A cloud management method and device for a product, a storage medium and an electronic device

Abstract

The application relates to a cloud management method and device of a product, a storage medium and an electronic device, and relates to the technical field of product management.The method comprises the following steps: extracting at least one actual keyword from actual problem description information, the actual keyword being a keyword for describing an abnormality of a repaired product; determining a fault risk value corresponding to the actual problem description information according to each actual keyword, historical faults corresponding to different product types and description keywords in fault description information of the historical faults; if the fault risk value exceeds a preset risk threshold value, determining whether the repaired product has a fault risk according to an actual product type; when the fault risk exists, sending product repair information and a first warning fault to a terminal of a maintenance personnel; and when the fault risk does not exist, sending a second warning fault, a warning product type and the product repair information to the terminal of the maintenance personnel.The application has the effect of improving the product fault troubleshooting efficiency.

Description

Technical Field

[0001] This application relates to the field of product management technology, specifically to a cloud management method, apparatus, storage medium, and electronic device for a product. Background Technology

[0002] Product management refers to the systematic management activities of an enterprise, centered on the entire product lifecycle, integrating resources through cross-departmental collaboration to achieve market positioning, strategic planning, and value optimization. The most crucial aspect of product management is after-sales service. Product repair, as a key step directly addressing physical product problems, is an indispensable part of a complete after-sales system. Good after-sales service enhances customer satisfaction, while an efficient repair process ensures rapid response and resolution of customer issues. Product repair refers to the process by which a user requests repair from the enterprise or its authorized service center when a purchased product malfunctions or is damaged. It is a link in after-sales service, primarily focusing on product repair.

[0003] Currently, the usual way to respond to a user's product repair request is to send the relevant product repair information to the relevant repair personnel, who then go to the site and troubleshoot the relevant products one by one based on the product repair information. However, since users are not product experts, their descriptions of the problems when reporting product repairs are often vague, which makes the troubleshooting efficiency low. Summary of the Invention

[0004] To improve the efficiency of product troubleshooting, this application provides a cloud management method, apparatus, storage medium, and electronic device for products.

[0005] The first aspect of this application provides a cloud-based management method for a product, specifically including: The system obtains product repair information sent by the user's terminal. The product repair information includes the actual product type of the product being repaired and a description of the actual problem of the product being repaired. The product being repaired is a new energy-related product that can be repaired. Extract at least one actual keyword from the actual problem description information, wherein the actual keyword is a keyword describing the abnormality of the reported product; Based on the actual keywords, historical faults corresponding to different product types, and the descriptive keywords in the fault description information of the historical faults, determine the fault risk value corresponding to the actual problem description information; If the fault risk value exceeds the preset risk threshold, then based on the actual product type, it is determined whether the product being repaired has a fault risk. When there is a risk of failure, a first alert fault is identified, and the product repair information and the first alert fault are sent to the repair personnel's terminal. The first alert fault is a fault that the product is prone to have. When there is no risk of failure, the alert product type and the corresponding second alert fault are determined, and the second alert fault, the alert product type, and the product repair information are sent to the terminal of the maintenance personnel. The alert product type is a product type that is prone to failure, and the second alert fault is a fault that is prone to occur in the product of the alert product type.

[0006] By employing the above technical solution, after obtaining the product repair information sent by the user, and combining the actual keywords describing the abnormality of the reported product, historical faults, and descriptive keywords, the overall probability of product failure is analyzed based on the actual problem description information input by the user. This is the fault risk value corresponding to the actual problem description information. If the fault risk value exceeds a preset risk threshold, it indicates a high overall probability of product failure under the given problem description information. Furthermore, by combining the actual product type of the reported product, the probability of the reported product itself failing is analyzed, thus accurately determining whether the reported product has a fault risk. If the reported product has a fault, the first high-probability warning fault is identified, and the product repair information and the first warning fault are sent to the repair personnel's terminal, enabling more targeted troubleshooting and improving the efficiency of product fault diagnosis. If the reported product does not have a fault risk, it indicates that the fault may lie with other products, not the reported product itself. Therefore, the warning product type and the second warning fault are identified and sent along with the product repair information to the repair personnel's terminal, further improving the efficiency of product fault diagnosis.

[0007] In one implementation, determining the fault risk value corresponding to the actual problem description information based on the actual keywords, historical faults corresponding to different product types, and descriptive keywords in the fault description information of the historical faults specifically includes: Identify at least one fault of concern from the historical faults corresponding to different product types; Based on the descriptive keywords in the fault description information of the fault to be concerned, at least one keyword to be concerned is determined corresponding to the fault to be concerned; Determine the fault weight coefficient of the fault to be concerned and determine the keyword weight coefficient of each of the keywords to be concerned. The fault weight coefficient is a weight coefficient that represents the probability of the fault to be concerned occurring, and the keyword weight coefficient is a weight coefficient that represents the probability of the corresponding keyword to be concerned appearing in the fault description information. Based on the actual keywords, the fault weight coefficients, and the keyword weight coefficients, the fault risk value corresponding to the actual problem description information is determined.

[0008] In one implementation, determining the fault risk value corresponding to the actual problem description information based on each of the actual keywords, the fault weight coefficient, and the keyword weight coefficient specifically includes: If at least one of the actual keywords exists among the keywords corresponding to the fault to be concerned, then the fault to be concerned is determined to be an important fault. Multiply the fault weight coefficient of the important fault by the keyword weight coefficient of each actual keyword to obtain the first product result corresponding to the important fault. The first product results corresponding to at least one of the important faults are summed to obtain the fault risk value corresponding to the actual problem description information.

[0009] In one implementation, determining whether the product requiring repair has a risk of failure based on the actual product type specifically includes: If at least one of the actual keywords exists among the keywords corresponding to the fault to be concerned, then the fault to be concerned is determined to be an important fault. Select at least one target fault corresponding to the actual product type from each of the important faults, and multiply the fault weight coefficient of the target fault by the keyword weight coefficient of each actual keyword to obtain the second product result corresponding to the target fault; Summing the results of each second product yields the comprehensive result corresponding to the target fault; The comprehensive results corresponding to each of the target faults are summed to obtain the final comprehensive result corresponding to the actual product type. If the final comprehensive result is greater than the preset summation threshold, it is determined that the product being repaired has a fault risk. If the final comprehensive result is not greater than the summation threshold, then it is determined that the product reported for repair does not have a fault risk; The determination of the first alert fault when a fault risk exists specifically includes: The maximum comprehensive result is selected from all the comprehensive results, and the target fault corresponding to the maximum comprehensive result is determined as the first alert fault.

[0010] In one implementation, determining the alert product type and the corresponding second alert fault when there is no risk of failure specifically includes: If at least one of the actual keywords exists among the keywords corresponding to the fault to be concerned, then the fault to be concerned is determined to be an important fault. From the aforementioned important faults, at least one reference fault corresponding to the same product type is selected. The fault weight coefficient of the reference fault is multiplied by the keyword weight coefficient of each actual keyword to obtain the third product result corresponding to the reference fault. Summing the results of each of the third products yields the summation result corresponding to the reference fault. The summation results corresponding to each of the reference faults are summed to obtain the final summation result. If the final summation result is greater than the preset summation threshold, then when the product type corresponding to the final summation result is the product type of the associated product, the product type corresponding to the final summation result is determined as the alert product type. The associated product is a product that has an operational association with the product reported for repair. The maximum summation result among all summation results corresponding to the final summation result is selected, and the reference fault corresponding to the maximum summation result is determined as the second alert fault.

[0011] In one embodiment, before obtaining the product repair information sent by the user's terminal, the method further includes: When the user reporting the problem inputs actual problem description information, at least one final fault corresponding to the actual product type is selected from each of the faults to be concerned. The fault weight coefficient of each final fault is multiplied by the keyword weight coefficient of the corresponding keyword to be monitored to obtain the fourth product result. The fourth product results corresponding to the same keyword to be monitored are summed to obtain the final product sum. If the final product sum is greater than a preset summation threshold, the virtual key corresponding to the keyword to be monitored is displayed on the terminal of the user who reported the repair.

[0012] In one implementation, the keywords to be monitored include the product part where the anomaly occurred, and the method further includes: Select at least one key fault corresponding to the actual product type from the faults to be concerned, and multiply the fault weight coefficient of the key fault by the keyword weight coefficient of the corresponding keywords to be concerned to obtain the multiplication results corresponding to the key fault. The summation result is obtained by multiplying the results of the key faults mentioned above, and summing the results of the multiplication results of each keyword of concern that includes the same product part. If the accumulated result is greater than the preset summation threshold, the corresponding product part is identified as the target part, and a photo upload reminder is sent to the terminal of the user who reported the repair for the target part.

[0013] A second aspect of this application provides a cloud management device for a product, specifically comprising: The information acquisition module is used to acquire product repair information sent by the user's terminal. The product repair information includes the actual product type of the product being repaired and the actual problem description of the product being repaired. The product being repaired is a new energy-related product that can be repaired. The information extraction module is used to extract at least one actual keyword from the actual problem description information, wherein the actual keyword is a keyword describing the abnormality of the reported product. The first determination module is used to determine the fault risk value corresponding to the actual problem description information based on each actual keyword, the historical faults corresponding to different product types, and the descriptive keywords in the fault description information of the historical faults. The second determination module is used to determine whether the reported product has a fault risk if the fault risk value exceeds a preset risk threshold, based on the actual product type. The first response module is used to identify a first alert fault when there is a risk of failure, and send the product repair information and the first alert fault to the terminal of the maintenance personnel. The first alert fault is a fault that the product is prone to have. The second response module is used to determine the alert product type and the corresponding second alert fault when there is no risk of failure, and send the second alert fault, the alert product type and the product repair information to the terminal of the maintenance personnel. The alert product type is a product type that is prone to failure, and the second alert fault is a fault that is prone to occur in the product of the alert product type.

[0014] By adopting the above technical solution, the information acquisition module receives product repair information sent by the user's terminal. Then, the information extraction module extracts at least one actual keyword from the actual problem description information. Next, the first judgment module determines the fault risk value corresponding to the actual problem description information based on the actual keyword, historical faults corresponding to different product types, and descriptive keywords in the fault description information of historical faults. When the fault risk value exceeds a preset risk threshold, the second judgment module determines whether there is a fault risk in the reported product based on the actual product type. Then, when there is a fault risk, the first response module determines the first alert fault and sends the product repair information and the first alert fault to the repair personnel's terminal. Finally, when there is no fault risk, the second response module determines the alert product type and the corresponding second alert fault and sends the second alert fault, the alert product type, and the product repair information to the repair personnel's terminal.

[0015] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when loaded and executed by a processor, performs the steps of the method described in any one of the first aspects.

[0016] A fourth aspect of this application provides an electronic device, specifically comprising: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, the processor being configured to load and execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of the first aspects.

[0017] In summary, this application includes at least one of the following beneficial technical effects: After obtaining the product repair information sent by the user, by combining the actual keywords describing the abnormality of the repaired product, historical faults, and descriptive keywords, the overall probability of product failure behind the actual problem description information currently entered by the user is analyzed, that is, the fault risk value corresponding to the actual problem description information. If the fault risk value exceeds the preset risk threshold, it means that under the premise of the actual problem description information, the overall probability of product failure is relatively high. Furthermore, by combining the actual product type of the reported product, the probability of the reported product itself malfunctioning is analyzed. This allows for a more accurate assessment of whether the reported product has a malfunction risk. If the reported product is malfunctioning, the most likely first-level warning fault is identified, and the product repair information and the first-level warning fault are sent to the repair personnel's terminal. This enables the repair personnel to conduct more targeted troubleshooting, thereby improving the efficiency of product fault diagnosis. If the reported product does not have a malfunction risk, it indicates that the malfunction may be in other products, not the reported product itself. In this case, the warning product type and the second-level warning fault are identified and sent to the repair personnel's terminal along with the product repair information, thereby improving the efficiency of product fault diagnosis. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a cloud management method for a product provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the relationship between a fault of concern and a keyword of concern, provided in an embodiment of this application. Figure 3 This is a schematic diagram of the structure of a cloud management device for a product provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a cloud management device for another product provided in this application embodiment.

[0019] Explanation of reference numerals in the attached diagram: 11. Information acquisition module; 12. Information extraction module; 13. First determination module; 14. Second determination module; 15. First response module; 16. Second response module; 17. Auxiliary input module; 18. Upload reminder module. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0021] In the description of the embodiments of this application, words such as "exemplarily," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0022] In the description of the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0023] See Figure 1 This application discloses a flowchart of a cloud management method for a product, which can be implemented using a computer program or run on a cloud management device for products based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone utility application, specifically including: S101: Obtain product repair information sent by the user's terminal. The product repair information includes the actual product type and the actual problem description of the product being repaired.

[0024] Specifically, in this embodiment, the user reporting the repair is a person working for the company served by the product supplier. The products provided by the product supplier are all new energy-related products, including but not limited to chargers, battery management systems (BMS), Automated Guided Vehicle (AGV) charging interfaces, batteries in AGVs, and industrial Ethernet devices. The terminal is a personal computer or smartphone. The actual product type is the product type of the reported product with the current malfunction. The actual problem description information is a textual description of the malfunction occurring in the reported product. The reported product is a new energy-related product that can be repaired. New energy-related products are products that use new energy technologies as their core and serve the production / storage / transmission / utilization of clean energy. For example, if the reported product is a charger, the corresponding actual problem description information would be "sudden shutdown," "charger display not lighting up," etc.

[0025] Furthermore, the cloud management method for the product disclosed in this application is executed by a cloud server. A service client from the product supplier is installed on the terminal, and the cloud server serves as the backend server for the service client. When a user discovers an abnormality in a running product, they open the service client on their terminal and click "Report a Repair." The cloud server then generates a product after-sales information collection form according to a preset template. This form includes, but is not limited to, fields such as product type, product serial number (SN), the user's name, the user's company, and a description of the product's malfunction. This after-sales information collection form is sent to the user's terminal. After the user completes the form, it is sent to the cloud server via the terminal. Finally, the cloud server receives the product repair information sent from the user's terminal. This repair information includes the actual product type and a description of the actual problem.

[0026] S102: Extract at least one actual keyword from the actual problem description information. The actual keyword is a keyword that describes the abnormality of the reported product.

[0027] Specifically, after obtaining the actual problem description information sent by the user reporting the problem, at least one actual keyword is extracted from the actual problem description information using a preset TF-IDF algorithm; that is, a keyword describing the abnormality of the reported product. In other embodiments, at least one actual keyword can also be extracted from the actual problem description information using a preset TextRank algorithm. For example, if the actual problem description information is: "Charging suddenly stopped, it's unclear what burned out, and the charger's display is currently not lit," then the final extracted actual keywords would be: "charging stopped" and "display not lit."

[0028] S103: Determine the fault risk value corresponding to the actual problem description information based on each actual keyword, the historical faults corresponding to different product types, and the descriptive keywords in the fault description information of the historical faults.

[0029] Specifically, after the actual keywords are determined, based on the historical repair records cached in the database, historical faults corresponding to different product types (faults that have occurred in products of different types) and the descriptive keywords contained in the fault description information sent by users for those historical faults are obtained. The historical repair records include the descriptive keywords extracted from the fault description information received from users in the past, the product type to which the fault description information belongs, and the specific fault ultimately identified by the repair personnel. The fault description information, like the actual problem description information, is a description of the product problem.

[0030] Furthermore, from the historical faults corresponding to different product types, the repetition frequency of individual historical faults is counted. The higher the repetition frequency, the more likely the corresponding historical fault is to occur. If the repetition frequency exceeds a preset frequency threshold, then the historical fault is identified as a fault of concern, i.e., a product fault that is likely to occur. There is at least one fault of concern. Then, based on the above historical repair records, the descriptive keywords of a single fault of concern in the multiple fault description information in the historical repairs are obtained. The repetition frequency of each individual descriptive keyword among all descriptive keywords is counted. If the repetition frequency exceeds a preset frequency threshold, then the descriptive keyword is identified as a keyword of concern corresponding to the fault of concern, i.e., a keyword that is likely to occur in the fault description information of the fault of concern.

[0031] First, determine the fault weight coefficient for each individual fault to be monitored. The fault weight coefficient is the ratio of the frequency of repetition of this individual fault to the sum of the frequencies of repetition of all faults to be monitored. This fault weight coefficient indicates the probability of the fault occurring. Next, determine the keyword weight coefficient for each keyword corresponding to this fault to be monitored. The keyword weight coefficient is the ratio of the frequency of repetition of this individual keyword to the sum of the frequencies of repetition of all keywords to be monitored. The keyword weight coefficient indicates the probability of the corresponding keyword appearing in the fault description information. For example, if there are three faults to monitor, namely b, c, and d, and fault b has a repetition frequency of 20 times, fault c has a repetition frequency of 40 times, and fault d has a repetition frequency of 40 times, then the fault weight coefficient of fault b is: 20 times / (20 times + 40 times + 40 times) = 0.2. Fault b corresponds to keywords b1, b2, and b3; fault c corresponds to keywords c1, c2, and c3; and fault d corresponds to keywords d1, d2, and d3. Among these, keyword b1 is repeated 10 times, keyword b2 is repeated 60 times, and keyword b3 is repeated 30 times. Therefore, the keyword weight coefficient of keyword b1 is: 10 times / (10 times + 60 times + 30 times) = 0.1. See details in [link to relevant documentation]. Figure 2 .

[0032] Finally, based on the actual keywords, fault weight coefficients, and keyword weight coefficients extracted from the actual problem description information, the fault risk value corresponding to the actual problem description information is determined. The fault risk value represents the probability of a product fault existing under the abnormal problem situation reflected in the actual problem description information. One feasible way to determine the fault risk value is as follows: if at least one actual keyword exists among the keywords corresponding to the fault to be monitored, then the fault to be monitored is identified as a critical fault, i.e., a fault that definitely exists, and at least one critical fault exists. Then, the fault weight coefficient of each critical fault is multiplied by the keyword weight coefficients of the corresponding actual keywords to obtain the first product results corresponding to the critical fault. The first product results represent the probability that the corresponding actual keyword exists in the fault description information when the user reports a critical fault. Finally, the first product results corresponding to each critical fault are summed to obtain the fault risk value corresponding to the actual problem description information. The fault risk value represents the overall probability of a product fault existing given that the user reports the actual problem description information.

[0033] S104: If the fault risk value exceeds the preset risk threshold, determine whether the product being repaired has a fault risk based on the actual product type.

[0034] Specifically, the fault risk value is compared with a preset risk threshold, which is a critical threshold for determining whether a fault risk exists. If the fault risk value exceeds the risk threshold, it indicates that, based on the analysis of the actual problem description information, the overall probability of a fault in the product of the company to which the current repair user belongs is relatively high. Therefore, it is necessary to determine whether the product with a genuine fault risk is the product being repaired. One feasible implementation method is to filter out at least one target fault corresponding to the actual product type from various important faults; that is, faults belonging to the actual product type. The fault weight coefficient of each target fault is multiplied by the keyword weight coefficient of the corresponding actual keywords to obtain the second product results corresponding to the target fault. The second product results represent the probability of the corresponding actual keywords appearing in the fault description information when the target fault exists. Further, the second product results are summed to obtain the comprehensive result corresponding to the target fault. The comprehensive result represents the probability of the repaired product having the target fault. The comprehensive results corresponding to each target fault are summed to obtain the final comprehensive result, which represents the overall probability of a fault occurring in the product of the actual product type. If the final summation result is greater than the preset summation threshold, it indicates that the overall probability of the actual product type malfunctioning is relatively high, thus indicating that the overall probability of the reported product malfunctioning is relatively high given the actual problem description information, and therefore it is determined that the reported product has a malfunction risk; conversely, if the summation result is not greater than the summation threshold, then it is determined that the reported product does not have a malfunction risk.

[0035] S105: When there is a risk of failure, identify the first alert fault and send the product repair information and the first fault to the repair personnel's terminal. The first alert fault is a fault that the product is prone to have.

[0036] Specifically, if it is determined that the reported product has a potential fault risk, then it is necessary to identify the first-priority fault for subsequent troubleshooting by the maintenance personnel. The specific determination process is as follows: select the highest comprehensive result from all the overall results, and identify the target fault (the fault most likely to exist in the reported product) corresponding to the highest comprehensive result as the first-priority fault. Finally, both the product repair information and the first-priority fault are sent to the maintenance personnel's terminal. In other embodiments, based on the various comprehensive results, the order of investigation for the corresponding target faults is determined. The higher the comprehensive result, the greater the probability that the reported product has the corresponding target fault, and the earlier the target fault is investigated, the higher its priority. Finally, the product repair information and the order of investigation for each target fault are sent to the maintenance personnel's terminal, thereby facilitating more targeted fault investigation of the reported product, efficiently identifying faults, and improving maintenance efficiency.

[0037] S106: When there is no risk of failure, identify the type of product to be alerted and the corresponding second alert fault, and send the second alert fault, the type of product to be alerted and the product repair information to the terminal of the maintenance personnel.

[0038] Specifically, if it is determined that the reported product has no fault risk, it means that the abnormality exhibited by the reported product is not caused by its own fault, but may be indirectly caused by the fault of its related products. Therefore, it is necessary to determine the product type of the potentially faulty product. One feasible implementation method is as follows: From various important faults, select at least one reference fault corresponding to the same product type. Then, multiply the fault weight coefficient of each reference fault by the keyword weight coefficient of each corresponding actual keyword to obtain the third product result corresponding to that reference fault. The third product result represents the probability that the corresponding actual keyword exists in the fault description information when the reference fault exists. Next, sum the third product results corresponding to the reference fault to obtain the summation result corresponding to that reference fault. The summation result represents the overall probability of the reference fault occurring given the actual problem description information. Further, sum the summation results corresponding to each reference fault to obtain the final summation result. The final summation result represents the probability of the corresponding product type malfunctioning given the actual problem description information. If the final summation result is greater than the preset summation threshold, it indicates that, given the actual problem description provided by the user, the corresponding product type is more likely to malfunction. This suggests that the malfunction is likely in the product type corresponding to the final summation result. Furthermore, if the product type corresponding to the final summation result is the same as the product type of the associated products, it further verifies that the product type corresponding to the final summation result is highly likely to malfunction. Therefore, the product type corresponding to the final summation result is designated as a "warning product type," meaning a product type prone to malfunction. This indicates that the actual product type filled in by the user in the product repair information is incorrect, and it also verifies that the associated products of the "warning product type" are at risk of malfunction. Finally, the largest summation result is selected from all the summation results corresponding to the final summation result. The reference fault corresponding to the final summation result is the most likely fault in the product of the "warning product type," and this reference fault is designated as the second "warning fault," meaning the most likely fault in the product of the "warning product type." Furthermore, the warning product type, the second "warning fault," and the product repair information sent by the user are sent to the repair personnel's terminal, enabling them to conduct more targeted troubleshooting. Among these, associated products are those currently operationally related to the product being repaired. For example, if the product being repaired is a charger, and the associated product is the battery in the AGV being charged by the charger, if the actual problem description for the product being repaired is "charging interruption," then it could be caused by a fault in the charger itself or a fault in the battery itself. Furthermore, operational association refers to two or more devices / components that depend on each other, communicate their states, and cooperate during operation; the operational status of one directly affects the normal operation of the other.It should be noted that the operation logs of the reported product and other products can be centrally managed through preset log management tools such as ELK Stack or Splunk. By searching by keywords (such as searching for the interaction object ID of "charger A"), related products that have data interaction with the reported product during runtime can be quickly located.

[0039] In other embodiments, before obtaining the product repair information sent by the user's terminal, the SDK provides an onInputChange interface to monitor the user's input of product repair information in real time. When it detects that the user is inputting a description of the actual problem, at least one final fault corresponding to the actual product type is selected from the various potential faults. That is, faults that the reported product may have. The fault weight coefficient of each final fault is multiplied by the keyword weight coefficient of the corresponding potential keywords to obtain the fourth product results corresponding to the final fault. The fourth product results represent the probability that the user's actual problem description contains the corresponding potential keywords when the reported product has the final fault. The fourth product results corresponding to the same potential keyword are summed to obtain the final product sum. The final product sum represents the probability that the user inputs the corresponding potential keywords when describing the problem when the reported product has an anomaly or fault. Finally, if the sum of the final products is greater than the preset summation threshold, it indicates that there is a high probability of inputting the corresponding keywords to be of interest. In this case, the keywords to be of interest corresponding to the sum of the final products will be displayed in a virtual form on the user's terminal. The user can directly click on the virtual product to replace manual input, thus enabling the user to input the problem description information more efficiently and accurately.

[0040] In another embodiment, after receiving the product repair information sent by the user's terminal, key faults corresponding to the actual product type are selected from the various faults to be monitored. The fault weight coefficient of each key fault is multiplied by the keyword weight coefficient of the corresponding keywords to be monitored, resulting in the multiplication results for that key fault. The multiplication results represent the probability that the user will input the corresponding keywords to be monitored when describing the problem when the product has a key fault. The keywords to be monitored include the product part that is abnormal. Further, the multiplication results of the keywords to be monitored that contain the same product part are summed to obtain an accumulated result. The accumulated result represents the probability that the corresponding product part is abnormal. If the accumulated result is greater than a preset summation threshold, it indicates that the corresponding product part of the product is more likely to be abnormal. The product part is then identified as the target part. A photo upload reminder is sent to the user's terminal, reminding the user to take a photo of the target part of the product and upload it. Finally, the photo uploaded by the user is also sent to the repair personnel's terminal, thereby better assisting the repair personnel in troubleshooting the product fault. For example, if the keyword of interest is "display not lit", then the corresponding product part is the display screen.

[0041] The implementation principle of the cloud management method for the product in this application embodiment is as follows: After obtaining the product repair information sent by the user, the system analyzes the overall probability of product failure behind the actual problem description information currently entered by the user, that is, the fault risk value corresponding to the actual problem description information. If the fault risk value exceeds the preset risk threshold, it means that under the premise of the actual problem description information, the overall probability of product failure is relatively high. Furthermore, by combining the actual product type of the reported product, the probability of the reported product itself malfunctioning is analyzed. This allows for a more accurate assessment of whether the reported product has a malfunction risk. If the reported product is malfunctioning, the most likely first-level warning fault is identified, and the product repair information and the first-level warning fault are sent to the repair personnel's terminal. This enables the repair personnel to conduct more targeted troubleshooting, thereby improving the efficiency of product fault diagnosis. If the reported product does not have a malfunction risk, it indicates that the malfunction may be in other products, not the reported product itself. In this case, the warning product type and the second-level warning fault are identified and sent to the repair personnel's terminal along with the product repair information, thereby improving the efficiency of product fault diagnosis.

[0042] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0043] Please see Figure 3 This is a schematic diagram of the structure of a cloud management device for a product provided in an embodiment of this application. This cloud management device for a product can be implemented as all or part of a device through software, hardware, or a combination of both. The device includes an information acquisition module 11, an information extraction module 12, a first determination module 13, a second determination module 14, a first response module 15, and a second response module 16.

[0044] Information acquisition module 11 is used to acquire product repair information sent by the user's terminal. The product repair information includes the actual product type of the product being repaired and the actual problem description of the product being repaired. The product being repaired is a new energy-related product that can be repaired. The information extraction module 12 is used to extract at least one actual keyword from the actual problem description information. The actual keyword is a keyword that describes the abnormality of the reported product. The first judgment module 13 is used to determine the fault risk value corresponding to the actual problem description information based on each actual keyword, the historical faults corresponding to different product types, and the descriptive keywords in the fault description information of the historical faults. The second determination module 14 is used to determine whether the product being repaired has a fault risk if the fault risk value exceeds the preset risk threshold, based on the actual product type. The first response module 15 is used to identify the first alert fault when there is a risk of failure, and send the product repair information and the first alert fault to the terminal of the repair personnel. The first alert fault is a fault that the product is prone to have. The second response module 16 is used to determine the alert product type and the corresponding second alert fault when there is no risk of failure, and send the second alert fault, the alert product type and the product repair information to the terminal of the maintenance personnel. The alert product type is the type of product that is prone to failure, and the second alert fault is the fault that is prone to occur in the product of the alert product type.

[0045] Optionally, the first determination module 13 is specifically used for: Identify at least one fault of concern from the historical faults corresponding to different product types; Based on the descriptive keywords in the fault description information of the faults to be concerned, determine at least one keyword to be concerned corresponding to the faults to be concerned; Determine the fault weight coefficient of the fault to be monitored and the keyword weight coefficient of each keyword to be monitored. The fault weight coefficient is a weight coefficient that represents the probability of the fault to be monitored occurring, and the keyword weight coefficient is a weight coefficient that represents the probability of the corresponding keyword to be monitored appearing in the fault description information. Based on each actual keyword, the fault weight coefficient, and the weight coefficient of each keyword, determine the fault risk value corresponding to the actual problem description information.

[0046] Optionally, the first determination module 13 is specifically used for: If at least one actual keyword exists among the keywords corresponding to the fault to be monitored, then the fault to be monitored is identified as an important fault. Multiply the fault weight coefficient of the important fault by the keyword weight coefficient of each actual keyword to obtain the first product result corresponding to the important fault. Summing the first product results corresponding to at least one important fault yields the fault risk value corresponding to the actual problem description information.

[0047] Optionally, the second determination module 14 is specifically used for: If at least one actual keyword exists among the keywords corresponding to the fault to be monitored, then the fault to be monitored is identified as an important fault. Select at least one target fault corresponding to the actual product type from each important fault, and multiply the fault weight coefficient of the target fault by the keyword weight coefficient of each actual keyword to obtain the second product result corresponding to the target fault. Summing the results of each second product yields the comprehensive result corresponding to the target fault; The comprehensive results corresponding to each target fault are summed to obtain the final comprehensive result corresponding to the actual product type. If the final comprehensive result is greater than the preset summation threshold, it is determined that the product being repaired has a fault risk. If the final summation result is not greater than the summation threshold, then it is determined that the product being repaired does not pose a risk of failure.

[0048] Optional, the first response module 15 is specifically used for: The maximum comprehensive result is selected from all the comprehensive results, and the target fault corresponding to the maximum comprehensive result is determined as the first alert fault.

[0049] Optional, the second response module 16 is specifically used for: If at least one actual keyword exists among the keywords corresponding to the fault to be monitored, then the fault to be monitored is identified as an important fault. Select at least one reference fault corresponding to the same product type from all important faults, and multiply the fault weight coefficient of the reference fault by the keyword weight coefficient of each actual keyword to obtain the third product result corresponding to the reference fault. Summing the results of each third product yields the summation result corresponding to the reference fault. The summation results corresponding to each reference fault are summed to obtain the final summation result. If the final summation result is greater than the preset summation threshold, then when the product type corresponding to the final summation result is the product type of the associated product, the product type corresponding to the final summation result is determined as the alert product type. The associated product is the product that has an operational association with the product reported for repair. Select the largest summation result among all summation results corresponding to the final summation result, and determine the reference fault corresponding to the largest summation result as the second alert fault.

[0050] Optional, such as Figure 4 As shown, the device also includes an auxiliary input module 17, specifically used for: When the system detects that the user has entered a description of the actual problem, select at least one final fault corresponding to the actual product type from the faults to be monitored. The fourth product result is obtained by multiplying the fault weight coefficient of each final fault with the keyword weight coefficient of the corresponding keywords to be monitored. The fourth product results corresponding to the same keyword to be monitored are summed to obtain the final product sum. If the final product sum is greater than the preset summation threshold, the virtual key corresponding to the keyword to be monitored is displayed on the terminal of the user who reported the repair.

[0051] Optionally, the device also includes an upload notification module 18, specifically used for: Select at least one key fault corresponding to the actual product type from the faults to be monitored, and multiply the fault weight coefficient of the key fault by the keyword weight coefficient of the corresponding keywords to be monitored to obtain the multiplication results corresponding to the key fault. The summation result is obtained by multiplying the results of each key fault and the corresponding keywords of concern for the same product part. If the summation result is greater than the preset summation threshold, the corresponding product part will be identified as the target part, and a photo upload reminder will be sent to the terminal of the user who reported the repair for the target part.

[0052] It should be noted that the cloud management device for a product provided in the above embodiments is only illustrated by the division of the above functional modules when executing the cloud management method for the product. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the cloud management device for a product and the cloud management method embodiment for a product provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

[0053] This application also discloses a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements a cloud management method for a product according to the above embodiments.

[0054] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0055] The cloud management method of a product according to the above embodiments is stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the above method.

[0056] This application also discloses an electronic device in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, it implements the cloud management method of the product described above.

[0057] The electronic device can be a desktop computer, a laptop computer, or a cloud server, and includes, but is not limited to, a processor and a memory. For example, the electronic device may also include input / output devices, network access devices, and buses.

[0058] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it.

[0059] The memory can be an internal storage unit of an electronic device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the electronic device. Furthermore, the memory can be a combination of an internal storage unit and an external storage device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0060] In this electronic device, the cloud management method of a product according to the above embodiment is stored in the memory of the electronic device and loaded and executed on the processor of the electronic device for convenient use.

[0061] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A cloud-based management method for a product, characterized in that, Applied to cloud servers, the method includes: The system obtains product repair information sent by the user's terminal. The product repair information includes the actual product type of the product being repaired and a description of the actual problem of the product being repaired. The product being repaired is a new energy-related product that can be repaired. Extract at least one actual keyword from the actual problem description information, wherein the actual keyword is a keyword describing the abnormality of the reported product; Based on the actual keywords, historical faults corresponding to different product types, and the descriptive keywords in the fault description information of the historical faults, determine the fault risk value corresponding to the actual problem description information; If the fault risk value exceeds the preset risk threshold, then based on the actual product type, it is determined whether the product being repaired has a fault risk. When there is a risk of failure, a first alert fault is identified, and the product repair information and the first alert fault are sent to the repair personnel's terminal. The first alert fault is a fault that the product is prone to have. When there is no risk of failure, the alert product type and the corresponding second alert fault are determined, and the second alert fault, the alert product type, and the product repair information are sent to the terminal of the maintenance personnel. The alert product type is a product type that is prone to failure, and the second alert fault is a fault that is prone to occur in the product of the alert product type.

2. The cloud management method for products according to claim 1, characterized in that, The step of determining the fault risk value corresponding to the actual problem description information based on the actual keywords, historical faults corresponding to different product types, and descriptive keywords in the fault description information of the historical faults specifically includes: Identify at least one fault of concern from the historical faults corresponding to different product types; Based on the descriptive keywords in the fault description information of the fault to be concerned, at least one keyword to be concerned is determined corresponding to the fault to be concerned; Determine the fault weight coefficient of the fault to be concerned and determine the keyword weight coefficient of each of the keywords to be concerned. The fault weight coefficient is a weight coefficient that represents the probability of the fault to be concerned occurring, and the keyword weight coefficient is a weight coefficient that represents the probability of the corresponding keyword to be concerned appearing in the fault description information. Based on the actual keywords, the fault weight coefficients, and the keyword weight coefficients, the fault risk value corresponding to the actual problem description information is determined.

3. The cloud management method for the product according to claim 2, characterized in that, The step of determining the fault risk value corresponding to the actual problem description information based on each of the actual keywords, the fault weight coefficient, and the keyword weight coefficient specifically includes: If at least one of the actual keywords exists among the keywords corresponding to the fault to be concerned, then the fault to be concerned is determined to be an important fault. Multiply the fault weight coefficient of the important fault by the keyword weight coefficient of each actual keyword to obtain the first product result corresponding to the important fault. The first product results corresponding to at least one of the important faults are summed to obtain the fault risk value corresponding to the actual problem description information.

4. The cloud management method for products according to claim 2, characterized in that, The step of determining whether the reported product is at risk of failure based on the actual product type specifically includes: If at least one of the actual keywords exists among the keywords corresponding to the fault to be concerned, then the fault to be concerned is determined to be an important fault. Select at least one target fault corresponding to the actual product type from each of the important faults, and multiply the fault weight coefficient of the target fault by the keyword weight coefficient of each actual keyword to obtain the second product result corresponding to the target fault; Summing the results of each second product yields the comprehensive result corresponding to the target fault; The comprehensive results corresponding to each of the target faults are summed to obtain the final comprehensive result corresponding to the actual product type. If the final comprehensive result is greater than the preset summation threshold, it is determined that the product being repaired has a fault risk. If the final comprehensive result is not greater than the summation threshold, then it is determined that the product reported for repair does not have a fault risk; The determination of the first alert fault when a fault risk exists specifically includes: The maximum comprehensive result is selected from all the comprehensive results, and the target fault corresponding to the maximum comprehensive result is determined as the first alert fault.

5. The cloud management method for the product according to claim 2, characterized in that, When there is no risk of failure, determining the type of product to be alerted and the corresponding second alert fault specifically includes: If at least one of the actual keywords exists among the keywords corresponding to the fault to be concerned, then the fault to be concerned is determined to be an important fault. From the aforementioned important faults, at least one reference fault corresponding to the same product type is selected. The fault weight coefficient of the reference fault is multiplied by the keyword weight coefficient of each actual keyword to obtain the third product result corresponding to the reference fault. Summing the results of each of the third products yields the summation result corresponding to the reference fault. The summation results corresponding to each of the reference faults are summed to obtain the final summation result. If the final summation result is greater than the preset summation threshold, then when the product type corresponding to the final summation result is the product type of the associated product, the product type corresponding to the final summation result is determined as the alert product type. The associated product is a product that has an operational association with the product reported for repair. The maximum summation result among all summation results corresponding to the final summation result is selected, and the reference fault corresponding to the maximum summation result is determined as the second alert fault.

6. The cloud management method for products according to claim 2, characterized in that, Before obtaining the product repair information sent by the user's terminal, the process also includes: When the user reporting the problem inputs actual problem description information, at least one final fault corresponding to the actual product type is selected from each of the faults to be concerned. The fault weight coefficient of each final fault is multiplied by the keyword weight coefficient of the corresponding keyword to be monitored to obtain the fourth product result. The fourth product results corresponding to the same keyword to be monitored are summed to obtain the final product sum. If the final product sum is greater than a preset summation threshold, the virtual key corresponding to the keyword to be monitored is displayed on the terminal of the user who reported the repair.

7. The cloud management method for products according to claim 2, characterized in that, The keywords to be monitored include the product parts where the anomaly occurred, and the method further includes: Select at least one key fault corresponding to the actual product type from the faults to be concerned, and multiply the fault weight coefficient of the key fault by the keyword weight coefficient of the corresponding keywords to be concerned to obtain the multiplication results corresponding to the key fault. The summation result is obtained by multiplying the results of the key faults mentioned above, and summing the results of the multiplication results of each keyword of concern that includes the same product part. If the accumulated result is greater than the preset summation threshold, the corresponding product part is identified as the target part, and a photo upload reminder is sent to the terminal of the user who reported the repair for the target part.

8. A cloud management device for a product, characterized in that, include: The information acquisition module (11) is used to acquire product repair information sent by the terminal of the user who reported the repair. The product repair information includes the actual product type of the product being repaired and the actual problem description information of the product being repaired. The product being repaired is a new energy-related product that can be repaired. The information extraction module (12) is used to extract at least one actual keyword from the actual problem description information, wherein the actual keyword is a keyword describing the abnormality of the reported product; The first determination module (13) is used to determine the fault risk value corresponding to the actual problem description information based on the actual keywords, the historical faults corresponding to different product types, and the description keywords in the fault description information of the historical faults. The second determination module (14) is used to determine whether the reported product has a fault risk if the fault risk value exceeds the preset risk threshold, based on the actual product type. The first response module (15) is used to determine the first alert fault when there is a risk of failure, and send the product repair information and the first alert fault to the terminal of the maintenance personnel. The first alert fault is a fault that the product is prone to have. The second response module (16) is used to determine the alert product type and the corresponding second alert fault when there is no risk of failure, and send the second alert fault, the alert product type and the product repair information to the terminal of the maintenance personnel. The alert product type is a product type that is prone to failure, and the second alert fault is a fault that is prone to occur in the product of the alert product type.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the method of any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor loads and executes the computer program, it implements the method of any one of claims 1-7.

Images