Early warning method and device, equipment and storage medium
By transforming the initial warning rules of smart home appliances into a tree structure, the target warning rule path is obtained and filtered, which solves the problem of low warning screening efficiency caused by complex rules and achieves fast and accurate warning processing.
Patent Information
- Application Number
- CN202411117816.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2026-03-03
AI Technical Summary
In existing smart home appliance early warning systems, complex or nested early warning rules require operators to conduct further investigations, reducing the efficiency of early warning investigations.
The initial warning rules are transformed into a tree-structured after-sales warning rules. Multiple candidate warning rule paths are obtained through user after-sales information, and the target warning rule path that is actually triggered is selected. The warning is then output and the target warning rule path is displayed.
This improves the efficiency of early warning and investigation, ensuring that operators can quickly locate and handle the actual triggered early warning rules.
Smart Images
Figure CN121599677A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of smart home appliance technology, specifically relating to an early warning method, device, equipment, and storage medium. Background Technology
[0002] To improve the overall user experience of smart home appliances, in addition to the usability aspects, manufacturers are also considering using monitoring of production information or user feedback in the early stages of production and the later stages of after-sales service to provide timely warnings and adjustments, thereby enhancing the user experience.
[0003] Existing technologies can provide timely warnings and adjustments in response to the aforementioned monitoring of production information or user feedback. A common approach is to directly broadcast the warning and display the triggered rule when a warning is triggered in the backend system.
[0004] However, the above method can only display the entire rule. If the warning rule is a nested rule or has high complexity, the operator still needs to further investigate based on the displayed entire warning rule, which reduces the efficiency of warning investigation. Summary of the Invention
[0005] To address the aforementioned problems in the prior art, this application provides an early warning method, apparatus, device, and storage medium.
[0006] Firstly, this application provides an early warning method, the method comprising:
[0007] When the user after-sales information of the smart home appliance is detected to meet the conditions for triggering the initial warning rule of the smart home appliance, it is determined whether the initial warning rule is a tree-structured after-sales warning rule; the root node in the after-sales warning rule indicates the target action of the corresponding non-tree-structured initial warning rule, and each child node indicates the sub-rule obtained by decomposing the corresponding non-tree-structured initial warning rule. The sub-rule is used to characterize the single judgment condition that needs to be met to trigger the after-sales warning rule.
[0008] If so, then multiple candidate warning rule paths are obtained from the initial warning rules based on the user's after-sales information;
[0009] The target warning rule path triggered by the user's after-sales information is determined from the multiple candidate warning rule paths;
[0010] Output the warning and the sub-rules corresponding to the target warning rule path.
[0011] In one possible implementation, obtaining multiple candidate early warning rule paths from the initial early warning rule based on the user's after-sales information includes:
[0012] Based on the monitoring data used to characterize the performance of the smart home appliances, which are statistically analyzed by the after-sales department, target monitoring parameters are extracted from the user after-sales information, and the triggered leaf nodes are obtained from the initial warning rules according to the target monitoring parameters.
[0013] Based on the initial warning rules, candidate warning rule paths from each leaf node to the root node are obtained.
[0014] In one possible implementation, determining the target early warning rule path triggered by the user's after-sales information from the plurality of candidate early warning rule paths includes:
[0015] Based on the sub-rules corresponding to each node in each candidate early warning rule path, the corresponding judgment monitoring parameters are obtained from the monitoring data;
[0016] Based on each judgment monitoring parameter, determine whether the corresponding sub-rule is triggered and output the result value. If the sub-rule is triggered, the result value output by the node corresponding to the sub-rule is a first preset value. If the sub-rule is not triggered, the result value output by the node corresponding to the sub-rule is a second preset value.
[0017] Based on the output value of each node in each candidate warning rule path, the target warning rule path triggered by the user's after-sales information is obtained from multiple candidate warning rule paths.
[0018] In one possible implementation, obtaining the target early warning rule path triggered by the user's after-sales information from multiple candidate early warning rule paths based on the result value output by each node of each candidate early warning rule path includes:
[0019] A result set is obtained based on the result value output by each node of each candidate early warning rule path, and a target result set in which all result values are the first preset value is filtered from multiple result sets.
[0020] The target early warning rule path is obtained based on the candidate early warning rule path corresponding to the target result set.
[0021] In one possible implementation, if the initial warning rule is not a tree-structured after-sales warning rule, the method further includes:
[0022] The initial warning rule is decomposed according to the judgment conditions contained in the initial warning rule to obtain at least one sub-rule, and the priority of each sub-rule is obtained at the same time.
[0023] The target action is determined based on the initial warning rule, and a tree-structured after-sales warning rule corresponding to the initial warning rule is constructed based on the target action, the at least one sub-rule, and the priority of each sub-rule.
[0024] In one possible implementation, obtaining the priority level of each sub-rule includes:
[0025] Priority for retrieving pre-stored monitoring data;
[0026] Extract the target parameters used as judgment conditions from each sub-rule, and obtain the priority of each target parameter according to the priority level of the monitoring data;
[0027] The priority of the corresponding sub-rule is obtained based on the priority of each target parameter.
[0028] In one possible implementation, constructing a tree-structured after-sales early warning rule corresponding to the initial early warning rule based on the target action, the at least one sub-rule, and the priority of each sub-rule includes:
[0029] The root node is determined based on the target action, the child nodes are determined based on the at least one sub-rule, and the level of the corresponding child node is determined based on the priority of each sub-rule.
[0030] Analyze the initial warning rule, obtain the logical relationship between the at least one sub-rule, and associate the corresponding at least one child node according to the logical relationship;
[0031] Based on the root node, at least one associated child node, and the hierarchy of each child node, the initial warning rule is transformed into a tree-structured after-sales warning rule.
[0032] Secondly, this application provides an early warning control device, including a determining module, an acquiring module, and an early warning module, wherein:
[0033] The determining module is used to determine whether the initial warning rule is a tree-structured after-sales warning rule when the detected user after-sales information of the smart home appliance meets the conditions for triggering the initial warning rule of the smart home appliance. The root node in the after-sales warning rule indicates the target action of the corresponding non-tree-structured initial warning rule, and each child node indicates a sub-rule obtained by decomposing the corresponding non-tree-structured initial warning rule. The sub-rule is used to characterize a single judgment condition that needs to be met to trigger the after-sales warning rule.
[0034] The acquisition module is used to, if so, acquire multiple candidate early warning rule paths from the initial early warning rules based on the user after-sales information;
[0035] The acquisition module is further configured to determine the target early warning rule path triggered by the user's after-sales information from the plurality of candidate early warning rule paths;
[0036] The early warning module is used to output early warnings and sub-rules corresponding to the target early warning rule path.
[0037] Thirdly, this application also provides an electronic device, comprising: at least one processor and a memory, wherein:
[0038] The memory is used to store computer-executed instructions;
[0039] The at least one processor is configured to execute computer execution instructions stored in the memory, such that the at least one processor performs the method as described in any of the first aspects.
[0040] Fourthly, this application also provides a computer storage medium storing computer execution instructions, which, when executed by a processor, are used to implement the method described in any of the first aspects.
[0041] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps of the scheme recommendation method as described in any of the first aspects.
[0042] This application provides an early warning method, apparatus, device, and storage medium. When it is determined that user after-sales information triggers an initial early warning rule, and the initial early warning rule is a tree-structured after-sales early warning rule, multiple candidate early warning rule paths that may be triggered are obtained, and the actual triggered target early warning rule path is analyzed and filtered out. An early warning is then output and the target early warning rule path is displayed. Through this method, the triggered target early warning rule path can be quickly determined from the initial early warning rule, improving the efficiency of early warning investigation. Attached Figure Description
[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0044] Figure 1 A flowchart illustrating an early warning method provided in this application embodiment. Figure 1 ;
[0045] Figure 2 A flowchart illustrating an early warning method provided in this application embodiment. Figure 2 ;
[0046] Figure 3 A schematic diagram of an initial early warning rule with a tree structure provided in an embodiment of this application;
[0047] Figure 4 A flowchart illustrating an early warning method provided in this application embodiment. Figure 3 ;
[0048] Figure 5 This is a schematic diagram of the structure of an early warning control device provided in an embodiment of this application;
[0049] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.
[0050] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0051] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0052] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention 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 embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.
[0053] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0054] As the types and functions of smart home appliances become more diverse, the after-sales service needs to monitor an increasing amount of performance data. Consequently, the number of early warning rules based on this performance data is also growing. However, if the early warning rules are nested or have a complex structure, when user after-sales information triggers an early warning rule, only the entire rule will be displayed. Operators will then need to further investigate to determine the actual target early warning rule that was triggered from the entire rule, increasing the difficulty of early warning investigation.
[0055] This application provides an early warning method. When it is determined that user after-sales information triggers an initial early warning rule, and the initial early warning rule is a tree-structured after-sales early warning rule, multiple candidate early warning rule paths that may be triggered are obtained based on the initial early warning rule. The method then analyzes and filters to identify the actual triggered target early warning rule path, outputs an early warning, and displays the target early warning rule path. Through this method, the triggered target early warning rule path can be quickly determined from the initial early warning rule, improving the efficiency of early warning investigation.
[0056] Next, the technical solutions shown in this application will be described in detail through specific embodiments. It should be noted that the following embodiments may exist alone or in combination with each other, and the same or similar content will not be described again in different embodiments.
[0057] Figure 1 A flowchart illustrating an early warning method provided in this application embodiment. Figure 1 .like Figure 1 As shown, the method includes:
[0058] S101. When the user after-sales information of the smart home appliance is detected to meet the conditions for triggering the initial warning rule of the smart home appliance, determine whether the initial warning rule is a tree-structured after-sales warning rule.
[0059] In the after-sales warning rule, the root node indicates the target action of the corresponding non-tree-shaped initial warning rule, and each child node indicates a sub-rule obtained by decomposing the corresponding non-tree-shaped initial warning rule. The sub-rule is used to characterize a single judgment condition that needs to be met to trigger the after-sales warning rule.
[0060] In this step, as the types and functions of smart home appliances increase, to ensure user experience and promptly troubleshoot problems based on user after-sales information, more and more initial warning rules have been set up in the back-end system. However, considering the similarity in the judgment of some abnormal parameters of smart home appliances, some initial warning rules have complex structures that monitor parameters of multiple smart home appliances simultaneously, meaning that the initial warning rule contains multiple parallel or nested judgment conditions. Current warnings, on the other hand, directly output the warning and display the entire initial warning rule when it is determined to be triggered. If the initial warning rule is a nested rule or has a complex structure, not all judgment conditions in the initial warning rule are triggered, requiring further investigation by operators, thus reducing the efficiency of warning troubleshooting.
[0061] For example, the initial warning rule A is: if the number of noise complaints for a certain model of smart washing machine exceeds 50, or if the number of noise complaints for all models of washing machines exceeds 150, then a warning is issued. Initial warning rule A contains two parallel judgment conditions. When initial warning rule A is triggered, both judgment conditions may be triggered, or only one judgment condition may be triggered, requiring further investigation by the operator.
[0062] Therefore, this embodiment transforms the initial warning rules into tree-structured after-sales warning rules, and uses these after-sales warning rules to obtain the actual triggered target warning rule path.
[0063] Specifically, when user after-sales information of smart home appliances is obtained, the data of smart home appliances is updated according to the user after-sales information. When it is determined that the updated data of smart home appliances triggers the initial warning rule, it is determined whether the initial warning rule is a tree-structured after-sales warning rule. Based on the determination result, it is decided whether to directly obtain the actual triggered target warning rule path according to the initial warning rule, or to convert the non-tree-structured initial warning rule into an after-sales warning rule and then execute the aforementioned action of obtaining the target warning rule path.
[0064] S102. If so, then obtain multiple candidate warning rule paths from the initial warning rules based on the user's after-sales information, and determine the target warning rule path triggered by the user's after-sales information from the multiple candidate warning rule paths.
[0065] In this step, the tree-structured after-sales warning rule includes a root node and at least one child node. The root node indicates the target action of the corresponding non-tree-structured initial warning rule, i.e., outputting a warning. Each child node indicates a sub-rule obtained by decomposing the corresponding non-tree-structured initial warning rule. Each sub-rule represents a single judgment condition that needs to be met to trigger the after-sales warning rule. Through the aforementioned tree-structured after-sales warning rule, the corresponding non-tree-structured initial warning rule is transformed into multiple judgment conditions. By determining the triggering status of each child node in the tree-structured after-sales warning rule, the target warning rule path actually triggered by user after-sales information is obtained from the tree-structured after-sales warning rule.
[0066] Therefore, when the initial warning rule is determined to be a tree-structured after-sales warning rule, multiple candidate warning rule paths that may be triggered by user after-sales information are obtained from the initial warning rule based on user after-sales information. Then, the triggering status of each node in each candidate warning rule path is determined, and the target warning rule path that is actually triggered by user after-sales information is obtained from the multiple candidate warning rule paths.
[0067] S103, Output warnings and sub-rules corresponding to the target warning rule paths.
[0068] In this step, once the target warning rule path is determined, a warning is output and the sub-rules corresponding to each sub-node in the determined target warning rule path are displayed to prompt backend operators that the warning rule actually triggered by the user's after-sales information can be dealt with in a timely manner.
[0069] This application provides an early warning method. When it is determined that user after-sales information triggers an initial early warning rule, and the initial early warning rule is a tree-structured after-sales early warning rule, multiple candidate early warning rule paths that may be triggered are obtained based on the initial early warning rule. The method then analyzes and filters to identify the actual triggered target early warning rule path, outputs an early warning, and displays the target early warning rule path. Through this method, the triggered target early warning rule path can be quickly determined from the initial early warning rule, improving the efficiency of early warning investigation.
[0070] Figure 2 A flowchart illustrating an early warning method provided in this application embodiment. Figure 2 This embodiment provides a detailed explanation of the specific steps for obtaining multiple candidate early warning rule paths and determining the target early warning rule path from among them. For example... Figure 2 As shown, the method includes:
[0071] S201. Based on the monitoring data used to characterize the performance of the smart home appliance, which is statistically analyzed by the after-sales department, the target monitoring parameters are extracted from the user's after-sales information, and the triggered leaf node is obtained from the initial warning rules according to the target monitoring parameters.
[0072] In this step, considering that most user after-sales information consists of complaints about the performance of smart home appliances from the user's own sensory perspective, such as: "The detergent smells very strong after each wash with my smart washing machine," the after-sales service department needs to analyze the user's after-sales information based on monitoring data when it receives the information, and extract the target monitoring parameter. For example: User after-sales information A is "The detergent smells very strong after each wash with my smart washing machine." The monitoring data includes: cleaning efficiency, noise level, running time, etc. Analyzing that "strong detergent smell" is affected by the washing machine's cleaning function, the extracted target monitoring parameter is "cleaning efficiency."
[0073] Furthermore, after extracting the target monitoring parameters from the user's after-sales information, the corresponding leaf nodes are filtered in the initial warning rules according to the target monitoring parameters, and it is determined whether the corresponding leaf node is triggered according to the rules corresponding to the leaf node. Finally, the triggered leaf nodes are obtained from the initial warning rules.
[0074] S202. Based on the initial warning rules, obtain the candidate warning rule path from each leaf node to the root node.
[0075] In this step, since the initial warning rule may be a nested rule or a rule with a complex structure, there may be different paths from the same leaf node to the root node, and multiple paths may be triggered. Therefore, it is necessary to determine the candidate warning rule paths from the leaf node to the root node, and to determine whether each node in each candidate warning rule path is triggered.
[0076] For example, Figure 3 This is a schematic diagram of the initial warning rule B. The target monitoring parameter extracted from the user's after-sales information is: "The washing machine vibrates significantly." Based on the target monitoring parameter, the leaf node d indicating "significant vibration" is triggered. Multiple candidate warning rule paths from leaf node d to root node a are obtained based on the initial warning rule B, resulting in:
[0077] The candidate warning rule path b, composed of nodes d, c, and a, is: when the vibration is large and the number of complaints about the dehydration function is greater than 50, an warning will be output.
[0078] The candidate warning rule path a, composed of nodes d, b, and a, is: when the vibration is large and the number of washing machine complaints is greater than 100, an warning is output.
[0079] S203. Based on the sub-rules corresponding to each node in each candidate early warning rule path, obtain the corresponding judgment monitoring parameters from the monitoring data, and determine whether the corresponding sub-rule is triggered based on each judgment monitoring parameter, and output the result value.
[0080] If a sub-rule is triggered, the result value output by the node corresponding to the sub-rule is a first preset value; if the sub-rule is not triggered, the result value output by the node corresponding to the sub-rule is a second preset value.
[0081] In this step, after obtaining multiple candidate warning rule paths from the initial warning rules, it is necessary to determine the triggering status of the nodes included in each candidate warning rule path, and obtain the target warning rule path from the multiple candidate warning rule paths based on the determination results.
[0082] Specifically, the sub-rules corresponding to each child node in each candidate early warning rule path are obtained. The judgment monitoring parameters for each sub-rule are obtained from the monitoring data, and the satisfaction of the corresponding sub-rule is determined based on these judgment monitoring parameters. The output value of each node is then determined based on the results.
[0083] This embodiment does not limit the first preset value and the second preset value in any way. For example, the first preset value can be 1 and the second preset value can be 0.
[0084] S204. Based on the output value of each node in each candidate warning rule path, obtain the target warning rule path triggered by user after-sales information from multiple candidate warning rule paths.
[0085] In this step, the target early warning rule path actually triggered by the user's after-sales information needs to ensure that every node in the path is triggered. Therefore, it is necessary to determine whether each sub-node in each candidate early warning rule path is satisfied based on the output values of multiple nodes in each candidate early warning rule path.
[0086] Specifically, a result set is obtained based on the result value output by each node of each candidate early warning rule path, and a target result set in which all result values are the first preset value is selected from multiple result sets;
[0087] The target early warning rule path is obtained based on the candidate early warning rule path corresponding to the target result set.
[0088] This application provides an early warning method. Based on user after-sales information, the triggered leaf nodes in the initial early warning rules are determined. Multiple candidate early warning rule paths are obtained based on the path from the leaf nodes to the root node. Then, by determining whether the rules corresponding to each node in each early warning rule path are satisfied, the actual triggered target early warning rule path is obtained from the multiple candidate early warning rule paths. This method can quickly filter out multiple sub-rules actually triggered by user after-sales information from the complete initial early warning rules, improving the efficiency and accuracy of early warning investigation.
[0089] Figure 4 A flowchart illustrating an early warning method provided in this application embodiment. Figure 3 This embodiment provides a detailed explanation of the specific steps for constructing a tree-structured after-sales early warning rule corresponding to a non-tree-structured initial early warning rule. For example... Figure 4 As shown, the method includes:
[0090] S401. Decompose the initial warning rule according to the judgment conditions contained in the initial warning rule to obtain at least one sub-rule.
[0091] In this step, when the user's after-sales information is detected to meet the initial warning rule for triggering smart home appliances, and the initial warning rule is not a tree structure, in order to ensure that the content displayed when outputting the warning can help the backend operators to process it quickly, it is necessary to prioritize building a tree structure of after-sales warning rules corresponding to the initial warning rules.
[0092] Specifically, the initial warning rule is analyzed, the judgment conditions contained in the initial warning rule are determined, and the initial warning rule is decomposed based on the judgment conditions to obtain at least one sub-rule.
[0093] For example, the initial warning rule C is: when the washing machine receives user complaints about excessive vibration or noise levels exceeding 60dB during operation, and the number of complaints exceeds 100, or the number of complaints about the spin-drying function exceeds 50, a warning is issued. Analyzing the initial warning rule C, the judgment conditions included in the initial warning rule C are determined to be: "excessive vibration," "noise level exceeding 60dB," "number of washing machine complaints exceeding 100," and "number of spin-drying function complaints exceeding 50." Based on these four judgment conditions, the initial warning rule C is broken down into sub-rules:
[0094] Category a: Excessive vibration; Category b: Noise level greater than 60dB; Category c: Number of washing machine complaints greater than 100; and Category d: Number of complaints about the spin-dry function greater than 50.
[0095] S402. Obtain the priority level of the pre-stored monitoring data, extract the target parameters used as judgment conditions in each sub-rule, obtain the priority of each target parameter according to the priority level of the monitoring data, and obtain the priority of the corresponding sub-rule according to the priority of each target parameter.
[0096] In this step, considering the hierarchy of the tree structure, it is necessary to determine the priority of the sub-rules obtained from the decomposition when constructing the after-sales early warning rules of the tree structure, and then determine the hierarchy of the nodes based on the priority.
[0097] Specifically, the priority levels of the predicted monitoring data are obtained, target parameters as judgment conditions are extracted from each sub-rule, and the priority level of each target parameter is determined according to the priority level of the monitoring parameters. After determining the priority of each target parameter, the priority of the corresponding sub-rule is determined according to the priority of each target parameter.
[0098] S403. Determine the target action based on the initial warning rule, and construct a tree-structured after-sales warning rule corresponding to the initial warning rule based on the target action, at least one sub-rule, and the priority of each sub-rule.
[0099] In this step, the root node of the tree-structured after-sales warning rule indicates the target action of the corresponding non-tree-structured initial warning rule, and each child node indicates the sub-rules obtained by decomposing the corresponding non-tree-structured initial warning rule. Therefore, before constructing the tree-structured after-sales warning rule corresponding to the initial warning rule, it is also necessary to determine the target action of the initial warning rule.
[0100] For example, the initial warning rule C is: when the washing machine is complained about by users for excessive vibration or noise exceeding 60dB during operation, and the number of complaints exceeds 100, or the number of complaints about the spin-drying function exceeds 50, a warning is issued. The target action determined according to the initial warning rule C is "issue a warning".
[0101] Specifically, the root node is determined based on the target action, the child node is determined based on the at least one sub-rule, and the level of the corresponding child node is determined based on the priority of each sub-rule.
[0102] Analyze the initial warning rule, obtain the logical relationship between the at least one sub-rule, and associate the corresponding at least one child node according to the logical relationship;
[0103] Based on the root node, at least one associated child node, and the hierarchy of each child node, the initial warning rule is transformed into a tree-structured after-sales warning rule.
[0104] This application provides an early warning method. When the triggered initial early warning rule is determined to be non-tree-structured, the method decomposes the initial early warning rule to obtain sub-rules and the priority of each sub-rule. Based on the initial early warning rule, the target action is obtained. Then, based on the target action, the sub-rules, and the priority of each sub-rule, a corresponding tree-structured after-sales early warning rule is constructed. Through this method, the non-tree-structured initial early warning rule is transformed into a tree-structured after-sales early warning rule that facilitates early warning investigation, enabling rapid location of the actual triggered sub-rule set when subsequent early warnings are triggered.
[0105] Figure 5 This is a schematic diagram of the structure of an early warning control device provided in an embodiment of this application. Figure 5 As shown, the early warning control device includes a determining module 501, an acquiring module 502, and an early warning module 503, wherein:
[0106] The determining module 501 is used to determine whether the initial warning rule is a tree-structured after-sales warning rule when the detected user after-sales information of the smart home appliance meets the conditions for triggering the initial warning rule of the smart home appliance. The root node in the after-sales warning rule indicates the target action of the corresponding non-tree-structured initial warning rule, and each child node indicates a sub-rule obtained by decomposing the corresponding non-tree-structured initial warning rule. The sub-rule is used to characterize a single judgment condition that needs to be met to trigger the after-sales warning rule.
[0107] The acquisition module 502 is used to, if so, acquire multiple candidate early warning rule paths from the initial early warning rules based on the user after-sales information;
[0108] The acquisition module 502 is further configured to determine the target early warning rule path triggered by the user's after-sales information from the plurality of candidate early warning rule paths;
[0109] The early warning module 503 is used to output early warnings and sub-rules corresponding to the target early warning rule path.
[0110] Figure 6This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 60 includes at least one processor 601 and a memory 602. Optionally, the electronic device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.
[0111] At least one processor 601 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0112] Optionally, in specific implementations, the processor 601 and memory 602 are implemented independently. In this case, the processor 601 and memory 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.
[0113] Optionally, in a specific implementation, if the processor 601 and the memory 602 are integrated on a single chip, the processor 601 and the memory 602 can communicate through an internal interface.
[0114] This application also provides a computer storage medium storing computer execution instructions, which, when executed by a processor, implement the aforementioned method.
[0115] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0116] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. Both the processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the control device of a garment handling apparatus.
[0117] The division of units described herein is merely a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0118] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0119] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0120] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0121] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.
[0122] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. An early warning method, characterized in that, The method includes: When the user after-sales information of the smart home appliance is detected to meet the conditions for triggering the initial warning rule of the smart home appliance, it is determined whether the initial warning rule is a tree-structured after-sales warning rule; the root node in the after-sales warning rule indicates the target action of the corresponding non-tree-structured initial warning rule, and each child node indicates the sub-rule obtained by decomposing the corresponding non-tree-structured initial warning rule. The sub-rule is used to characterize the single judgment condition that needs to be met to trigger the after-sales warning rule. If so, then multiple candidate warning rule paths are obtained from the initial warning rules based on the user's after-sales information; The target warning rule path triggered by the user's after-sales information is determined from the multiple candidate warning rule paths; Output the warning and the sub-rules corresponding to the target warning rule path.
2. The method according to claim 1, characterized in that, The step of obtaining multiple candidate warning rule paths from the initial warning rules based on the user's after-sales information includes: Based on the monitoring data used to characterize the performance of the smart home appliances, which are statistically analyzed by the after-sales department, target monitoring parameters are extracted from the user after-sales information, and the triggered leaf nodes are obtained from the initial warning rules according to the target monitoring parameters. Based on the initial warning rules, candidate warning rule paths from each leaf node to the root node are obtained.
3. The method according to claim 2, characterized in that, Determining the target warning rule path triggered by the user's after-sales information from the plurality of candidate warning rule paths includes: Based on the sub-rules corresponding to each node in each candidate early warning rule path, the corresponding judgment monitoring parameters are obtained from the monitoring data; Based on each judgment monitoring parameter, determine whether the corresponding sub-rule is triggered and output the result value. If the sub-rule is triggered, the result value output by the node corresponding to the sub-rule is a first preset value. If the sub-rule is not triggered, the result value output by the node corresponding to the sub-rule is a second preset value. Based on the output value of each node in each candidate warning rule path, the target warning rule path triggered by the user's after-sales information is obtained from multiple candidate warning rule paths.
4. The method according to claim 3, characterized in that, The step of obtaining the target early warning rule path triggered by the user's after-sales information from multiple candidate early warning rule paths based on the result value output by each node of each candidate early warning rule path includes: A result set is obtained based on the result value output by each node of each candidate early warning rule path, and a target result set in which all result values are the first preset value is filtered from multiple result sets. The target early warning rule path is obtained based on the candidate early warning rule path corresponding to the target result set.
5. The method according to any one of claims 1-4, characterized in that, If the initial warning rule is not a tree-structured after-sales warning rule, the method further includes: The initial warning rule is decomposed according to the judgment conditions contained in the initial warning rule to obtain at least one sub-rule, and the priority of each sub-rule is obtained at the same time. The target action is determined based on the initial warning rule, and a tree-structured after-sales warning rule corresponding to the initial warning rule is constructed based on the target action, the at least one sub-rule, and the priority of each sub-rule.
6. The method according to claim 5, characterized in that, The process of obtaining the priority level of each sub-rule includes: Priority for retrieving pre-stored monitoring data; Extract the target parameters used as judgment conditions from each sub-rule, and obtain the priority of each target parameter according to the priority level of the monitoring data; The priority of the corresponding sub-rule is obtained based on the priority of each target parameter.
7. The method according to claim 6, characterized in that, The step of constructing a tree-structured after-sales early warning rule corresponding to the initial early warning rule based on the target action, the at least one sub-rule, and the priority of each sub-rule includes: The root node is determined based on the target action, the child nodes are determined based on the at least one sub-rule, and the level of the corresponding child node is determined based on the priority of each sub-rule. Analyze the initial warning rule, obtain the logical relationship between the at least one sub-rule, and associate the corresponding at least one child node according to the logical relationship; Based on the root node, at least one associated child node, and the hierarchy of each child node, the initial warning rule is transformed into a tree-structured after-sales warning rule.
8. An early warning control device, characterized in that, It includes a determination module, an acquisition module, and an early warning module, among which: The determining module is used to determine whether the initial warning rule is a tree-structured after-sales warning rule when the detected user after-sales information of the smart home appliance meets the conditions for triggering the initial warning rule of the smart home appliance. The root node in the after-sales warning rule indicates the target action of the corresponding non-tree-structured initial warning rule, and each child node indicates a sub-rule obtained by decomposing the corresponding non-tree-structured initial warning rule. The sub-rule is used to characterize a single judgment condition that needs to be met to trigger the after-sales warning rule. The acquisition module is used to, if so, acquire multiple candidate early warning rule paths from the initial early warning rules based on the user after-sales information; The acquisition module is further configured to determine the target early warning rule path triggered by the user's after-sales information from the plurality of candidate early warning rule paths; The early warning module is used to output early warnings and sub-rules corresponding to the target early warning rule path.
9. An electronic device, characterized in that, include: At least one processor and memory, wherein: The memory is used to store computer-executed instructions; The at least one processor is configured to execute computer execution instructions stored in the memory, such that the at least one processor performs the method as described in any one of claims 1 to 7.
10. A computer storage medium, characterized in that, The computer storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.