Abnormality analysis method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an anomaly analysis method and device, electronic equipment and a storage medium, and relates to the field of intelligent equipment. The method comprises the following steps: acquiring a first information set of a plurality of production batches, wherein the first information set comprises information of intelligent equipment in a production stage and an activation stage; for each first information set, counting information in the first information set to obtain a statistical result, and if it is determined that at least one of the statistical result and the first information set is abnormal, taking the production batch as an abnormal batch, and obtaining information related to the abnormality from the first information set as target information; analysis rules are obtained, each analysis rule corresponds to one dimension, the target information of all the abnormal batches is analyzed according to the analysis rules, and the common distribution characteristics of the abnormal batches on the corresponding dimensions are obtained to serve as a first analysis result; and analyzing each first analysis result to obtain an abnormal analysis result. Systematic detection of abnormal batches is realized, and the production quality management and control level is improved.

Description

Technical Field

[0001] This application relates to the field of smart device technology, and more specifically, to an anomaly analysis method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the actual production process of smart devices, various anomalies may be encountered, which may affect production progress and equipment activation.

[0003] However, in related technologies, when abnormal situations occur in smart devices, it is difficult to analyze the specific causes of the abnormalities after they are detected, making it impossible to prevent problems at the source and improve the level of production quality control. Summary of the Invention

[0004] This application provides an anomaly analysis method, apparatus, electronic device, and storage medium to address the technical problem of failing to improve production quality control by preventing problems at their source.

[0005] According to a first aspect of the embodiments of this application, an anomaly analysis method is provided, the method comprising: acquiring a first information set corresponding to each of multiple production batches, the first information set including at least one piece of information of each smart device in the same production batch during the production stage and the activation stage; For each first information set, at least one piece of information in the first information set is statistically analyzed to obtain at least one corresponding statistical result. If it is determined that at least one statistical result and at least one of the first information set are abnormal, the corresponding production batch is regarded as an abnormal batch, and information related to the abnormality is obtained from the first information set as the target information of the abnormal batch. Obtain at least one predefined analysis rule, each analysis rule corresponds to a dimension, and is used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension; For each analysis rule, the target information of each abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, and this is taken as the first analysis result. The results of each initial analysis are analyzed to obtain anomaly analysis results; these results are used to indicate the causes of anomalies.

[0006] In one possible implementation, the first information set includes activation records and tag unbinding records for each smart device; the activation records record whether the corresponding smart device is activated through the main scheme or the backup scheme; the tag unbinding records record the number of times the device tags bound to the smart device have been unbound in the past and the workstation number used to produce the smart device; the statistical results include at least one of the backup activation ratio, unbinding ratio, first unbinding count, second unbinding count, and third unbinding count; the device tags are used to store the device information of the smart device; For the backup activation ratio, the activation methods of each smart device in the first information set are statistically analyzed to obtain the total number of activations and the number of backup activations of smart devices activated through backup schemes. The ratio between the number of backup activations and the total number of activations is taken as the backup activation ratio of the production batch corresponding to the first information set. Regarding the unbinding ratio and the first unbinding count, the unbinding records of each smart device in the first information set are statistically analyzed to obtain the total number of unbinding device tags for all smart devices in the production batch. The ratio of the total number of unbinding counts to the total number of smart devices in the production batch is used as the unbinding ratio. For the first unbinding count, the unbinding records of tags of each smart device in the first information set are statistically analyzed to obtain the first unbinding count of each smart device unbinding the device tag; For the second unbinding count, the tag unbinding records within a preset time period in the first information set are statistically analyzed to obtain the second unbinding count corresponding to the preset time period. For the third unbinding count, the workstation numbers in the tag unbinding record are counted to obtain the third unbinding count corresponding to each workstation number.

[0007] In another possible implementation, the first information set also includes the device tag currently bound to the smart device and the smart device's production plan; If at least one statistical result and the first information set meet at least one of the following conditions, the corresponding production batch will be considered an abnormal batch: The standby activation ratio is greater than the activation ratio threshold. The unbinding ratio is greater than the unbinding ratio threshold; The first unbinding attempt exceeds the first unbinding attempt threshold; The second unbinding attempt exceeds the second unbinding attempt threshold; The third unbinding record exceeds the threshold for the number of third unbinding attempts; The production plan corresponding to the tag that has been bound to the smart device is inconsistent with the production plan corresponding to the smart device.

[0008] In another possible implementation, the target information of the abnormal batch includes at least one of the following: the production time period of the abnormal batch, the production line number of the production line, the workstation number of the workstation used to produce the intelligent equipment, and the operator number. When the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the time dimension, the production time period corresponding to each abnormal batch is summarized, and the first batch quantity of the abnormal batch in each production time period is obtained as the common distribution characteristic of each abnormal batch in the time dimension. When the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the production line dimension, the production line numbers of each abnormal batch are summarized, and the number of the second batch of the abnormal batches for each production line number is obtained as the common distribution characteristics of each abnormal batch in the production line dimension. When the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the workstation dimension, the abnormal smart devices in each abnormal batch whose first unbinding count is greater than the first unbinding count threshold are counted, the workstation number of the workstation used for the abnormal smart device is obtained, the workstation number of the workstation used for the abnormal smart device is counted, and the first device quantity corresponding to each workstation number is obtained, which is used as the common distribution characteristic of each abnormal batch in the workstation dimension. When the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in terms of personnel, the abnormal smart devices in each abnormal batch whose first unbinding count is greater than the first threshold are counted, the operator ID of each abnormal smart device is obtained, the operator ID of each abnormal smart device is counted, and the number of second devices corresponding to each operator ID is obtained, which is used as the common distribution characteristic of each abnormal batch in terms of operator.

[0009] In yet another possible implementation, the anomaly analysis results include at least one of the following: an abnormal time period; an abnormal production line; an abnormal workstation; and an abnormal operator. For each production time period, if the quantity of the first batch corresponding to the production time period is greater than the threshold of the quantity of the first batch, then the production time period is regarded as an abnormal time period. For each production line number, if the quantity of the second batch corresponding to the production line number is greater than the threshold of the second batch quantity, then the production line corresponding to the production line number is regarded as an abnormal production line. For each workstation number, if the number of first devices corresponding to the workstation number is greater than the threshold for the number of first devices, then the workstation corresponding to the workstation number is regarded as an abnormal workstation. For each operator number, if the number of second devices corresponding to the operator number is greater than the threshold for the number of second devices, then the operator corresponding to the operator number is considered an abnormal operator.

[0010] In yet another possible implementation, each production batch corresponds to one production line; After obtaining the anomaly analysis results, determine the total number of production batches and the number of abnormal batches from the multiple production batches. The ratio of the number of abnormal batches to the total number of batches is used as the target ratio. If the target ratio is not less than the first ratio and less than the second ratio, an alarm message is generated to instruct managers to pay attention to the abnormal batch. If the target ratio is not less than the second ratio and less than the third ratio, an anomaly report is generated to indicate that the abnormal batch should be investigated. If the target ratio is not less than the third ratio, then the production lines corresponding to the abnormal batches will be statistically analyzed to determine the number of abnormal batches for each production line, and the production process of the production line with the largest number of abnormal batches will be suspended.

[0011] In another possible implementation, after obtaining the anomaly analysis results, the first production plan for the new production batch is received; the first production plan includes at least one of the first production time period, the first production line number, the first workstation number, and the first operator number. If it is determined that the first production plan meets at least two of the following conditions, an early warning message indicating that there is an anomaly in the production plan will be generated; The first production period coincides with the abnormal period. The first workstation number is consistent with the production line number corresponding to the abnormal production line; The first workstation number is consistent with the abnormal workstation number corresponding to the abnormal workstation; The operator number corresponding to the first operator and the abnormal operator is the same.

[0012] In another possible implementation, for any first information set, the first information set is input into the anomaly detection model to obtain the prediction result output by the anomaly detection model. The prediction result is used to indicate whether the production batch corresponding to the first information set is an abnormal batch. The anomaly detection model is trained using the first information set of samples as training samples and whether the production batch of the sample corresponding to the first information set is an abnormal batch as training labels.

[0013] According to a second aspect of the embodiments of this application, an anomaly analysis apparatus is provided, the apparatus comprising: The first acquisition module is used to acquire a first information set corresponding to each of multiple production batches. The first information set includes at least one piece of information about each smart device in the same production batch during the production stage and the activation stage. The statistics module is used to perform statistics on at least one piece of information in each first information set to obtain at least one corresponding statistical result. If it is determined that at least one statistical result and at least one of the first information sets are abnormal, the corresponding production batch is regarded as an abnormal batch, and information related to the abnormality is obtained from the first information set as the target information of the abnormal batch. The second acquisition module is used to acquire at least one predefined analysis rule, each analysis rule corresponds to a dimension, and is used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension. The first analysis module is used to analyze the target information of each abnormal batch according to each analysis rule, obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, and use it as the first analysis result. The second analysis module is used to analyze the results of each first analysis to obtain anomaly analysis results; the anomaly analysis results are used to indicate the reasons for the anomalies.

[0014] According to a third aspect of the embodiments of this application, an electronic device is provided, the electronic device including a memory, a processor and a computer program stored in the memory, wherein the processor executes the program to implement the steps of the method provided in the first aspect.

[0015] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method provided in the first aspect.

[0016] According to a fifth aspect of the present application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium, wherein when a processor of a computer device reads the computer instructions from the computer-readable storage medium, the processor executes the computer instructions, causing the computer device to perform steps implementing the method provided in the first aspect.

[0017] The beneficial effects of the technical solutions provided in this application are: First, the anomaly analysis method provided in this application provides sufficient and powerful evidence for anomaly analysis of production batches by acquiring the first information sets corresponding to each of multiple production batches. Since the first information set is a combination of at least one piece of information for recording the smart device in the production stage and the activation stage, it provides sufficient and powerful evidence for anomaly analysis of production batches. Secondly, by statistically analyzing at least one piece of information in the first information set, at least one corresponding statistical result is obtained, thus realizing the statistical analysis of various information at the entire level of the production batch. If it is determined that at least one statistical result and the first information set are abnormal, the corresponding production batch is regarded as an abnormal batch. By analyzing whether there are abnormalities in the statistical results and the first information set, anomaly analysis is realized from the overall level of the production batch and the level of individual intelligent devices, thereby improving the accuracy of anomaly analysis. Information related to anomalies is obtained from the first information set as the target information of the anomaly batch. At least one predefined analysis rule is obtained, and each analysis rule corresponds to a dimension. It is used to analyze the common distribution characteristics of each anomaly batch in the corresponding dimension. For each analysis rule, the target information of the anomaly batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each anomaly batch in the corresponding dimension. This is used as the first analysis result. By determining the common distribution characteristics of each anomaly batch in multiple dimensions, it is confirmed that the anomaly batch has anomalies. This provides strong data support for the analysis of the reasons for the anomalies in the anomaly batch. Finally, the results of each initial analysis are analyzed to obtain anomaly analysis results that indicate the cause of the anomalies. By determining the common distribution characteristics of each abnormal batch in multiple dimensions, anomaly analysis results that accurately pinpoint the cause of the anomalies can be obtained, providing strong data support for the improvement of the production process and improving the level of production quality control. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0019] Figure 1 This is a schematic diagram of the system architecture for implementing the anomaly analysis method provided in the embodiments of this application; Figure 2 A flowchart illustrating an anomaly analysis method provided in an embodiment of this application; Figure 3 A flowchart illustrating yet another anomaly analysis method provided in this application embodiment; Figure 4 This is a schematic diagram of the structure of an anomaly analysis device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0021] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a,” “an,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.”

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0023] The relevant technologies are explained below: In the production process of smart devices, device tags are an important bridge connecting smart devices and information systems. They are typically used to record key information such as unique device identifiers and activation codes. However, in actual production, due to reasons such as damaged tags, printing errors, or human error, device tags often need to be unbound and rebound. Existing technologies usually only record the final binding relationship and lack a complete record of the tag binding history. This makes it impossible to track the historical changes in device tag binding and difficult to analyze the causes of anomalies. When redundant queries are used excessively to obtain activation codes, the system cannot identify such anomalies and issue warnings. There is a lack of a systematic detection and analysis mechanism for abnormal behavior of device tag binding, making it impossible to prevent problems at the source.

[0024] To address at least one of the aforementioned technical problems or areas requiring improvement in related technologies, this application proposes an anomaly analysis method. This method acquires a first information set corresponding to each of multiple production batches, and statistically analyzes at least one piece of information within the first information set to obtain at least one corresponding statistical result. If an anomaly is determined in either the statistical result or the first information set, the corresponding production batch is designated as an abnormal batch. Information related to the anomaly is then obtained from the first information set as the target information for the abnormal batch. At least one predefined analysis rule is acquired, each corresponding to a dimension, used to analyze the common distribution characteristics of each abnormal batch along that dimension. For each analysis rule, the target information of the abnormal batch is analyzed according to the rule to obtain the common distribution characteristics of each abnormal batch along that dimension, which serve as the first analysis result. Each first analysis result is then analyzed to obtain an anomaly analysis result indicating the cause of the anomaly. This method, by acquiring a first information set used to record the intelligent device during the production and activation stages, provides sufficient basis for anomaly analysis. By determining the common distribution characteristics of each abnormal batch along multiple dimensions, it enables the acquisition of anomaly analysis results that accurately pinpoint the cause of the anomaly, providing strong data support for production process improvement and enhancing the level of production quality control.

[0025] The technical solutions of this application and their effects are described below through several exemplary embodiments. It should be noted that the following embodiments can be referenced, borrowed from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0026] Figure 1 This is a schematic diagram of the system architecture for implementing the anomaly analysis method provided in an embodiment of this application, wherein the system architecture includes: a terminal 120 and a server 140.

[0027] Terminal 120 has an application program with anomaly analysis methods installed and running. Terminal 120 is used to determine the anomaly analysis results based on the first information set corresponding to each of the multiple production batches.

[0028] Terminal 120 is connected to server 140 via a wireless network or a wired network.

[0029] Server 140 includes at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Illustratively, server 140 includes a processor 144 and a memory 142, the memory 142 including a display module 1421, a control module 1422, and a receiving module 1423. Server 140 is used to provide background services for the application of the method. Optionally, server 140 undertakes the primary computing work, and terminal 120 undertakes secondary computing work; or, server 140 undertakes secondary computing work, and terminal 120 undertakes primary computing work; or, server 140 and terminal 120 collaborate on computing using a distributed computing architecture.

[0030] Optionally, the device type of the terminal includes at least one of the following: smartphone, tablet computer, e-book reader, Moving Picture Experts Group Audio Layer III (MP3) player, Moving Picture Experts Group Audio Layer IV (MP4) player, laptop computer, and desktop computer.

[0031] Those skilled in the art will understand that the number of terminals described above can be more or less. For example, there may be only one terminal, or there may be dozens or hundreds of terminals, or even more. This application does not limit the number of terminals or the type of device.

[0032] This application provides an anomaly analysis method, such as... Figure 2 As shown, the method includes: S101, obtain the first information set corresponding to each of the multiple production batches.

[0033] In the embodiments of this application, the first information set includes at least one piece of information about each smart device in the same production batch during the production stage and the activation stage. That is, there is a corresponding first information set for each production batch, which includes at least one piece of information about all smart devices in the current production batch during the production stage and the activation stage.

[0034] In this application embodiment, a smart device refers to a device that needs to be activated by an activation code. A smart device can be a smart home device, such as a smart lamp or a smart door lock. A smart device can also be a smart home appliance, such as a smart refrigerator or a smart clothes dryer.

[0035] In this embodiment, the first information set includes at least one piece of information related to the smart device that is recorded during the production and activation phases. For example, during the production phase, at least one piece of information such as the smart device's device identifier, operation timestamp, production line number, workstation number, production plan number, device tag, and device status can be recorded. During the activation phase, at least one piece of information such as the smart device's device identifier, activation code, activation time, activation method, activation result, activation geographical environment, and activation network environment can be recorded.

[0036] S102, for each first information set, statistical analysis is performed on at least one piece of information in the first information set to obtain at least one corresponding statistical result. If it is determined that at least one statistical result and at least one of the information in the first information set are abnormal, the corresponding production batch is regarded as an abnormal batch, and information related to the abnormality is obtained from the first information set as the target information of the abnormal batch.

[0037] In this embodiment of the application, for each first information set, at least one piece of information in the information set is statistically analyzed to obtain at least one corresponding statistical result. The statistical result can be obtained based on the statistical analysis of all smart devices in the same production batch, or it can be obtained based on the information of smart devices in the same production batch that share the same characteristics. In other words, the statistical result can characterize the specific content of the current production batch from the perspective of the entire production batch. The statistical result is a specific numerical value, which can be a decimal or a positive integer. For example, if the first information set includes the activation methods of each smart device, then the corresponding statistical results of the activation methods can be obtained by statistically analyzing the activation methods of each smart device in the first information set (such as the number of times activated by the main scheme, the number of times activated by the backup scheme, and the ratio of the number of times activated by the backup scheme to the number of times activated by all schemes).

[0038] In this embodiment of the application, if it is determined that at least one of the statistical results and at least one of the first information set is abnormal, then the production batch corresponding to the first information set is regarded as an abnormal batch. That is, the statistical results and the first information set are checked for abnormality respectively. As long as at least one of them is abnormal, it means that the current production batch is abnormal and the current production batch is regarded as an abnormal batch.

[0039] In this embodiment of the application, by performing anomaly analysis on the statistical results, it is determined whether the current production batch is an abnormal batch. This analysis is performed on the production batch at the level of the entire batch (overall level). Since the statistical result is a single value or a set of values, when detecting whether there is an anomaly in the statistical result, the normal value range corresponding to the content represented by the statistical result can be predefined. If the value corresponding to the statistical result does not fall within the normal value range, it is determined that the statistical result is abnormal. If the value corresponding to the statistical result falls within the normal value range, it is determined that the statistical result is not abnormal.

[0040] In this embodiment, since the information in the first information set is information about each smart device during the production and activation stages, i.e., the information in the first information set is specific to the smart devices, detecting whether there are anomalies in the first information set involves checking each smart device in the production batch for anomalies, i.e., analyzing the production batch from the level of a single smart device (individual level). When detecting whether there are anomalies in the information in the first information set, information comparison can be used. If the information recorded in the first information set is inconsistent with the pre-recorded information...

[0041] In this embodiment of the application, anomaly detection is performed on the current production batch at both the overall level and the individual level, which effectively ensures the accurate capture of anomalies in the production batch.

[0042] In this embodiment of the application, after identifying the abnormal batch, since it is necessary to analyze the abnormal situation of the abnormal batch, information related to the detected abnormality is obtained from the first information set of each abnormal batch as the target information of the current abnormal batch. The target information refers to information related to the abnormal situation of the abnormal batch. For example, if the abnormality of the current abnormal batch is that the total number of unbindings of the device tags of the smart devices in the batch exceeds the normal total number of unbindings, then it can be determined that the current abnormal batch is abnormal in the number of unbindings. The number of unbindings of the device tags of each smart device is recorded as the target information to facilitate analysis in subsequent processes.

[0043] S103, Obtain at least one predefined analysis rule.

[0044] In the embodiments of this application, each analysis rule corresponds to a dimension and is used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension. That is, each analysis rule is used to analyze the common distribution characteristics of each abnormal batch in one dimension. The obtained abnormal analysis rules can analyze the common distribution characteristics of each abnormal batch in the time dimension, or the common distribution characteristics of each abnormal batch in the spatial dimension, and other distribution characteristics in multiple dimensions.

[0045] S104. For each analysis rule, the target information of each abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, and this is taken as the first analysis result.

[0046] In this embodiment of the application, each analysis rule is used one by one to analyze the target information of each abnormal batch. This means that the target information of each abnormal batch is processed one by one using the current analysis rule to obtain the feature distribution of each abnormal batch in the corresponding dimension. The feature distribution of each abnormal batch in the corresponding dimension is summarized to obtain the common distribution characteristics of all abnormal batches in the corresponding dimension. The common distribution characteristics obtained in the corresponding dimension are used as the first analysis result. That is, a first analysis result can be obtained based on each analysis rule.

[0047] S105, Analyze each of the first analysis results to obtain the anomaly analysis results.

[0048] In this embodiment of the application, the anomaly analysis results are used to indicate the cause of the anomaly. Since the first analysis result represents the common distribution characteristics of all abnormal batches in the corresponding dimension, by analyzing each first analysis result, it is possible to analyze from multiple dimensions whether the cause of the anomaly in all abnormal batches is correlated with each dimension, thereby obtaining the analysis results used to indicate the cause of the anomaly.

[0049] In one example, if the first analysis result represents the common distribution characteristics of all abnormal batches in the production line dimension, and after analyzing the first analysis result, it is found that the number of abnormal batches generated through production line 1 is relatively large, then an anomaly analysis result indicating that there is an anomaly in production line 1 can be obtained.

[0050] First, the anomaly analysis method provided in this application provides sufficient and powerful evidence for anomaly analysis of production batches by acquiring the first information sets corresponding to each of multiple production batches. Since the first information set is a combination of at least one piece of information for recording the smart device in the production stage and the activation stage, it provides sufficient and powerful evidence for anomaly analysis of production batches. Secondly, by statistically analyzing at least one piece of information in the first information set, at least one corresponding statistical result is obtained, thus realizing the statistical analysis of various information at the entire level of the production batch. If it is determined that at least one statistical result and the first information set are abnormal, the corresponding production batch is regarded as an abnormal batch. By analyzing whether there are abnormalities in the statistical results and the first information set, anomaly analysis is realized from the overall level of the production batch and the level of individual intelligent devices, thereby improving the accuracy of anomaly analysis. Information related to anomalies is obtained from the first information set as the target information of the anomaly batch. At least one predefined analysis rule is obtained, and each analysis rule corresponds to a dimension. It is used to analyze the common distribution characteristics of each anomaly batch in the corresponding dimension. For each analysis rule, the target information of the anomaly batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each anomaly batch in the corresponding dimension. This is used as the first analysis result. By determining the common distribution characteristics of each anomaly batch in multiple dimensions, it is confirmed that the anomaly batch has anomalies. This provides strong data support for the analysis of the reasons for the anomalies in the anomaly batch. Finally, the results of each initial analysis are analyzed to obtain anomaly analysis results that indicate the cause of the anomalies. By determining the common distribution characteristics of each abnormal batch in multiple dimensions, anomaly analysis results that accurately pinpoint the cause of the anomalies can be obtained, providing strong data support for the improvement of the production process and improving the level of production quality control.

[0051] Based on the above embodiments, as an optional embodiment, the first information set includes activation records and tag unbinding records of each smart device; the activation record is used to record whether the corresponding smart device is activated through the main scheme or the backup scheme; the tag unbinding record is used to record the number of times the device tag bound to the smart device has been unbound in the past and the workstation number of the workstation used to produce the smart device; the statistical results include at least one of the backup activation ratio, unbinding ratio, first unbinding count, second unbinding count, and third unbinding count; the device tag is used to store the device information of the smart device.

[0052] In this embodiment of the application, the activation record of the smart device included in the first information set is used to record whether the corresponding smart device is activated by the main scheme or by the backup scheme. The main scheme activation refers to activation by scanning the device tag on the smart device to obtain the activation code. The backup scheme activation refers to activation by obtaining the activation code through a redundant query. For example, if activation cannot be performed by the device tag, activation can be performed by obtaining the activation code through a backup device tag.

[0053] In this embodiment, the device tag is used to store device information of the smart device. When the device tag is produced, it is bound to the smart device and attached to the body of the smart device. When activating the smart device, the relevant information of the smart device can be obtained by scanning the tag attached to the body of the smart device, thereby obtaining the activation code.

[0054] In this embodiment of the application, the activation record in the first information set may further include: the activation code of the smart device, the activation time of the smart device, the activation result of the smart device, the activation environment information of the smart device, etc.

[0055] In this embodiment of the application, the first information set includes the tag unbinding record of the smart device, which is used to record the historical tag unbinding situation of the corresponding smart device. That is, it includes the total number of times the device tag bound to the smart device was unbound in the past and the workstation number of the workstation used to produce the smart device. The workstation for producing smart devices refers to the work area specially set up in the production process of smart devices to perform specific tasks or operations. Each workstation can be completed by manual labor, automated equipment or a combination of both to ensure that the production process is carried out efficiently and accurately. Each production line has multiple workstations.

[0056] In this embodiment of the application, the tag unbinding record may also include: unbinding time, unbinding reason, and other information related to unbinding.

[0057] In this embodiment of the application, each operation on the device tag will generate a new record and store it in the first information set, so as to fully record the change trajectory of the device tag's tag status, rather than just updating the latest status of the device tag.

[0058] In this embodiment, the backup activation ratio refers to the proportion of smart devices activated using the backup activation scheme within the same abnormal batch, out of all smart devices activated by different activation methods; the unbinding ratio refers to the proportion of the total number of unbinding attempts of all smart devices within the same abnormal batch to the total number of unbinding attempts of all smart devices; the first unbinding attempt refers to the number of times each smart device is unbound within the same abnormal batch, i.e., each smart device has a corresponding first unbinding attempt; the second unbinding attempt refers to the total number of times all smart devices unbind their device tags within a preset time period; and the third unbinding attempt refers to the total number of times the smart devices corresponding to each workstation number are unbound, i.e., each workstation number corresponds to a third unbinding attempt.

[0059] In this embodiment of the application, the backup activation ratio is obtained in the following way: the activation methods of each smart device in the first information set are statistically analyzed to obtain the total number of activations and the number of backup activations of smart devices activated through backup schemes, and the ratio between the number of backup activations and the total number of activations is used as the backup activation ratio of the production batch corresponding to the first information set.

[0060] In this embodiment of the application, the activation methods of each smart device in the first information set are statistically analyzed to determine the number of smart devices activated using the backup scheme, i.e., the number of backup activations, and the number of smart devices activated using the main scheme. The two quantities obtained above are added together to obtain the total number of activations for the current production batch. The ratio between the number of backup activations and the total number of activations is used as the backup activation ratio for the production batch corresponding to the first information set.

[0061] In this embodiment of the application, the unbinding ratio is obtained in the following way: the unbinding records of each smart device in the first information set are statistically analyzed to obtain the total number of times the device tags of all smart devices in the production batch are unbound, and the ratio of the total number of unbinding times to the total number of smart devices in the production batch is used as the unbinding ratio.

[0062] In this embodiment of the application, the tag unbinding records of each smart device in the first information set are statistically analyzed. Each tag unbinding record is equivalent to one tag unbinding. The tag unbinding records of each smart device are added together to obtain the total number of times the smart devices in the current production batch unbind the device tags. The ratio between the total number of unbinding times and the number of all smart devices in the production batch is used as the unbinding ratio.

[0063] In this embodiment of the application, the first unbinding count is obtained by statistically analyzing the tag unbinding records of each smart device in the first information set to obtain the first unbinding count of each smart device from the device tag.

[0064] In this embodiment of the application, the tag unbinding records corresponding to each smart device in the first information set are statistically analyzed to determine the number of tag unbinding records corresponding to each smart device, that is, to obtain the first unbinding count of each smart device unbinding the device tag.

[0065] In this embodiment of the application, the second unbinding count is obtained by statistically analyzing the tag unbinding records within a preset time period in the first information set to obtain the second unbinding count corresponding to the preset time period.

[0066] In this embodiment of the application, all tag unbinding records within a preset time period in the first information set are statistically analyzed to determine the number of tag unbinding records within the preset time period. One tag unbinding record corresponds to one device tag unbinding, thereby obtaining the second number of unbindings within the preset time period of the current production batch.

[0067] In this embodiment of the application, the third unbinding count is obtained by counting the workstation numbers in the tag unbinding record and obtaining the third unbinding count corresponding to each workstation number.

[0068] In this embodiment of the application, the workstation numbers recorded in each tag unbinding record in the first information set are statistically analyzed. Each tag unbinding record corresponds to one workstation number. Based on the number of times each workstation number is recorded in the tag unbinding record, the third unbinding count corresponding to each workstation number is determined.

[0069] In the above scheme, the backup activation ratio, unbinding ratio, first unbinding count, second unbinding count, and third unbinding count of each batch are determined through the first information set. That is, statistical results are obtained from the perspective of the overall production batch and the perspective of individual devices, providing comprehensive information for the anomaly detection of subsequent production batches.

[0070] Based on the above embodiments, as an optional embodiment, the first information set also includes the device tag currently bound to the smart device and the production plan of the smart device.

[0071] In this embodiment of the application, each smart device belongs to a corresponding production plan. The device identifier of the smart device is generated based on the corresponding production activation and then assigned to the smart device.

[0072] In this embodiment of the application, if at least one statistical result and the first information set exhibit at least one of the following conditions, the corresponding production batch is designated as an abnormal batch: The standby activation ratio is greater than the activation ratio threshold. The unbinding ratio is greater than the unbinding ratio threshold; The first unbinding attempt exceeds the first unbinding attempt threshold; The second unbinding attempt exceeds the second unbinding attempt threshold; The third unbinding record exceeds the threshold for the number of third unbinding attempts; The production plan corresponding to the tag that has been bound to the smart device is inconsistent with the production plan corresponding to the smart device.

[0073] In this embodiment, the standby activation ratio refers to the proportion of the number of times the standby scheme is used to activate the current production batch out of all activations. Under normal circumstances, the main scheme should be used for activation. If the number of times the standby scheme is used to activate a production batch is too high, it indicates that the current production batch is abnormal. Therefore, an activation ratio threshold is set in advance. When the standby activation ratio is greater than the activation ratio threshold, it indicates that the number of times the standby scheme is used to activate the current production batch is too high, and the current production batch is abnormal. The current production batch is then classified as an abnormal batch.

[0074] In this embodiment, the unbinding ratio refers to the ratio of the total number of unbinding times of smart devices in the current production batch to the total number of smart devices in the batch. Since an excessively high unbinding ratio indicates that there are abnormalities in the device tags in the current production batch, a pre-set unbinding ratio threshold is used. When the unbinding ratio is greater than the unbinding ratio threshold, it indicates that the device tags in the current production batch have been unbound too many times. Therefore, the current production batch is regarded as an abnormal batch.

[0075] In this embodiment, the first unbinding count refers to the unbinding count of each smart device in the current production batch. If the unbinding count of a certain smart device is too high, it indicates that the smart device is abnormal. Since the smart device belongs to the current production batch, it means that the current production batch is abnormal. Therefore, a first unbinding count threshold is preset, and the first unbinding count of each smart device is compared with the first unbinding count threshold. When the first unbinding count of any smart device is greater than the first unbinding count threshold, it means that there is an abnormal smart device in the current production batch. Therefore, the current production batch is regarded as an abnormal batch.

[0076] In this embodiment of the application, in order to avoid the production batch only experiencing anomalies within a certain time period and failing to detect the anomalies by calculating the unbinding ratio, a second unbinding count is obtained and a second unbinding count threshold is set. When the second unbinding count is greater than the second unbinding count threshold, it indicates that the production batch has unbound the device tag too many times within the preset time period. Therefore, the production batch is abnormal and is regarded as an abnormal batch.

[0077] In this embodiment of the application, the number of times the equipment tag is unbound at each workstation within the production batch is analyzed. If the number of times the equipment tag is unbound at a certain workstation is too high, it indicates that there is a problem with the production at that workstation. Therefore, a third unbinding number threshold is preset, and the third unbinding number corresponding to each workstation number is compared with the third unbinding number threshold. If the third unbinding number corresponding to any workstation number is greater than the third unbinding number threshold, it indicates that there is a problem with the workstation corresponding to that workstation number, and the current production batch is regarded as an abnormal batch.

[0078] In this embodiment, the device tags bound to each smart device are determined. The device identifier of the device can be obtained based on the device tag. Each device identifier has its corresponding production plan, thereby determining the production plan corresponding to the device tag. The production activation corresponding to the device tag is compared with the production plan of the smart device actually recorded in the first information set. If the production plans are inconsistent, it indicates that there is an anomaly in the current smart device. If any smart device has the above anomaly, it indicates that there is an anomaly in the current production batch, and the production batch is regarded as an abnormal batch.

[0079] In the above scheme, for each production batch, based on statistical information that can characterize the production batch as a whole and local statistical information, the abnormal situation of the production batch is analyzed, thus achieving a more comprehensive and accurate analysis of the abnormality of the production batch.

[0080] Based on the above embodiments, as an optional embodiment, the target information of the abnormal batch includes at least one of the following: the production time period of the abnormal batch, the production line number of the production line, the workstation number of the workstation used to produce intelligent equipment, and the operator number.

[0081] In this embodiment, the production time period of the abnormal batch refers to the time period in which the intelligent equipment of the abnormal batch is produced; the production line number refers to the production line number of the production line that produces the intelligent equipment of the abnormal batch. Each production batch is produced through one production line, and each production line has multiple workstations. Each workstation is represented by a workstation number, and each workstation number is assigned to an operator to produce and operate the intelligent equipment. The operator is represented by an operator number.

[0082] In this embodiment of the application, when the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the time dimension, the production time periods corresponding to each abnormal batch are summarized, and the first batch quantity of the abnormal batches in each production time period is obtained as the common distribution characteristics of each abnormal batch in the time dimension.

[0083] In this embodiment of the application, when confirming the common distribution characteristics of all abnormal batches in the time dimension, the production time period corresponding to each abnormal batch is first summarized to determine the number of abnormal batches in each production time period, i.e. the number of the first batch. By confirming the number of abnormal batches in each production time period, it can be known in which time periods the abnormal batches are distributed, thereby obtaining the common distribution characteristics of each abnormal batch in the time dimension.

[0084] In this embodiment of the application, when the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the production line dimension, the production line numbers of each abnormal batch are summarized, and the number of the second batch of the abnormal batches of each production line number is obtained as the common distribution characteristics of each abnormal batch in the production line dimension.

[0085] In this embodiment of the application, when confirming the common distribution characteristics of all abnormal batches in the production line dimension, the production lines corresponding to the abnormal batches are first summarized to determine the number of abnormal batches corresponding to each production line, that is, the number of the second batch. By confirming the number of abnormal batches corresponding to the production line, the distribution of abnormal batches on each production line can be known, thereby obtaining the common distribution characteristics of each abnormal batch in the production line dimension.

[0086] In this embodiment of the application, when the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the workstation dimension, the abnormal smart devices in each abnormal batch whose first unbinding count is greater than the first unbinding count threshold are statistically analyzed to obtain the workstation number of the workstation used for the abnormal smart device. The workstation number of the workstation used for the abnormal smart device is statistically analyzed to obtain the first device quantity corresponding to each workstation number, which is used as the common distribution characteristic of each abnormal batch in the workstation dimension.

[0087] In this embodiment of the application, when confirming the common distribution characteristics of all abnormal batches in the workstation dimension, the first step is to identify the smart devices in the abnormal batch whose first unbinding count is greater than the first unbinding count threshold. If the first unbinding count is greater than the first unbinding count threshold, it indicates that the smart device is abnormal. Then, the workstation number of the workstation used to produce the abnormal smart device is obtained, and the number of abnormal smart devices produced by each workstation number is counted to obtain the first device number of each workstation number. By confirming the first device number corresponding to each workstation number, the distribution of abnormal smart devices in the workstation can be obtained, thereby obtaining the common distribution characteristics of each abnormal batch in the workstation dimension.

[0088] In this embodiment of the application, when the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the personnel dimension, the abnormal smart devices in each abnormal batch whose first unbinding count is greater than the first threshold are counted, the operator number of each abnormal smart device is obtained, the operator number of each abnormal smart device is counted, and the second device quantity corresponding to each operator number is obtained, which is used as the common distribution characteristic of each abnormal batch in the operator dimension.

[0089] In this embodiment of the application, when confirming the common distribution characteristics of all abnormal batches in the personnel dimension, the first step is to identify the smart devices in each abnormal batch whose first unbinding count is greater than the second threshold. If the first unbinding count of a smart device is greater than the first threshold, it indicates that the smart device is abnormal. The number of abnormal smart devices corresponding to each operator number is counted to obtain the second number of devices for each operator number. By confirming the second number of devices corresponding to each operator number, the distribution of abnormal smart devices among operators can be obtained, thereby obtaining the common distribution characteristics of each abnormal batch in the workstation dimension.

[0090] In the above scheme, the common distribution characteristics of all acquired abnormal batches are determined from multiple dimensions such as time, production line, workstation, and operator, providing comprehensive information support for subsequent specific analysis of abnormal batches.

[0091] Based on the above embodiments, as an optional embodiment, the anomaly analysis results include at least one of the following: abnormal time period; abnormal production line; abnormal workstation; and abnormal operator.

[0092] In this embodiment of the application, for each production time period, if the quantity of the first batch corresponding to the production time period is greater than the threshold of the quantity of the first batch, then the production time period is regarded as an abnormal time period.

[0093] In this embodiment of the application, an abnormal time period refers to a time period in which there is an anomaly. Therefore, an anomaly threshold (first batch quantity threshold) is set to determine whether there is an anomaly in each time period. For each production time period, if the first batch quantity, which is used to represent the number of abnormal batches corresponding to the production time period, is greater than the first batch quantity threshold, it indicates that there is an anomaly in the current production time period, and the current production time period is regarded as an abnormal time period.

[0094] In this embodiment of the application, for each production line number, if the quantity of the second batch corresponding to the production line number is greater than the threshold of the quantity of the second batch, then the production line corresponding to the production line number is regarded as an abnormal production line.

[0095] In this application embodiment, an abnormal production line refers to a production line with abnormalities. This application determines whether the current production line is an abnormal production line by judging the number of abnormal batches produced by each production line. Therefore, a second batch quantity threshold is preset, and the second batch quantity corresponding to each production line number is compared with the second batch quantity threshold. When the second batch quantity is greater than the second batch quantity threshold, the production line corresponding to the production line number is regarded as an abnormal production line.

[0096] In this embodiment of the application, for each workstation number, if the number of first devices corresponding to the workstation number is greater than the threshold of the number of first devices, then the workstation corresponding to the workstation number is regarded as an abnormal workstation.

[0097] In this embodiment of the application, an abnormal production line refers to a workstation with abnormalities. The current workstation is determined as an abnormal workstation by judging the number of intelligent devices that produce abnormalities at each workstation. Therefore, a first device quantity threshold is preset, and the first device quantity corresponding to each workstation number is compared with the first device quantity threshold. When the first device quantity is greater than the first device quantity threshold, the workstation corresponding to the corresponding workstation number is regarded as an abnormal workstation.

[0098] In this embodiment of the application, for each operator number, if the number of second devices corresponding to the operator number is greater than the threshold of the number of second devices, then the operator corresponding to the operator number is regarded as an abnormal operator.

[0099] In this embodiment of the application, an abnormal operator refers to an operator who is abnormal. The operator is determined to be an abnormal operator by judging the number of smart devices operated abnormally by each operator. Therefore, a second device number threshold is preset, and the number of second devices corresponding to the operator number is compared with the second device number threshold. When the number of second devices is greater than the second device number threshold, the operator corresponding to the operator number is regarded as an abnormal operator.

[0100] In the above scheme, all abnormal batches are analyzed from multiple dimensions. The distribution characteristics of all abnormal batches in multiple dimensions are used to determine whether the cause of the abnormality is related to a specific time period (abnormal time period), a specific production line (abnormal production line), a specific workstation (abnormal workstation), and a specific operator (abnormal operator). Tracing the root cause of the abnormal batches is beneficial for updating the production line, providing data support for production process optimization, and continuously improving the production quality of intelligent equipment.

[0101] Based on the above embodiments, as an optional embodiment, each production batch corresponds to one production line, and an anomaly analysis method is provided, such as... Figure 3 As shown, the specific content is as follows: S201, determine the total number of production batches and the number of abnormal batches; S202, the ratio of the number of abnormal batches to the total number of batches is used as the target ratio; S203-1, If ​​the target ratio is not less than the first ratio and less than the second ratio, an alarm message is generated to instruct managers to pay attention to the abnormal batch. S203-2, If the target ratio is not less than the second ratio and less than the third ratio, an anomaly report is generated to indicate that the abnormal batch should be investigated. S203-3 If the target ratio is not less than the third ratio, then the production lines corresponding to the abnormal batches are statistically analyzed to determine the number of abnormal batches for each production line, and the production process of the production line with the largest number of batches is suspended.

[0102] In S201 of this application embodiment, the batch number of the multiple production batches obtained is determined, that is, the total batch number, and the number of abnormal batches is determined from the multiple production batches obtained, that is, the abnormal batch number.

[0103] In S202 of this application embodiment, the ratio between the number of abnormal batches and the total number of batches is used as the target ratio to obtain the proportion of abnormal batches to the total number of production batches among the currently acquired multiple production batches.

[0104] In this embodiment, a higher target ratio indicates more abnormal batches, thus requiring greater attention to the current anomalies and higher severity. To avoid unnecessary disruption to normal production and to ensure timely resolution of major issues, differentiated processing is implemented based on severity, as follows: In S203-1 of this application embodiment, a first ratio and a second ratio are preset. If the target ratio is between the first ratio and the second ratio, it indicates that the current abnormal situation is relatively minor. Therefore, when the target ratio is not less than the first ratio and less than the second ratio, an alarm message is generated to instruct the administrator to control the abnormal batch.

[0105] In S203-2 of this application embodiment, a second ratio and a third ratio are preset. When the target ratio is between the second ratio and the third ratio, it indicates that the current abnormal situation needs to be taken seriously and investigated. Therefore, when the target ratio is not less than the second ratio and less than the third ratio, an abnormal report is generated to instruct the management personnel to investigate the abnormal batch.

[0106] In S203-3 of this application embodiment, if the target ratio is not less than the third ratio, it indicates that the current abnormal situation is very serious and the production process needs to be directly suspended. Therefore, when the target ratio is not less than the third ratio, the production lines corresponding to each abnormal batch are statistically analyzed to determine the number of abnormal batches corresponding to each production line, thereby determining the production line that produces the most abnormal batches and suspending the production process of the above production line to avoid more production batches from becoming abnormal.

[0107] In the above plan, the severity of the abnormality is determined based on the proportion of abnormal batches, and corresponding differentiated treatment is implemented to ensure that major issues are intervened in a timely manner while avoiding unnecessary interference with the normal production process. Based on the above embodiments, as an optional embodiment, after the anomaly analysis results, the first production plan for the new production batch is received; the first production plan includes at least one of the first production time period, the first production line number, the first workstation number, and the first operator number. If it is determined that the first production plan meets at least two of the following conditions, an early warning message indicating that there is an anomaly in the first production plan will be generated; The first production period coincides with the abnormal period. The production line number is consistent with the production line number corresponding to the abnormal production line; The first workstation number is consistent with the abnormal workstation number corresponding to the abnormal workstation; The operator number corresponding to the first operator and the abnormal operator is the same.

[0108] In this embodiment of the application, after determining the anomaly analysis results, the first production plan for the new production batch is received. The production plan includes the production time period for producing intelligent equipment, i.e., the first production time period, as well as the first production line number of the production line for producing intelligent equipment, the first workstation number corresponding to each intelligent equipment, and the operator number corresponding to each intelligent equipment.

[0109] In this embodiment of the application, since we obtained abnormal time periods, abnormal production lines, abnormal workstations and abnormal operators by acquiring abnormal analysis results, in order to avoid the continued generation of abnormal batches, we compare various information in the first production plan of the new production batch with the information contained in the abnormal analysis results to determine whether the currently received first production plan can be executed.

[0110] In this embodiment, it is determined whether the first production time period is consistent with the abnormal time period, whether the first production line number is consistent with the production line number corresponding to the abnormal production line, whether the first workstation number is consistent with the abnormal workstation number corresponding to the abnormal workstation, and whether the first operator number is consistent with the operator number corresponding to the abnormal operator. If at least two of the above determination results are consistent, it indicates that the information in the current first production plan has a high degree of overlap with the abnormal analysis results, and an early warning message indicating that there is an abnormality in the first production plan is generated, that is, it is not recommended to use the above combination for the production of intelligent equipment.

[0111] In the above scheme, by comparing the information in the first production plan with the anomaly analysis results, an early warning is issued when there is a high degree of overlap, which reduces the probability of anomalies occurring and avoids a high degree of overlap between the various information in the upcoming first production plan and the information contained in the anomaly analysis results, thus preventing the continued generation of abnormal batches.

[0112] Based on the above embodiments, as an optional embodiment, for any first information set, the first information set is input into the anomaly detection model to obtain the prediction result output by the anomaly detection model. The prediction result is used to indicate whether the production batch corresponding to the first information set is an abnormal batch.

[0113] In this embodiment of the application, the anomaly detection model is trained using the first information set of samples as training samples and whether the production batch of the sample corresponding to the first information set of samples is an abnormal batch as training label.

[0114] In this embodiment of the application, the model is trained by using the first information set of samples and whether the production batch corresponding to the first information set of samples is an abnormal batch until the model converges, thus obtaining an anomaly detection model. By allowing the model to fully learn the characteristics of normal production batches and abnormal batches, it is possible to detect whether the production batch corresponding to the first information set is an abnormal batch by inputting the first information set into the anomaly detection model during the detection of abnormal batches.

[0115] In the above scheme, machine learning technology is used to automatically identify abnormal patterns, thereby improving the accuracy and intelligence of anomaly detection.

[0116] In this embodiment of the application, an abnormal batch can be determined by combining an anomaly detection model with a first statistical result and a first information method to jointly confirm the abnormal batches of multiple production batches currently acquired, which can effectively improve the accuracy of abnormal batch detection.

[0117] In this embodiment of the application, a multi-dimensional data table (first information set) is constructed in the production environment to record the complete historical trajectory of the change status of the device tag and the device activation record. By combining and analyzing the device unbinding record and the device activation record, automatic detection, contextualization and source tracing of production batch anomalies can be realized. This can effectively identify abnormal operation of the device tag in the production process, improve the quality control capability of intelligent devices, reduce the device activation failure rate, and provide effective data support for production process optimization.

[0118] The anomaly analysis method provided in this application can be applied to the field of smart device manufacturing, especially to the production process management of smart home appliances and smart home devices that require activation codes to be bound to device tags. Specifically, it is applicable to: production quality control of smart home appliances, tag management and activation process optimization of IoT devices, and electronic product production lines with serial number management requirements.

[0119] In this embodiment of the application, a dedicated visualization development platform can also be built to intuitively display the distribution characteristics and trend changes of abnormal batches in various dimensions.

[0120] In this embodiment of the application, IoT data during the use of smart devices can also be integrated to correlate and analyze data from the production and usage stages, forming a closed-loop management system.

[0121] In this application, the anomaly analysis method is executed through the following modules, which include: a multi-data recording module, a device activation monitoring module, an anomaly analysis module, a source tracing analysis module, and an early warning processing module.

[0122] The multi-dimensional data recording module is used to collect and store the entire lifecycle data of device tag generation, binding, and unbinding for each smart device; The device activation monitoring module is used to record activation-related information such as activation method and activation result during the device activation process; The anomaly analysis module is used to analyze and identify abnormal batches in production batches that exhibit abnormal label binding behavior based on preset rules. Source tracing analysis is used to perform multi-dimensional source tracing analysis on detected abnormal batches; The context processing module is used to trigger corresponding warnings and processing procedures based on the severity of the anomaly.

[0123] In this embodiment, by recording historical data of smart devices from multiple dimensions, complete tracking of the entire lifecycle of device tags is achieved, providing sufficient evidence for anomaly analysis; the approach shifts from passively responding to device tag issues to proactively detecting batch anomalies, providing early warnings and resolving potential risks; multi-dimensional cross-analysis accurately pinpoints the causes of anomalies in abnormal batches, facilitating targeted guidance for production process improvements; differentiated handling is implemented based on severity, ensuring timely intervention for major issues while avoiding unnecessary disruption to normal production; and anomaly behavior analysis provides data support for production process optimization, continuously improving the production quality of smart devices.

[0124] This application provides an anomaly analysis device, such as... Figure 4 As shown, the anomaly analysis device 40 may include: a first acquisition module 401, a statistics module 402, a second acquisition module 403, a first analysis module 404, and a second analysis module 405.

[0125] Specifically, the first acquisition module 401 is used to acquire a first information set corresponding to each of multiple production batches. The first information set includes at least one piece of information of each smart device in the same production batch during the production stage and the activation stage. The statistics module 402 is used to perform statistics on at least one piece of information in each first information set to obtain at least one corresponding statistical result. If it is determined that at least one statistical result and at least one of the first information sets are abnormal, the corresponding production batch is regarded as an abnormal batch, and information related to the abnormality is obtained from the first information set as the target information of the abnormal batch. The second acquisition module 403 is used to acquire at least one predefined analysis rule, each analysis rule corresponds to a dimension, and is used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension; The first analysis module 404 is used to analyze the target information of each abnormal batch according to each analysis rule, obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, and use them as the first analysis result. The second analysis module 405 is used to analyze each of the first analysis results to obtain anomaly analysis results; the anomaly analysis results are used to indicate the cause of the anomaly.

[0126] The anomaly analysis device provided in this application acquires a first information set corresponding to each of multiple production batches, and performs statistics on at least one piece of information in the first information set to obtain at least one corresponding statistical result. If an anomaly is determined in at least one statistical result and the first information set, the corresponding production batch is designated as an abnormal batch. Information related to the anomaly is obtained from the first information set as the target information of the abnormal batch. At least one predefined analysis rule is acquired, each analysis rule corresponding to a dimension, used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension. For each analysis rule, the target information of the abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension as the first analysis result. Each first analysis result is analyzed to obtain an anomaly analysis result indicating the cause of the anomaly. The above scheme provides sufficient basis for anomaly analysis by acquiring a first information set for recording the intelligent device in the production and activation stages. By determining the common distribution characteristics of each abnormal batch in multiple dimensions, it is possible to obtain anomaly analysis results that accurately locate the cause of the anomaly, providing strong data support for the improvement of the production process and improving the level of production quality control.

[0127] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0128] This application provides an electronic device (computer device / equipment / system) including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of an anomaly analysis method. Compared with related technologies, it can achieve the following: by acquiring a first information set corresponding to each of multiple production batches, and statistically analyzing at least one piece of information in the first information set to obtain at least one corresponding statistical result; if it is determined that there is an anomaly in at least one statistical result and the first information set, the corresponding production batch is designated as an anomaly batch, and information related to the anomaly is obtained from the first information set as target information for the anomaly batch; at least one predefined analysis rule is obtained, and each analysis rule is associated with a dimension. The method is used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension. For each analysis rule, the target information of the abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, which is used as the first analysis result. The first analysis result is then analyzed to obtain the anomaly analysis result used to indicate the cause of the anomaly. The above scheme provides sufficient basis for anomaly analysis by obtaining the first information set used to record the intelligent device in the production and activation stages. By determining the common distribution characteristics of each abnormal batch in multiple dimensions, it is possible to obtain anomaly analysis results that accurately locate the cause of the anomaly, providing strong data support for the improvement of the production process and improving the level of production quality control.

[0129] In one alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this application.

[0130] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0131] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0132] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.

[0133] The memory 4003 stores computer programs that execute embodiments of this application, and its execution is controlled by the processor 4001. The processor 4001 executes the computer programs stored in the memory 4003 to implement the steps shown in the foregoing method embodiments.

[0134] The electronic device package may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0135] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps and corresponding content of the aforementioned method embodiments. Compared with existing technologies, this approach achieves the following: by acquiring the first information sets corresponding to multiple production batches, and statistically analyzing at least one piece of information in the first information sets to obtain at least one corresponding statistical result, if an anomaly is determined in at least one statistical result and the first information set, the corresponding production batch is designated as an abnormal batch. Information related to the anomaly is then obtained from the first information set as the target information of the abnormal batch. At least one predefined analysis rule is acquired, with each analysis rule corresponding to a dimension, used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension. For each analysis rule, the target information of the abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, which is then used as the first analysis result. Each first analysis result is analyzed to obtain an anomaly analysis result indicating the cause of the anomaly. This approach provides sufficient basis for anomaly analysis by acquiring the first information sets used to record the intelligent devices in the production and activation stages. By determining the common distribution characteristics of each abnormal batch in multiple dimensions, it enables the acquisition of anomaly analysis results that accurately pinpoint the cause of the anomaly, providing strong data support for improving the production process and enhancing the level of production quality control.

[0136] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium, a computer-readable medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0137] This application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments. Compared with the prior art, it can achieve: By acquiring the first information sets corresponding to multiple production batches and statistically analyzing at least one piece of information in the first information sets to obtain at least one corresponding statistical result, if an anomaly is found between the at least one statistical result and the first information set, the corresponding production batch is designated as an abnormal batch. Information related to the anomaly is then obtained from the first information set as the target information of the abnormal batch. At least one predefined analysis rule is acquired, with each analysis rule corresponding to a dimension, used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension. For each analysis rule, the target information of the abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, which is then used as the first analysis result. Each first analysis result is analyzed to obtain an anomaly analysis result indicating the cause of the anomaly. The above scheme provides sufficient basis for anomaly analysis by acquiring the first information set used to record the intelligent devices in the production and activation stages. By determining the common distribution characteristics of each abnormal batch in multiple dimensions, it is possible to obtain anomaly analysis results that accurately locate the cause of the anomaly, providing strong data support for the improvement of the production process and improving the level of production quality control.

[0138] The terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the illustrations or text descriptions.

[0139] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0140] The above are only optional implementation methods for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application, without departing from the technical concept of this application, also fall within the protection scope of the embodiments of this application.

Claims

1. An anomaly analysis method, characterized in that, include: Obtain a first information set corresponding to each of multiple production batches, wherein the first information set includes at least one piece of information about each smart device in the same production batch during the production stage and the activation stage; For each first information set, at least one piece of information in the first information set is statistically analyzed to obtain at least one corresponding statistical result. If it is determined that there is an anomaly between the at least one statistical result and at least one of the first information set, the corresponding production batch is regarded as an abnormal batch, and information related to the anomaly is obtained from the first information set as the target information of the abnormal batch. Obtain at least one predefined analysis rule, each analysis rule corresponds to a dimension, and is used to analyze the common distribution characteristics of each abnormal batch in the corresponding dimension; For each analysis rule, the target information of each abnormal batch is analyzed according to the analysis rule to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension, and this is used as the first analysis result. The results of each first analysis are analyzed to obtain anomaly analysis results; the anomaly analysis results are used to indicate the cause of the anomaly.

2. The method according to claim 1, characterized in that, The first information set includes activation records and tag unbinding records for each smart device; the activation records are used to record whether the corresponding smart device is activated through the main scheme or the backup scheme; the tag unbinding records are used to record the number of times the device tags bound to the smart device have been unbound in the past and the workstation number of the workstation used to produce the smart device; The statistical results include at least one of the following: backup activation ratio, unbinding ratio, first unbinding count, second unbinding count, and third unbinding count; The device tag is used to store device information of the smart device; The step of statistically analyzing at least one piece of information in the first information set to obtain a corresponding statistical result includes: For the backup activation ratio, the activation methods of each smart device in the first information set are statistically analyzed to obtain the total number of activations and the number of backup activations of smart devices activated through backup schemes. The ratio between the number of backup activations and the total number of activations is taken as the backup activation ratio of the production batch corresponding to the first information set. Regarding the unbinding ratio, the unbinding records of each smart device in the first information set are statistically analyzed to obtain the total number of times the device tags of all smart devices in the production batch are unbound. The ratio of the total number of unbinding times to the total number of smart devices in the production batch is used as the unbinding ratio. For the first unbinding count, the tag unbinding records of each smart device in the first information set are statistically analyzed to obtain the first unbinding count of each smart device unbinding the device tag; For the second unbinding count, the tag unbinding records within a preset time period in the first information set are statistically analyzed to obtain the second unbinding count corresponding to the preset time period; For the third unbinding count, the workstation numbers in the tag unbinding record are counted to obtain the third unbinding count corresponding to each workstation number.

3. The method according to claim 2, characterized in that, The first information set also includes the device tag currently bound to the smart device and the smart device's production plan; If it is determined that at least one statistical result and at least one of the first information sets are abnormal, then the corresponding production batch is designated as an abnormal batch, including: If at least one of the statistical results and the first information set exists in at least one of the following situations, the corresponding production batch will be considered an abnormal batch: The backup activation ratio is greater than the activation ratio threshold. The unbinding ratio is greater than the unbinding ratio threshold; The first number of unbinding attempts is greater than the first unbinding attempt threshold. The second number of unbinding attempts is greater than the second unbinding attempt threshold. The third unbinding record is greater than the third unbinding count threshold; The production plan corresponding to the device tag bound to the smart device is inconsistent with the production plan corresponding to the smart device.

4. The method according to claim 2, characterized in that, The target information of the abnormal batch includes at least one of the following: the production time period of the abnormal batch, the production line number of the production line, the workstation number of the workstation used to produce intelligent equipment, and the operator number. The step of analyzing the target information of each abnormal batch according to the analysis rules to obtain the common distribution characteristics of each abnormal batch in the corresponding dimension includes: When the analysis rule is used to analyze the common distribution characteristics of each abnormal batch in the time dimension, the production time period corresponding to each abnormal batch is summarized, and the first batch number of abnormal batches in each production time period is obtained as the common distribution characteristics of each abnormal batch in the time dimension. When the analysis rule is used to analyze the common distribution characteristics of each abnormal batch in the production line dimension, the production line number of each abnormal batch is summarized, and the number of the second batch of the abnormal batch for each production line number is obtained as the common distribution characteristics of each abnormal batch in the production line dimension. When the analysis rule is used to analyze the common distribution characteristics of each abnormal batch in the workstation dimension, the abnormal smart devices in each abnormal batch whose first unbinding count is greater than the first unbinding count threshold are counted, the workstation number of the workstation used for the abnormal smart device is obtained, the workstation number of the workstation used for the abnormal smart device is counted, and the first device quantity corresponding to each workstation number is obtained, which is used as the common distribution characteristics of each abnormal batch in the workstation dimension. When the analysis rules are used to analyze the common distribution characteristics of each abnormal batch in the personnel dimension, the abnormal smart devices in each abnormal batch with the first unbinding count greater than the first threshold are counted, the operator ID of each abnormal smart device is obtained, the operator ID of each abnormal smart device is counted, and the number of second devices corresponding to each operator ID is obtained, which is used as the common distribution characteristic of each abnormal batch in the operator dimension.

5. The method according to claim 4, characterized in that, The anomaly analysis results include abnormal time periods and abnormal production lines. abnormal At least one of the workstation staff and the personnel performing abnormal operations; The summarization of the results of each first analysis yields the anomaly analysis results, including: For each production time period, if the quantity of the first batch corresponding to the production time period is greater than the threshold of the quantity of the first batch, then the production time period is regarded as an abnormal time period. For each production line number, if the quantity of the second batch corresponding to the production line number is greater than the threshold of the quantity of the second batch, then the production line corresponding to the production line number is regarded as an abnormal production line. For each workstation number, if the number of first devices corresponding to the workstation number is greater than the threshold of the number of first devices, then the workstation corresponding to the workstation number is regarded as an abnormal workstation. For each operator number, if the number of second devices corresponding to the operator number is greater than the threshold for the number of second devices, then the operator corresponding to the operator number is considered an abnormal operator.

6. The method according to claim 1, characterized in that, Each production batch corresponds to one production line; After obtaining the anomaly analysis results, the process also includes: Determine the total number of production batches and the number of abnormal batches; The ratio of the number of abnormal batches to the total number of batches is used as the target ratio. If the target ratio is not less than the first ratio and less than the second ratio, an alarm message is generated to instruct managers to pay attention to the abnormal batch. If the target ratio is not less than the second ratio and less than the third ratio, an anomaly report is generated to indicate that the abnormal batch should be investigated. If the target ratio is not less than the third ratio, then the production lines corresponding to the abnormal batches are statistically analyzed to determine the number of abnormal batches for each production line, and the production process of the production line with the largest number of batches is suspended.

7. The method according to claim 5, characterized in that, After obtaining the anomaly analysis results, the process further includes: Receive the first production plan for the new production batch; the first production plan includes at least one of the following: first production time period, first production line number, first workstation number, and first operator number; If it is determined that the first production plan meets at least two of the following conditions, then an early warning message indicating that the first production plan is abnormal is generated; The first production time period coincides with the abnormal time period. The first production line number is consistent with the production line number corresponding to the abnormal production line; The first workstation number is consistent with the abnormal workstation number corresponding to the abnormal workstation; The operator number corresponding to the first operator is the same as that of the abnormal operator.

8. The method according to claim 1, characterized in that, The determination that at least one statistical result and at least one of the first information set are abnormal also includes: For any first information set, the first information set is input into the anomaly detection model to obtain the prediction result output by the anomaly detection model. The prediction result is used to indicate whether the production batch corresponding to the first information set is an abnormal batch. The anomaly detection model is trained using the first information set of samples as training samples and whether the production batch of the sample corresponding to the first information set of samples is an abnormal batch as training labels.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-8.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-8.

Images