Feedback information processing method, system and storage medium

Abstract

The embodiment of the present application provides a feedback information processing method, system and storage medium, the method comprising: obtaining user feedback information; classifying the user feedback information according to key field information of the user feedback information to obtain classification results; calculating the weight value of the classification results; and determining the response content of the user feedback information according to the weight value of the classification results and the content of the classification results. This can improve the problem that the existing processing flow is difficult to quickly respond to user feedback information.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a feedback information processing method, system and storage medium. Background Art

[0002] An existing user feedback information processing process is: users feedback the problem to the intermediate roles such as operations, sales, and counseling personnel, and the corresponding staff manually enters the user feedback into the work order system. After the work order system creates a work order based on the user feedback content, it notifies the current on-duty personnel (such as customer service). The on-duty personnel understand, reproduce, and troubleshoot the problem reported by the user, and after confirming that the problem is not caused by misoperation, determine the module to which the problem belongs and select the relevant technical team, communicate with the developers about the problem, and after conducting complex problem troubleshooting, communication, and discussion, assign the processing task to the corresponding staff.

[0003] This processing flow requires a lot of human participation. Different users may describe the problem differently when initiating a work order, and different on-duty personnel may have different understandings of the problem described in the work order. When there is a large amount of human participation, it will be difficult to respond quickly to user feedback. Summary of the invention

[0004] The purpose of the present application is to provide a feedback information processing method, system and storage medium, which can improve the problem that the existing processing flow is difficult to respond quickly to user feedback information.

[0005] In a first aspect, the present application provides a feedback information processing method, the method comprising:

[0006] Obtain user feedback information;

[0007] Classifying the user feedback information according to key field information of the user feedback information to obtain a classification result;

[0008] Calculating a weight value of the classification result;

[0009] The response content of the user feedback information is determined according to the weight value of the classification result and the content of the classification result.

[0010] In the above method, user feedback information can be quickly classified, and the response content of the user feedback information can be quickly determined based on the weight calculation results and classification results after classification. The whole method can reduce the human participation links, avoid the impact of processing efficiency due to differences in problem description, problem understanding, etc. among different processors, and is conducive to timely and rapid response to user feedback information.

[0011] In an optional implementation manner, the classification result includes a first classification result, and the classification of the user feedback information according to the key field information of the user feedback information to obtain the classification result includes:

[0012] Inputting the key field information into a trained big data analysis model for problem comparison to obtain the first classification result corresponding to the key field information;

[0013] Wherein, the key field information includes at least one classification item.

[0014] Through the above implementation method, user feedback information can be classified based on the trained big data analysis model, which can achieve faster and more accurate classification. The key field information can be matched to the first classification result with finer division granularity based on the previously accumulated data content, which is conducive to reducing invalid communication time. When tasks are distributed based on the first classification result obtained in this way, it will be helpful to reduce the error rate of task distribution.

[0015] In an optional implementation manner, before classifying the user feedback information according to the key field information of the user feedback information to obtain the classification result, the method further includes:

[0016] Perform keyword tagging on the user feedback information to obtain a tagging result;

[0017] Extracting key business content from the annotation results to obtain keyword extraction results;

[0018] Classification is performed according to the keyword extraction result to obtain a second classification result, wherein the second classification result includes at least one classification item.

[0019] The above implementation method is conducive to realizing two-level classification of user feedback information. By labeling user feedback information with keywords, extracting and classifying it, the understanding of different business problems by different processors can be unified. When key business information in user feedback information is extracted and integrated to obtain keyword extraction results and second classification results, it is conducive to reducing communication costs and improving problem-solving efficiency.

[0020] In an optional implementation manner, the calculating the weight value of the classification result includes:

[0021] Obtain sub-weight values ​​corresponding to each question field in the classification result;

[0022] The sub-weight values ​​corresponding to the various question fields are added together to obtain a total question weight value, which serves as the weight value of the classification result.

[0023] Through the above implementation, the user feedback information is processed based on the weight analysis calculation. The size of the weight value is conducive to objectively judging the user feedback information and can provide data reference for the task distribution process.

[0024] In an optional implementation, after calculating the weight value of the classification result, the method further includes:

[0025] When the weight value of the classification result is greater than a set threshold, determining a target service account corresponding to the classification result according to a business mapping relationship pre-set for the classification result;

[0026] Generate a target work order carrying the user feedback information;

[0027] A to-do reminder is sent to the target service account according to the target work order, so that the target service account can provide a solution for the user feedback information according to the to-do reminder.

[0028] Through the above implementation method, when the weight value of the classification result is high, the target service account is determined based on the user feedback information with a higher weight value according to the business mapping relationship, so that a more matching processing personnel can be found, which is conducive to the rapid implementation of task distribution.

[0029] In an optional embodiment, the method further comprises:

[0030] When the weight value of the classification result is greater than the set threshold, obtaining the operation log associated with the user feedback information within a specified period;

[0031] After determining the target service account corresponding to the classification result, the method further includes:

[0032] The operation log and the user feedback information are sent to the target service account, so that the target service account can provide a solution for the user feedback information according to the operation log and the user feedback information.

[0033] Through the above implementation method, in addition to collecting user feedback information, business-related data can be combined to obtain the user's operation log. Compared with the method of providing solutions to user feedback information based only on the content of user feedback information, it is conducive to better analyzing user behavior, analyzing the correctness of user feedback information, and providing data reference for the problem troubleshooting process.

[0034] In an optional embodiment, the method further comprises:

[0035] Receive a solution or a processed prompt message sent by the target service account according to the user feedback information;

[0036] The solution or the processed prompt message is sent to the initiator of the user feedback information as the response content of the user feedback information.

[0037] Through the above implementation, the solution or processing result provided by the processing personnel for the user feedback information with a higher weight value can be fed back to the initiator of the user feedback information in a timely manner.

[0038] In an optional implementation manner, determining the response content of the user feedback information according to the weight value of the classification result and the content of the classification result includes:

[0039] When the weight value of the classification result is less than a set threshold, acquiring a solution associated with the classification result from a database according to the content of the classification result;

[0040] The solution and the designated link provided for the user feedback information are used as response content of the user feedback information.

[0041] Through the above implementation, when the weight value of the classification result is low, a general solution can be quickly obtained from the database without manual intervention, and a manual intervention entrance can be provided to the user by providing a designated link for the user's feedback information. In this way, when the general solution does not work or the user still does not know how to solve the problem after obtaining the general solution, a quick process can be performed based on the designated link.

[0042] In an optional implementation manner, determining the response content of the user feedback information according to the weight value of the classification result and the content of the classification result further includes:

[0043] When the weight value of the classification result is greater than the set threshold, a prompt message in a preset format is obtained from the database as a partial response content of the user feedback information.

[0044] Through the above implementation, when a solution cannot be provided to the user yet, a prompt message in a preset format can be used as a response content for feedback, which helps to avoid the user from continuously waiting or repeatedly submitting the same user feedback information.

[0045] In a second aspect, the present application provides a feedback information processing system, comprising:

[0046] Memory;

[0047] processor;

[0048] The memory stores a computer program executable by the processor, and when the computer program is executed by the processor, the method described in the first aspect is performed.

[0049] In a third aspect, the present application provides a storage medium storing a computer program executable by a processor, wherein the computer program, when executed by the processor, performs the method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A flowchart of a feedback information processing method provided in an embodiment of the present application.

[0052] Figure 2 A partial flow chart of a feedback information processing method provided in an embodiment of the present application.

[0053] Figure 3 Another partial flow chart of a feedback information processing method provided in an embodiment of the present application.

[0054] Figure 4 A partial flow chart of another feedback information processing method provided in an embodiment of the present application.

[0055] Figure 5 Another partial flow chart of another feedback information processing method provided in an embodiment of the present application.

[0056] Figure 6 A flowchart of another part of another feedback information processing method provided in an embodiment of the present application.

[0057] Figure 7 A device structure block diagram of a feedback information processing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0059] Given that different users may have different descriptions of the same problem when initiating a work order, and different intermediate processing personnel and different on-duty personnel may have different understandings of the work order description, the existing processing method may not be able to quickly and effectively classify the work order content. On-duty personnel may find it difficult to accurately, timely, and effectively distribute the work orders they receive, which will waste time because it is difficult to quickly find the right person to handle the problem, thus affecting the efficiency of problem solving.

[0060] If tasks are distributed only through a simple work order system, the simple work order system has weak processing capabilities and is unable to identify and classify complex user feedback information. Users usually choose the processing personnel to solve the problem when submitting a work order. The user may not be able to select the right processing personnel because he or she does not understand the business problem or the division of functional tasks. Therefore, the processing efficiency is still low.

[0061] If users fail to find the right person to resolve their issues, they may continue to wait or submit tickets repeatedly.

[0062] In view of the fact that the existing schemes are difficult to provide quick feedback to user feedback information in a timely manner due to the complexity and diversity of user feedback information and the many human-involved links, the inventor proposes the following embodiments to improve it. In the method provided in the embodiment of the present application, the user feedback information submitted by the user is regarded as a problem to be processed, and classification and weight calculation are performed for the problem to be processed, so as to quickly determine the response content for the user feedback information, so as to quickly respond to the user feedback information. When it is determined based on the weight value that it is necessary to assist the user in solving the problem by manual intervention for the user feedback information, the method of the embodiment of the present application can quickly distribute tasks for the user feedback information, so as to quickly treat the problem to be processed as a task and send it to the corresponding processing personnel for processing. When issuing tasks, the method of the embodiment of the present application can send the collected operation logs to the processing personnel together, so that the processing personnel can know the user behavior and evaluate the correctness of the user feedback information.

[0063] See also Figure 1 , Figure 1 This is a flow chart of a feedback information processing method provided in an embodiment of the present application, which can be applied to a feedback information processing system provided in an embodiment of the present application. The feedback information processing system can be a server or a server cluster.

[0064] like Figure 1 As shown, the method includes: steps S11-S17. Among them, the steps S11-S17 can be regarded as the content before task distribution, and the content of S11-S17 is conducive to rapid response.

[0065] S11: Obtain user feedback information.

[0066] The user feedback information may be the content submitted by the user to the work order system through the designated feedback channel. The designated feedback channel may be a problem feedback portal of a software application (APP), a website, or a mini-program plug-in. The user feedback information may be, but is not limited to: the results obtained through a questionnaire survey, the content filled in by the user in the work order template, the question selected by the user from multiple alternative questions, etc.

[0067] S13: Classify the user feedback information according to key field information of the user feedback information to obtain a classification result.

[0068] The key field information about the user feedback information may be content obtained by pre-processing the user feedback information through means such as automatic text information annotation and key content extraction, or may be content obtained through a preset classification template.

[0069] The classification in the embodiment of the present application may include primary classification and secondary classification. Based on the result of the primary classification, secondary classification may be performed. The classification result in S13 refers to the result of the secondary classification.

[0070] Exemplarily, for user feedback information collected through non-specific templates, key field information of the user feedback information can be obtained through automated text information annotation and key content extraction, and based on this, the user feedback information is classified into a primary category to obtain a second classification result (that is, the result of the primary classification is called the second classification result, and the result obtained after secondary classification based on the second classification result can be called the first classification result).

[0071] The process of preprocessing the user feedback information may include steps S121-S123 (such as Figure 2 shown).

[0072] S121: Perform keyword tagging on the user feedback information to obtain a tagging result.

[0073] In an embodiment of the present application, after obtaining user feedback information (for example, after obtaining user feedback information in a work order system), a text annotation tool can be used to annotate the specific information of the user feedback information to obtain an annotation result. The annotation process can be regarded as adding attributes to some fields in the user feedback information and determining the relationship between the fields. Exemplarily, the text annotation tool can be a BRAT text annotation tool.

[0074] S122: Extract key business content from the annotation results to obtain keyword extraction results.

[0075] After the annotation is completed, the annotated text information can be segmented and extracted by a dependency syntax analysis tool to extract the key business content related to the problem and obtain keyword extraction results. Exemplarily, the dependency syntax analysis tool can be a DDparser dependency syntax analysis tool.

[0076] S123: Classify according to the keyword extraction result to obtain a second classification result, wherein the second classification result includes at least one classification item.

[0077] The extracted keyword extraction results may be integrated and classified to obtain a second classification result including one or more classification items. The second classification result is a general term for one or more classification items of different categories.

[0078] The implementation method of S121-S123 is conducive to the two-level classification of user feedback information. When the user feedback information is keyword-tagged, word-segmented and classified through BRAT and DDparser, the understanding of different business issues by different processors (such as question and answer duty personnel, product business planners, R&D personnel, etc.) can be unified. When the key business information in the user feedback information is extracted and integrated to obtain the keyword extraction results and the second classification results, it is conducive to reducing communication costs and improving problem-solving efficiency.

[0079] As for user feedback information obtained by using a preset specific template, when preset classification items such as classification fields and classification identifiers are set in the template, the content selected or filled in by the user at a specific position in the template can be identified, the user feedback information can be analyzed, or the type of the template itself can be identified, thereby performing a primary classification on the user feedback information and obtaining a second classification result.

[0080] In the embodiment of the present application, the input parameter of the secondary classification is the key field information of the user feedback information, which may include at least one classification item. Each classification item can be regarded as a classification result with a relatively general classification level. The classification output result of the secondary classification is recorded as the first classification result, which is regarded as a classification result with a relatively detailed classification level.

[0081] In order to obtain a classification result with a finer granularity and to classify the user feedback information more appropriately, the above process of S13 may include: S131.

[0082] S131: Input the key field information into the trained big data analysis model for problem comparison to obtain a first classification result corresponding to the key field information.

[0083] The key field information includes at least one classification item. For example, the key field information may be the annotation result obtained in the above S121-S123, the keyword extraction result, or the second classification result obtained after the first-level classification.

[0084] Among them, the big data analysis model can provide data reference for the secondary classification, which is used to realize the classification and aggregation functions. The big data analysis model is a model that has been trained with a large number of samples and continuously optimized, referred to as a model. In an embodiment of the present application, the key field information of the current user feedback information can be compared with the historical sedimentation data of the model, so as to match all classification items in the current key field information with a more appropriate first classification result in combination with the business and products. The embodiment of the present application does not limit the specific big data analysis model.

[0085] Through the implementation of S131 above, user feedback information can be classified based on a trained big data analysis model, which can achieve faster and more accurate classification. Key field information can be matched to a first classification result with a finer granularity based on previously accumulated data content, which is conducive to reducing ineffective communication time. When tasks are distributed based on the first classification result obtained in this way, it will be helpful to reduce the error rate of task distribution. By collecting feedback problems for big data model training and continuous model learning, problem identification and problem classification can be performed faster and more accurately while precipitating and collecting problems, improving product experience, and strengthening business depth.

[0086] S15: Calculate the weight value of the classification result.

[0087] As an implementation of the above S15, the S15 may include sub-steps S151-S152.

[0088] S151: Obtain the sub-weight values ​​corresponding to each question field in the classification result.

[0089] Among them, the number of question fields in the classification result is related to the actual classification situation. The sub-weight values ​​corresponding to different question fields may vary according to the actual business scenario. For example, the weights of question fields involving orders, payments, APP usage, course materials, course videos, course courseware, etc. may be different. In an embodiment of the present application, the sub-weight value of each question field can be regarded as a preset value.

[0090] In addition, for feedback information on complaints and improvements, a higher weight value can be set to highlight user problems and thus improve processing efficiency.

[0091] S152: Add up the sub-weight values ​​corresponding to each question field to obtain a total question weight value as the weight value of the classification result.

[0092] The “classification result” in S15, S151, and S152 may be the first classification result obtained by S131, that is, weight calculation is performed on the first classification result.

[0093] To facilitate understanding, the methods of S11-S15 will be introduced using two examples. In both examples, user feedback information is preprocessed by means of automatic text information annotation and key content extraction, and primary and secondary classifications are performed based on this. The weight is calculated based on the results of the secondary classification to obtain the total weight value of the question.

[0094] The user feedback information obtained in the two examples are respectively recorded as Q1 and Q2. The processing process based on the user feedback information Q1 can refer to Example 1 shown in Table 1, and the processing process based on the user feedback information Q2 can refer to Example 2 shown in Table 2.

[0095] Table 1 - Example 1

[0096]

[0097]

[0098] In Example 1 shown in Table 1, after keyword annotation of the user feedback information Q1, the annotated contents are "3pm", "Android phone", "C1 APP", "Course", "Order", "Payment", "C2 Payment Tool" and "No Response", as the annotation results of the user feedback information Q1. After the annotation is completed, the integrated keyword extraction results include the fields "Android", "C1 APP", "C2 Payment Tool" and "Payment". After the first-level classification based on the annotation results and the keyword extraction results, the second classification results obtained include the four problems of "Android APP problem", "Order problem", "Payment problem" and "C2 Payment Tool problem". After the second-level classification of the user feedback information Q1, the user feedback information Q1 is classified as "APP order payment problem" to obtain the first classification result. After weight calculation based on the first classification result, the sub-weight values ​​corresponding to the three problem fields in the first classification result are summed to obtain the total problem weight value of the first classification result, that is, the weight value of the classification result in S15.

[0099] It should be noted that users do not have to write information such as "Android phone", "C1 APP", and "C2 payment tool" when giving feedback, and the server will automatically obtain it (with user authorization). Of course, any other information that can be obtained can also be automatically obtained, such as time, location, terminal model, etc., which will not be elaborated on.

[0100] Table 2 - Example 2

[0101]

[0102]

[0103] In Example 2 shown in Table 2, after keyword annotation of the user feedback information Q2, the annotated contents are "iOS", "live broadcast", "video", "stuck", "re-enter" and "can", as the annotation results of the user feedback information Q2. After the annotation, the integrated and extracted keyword extraction results include the fields "iOS", "live broadcast", "video" and "stuck". After the first-level classification based on the annotation results and the keyword extraction results, the second classification results obtained include the two problems of "iOSAPP problem" and "video live broadcast freeze problem". After the second-level classification of the user feedback information Q2, the user feedback information Q2 is classified as "iOSAPP video live broadcast freeze problem feedback" to obtain the first classification result. After weight calculation based on this first classification result, the sub-weight values ​​corresponding to the two problem fields in the first classification result are summed to obtain the total problem weight value of the first classification result, that is, the weight value of the classification result in S15 is obtained.

[0104] Among them, based on the weight analysis calculation of S151-S152, the user feedback information is processed and the total weight value of the problem is obtained. The size of the weight value is conducive to objectively judging the user feedback information, and can provide data reference for the task distribution process. The calculation results based on the weight analysis are conducive to providing faster and more effective solutions, especially in the face of some key business or customer actions (such as placing orders, paying, attending classes, etc.). The method of the embodiment of the present application can solve user problems faster and provide users with efficient services, which is conducive to reducing user churn and improving user experience in a fast feedback manner.

[0105] After the weight value of the classification result is obtained through S15, S17 may be executed to determine the response content of the user feedback information, so as to quickly respond to the user feedback information.

[0106] S17: Determine the response content of the user feedback information according to the weight value of the classification result and the content of the classification result.

[0107] When the response content of the user feedback information is determined, the response content is sent to the initiator of the user feedback information.

[0108] In the embodiment of the present application, different response contents can be obtained from the database according to the difference in weight values. In the case of a large weight value, it is considered that manual intervention is required to assist in solving the problem. In the case of a small weight value, it is considered that no manual intervention is required temporarily and the general solution stored in the database can be used temporarily. In order to quickly respond to user feedback information in different situations, such as Figure 3As shown, S17 may include: S171-S173. When the weight value of the classification result is less than the set threshold, S171-S172 are executed, and when the weight value of the classification result is greater than or equal to the set threshold, S173 is executed.

[0109] S171: When the weight value of the classification result is less than a set threshold, a solution associated with the classification result is obtained from a database according to the content of the classification result.

[0110] Among them, when the weight value of the classification result is less than the set threshold, a specified number of solutions (for example, 3 or 5 problems whose characteristics are closest to the first classification result) can be obtained from the database according to the content of the classification result. The solution obtained by S171 can be a general solution obtained from the result database. The result database pre-stores general solutions to various common problems and general problems, and after each problem is solved, the latest solution can be entered into the result database to realize self-learning of the result database.

[0111] In order to avoid the situation where the solutions obtained from the database still cannot provide effective help to the user (for example, the general solution does not work), or the user still does not know how to solve the problem after obtaining the general solution, a designated link can be provided to the user who initiated the user feedback information as a manual solution entry.

[0112] S172: The solution obtained from the database and the designated link provided for the user feedback information are used as the response content of the user feedback information.

[0113] The solution obtained from the database and the designated link provided for the user feedback information may be sent to the initiator of the user feedback information.

[0114] S173: When the weight value of the classification result is greater than a set threshold, a prompt message in a preset format is obtained from the database as a partial response content of the user feedback information.

[0115] In actual application scenarios, user feedback information related to key businesses such as orders, payments, registration, and classes may have a higher corresponding weight value. When faced with these high-weight problems, backend processing personnel may be required to assist in solving them. Before the backend processing personnel have given a solution or the pending problem has not been completely resolved, a prompt message in a preset format can be obtained from the database, and the prompt message in the preset format can be sent to the initiator of the user feedback information for temporary quick feedback.

[0116] Exemplarily, the prompt message in the preset format may be, but is not limited to, "Please wait", "D from department 5 has been contacted, please wait", "Please check after 15 minutes to see if the problem is solved", etc.

[0117] For example, if the preset threshold is 5, for example 1 shown in Table 1, the total weight value of question Q1 is 11, which has exceeded the threshold, so a response can be made based on the implementation of S173. For example 2 shown in Table 2, the total weight value of question Q2 is 3, which has not exceeded the threshold, so a response can be made based on the implementation of S171-S172.

[0118] Through the implementation of S171-S173 above, when the weight value of the classification result is low, a general solution can be quickly obtained from the database without manual intervention, and a manual intervention entrance can be provided to the user by providing a designated link for the user feedback information. In this way, when the solution in the database does not work, it can be quickly processed based on the designated link. In the case where the weight value of the classification result is greater than the set threshold and a solution cannot be provided to the user, a prompt message in a preset format is first fed back as the response content, which helps to avoid the user from continuously waiting or repeatedly submitting the same user feedback information.

[0119] Through the above-mentioned methods S11-S17, user feedback information can be quickly classified, and the response content of the user feedback information can be quickly determined based on the weight calculation results and classification results after classification. The whole method can reduce the human participation links, avoid the impact of processing efficiency due to differences in problem description, problem understanding, etc. among different processors, and is conducive to timely and rapid response to user feedback information.

[0120] In the embodiment of the present application, after calculating the weight value of the classification result through S15, the above method may further include a task distribution process. The steps of the task distribution process may include S21-S23 (such as Figure 4 shown).

[0121] S21: When the weight value of the classification result is greater than a set threshold, a target service account corresponding to the classification result is determined according to a business mapping relationship pre-set for the classification result.

[0122] If the feedback information processing system includes a distribution server, the distribution server can be called to determine the target service account. The distribution server can maintain the mapping relationship between the key field content and the business function on the service side, and the distribution server can maintain the mapping relationship between the business function and the business processing personnel of each module.

[0123] In an embodiment of the present application, the business mapping relationship set for the classification result can be determined by the distribution server. The distribution server can find the target service account matching the first classification result based on the first classification result determined above and the business mapping relationship pre-set for the first classification result, so as to distribute the task and send the corresponding user feedback information as a task to be processed to the target service account.

[0124] Among them, by maintaining the business mapping files between the service-side business and the business processing personnel, the division of labor and responsibilities of personnel in different business modules and different business sub-modules will be clearer and more detailed, and the mapping selection will be performed in an automated manner, avoiding many problems related to the different levels of familiarity of different users, intermediate processors, and on-duty personnel with the business team. This can significantly reduce invalid communication links, make the problem-solving process more timely and accurate, and reduce the waste of resources of product R&D personnel.

[0125] In order to facilitate task recording and task distribution, when the weight value of the classification result is greater than a set threshold, S22 may be further executed.

[0126] S22: Generate a target work order carrying user feedback information.

[0127] The content of the target work order may include but is not limited to: the specific content of the user feedback information, the time of submitting the user feedback information (recorded as the feedback time), the target service account, the identity of the initiator of the user feedback information, the work order number, the second classification result, the first classification result, the total weight value of the problem, etc.

[0128] S23: Send a to-do reminder to the target service account according to the target work order, so that the target service account can provide a solution for the user feedback information according to the to-do reminder.

[0129] Among them, the target work order and the to-do reminder generated according to the target work order can be sent to the target service account.

[0130] The content of the to-do reminder may include, but is not limited to: a summary of the target work order, a link generated based on the target work order, a QR code, etc.

[0131] Optionally, when user feedback information is obtained and the total weight value of the problem is determined to exceed a set threshold, the target service account can be determined through the distribution server, and the processing task can be issued to the processing personnel corresponding to the target service account in a specified task distribution method. The notification implementation form of the specified task distribution method can be, but is not limited to: email notification method, notification method provided by the online business system, notification method of instant messaging tools (such as WeChat notification, DingTalk notification, etc.), SMS notification method, and any other notification method set, of course, it can also be a combination of notification methods.

[0132] Through the implementation of S21-S23 above, when the weight value of the classification result is high, the target service account is determined based on the user feedback information with a higher weight value according to the business mapping relationship, so that more matching processing personnel can be found, which is conducive to the rapid implementation of task distribution. In the form of automatic distribution of tasks and recording, for example, using an automated email system to record files in the processing process (such as operation logs, target work orders or other intermediate processing flow information), and completing data reception and forwarding, task distribution and result feedback can be quickly implemented, which is conducive to providing users with more efficient services. The method of determining the target service account based on the above first classification result and then distributing tasks can achieve more accurate automatic task distribution.

[0133] Optionally, the steps of the task distribution process may also include S24 and S25 (such as Figure 5 shown).

[0134] S24: When the weight value of the classification result is greater than a set threshold, the operation log associated with the user feedback information within a specified period is obtained.

[0135] Exemplarily, for ease of understanding, taking the total weight value of the question corresponding to Q1 in the aforementioned Example 1 as 11 as an example, if the set threshold is 5, it is determined that the total weight value of the question of the first classification result is greater than the set threshold, and the operation log within the specified time period can be obtained based on the identity of the initiator of the user feedback information and the feedback time, with the two hours before the feedback time as the starting point of the specified time period and the two hours after the feedback time as the end point of the specified time period (if the interval from the feedback time to the current time is less than two hours, the current time is directly used as the end point of the specified time period). It can be understood that the length of the specified time period can be set arbitrarily and can be not limited to two hours.

[0136] The operation log can be obtained through the distribution server, or the distribution server can call the business server to obtain the operation log, so that the distribution server obtains the operation log provided by the business server. Both the distribution server and the business server can be regarded as part of the feedback information processing system.

[0137] After determining the target service account corresponding to the classification result, based on S24, the task distribution process may include S25.

[0138] S25: Send the operation log and the user feedback information to the target service account, so that the target service account can provide a solution for the user feedback information according to the operation log and the user feedback information.

[0139] Among them, the target work order carrying the user feedback information and the collected operation logs can be sent to the target service account through the distribution server, so that the processing personnel corresponding to the target service account can provide a solution to the initiator of the user feedback information in time.

[0140] Through the implementation method of S24 and S25 above, in addition to collecting user feedback information, the user's operation log and business data can be obtained in combination with business-related data services. Compared with the method of providing solutions for user feedback information based only on user feedback information, this is conducive to better analyzing user behavior, analyzing the correctness of user feedback information, and providing data reference for the problem troubleshooting process.

[0141] Optionally, after determining the target service account, for example, after S23 or S25, the method may further include S26-S27 (eg Figure 6 shown).

[0142] S26: Receive a solution or processed prompt message sent by the target service account according to the user feedback information.

[0143] S27: Sending the solution or the processed prompt message as the response content of the user feedback information to the initiator of the user feedback information.

[0144] The specific method of receiving and sending the solution or processed prompt message provided by the target service account is related to the actual implementation form of the task distribution method. For example, the solution or processed prompt message of the target service account can be checked and forwarded through the email system, and this application does not limit this.

[0145] Normally, through the aforementioned S17 (including S171-S173), a general solution can be quickly fed back for simpler problems, and a prompt message without a specific solution can be quickly fed back for more complex problems. Through S27, after a part of the response content has been fed back for user feedback information with a higher weight value (for example, the prompt message in the aforementioned preset format without a specific solution), the solution or processed prompt message sent by the target service account based on the user feedback information can be sent as another part of the response content of the user feedback information to the initiator of the user feedback information.

[0146] Through the implementation of S26-S27 above, the solution or processing result provided by the processing personnel for the user feedback information with a higher weight value can be fed back to the initiator of the user feedback information in a timely manner.

[0147] Optionally, the server cluster corresponding to the above feedback information processing system may include: a response processing server, a distribution server, and a business server. The response processing server, the distribution server, and the business server may directly or indirectly interact with each other.

[0148] The response processing server can be used to execute the content related to data analysis, processing, classification, and calculation in the aforementioned method, the distribution server can be used to execute the content related to the task distribution process and data forwarding in the aforementioned method, and the business server can be used to obtain operation logs. Of course, there can be more servers or more division methods in the feedback information processing system.

[0149] In some possible implementations, when the key field information carried in the received user feedback information is too little to obtain an accurate classification result, the corresponding user may be prompted to complete and supplement the user feedback information. Of course, the blank boxes or options of the key descriptions may also be set as mandatory, so that users can get better guidance when giving feedback, which will not be elaborated.

[0150] In other possible implementations, after obtaining user feedback information and acquiring key field information, the key field information can also be fed back to the user so that the user can improve and supplement the user feedback information by selection, addition, deletion, modification, etc., thereby improving the accuracy of the response result.

[0151] In another possible implementation, when submitting user feedback information, the user may also select a corresponding label from the template library, such as payment issue, service issue, emergency, etc., which will not be elaborated herein.

[0152] Based on the same inventive concept, an embodiment of the present application provides a feedback information processing system.

[0153] The feedback information processing system has computing processing capability and network communication capability, and is used to implement the aforementioned feedback information processing method.

[0154] like Figure 7 As shown, the feedback information processing system includes: a memory 301, a processor 302, and a communication component 303, etc. The feedback information processing system can be any server in a server cluster.

[0155] The memory 301 can be used to store computer programs and functional modules, for example, it can be used to store program instructions or functional modules corresponding to the feedback information processing method in the embodiment of the present application. The processor 302 implements part or all of the content of the feedback information processing method provided in the embodiment of the present application by running the computer program stored in the memory 301.

[0156] The memory 301 is a storage medium, which may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The processor 302 and other possible components may access the memory 301 under the control of a storage controller.

[0157] The processor 302 has a computing and processing capability, and may be an integrated circuit chip, a general-purpose processor, including a central processing unit (CPU), a microcontroller unit (MCU), a network processor (NP) or other conventional processors, or a dedicated processor, including 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, and a processor constructed of discrete hardware components. The processor 302 may implement or execute the methods and steps disclosed in the embodiments of the present application.

[0158] The communication component 303 includes a communication bus, which is used to realize direct or indirect connection between various entity components in the feedback information processing system.

[0159] Understandably, Figure 7 The structure shown is for illustration only. The feedback information processing system may also include Figure 7 The structures shown may have more or fewer components, or may have the same Figure 7Different configurations.

[0160] Based on the same inventive concept, an embodiment of the present application further provides a storage medium, on which a computer program executable by a processor is stored. When the computer program is executed by the processor, part or all of the content in the aforementioned feedback information processing method is executed.

[0161] In summary, through the technical solution provided by the embodiment of the present application, user feedback information can be regarded as a problem to be processed, and the processes such as user feedback, problem classification, problem analysis, problem precipitation, division of the business team to which the problem belongs, problem solving, and result feedback can be automated. The number of task participants and task distribution personnel can be reduced during the entire processing process, thereby releasing human resources and improving problem solving efficiency. When classifying different user feedback information, the business division of the problem will be more objective and accurate, and the division granularity will be more detailed, which can reduce invalid communication time and reduce the error rate of task distribution. From the beginning of collecting user feedback information to providing users with response content, the processing efficiency can be improved, and the user feedback information can be better precipitated and analyzed by using a big data analysis model to help with classification, which can better provide a basis for the problem solving process and product iteration process.

[0162] In the embodiments provided in this application, it should be understood that the disclosed embodiments can be implemented in other ways. The embodiments described above are only exemplary. For example, the division of modules and servers is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components and servers can be combined or integrated into another system.

[0163] In addition, the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the contents may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] It should be noted that if the corresponding functions of the above methods are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device to execute all or part of the steps of the methods of each embodiment of the present application.

[0165] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0166] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of protection of the present application.

Claims

1. A feedback information processing method, characterized in that: The method comprises: Obtain user feedback information; According to the key field information of the user feedback information, the user feedback information is classified to obtain a classification result; wherein the classification includes a primary classification and a secondary classification, and the secondary classification is performed based on the result of the primary classification, and the classification result includes the result of the secondary classification; the secondary classification result is obtained by integrating and classifying the extraction results of the extracted key field information; the secondary classification result includes one or more classification items, and the second classification result is a general term for one or more classification items of different categories; the result of the primary classification is called the second classification result, and the result obtained after the secondary classification is performed based on the second classification result is the first classification result; the first classification result is a classification result with a relatively detailed division layer; Calculating a weight value of the classification result; Determining the response content of the user feedback information according to the weight value of the classification result and the content of the classification result; The step of calculating the weight value of the classification result includes: Obtain the sub-weight values ​​corresponding to each problem field in the classification result; add the sub-weight values ​​corresponding to each problem field to obtain the total problem weight value as the weight value of the classification result; wherein the complaint feedback information and improvement feedback information in the classification result are set with a higher weight value; The determining, according to the weight value of the classification result and the content of the classification result, the response content of the user feedback information includes: When the weight value of the classification result is less than a set threshold, acquiring a solution associated with the classification result from a database according to the content of the classification result; using the solution and the designated link provided for the user feedback information as the response content of the user feedback information; or, When the weight value of the classification result is greater than a set threshold, determining a target service account corresponding to the classification result according to a business mapping relationship pre-set for the classification result; Generate a target work order carrying the user feedback information; Sending a to-do reminder to the target service account according to the target work order, so that the target service account can provide a solution for the user feedback information according to the to-do reminder; Receive a solution or a processed prompt message sent by the target service account according to the user feedback information; The solution or the processed prompt message is sent to the initiator of the user feedback information as the response content of the user feedback information.

2. The method according to claim 1, characterized in that The classification result includes a first classification result, wherein the user feedback information is classified according to the key field information of the user feedback information to obtain the classification result, including: Inputting the key field information into a trained big data analysis model for problem comparison to obtain the first classification result corresponding to the key field information; Wherein, the key field information includes at least one classification item; Before classifying the user feedback information according to the key field information of the user feedback information to obtain the classification result, the method further includes: Perform keyword tagging on the user feedback information to obtain a tagging result; Extracting key business content from the annotation results to obtain keyword extraction results; Classification is performed according to the keyword extraction result to obtain a second classification result, wherein the second classification result includes at least one classification item.

3. The method according to claim 1, characterized in that The method further comprises: When the weight value of the classification result is greater than the set threshold, obtaining the operation log associated with the user feedback information within a specified period; After determining the target service account corresponding to the classification result, the method further includes: The operation log and the user feedback information are sent to the target service account, so that the target service account can provide a solution for the user feedback information according to the operation log and the user feedback information.

4. The method according to claim 1, characterized in that: The step of determining the response content of the user feedback information according to the weight value of the classification result and the content of the classification result further includes: When the weight value of the classification result is greater than the set threshold, a prompt message in a preset format is obtained from the database as a partial response content of the user feedback information.

5. A feedback information processing system, characterized in that: include: Memory; processor; The memory stores a computer program executable by the processor, and when the computer program is executed by the processor, the method according to any one of claims 1 to 4 is performed.

6. A storage medium, characterized in that: The storage medium stores a computer program executable by a processor, and when the computer program is executed by the processor, the method according to any one of claims 1 to 4 is performed.

Images