Operation and maintenance methods, devices and electronic equipment
Through the decision tree model, analyzing customer perception indicators and matching optimized maintenance strategies, the problems of low efficiency and poor results of mobile network operation and maintenance processing are solved, and the accuracy and user experience of operation and maintenance processing are improved.
Patent Information
- Application Number
- CN202010695530.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-07-17
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2040-07-17
AI Technical Summary
In the prior art, the operation and maintenance processing efficiency of mobile networks is low, and the maintenance strategy matching is inaccurate, resulting in poor operation and maintenance results.
A pre-trained decision tree model is used to determine the probability of dissatisfaction reasons based on customer perceived indicator values, and the operation and maintenance processing is carried out based on these probability matching the corresponding maintenance strategies, and the operation and maintenance contribution value and demand value are optimized for strategy selection.
It improves the accuracy and success rate of operation and maintenance processing, reduces labor costs, realizes active maintenance of mobile network users, and improves user experience.
Smart Images

Figure CN113962403B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to an operation and maintenance processing method, device and electronic equipment. Background Art
[0002] At present, with the continuous development of the communications industry, the competition among major operators in the communications industry is becoming increasingly fierce. With the continuous deepening of the operator system reform, operators can only gain market competitive advantages by adhering to customer-centricity and improving customer satisfaction. Usually, customers will express their dissatisfaction and obtain their needs through complaints.
[0003] In the prior art, the operation and maintenance of mobile networks is usually carried out by analyzing the received complaint texts to obtain the reasons why the complaining users are dissatisfied with the mobile network, and then manually formulating maintenance strategies for individual reasons of dissatisfaction based on prior experience, and performing operation and maintenance processing on the mobile network based on the formulated maintenance strategies. This may result in problems such as low efficiency of operation and maintenance processing and poor operation and maintenance results caused by inaccurate matching of maintenance strategies. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide an operation and maintenance processing method, device and electronic equipment, so as to at least solve the problems of low operation and maintenance processing efficiency and poor operation and maintenance effect existing in the prior art.
[0005] In order to solve the above technical problems, the embodiments of the present application adopt the following technical solutions:
[0006] In a first aspect, an embodiment of the present application further provides an operation and maintenance processing method, including:
[0007] Obtain the indicator values of multiple customer perception indicators of the target user for the operation and maintenance object;
[0008] Based on a pre-trained decision tree model and the index values of the multiple customer perception indicators, determining the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator, the decision tree model is trained based on the operation and maintenance object customer complaint sample data and corresponding labels, the operation and maintenance object customer complaint sample data includes the index values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the dissatisfaction reasons and the customer perception indicators corresponding to the dissatisfaction reasons;
[0009] Determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason;
[0010] Operation and maintenance processing is performed based on the matched maintenance strategy.
[0011] Optionally, determining a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user includes:
[0012] Determine the operation and maintenance demand value of the target user based on the operation and maintenance object, the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user, and the weight of each dissatisfaction reason corresponding to each customer perception indicator under each type of service demand;
[0013] Selecting at least one maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons as a candidate maintenance strategy to obtain a set of candidate maintenance strategies;
[0014] Based on the operation and maintenance contribution values of each selected candidate maintenance strategy to each type of service demand, determining a total operation and maintenance contribution value corresponding to the candidate maintenance strategy set;
[0015] If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to a preset threshold, the selected candidate maintenance strategy set is determined as the matching maintenance strategy.
[0016] Optionally, determining a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user further includes:
[0017] If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is greater than the preset threshold, the steps of selecting at least one maintenance strategy as a candidate maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons to determining the total operation and maintenance contribution value corresponding to the candidate maintenance strategy set are repeated until the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to the preset threshold.
[0018] Optionally, after performing operation and maintenance processing based on the matched maintenance strategy, the method further includes:
[0019] Based on the operation and maintenance processing results and the matched maintenance strategies, the weights of each dissatisfaction reason corresponding to each customer perception indicator under each service demand are updated.
[0020] Optionally, before determining the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator based on the pre-trained decision tree model and the indicator values of the plurality of customer perception indicators, the method further comprises:
[0021] Obtain customer complaint sample data and corresponding labels for the operation and maintenance object;
[0022] The index values of multiple customer perception indicators of the operation and maintenance object by the complaining user are used as training samples, and the reasons for the dissatisfaction of the complaining user with the operation and maintenance object and the customer perception indicators corresponding to the reasons for the dissatisfaction are used as labels. Training is performed based on a decision tree algorithm to obtain the decision tree model.
[0023] Optionally, obtaining customer complaint sample data and corresponding labels for the operation and maintenance object includes:
[0024] Obtain historical complaint texts against the operation and maintenance object;
[0025] Extracting keywords from the historical complaint text;
[0026] Based on the keywords in the historical complaint text and the dissatisfaction reason type library, determine the dissatisfaction reasons of the complaining users in the historical complaint text with the operation and maintenance object and the customer perception indicators corresponding to the dissatisfaction reasons, wherein the dissatisfaction reason type library includes keywords corresponding to various dissatisfaction reasons under various customer perception indicators of the operation and maintenance object;
[0027] Based on the service usage data of the operation and maintenance object by the complaining user, the index values of multiple customer perception indicators of the operation and maintenance object by the complaint are determined.
[0028] Optionally, obtaining customer complaint sample data and corresponding labels for the operation and maintenance object further includes:
[0029] For each dissatisfaction reason corresponding to each customer perception indicator of the operation and maintenance object, determine the number of complaints for the dissatisfaction reason;
[0030] If the number of complaints for the dissatisfaction reason is less than the preset number, a questionnaire is generated based on the dissatisfaction reason and the survey result data of the questionnaire is obtained;
[0031] If the survey result data indicates that the number of users surveyed who have the reason for dissatisfaction accounts for more than a preset proportion, then obtaining the index values of multiple customer perception indexes of the operation and maintenance object of the surveyed users who have the reason for dissatisfaction;
[0032] The customer complaint sample data is updated based on the indicator values of the surveyed users on a plurality of customer perception indicators of the operation and maintenance object.
[0033] Optionally, the decision tree model includes any one of the following models: a random forest model, a naive Bayes model, a bagging model, or an adaptive enhanced AdaBoost model.
[0034] In a second aspect, an embodiment of the present application provides an operation and maintenance processing device, including:
[0035] The first acquisition module is used to obtain the index values of multiple customer perception indicators of the target user for the operation and maintenance object;
[0036] A first determination module is used to determine the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator based on a pre-trained decision tree model and the indicator values of the multiple customer perception indicators, wherein the decision tree model is trained based on the operation and maintenance object customer complaint sample data and corresponding labels, the operation and maintenance object customer complaint sample data includes the indicator values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the dissatisfaction reasons and the customer perception indicators corresponding to the dissatisfaction reasons;
[0037] A second determination module is used to determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason;
[0038] An operation and maintenance processing module is used to perform operation and maintenance processing based on the matched maintenance strategy.
[0039] Optionally, the second determining module is specifically configured to:
[0040] Determine the operation and maintenance demand value of the target user based on the operation and maintenance object, the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user, and the weight of each dissatisfaction reason corresponding to each customer perception indicator under each type of service demand;
[0041] Selecting at least one maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons as a candidate maintenance strategy to obtain a set of candidate maintenance strategies;
[0042] Based on the operation and maintenance contribution values of each selected candidate maintenance strategy to each type of service demand, determining a total operation and maintenance contribution value corresponding to the candidate maintenance strategy set;
[0043] If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to a preset threshold, the selected candidate maintenance strategy set is determined as the matching maintenance strategy.
[0044] Optionally, the second determining module is further specifically configured to:
[0045] If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is greater than the preset threshold, the steps of selecting at least one maintenance strategy as a candidate maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons to determining the total operation and maintenance contribution value corresponding to the candidate maintenance strategy set are repeated until the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to the preset threshold.
[0046] Optionally, the device further comprises:
[0047] The updating module is used to update the weight of each dissatisfaction reason corresponding to each customer perception indicator under each service demand based on the operation and maintenance processing result and the operation and maintenance contribution value corresponding to each service demand of the matched maintenance strategy.
[0048] Optionally, the device further comprises a training module, wherein the training module is used to:
[0049] Obtain customer complaint sample data and corresponding labels for the operation and maintenance object;
[0050] The index values of multiple customer perception indicators of the operation and maintenance object by the complaining user are used as training samples, and the reasons for the dissatisfaction of the complaining user with the operation and maintenance object and the customer perception indicators corresponding to the reasons for the dissatisfaction are used as labels. Training is performed based on a decision tree algorithm to obtain the decision tree model.
[0051] Optionally, the training module is specifically used for:
[0052] Obtain historical complaint texts against the operation and maintenance object;
[0053] Extracting keywords from the historical complaint text;
[0054] Based on the keywords in the historical complaint text and the dissatisfaction reason type library, determine the dissatisfaction reasons of the complaining users in the historical complaint text with the operation and maintenance object and the customer perception indicators corresponding to the dissatisfaction reasons, wherein the dissatisfaction reason type library includes keywords corresponding to various dissatisfaction reasons under various customer perception indicators of the operation and maintenance object;
[0055] Based on the service usage data of the operation and maintenance object by the complaining user, the index values of multiple customer perception indicators of the operation and maintenance object by the complaint are determined.
[0056] Optionally, the training module is further specifically used for:
[0057] For each dissatisfaction reason corresponding to each customer perception indicator of the operation and maintenance object, determine the number of complaints for the dissatisfaction reason;
[0058] If the number of complaints for the dissatisfaction reason is less than the preset number, a questionnaire is generated based on the dissatisfaction reason and the survey result data of the questionnaire is obtained;
[0059] If the survey result data indicates that the number of users surveyed who have the reason for dissatisfaction accounts for more than a preset proportion, then obtaining the index values of multiple customer perception indexes of the operation and maintenance object of the surveyed users who have the reason for dissatisfaction;
[0060] The customer complaint sample data is updated based on the indicator values of the surveyed users on a plurality of customer perception indicators of the operation and maintenance object.
[0061] Optionally, the decision tree model includes any one of the following models: a random forest model, a naive Bayes model, a bagging model, or an adaptive enhanced AdaBoost model.
[0062] In a third aspect, an embodiment of the present application provides an electronic device, including:
[0063] processor;
[0064] a memory for storing instructions executable by the processor;
[0065] The processor is configured to execute the instructions to implement the method as described in the first aspect.
[0066] In a fourth aspect, the present application provides a computer-readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method described in the first aspect.
[0067] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:
[0068] By obtaining the index values of multiple customer perception indicators of the target user for the operation and maintenance object, and based on a pre-trained decision tree model and the index values of multiple customer perception indicators, the probability of the target user generating each reason for dissatisfaction corresponding to each customer perception indicator is determined, and further according to the probability of the operation and maintenance object and the target user generating each reason for dissatisfaction corresponding to each customer perception indicator, a matching maintenance strategy is determined, and operation and maintenance processing is performed based on the matching maintenance strategy. Compared with the method in the prior art of performing operation and maintenance processing based on the content of the complaint after receiving the user complaint, the operation and maintenance processing method provided in the embodiment of the present application can realize active maintenance of mobile network users and improve user experience. In addition, the reasons for user dissatisfaction with the mobile network are subdivided from multiple dimensions of the operation and maintenance object. The decision tree model is trained based on the sample data of customer complaints of the operation and maintenance object and the corresponding labels. The sample data of customer complaints of the operation and maintenance object include the indicator values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the reasons for dissatisfaction and the customer perception indicators corresponding to the reasons for dissatisfaction. Therefore, the prediction results output by the decision tree model reflect the probabilities of various reasons for dissatisfaction of the target user under different customer perception indicators of the operation and maintenance object, and then the probabilities of these different reasons for dissatisfaction are comprehensively generated to match the corresponding maintenance strategies. Compared with the method of manually matching the maintenance strategies based on a single reason for dissatisfaction, the maintenance strategies for the target users are more in line with the user's operation and maintenance needs, thereby improving the accuracy and success rate of the operation and maintenance processing and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0070] Figure 1 A flowchart of an operation and maintenance processing method provided for an embodiment of the present application;
[0071] Figure 2 A flowchart of a method for training a decision tree model provided for one embodiment of the present application;
[0072] Figure 3 A flowchart of another operation and maintenance processing method provided for an embodiment of the present application;
[0073] Figure 4 A block diagram of an operation and maintenance processing device provided for one embodiment of the present application;
[0074] Figure 5 A block diagram of another operation and maintenance processing device provided for an embodiment of the present application;
[0075] Figure 6 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION
[0076] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0077] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0078] See also Figure 1 , the present application embodiment provides an operation and maintenance processing method, such as Figure 1 As shown, the method may include the following steps:
[0079] S102: Obtain indicator values of multiple customer perception indicators of the target user for the operation and maintenance object.
[0080] In an embodiment of the present application, the operation and maintenance object may be one or more of the various products, services, and businesses provided by the mobile network operator. For example, the operation and maintenance object may include but is not limited to 4G services, home broadband services, government services, Magic Box and business hall services, etc.
[0081] The customer perception indicators of the operation and maintenance objects refer to the evaluation indicators of the operation and maintenance objects that can affect customer perception. Different operation and maintenance objects have different customer perception indicators. For example, the customer perception indicators of 4G services may include, but are not limited to: tariff packages, network quality, business promotion and handling, service level, etc.; the customer perception indicators of government services may include, but are not limited to: product reliability, tariff prices, service activation, fault handling, customer manager services and other indicators that affect user perception; the customer perception indicators of business hall services may include, but are not limited to: business hall environment, waiting time in queues, business handling time, salesperson service attitude and other indicators, etc.
[0082] Each customer perception indicator may affect user satisfaction in different ways, that is, users may have multiple reasons for dissatisfaction with each customer perception indicator of the operation and maintenance object. For example, for the customer perception indicator of user reasons for home broadband services, the reasons for dissatisfaction that users may have for this customer perception indicator include but are not limited to: not knowing how to use the set-top box remote control, the battery of the set-top box remote control has problems, not knowing how to connect to the set-top box, etc.
[0083] S104: Based on the pre-trained decision tree model and the index values of the plurality of customer perception indexes, determine the probability of each dissatisfaction reason corresponding to each customer perception index being generated by the target user.
[0084] In the embodiment of the present application, the decision tree model is trained based on the sample data of customer complaints of the operation and maintenance object and the corresponding labels. The sample data of customer complaints of the operation and maintenance object includes the index values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the reasons for dissatisfaction and the customer perception indicators corresponding to the reasons for dissatisfaction.
[0085] The decision tree model in the embodiment of the present application may, for example, include any of the following algorithms: a random forest model, a naive Bayes model, a bagging model, an AdaBoost (Adaptive Boosting) model, etc., which is not limited in the embodiment of the present application.
[0086] It should be noted that the process of training the above decision tree model will be described below. Figure 2 The detailed description is given in the embodiment shown in the figure and will not be repeated here.
[0087] S106. Determine a matching maintenance strategy based on the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user.
[0088] S108. Perform operation and maintenance based on the matched maintenance strategy.
[0089] Among them, there is a corresponding relationship between the maintenance strategy and the dissatisfaction reason. That is to say, for each dissatisfaction reason corresponding to each customer perception indicator of the operation and maintenance object, a maintenance strategy for the dissatisfaction reason is pre-set.
[0090] After obtaining the probability of each dissatisfaction reason of the target user corresponding to each customer perception indicator of the operation and maintenance object, a corresponding maintenance strategy can be determined based on the probability of each dissatisfaction reason and the maintenance strategy corresponding to each dissatisfaction reason.
[0091] It should be noted that the operation and maintenance object in the embodiment of the present application may be one or more. For the latter, the operation and maintenance object may include all products, services and businesses provided by the mobile network operator, and may also include some products, services and businesses provided by the mobile network operator that have a greater impact on user satisfaction. Secondly, the multiple customer perception indicators of the operation and maintenance object may include all evaluation indicators of the operation and maintenance object, and may also include some evaluation indicators of the operation and maintenance object that have a greater impact on user satisfaction.
[0092] The operation and maintenance processing method provided in this embodiment obtains the index values of multiple customer perception indicators of the target user for the operation and maintenance object, and based on the pre-trained decision tree model and the index values of multiple customer perception indicators, determines the probability of the target user generating each reason for dissatisfaction corresponding to each customer perception indicator, further determines the matching maintenance strategy based on the probability of each reason for dissatisfaction generated by the operation and maintenance object and the target user corresponding to each customer perception indicator, and performs operation and maintenance processing based on the matching maintenance strategy. Compared with the method of performing operation and maintenance processing based on the content of the complaint after receiving the user complaint in the prior art, the operation and maintenance processing method provided in the embodiment of the present application can realize active maintenance of mobile network users and improve user experience. In addition, the reasons for user dissatisfaction with the mobile network are subdivided from multiple dimensions of the operation and maintenance object. The decision tree model is trained based on the sample data of customer complaints of the operation and maintenance object and the corresponding labels. The sample data of customer complaints of the operation and maintenance object include the indicator values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the reasons for dissatisfaction and the customer perception indicators corresponding to the reasons for dissatisfaction. Therefore, the prediction results output by the decision tree model reflect the probabilities of various reasons for dissatisfaction of the target user under different customer perception indicators of the operation and maintenance object, and then the corresponding maintenance strategies are matched for the target users based on the comprehensive probabilities of these different reasons for dissatisfaction. Compared with the method of manually matching the maintenance strategies based on a single reason for dissatisfaction, the maintenance strategies for the target users are more in line with the operation and maintenance needs of the target users, thereby improving the accuracy and success rate of the operation and maintenance processing and reducing labor costs.
[0093] In order to enable those skilled in the art to better understand the technical solution provided by the embodiments of the present application, the operation and maintenance processing method provided by the embodiments of the present application is described in detail below.
[0094] First, with respect to the decision tree model in the above step S104, the embodiment of the present application also includes a training method for the decision tree model.
[0095] It is worth noting that the training of the decision tree model is carried out in advance based on the sample data of customer complaints of the operation and maintenance objects collected from the mobile network operation platform. In the subsequent operation and maintenance process, there is no need to train the decision tree model every time. Alternatively, the decision tree model can be periodically updated based on the new sample data of customer complaints of the operation and maintenance objects collected from the mobile network operation platform to improve the prediction accuracy of the decision tree model, thereby improving the accuracy and success rate of subsequent operation and maintenance processing.
[0096] Specifically, the training method of the above decision tree model is as follows: Figure 2 As shown, including:
[0097] S202: Obtain customer complaint sample data and corresponding labels for the operation and maintenance object.
[0098] Among them, the customer complaint sample data includes the index values of multiple customer perception indicators of the operation and maintenance object by multiple complaining users, as well as the reasons for dissatisfaction of each complaining user with the operation and maintenance object and the customer perception indicators corresponding to the reasons for dissatisfaction.
[0099] In the embodiment of the present application, customer complaint sample data for the operation and maintenance object can be obtained in a variety of ways.
[0100] In a first optional implementation, customer complaint sample data and corresponding labels for the operation and maintenance object may be obtained based on the historical complaint texts of the complaining users.
[0101] Specifically, each historical complaint text regarding the operation and maintenance object can be obtained, and the keywords in the historical complaint text can be extracted. Further, based on the keywords in the historical complaint text and the dissatisfaction reason library, the reasons for dissatisfaction of the complaining user in the historical complaint text with the operation and maintenance object and the customer perception indicators corresponding to the reasons for dissatisfaction can be determined. Based on the business usage data of the operation and maintenance object by the complaining user, the index values of multiple customer perception indicators of the operation and maintenance object by the complaining user can be determined.
[0102] Among them, the dissatisfaction reason type library includes keywords corresponding to various dissatisfaction reasons under each customer perception indicator of the operation and maintenance object. By performing similarity matching between the keywords in the historical complaint text and the keywords corresponding to various dissatisfaction reasons, the dissatisfaction reasons generated by the complaining users and the corresponding customer perception indicators are determined based on the similarity obtained by matching.
[0103] The business usage data of the operation and maintenance object by the user may include, for example, the attribute data of the user, the consumption behavior data of the user for the operation and maintenance object, and the usage data record of the operation and maintenance object. Among them, the attribute data of the user refers to the basic information of the user, which may include but is not limited to the user's age, gender, geographical region, etc. The consumption behavior data of the user for the operation and maintenance object refers to the data used to characterize the consumption behavior of the user for the operation and maintenance object, which may include but is not limited to the average revenue per user (ARPU), the amount of funds spent on the operation and maintenance object, etc. The usage data record of the user for the operation and maintenance object refers to the usage data record of the user for the operation and maintenance object, which may include but is not limited to the business handling record corresponding to the operation and maintenance object, the traffic usage corresponding to the operation and maintenance object, the number of complaints generated by the user against the operation and maintenance object, etc.
[0104] In a second optional implementation, customer complaint sample data and corresponding labels for the operation and maintenance object may be obtained through a questionnaire survey.
[0105] Specifically, a corresponding questionnaire can be set based on multiple customer perception indicators of the operation and maintenance object and questionnaire survey result data can be obtained. For each questionnaire, the reasons for the dissatisfaction of the surveyed users with the operation and maintenance object and the customer perception indicators corresponding to the reasons for the dissatisfaction are determined based on the questionnaire survey result data of the questionnaire, and the indicator values of the multiple customer perception indicators of the operation and maintenance object of the surveyed users are determined based on the business usage data of the operation and maintenance object of the surveyed users.
[0106] In some other optional implementations, customer complaint sample data and corresponding labels for the operation and maintenance object may be obtained based on the historical complaint texts and questionnaire survey data of the complaining users.
[0107] Specifically, after obtaining the customer complaint sample data and corresponding labels for the operation and maintenance object through the first optional implementation method described above, the number of complaints for each dissatisfaction reason corresponding to each customer perception indicator of the operation and maintenance object can also be determined. If the number of complaints for the dissatisfaction reason is less than the preset number, a questionnaire is generated based on the dissatisfaction reason and the survey result data of the questionnaire is obtained. Furthermore, if the survey result data indicates that the number of users of the surveyed users who generated the dissatisfaction reason accounts for more than a preset proportion, the index values of the multiple customer perception indicators of the operation and maintenance object for the surveyed users who generated the dissatisfaction reason are obtained, and based on the index values of the multiple customer perception indicators of the operation and maintenance object for the surveyed users, the customer complaint sample data is updated.
[0108] It can be understood that, through this implementation, it is possible to avoid the situation where the number of sample data corresponding to a certain dissatisfaction reason under a certain customer perception indicator is too small to affect the accuracy of the decision tree model finally trained.
[0109] S204, using the index values of multiple customer perception indicators of the operation and maintenance object by the complaining user as training samples, using the reasons for the dissatisfaction of the complaining user with the operation and maintenance object and the customer perception indicators corresponding to the reasons for the dissatisfaction as labels, training is performed based on a decision tree algorithm to obtain a decision tree model.
[0110] Specifically, the decision tree model is obtained by taking the index values of multiple customer perception indicators of the operation and maintenance object of the complaining user as input and the corresponding labels as output, and training through a decision tree algorithm.
[0111] The decision tree algorithm in the embodiment of the present application may include, for example, any of the following algorithms: random forest algorithm, naive Bayes algorithm, bagging algorithm, AdaBoost (Adaptive Boosting) algorithm, etc., which is not limited in the embodiment of the present application.
[0112] Next, with respect to the above step S106, in an optional implementation manner, as Figure 3 As shown, step S106 may include:
[0113] S1061, determining the operation and maintenance demand value of the target user based on the operation and maintenance object, the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user, and the weight of each dissatisfaction reason corresponding to each customer perception indicator under each type of service demand.
[0114] The service demands in this application may include, for example, but are not limited to, network quality demands, fee demands, business demands, and emotional demands.
[0115] Specifically, the user's operation and maintenance demand value can be expressed by α∑P i T ×Y i Determine, where α represents the demand adjustment factor corresponding to each type of service demand, which can be customized according to actual needs. For example, α can be set to (0.25, 0.30, 0.1, 0.2, 0.15); P i T represents the weight corresponding to the i-th user, p inmqs represents the weight of the qth dissatisfaction reason generated by the i-th user under the m-th customer perception indicator of the n-th operation and maintenance object under the s-th service demand; y inmqs It represents the probability of the qth reason of dissatisfaction caused by the i-th user under the m-th customer perception indicator of the n-th operation and maintenance object.
[0116] S1062. Select at least one maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons as a candidate maintenance strategy to obtain a set of candidate maintenance strategies.
[0117] S1063: Based on the operation and maintenance contribution values of the selected candidate maintenance strategies to various types of service demands, determine the total operation and maintenance contribution value corresponding to the candidate maintenance strategy set.
[0118] Specifically, the total operation and maintenance contribution value corresponding to the candidate operation and maintenance set can be obtained by Determine, where β represents the contribution adjustment factor corresponding to each type of service demand, which can be customized according to actual needs. For example, β can be set to (0.25, 0.30, 0.1, 0.15, 0.2); E ij It represents the operation and maintenance contribution value of the j-th candidate maintenance strategy to the i-th service demand.
[0119] S1064: If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to a preset threshold, the selected candidate maintenance strategy set is determined as the matching maintenance strategy.
[0120] Furthermore, the above step S106 may also include:
[0121] S1065. If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is greater than the preset threshold, repeat the above steps S1062 and S1063 until the difference between the total operation and maintenance contribution value and the operation and maintenance demand value corresponding to the screened candidate maintenance strategy set is less than or equal to the preset threshold.
[0122] It can be understood that the user's operation and maintenance demand value is determined by the probability of various reasons for dissatisfaction generated by various customer perception indicators of the operation and maintenance object and the weights of various reasons for dissatisfaction under various service demands, so that the determined operation and maintenance demand value takes into account the user's operation and maintenance demand situation for various service demands; the total operation and maintenance contribution value of the selected maintenance strategy is determined by the selected maintenance strategy and the operation and maintenance contribution value of each maintenance strategy to various service demands, so that the selection of the maintenance strategy takes into account the impact of various service demands of the user, and then the maintenance strategy for the user is determined based on the user's operation and maintenance demand value and the total operation and maintenance contribution value corresponding to the selected maintenance strategy, which can improve the matching accuracy of the maintenance strategy and thus improve the efficiency of repairing user satisfaction.
[0123] In another embodiment of the present application, in order to further improve the accuracy of operation and maintenance processing, after the above-mentioned step S106, the operation and maintenance processing method described in any of the above embodiments of the present application may also include: obtaining the operation and maintenance processing results of the matched maintenance strategy, and based on the operation and maintenance processing results and the operation and maintenance contribution values of the matched strategies corresponding to each type of service demands, updating the weights of various dissatisfaction reasons under each customer perception indicator of the operation and maintenance object under each type of service demands.
[0124] Specifically, for each type of service demand, the weight of each dissatisfaction reason under the service demand may be updated based on the average value of the operation and maintenance contribution value of the successful operation and maintenance maintenance strategy under the service demand.
[0125] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0126] See also Figure 4 , the present application embodiment also provides an operation and maintenance processing device, such as Figure 4 As shown, the apparatus 400 may include:
[0127] The first acquisition module 410 is used to obtain the index values of multiple customer perception indicators of the target user for the operation and maintenance object;
[0128] A first determination module 420 is used to determine the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator based on a pre-trained decision tree model and the indicator values of the multiple customer perception indicators, wherein the decision tree model is trained based on the operation and maintenance object customer complaint sample data and corresponding labels, the operation and maintenance object customer complaint sample data includes the indicator values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the dissatisfaction reasons and the customer perception indicators corresponding to the dissatisfaction reasons;
[0129] The second determination module 430 is used to determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason;
[0130] The operation and maintenance processing module 440 is used to perform operation and maintenance processing based on the matched maintenance strategy.
[0131] Optionally, the second determining module 430 is specifically configured to:
[0132] Determine the operation and maintenance demand value of the target user based on the operation and maintenance object, the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user, and the weight of each dissatisfaction reason corresponding to each customer perception indicator under each type of service demand;
[0133] Selecting at least one maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons as a candidate maintenance strategy to obtain a set of candidate maintenance strategies;
[0134] Based on the operation and maintenance contribution values of each selected candidate maintenance strategy to each type of service demand, determining a total operation and maintenance contribution value corresponding to the candidate maintenance strategy set;
[0135] If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to a preset threshold, the selected candidate maintenance strategy set is determined as the matching maintenance strategy.
[0136] Optionally, the second determining module 430 is further specifically configured to:
[0137] If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is greater than the preset threshold, the steps of selecting at least one maintenance strategy as a candidate maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons to determining the total operation and maintenance contribution value corresponding to the candidate maintenance strategy set are repeated until the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to the preset threshold.
[0138] Alternatively, if Figure 5 As shown, the device 400 also includes:
[0139] The updating module 450 is used to update the weight of each dissatisfaction reason corresponding to each customer perception indicator under each service demand based on the operation and maintenance processing result and the operation and maintenance contribution value of each service demand corresponding to the matched maintenance strategy.
[0140] Alternatively, if Figure 5 As shown, the apparatus 400 further includes a training module 460. The training module 460 is used to:
[0141] Obtain customer complaint sample data and corresponding labels for the operation and maintenance object;
[0142] The index values of multiple customer perception indicators of the operation and maintenance object by the complaining user are used as training samples, and the reasons for the dissatisfaction of the complaining user with the operation and maintenance object and the customer perception indicators corresponding to the reasons for the dissatisfaction are used as labels. Training is performed based on a decision tree algorithm to obtain the decision tree model.
[0143] Optionally, the training module 460 is specifically used for:
[0144] Obtain historical complaint texts against the operation and maintenance object;
[0145] Extracting keywords from the historical complaint text;
[0146] Based on the keywords in the historical complaint text and the dissatisfaction reason type library, determine the dissatisfaction reasons of the complaining users in the historical complaint text with the operation and maintenance object and the customer perception indicators corresponding to the dissatisfaction reasons, wherein the dissatisfaction reason type library includes keywords corresponding to various dissatisfaction reasons under various customer perception indicators of the operation and maintenance object;
[0147] Based on the service usage data of the operation and maintenance object by the complaining user, the index values of multiple customer perception indicators of the operation and maintenance object by the complaint are determined.
[0148] Optionally, the training module 460 is further specifically configured to:
[0149] For each dissatisfaction reason corresponding to each customer perception indicator of the operation and maintenance object, determine the number of complaints for the dissatisfaction reason;
[0150] If the number of complaints for the dissatisfaction reason is less than the preset number, a questionnaire is generated based on the dissatisfaction reason and the survey result data of the questionnaire is obtained;
[0151] If the survey result data indicates that the number of users surveyed who have the reason for dissatisfaction accounts for more than a preset proportion, then obtaining the index values of multiple customer perception indexes of the operation and maintenance object of the surveyed users who have the reason for dissatisfaction;
[0152] The customer complaint sample data is updated based on the indicator values of the surveyed users on a plurality of customer perception indicators of the operation and maintenance object.
[0153] Optionally, the decision tree model includes any one of the following models: a random forest model, a naive Bayes model, a bagging model, or an adaptive enhanced AdaBoost model.
[0154] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0155] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0156] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0157] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an operation and maintenance processing device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:
[0158] Obtain the indicator values of multiple customer perception indicators of the target user for the operation and maintenance object;
[0159] Based on a pre-trained decision tree model and the index values of the multiple customer perception indicators, determining the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator, the decision tree model is trained based on the operation and maintenance object customer complaint sample data and corresponding labels, the operation and maintenance object customer complaint sample data includes the index values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the dissatisfaction reasons and the customer perception indicators corresponding to the dissatisfaction reasons;
[0160] Determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason;
[0161] Operation and maintenance processing is performed based on the matched maintenance strategy.
[0162] The above application Figure 1The method performed by the operation and maintenance processing device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0163] The electronic device may also perform Figure 1 The method is implemented, and the operation and maintenance processing device is implemented Figures 1 to 3 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0164] Of course, in addition to software implementation methods, the electronic device of the present application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0165] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to execute Figure 1 The method of the embodiment shown is specifically used to perform the following operations:
[0166] Obtain the indicator values of multiple customer perception indicators of the target user for the operation and maintenance object;
[0167] Based on a pre-trained decision tree model and the index values of the multiple customer perception indicators, determining the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator, the decision tree model is trained based on the operation and maintenance object customer complaint sample data and corresponding labels, the operation and maintenance object customer complaint sample data includes the index values under multiple different customer perception indicators of the operation and maintenance object, and the labels include the dissatisfaction reasons and the customer perception indicators corresponding to the dissatisfaction reasons;
[0168] Determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason;
[0169] Operation and maintenance processing is performed based on the matched maintenance strategy.
[0170] In short, the above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
[0171] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0172] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0173] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0174] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
Claims
1. An operation and maintenance processing method, characterized in that: include: Obtain the indicator values of multiple customer perception indicators of the target user for the operation and maintenance object; Based on a pre-trained decision tree model and the index values of the multiple customer perception indicators, determine the probability that the target user generates each dissatisfaction reason corresponding to each customer perception indicator, the decision tree model is trained based on customer complaint sample data of the operation and maintenance object and the corresponding labels, the customer complaint sample data of the operation and maintenance object includes the index values under multiple different customer perception indicators of the operation and maintenance object, the labels include the dissatisfaction reasons and the customer perception indicators corresponding to the dissatisfaction reasons, the labels are determined based on a dissatisfaction reason type library and keywords extracted from historical complaint texts for the operation and maintenance object, the dissatisfaction reason type library includes keywords corresponding to various dissatisfaction reasons under each customer perception indicator of the operation and maintenance object, and the index values under the multiple different customer perception indicators are determined based on the business usage data of the operation and maintenance object by the complaining users of the historical complaint texts; Determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason; Performing operation and maintenance processing based on the matched maintenance strategy; The determining of a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user includes: Determine the operation and maintenance demand value of the target user based on the operation and maintenance object, the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user, and the weight of each dissatisfaction reason corresponding to each customer perception indicator under each type of service demand; Selecting at least one maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons as a candidate maintenance strategy to obtain a set of candidate maintenance strategies; Based on the operation and maintenance contribution values of each selected candidate maintenance strategy to each type of service demand, determining a total operation and maintenance contribution value corresponding to the candidate maintenance strategy set; If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to a preset threshold, the selected candidate maintenance strategy set is determined as the matching maintenance strategy.
2. The method according to claim 1, characterized in that According to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, a matching maintenance strategy is determined, which also includes: If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is greater than the preset threshold, the steps of selecting at least one maintenance strategy as a candidate maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons to determining the total operation and maintenance contribution value corresponding to the candidate maintenance strategy set are repeated until the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to the preset threshold.
3. The method according to claim 1, characterized in that After performing operation and maintenance processing based on the matched maintenance strategy, the method further includes: Based on the operation and maintenance processing results and the matched maintenance strategies, the weights of each dissatisfaction reason corresponding to each customer perception indicator under each service demand are updated.
4. The method according to claim 1, characterized in that: Before determining the probability of the target user generating each dissatisfaction reason corresponding to each customer perception indicator based on the pre-trained decision tree model and the indicator values of the plurality of customer perception indicators, the method further includes: Obtain customer complaint sample data and corresponding labels for the operation and maintenance object; The index values of multiple customer perception indicators of the operation and maintenance object by the complaining users are used as training samples, and the reasons for the dissatisfaction of the complaining users with the operation and maintenance object and the customer perception indicators corresponding to the reasons for the dissatisfaction are used as labels. Training is performed based on a decision tree algorithm to obtain the decision tree model.
5. The method according to claim 1, characterized in that Obtaining customer complaint sample data and corresponding labels for the operation and maintenance object, further comprising: For each dissatisfaction reason corresponding to each customer perception indicator of the operation and maintenance object, determine the number of complaints for the dissatisfaction reason; If the number of complaints for the dissatisfaction reason is less than the preset number, a questionnaire is generated based on the dissatisfaction reason and the survey result data of the questionnaire is obtained; If the survey result data indicates that the number of users surveyed who have the reason for dissatisfaction accounts for more than a preset proportion, then obtaining the index values of multiple customer perception indexes of the operation and maintenance object of the surveyed users who have the reason for dissatisfaction; The customer complaint sample data is updated based on the indicator values of the surveyed users on a plurality of customer perception indicators of the operation and maintenance object.
6. The method according to any one of claims 1 to 5, characterized in that The decision tree model includes any of the following models: random forest model, naive Bayes model, bagging model, adaptive enhanced AdaBoost model.
7. An operation and maintenance processing device, characterized in that: include: The first acquisition module is used to obtain the index values of multiple customer perception indicators of the target user for the operation and maintenance object; A first determination module is used to determine the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user based on a pre-trained decision tree model and the indicator values of the multiple customer perception indicators, the decision tree model is trained based on customer complaint sample data of the operation and maintenance object and corresponding labels, the customer complaint sample data of the operation and maintenance object includes indicator values under multiple different customer perception indicators of the operation and maintenance object, the labels include dissatisfaction reasons and customer perception indicators corresponding to the dissatisfaction reasons, the labels are determined based on a dissatisfaction reason type library and keywords extracted from historical complaint texts for the operation and maintenance object, the dissatisfaction reason type library includes keywords corresponding to various dissatisfaction reasons under each customer perception indicator of the operation and maintenance object, and the indicator values under the multiple different customer perception indicators are determined based on the business usage data of the operation and maintenance object by the complaining user based on the historical complaint texts; A second determination module is used to determine a matching maintenance strategy according to the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the operation and maintenance object and the target user, wherein the maintenance strategy corresponds to the dissatisfaction reason; An operation and maintenance processing module, used for performing operation and maintenance processing based on the matched maintenance strategy; The second determining module is specifically used for: Determine the operation and maintenance demand value of the target user based on the operation and maintenance object, the probability of each dissatisfaction reason corresponding to each customer perception indicator generated by the target user, and the weight of each dissatisfaction reason corresponding to each customer perception indicator under each type of service demand; Selecting at least one maintenance strategy from the maintenance strategies corresponding to all the dissatisfaction reasons as a candidate maintenance strategy to obtain a set of candidate maintenance strategies; Based on the operation and maintenance contribution values of each selected candidate maintenance strategy to each type of service demand, determining a total operation and maintenance contribution value corresponding to the candidate maintenance strategy set; If the difference between the total operation and maintenance contribution value and the operation and maintenance demand value is less than or equal to a preset threshold, the selected candidate maintenance strategy set is determined as the matching maintenance strategy.
8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Fault diagnosis method and device
CN106209405A
Power operation and maintenance information knowledge graph construction method
CN108460136A
Construction method of power information operation and maintenance knowledge model
CN108874783A
Method and device for solving potential complaints, computer equipment and storage medium
CN109871597A
