the first sample feature vector and the second sample feature vector into a device inventory result prediction model to be trained, and obtaining state change information corresponding to the sample device as a predicted device inventory result corresponding to the sample device; The actual device inventory result corresponding to the sample device is obtained, and according to the difference between the predicted device inventory result and the actual device inventory result, the device inventory result prediction model to be trained is iteratively trained to obtain the pre-trained device inventory result prediction model.
7. An equipment inventory device, characterized in that: The device comprises: An information acquisition module is used to acquire tag information of the device to be counted; the tag information is obtained by identifying a wireless radio frequency identification tag set on the device to be counted; A status acquisition module is used to parse the tag information to obtain the current status information of the device to be counted and to obtain the historical status information of the device to be counted; An information processing module, used to pre-process the current state information and the historical state information respectively, to obtain the pre-processed current state information and the pre-processed historical state information of the device to be counted; A feature extraction module, used to perform feature extraction processing on the preprocessed current state information and the preprocessed historical state information respectively, to obtain a first feature vector corresponding to the preprocessed current state information and a second feature vector corresponding to the preprocessed historical state information; The result prediction module is used to input the first feature vector and the second feature vector into a pre-trained device inventory result prediction model to obtain the state change information corresponding to the device to be inventoried as the target device inventory result corresponding to the device to be inventoried.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.