Rectification task generation method and system responding to customer feedback, equipment and medium

Abstract

A method, system, device and medium for generating a rectification task in response to customer feedback, the method for generating the rectification task in response to customer feedback comprising: collecting feedback data sent by a customer, the feedback data at least comprising textualized data generated and formed in telephone recording, text, order comment and order complaint channels; performing sentiment analysis on the feedback data to obtain negative feedback data, and performing theme recognition on the negative feedback data to obtain a theme category; performing dimensionalization processing on the negative feedback data based on the negative feedback data and the corresponding theme category to obtain a rectification special dimension; and automatically generating a corresponding rectification task based on the rectification special dimension. According to the invention, the feedback sensitivity of the negative sound of the user is improved, and the housing experience of the user and the service quality of the hotel are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of customer management services, and in particular relates to a method, system, device and medium for generating rectification tasks in response to customer feedback. Background Art

[0002] The current hotel management system mainly relies on manual recording and analysis to process customer feedback information, which is inefficient and has limited accuracy. It is difficult to fully and accurately identify and process voices from different channels, especially negative voices or negative voices, which leads to customer dissatisfaction and the problem cannot be solved in a timely and effective manner, affecting the overall service quality and customer satisfaction. In addition, other voices of customer feedback, such as positive voices or positive voices, are not reflected in hotel management, which in turn reduces the enthusiasm of hotel service personnel and is not conducive to building their own service advantages and service characteristics in hotel management. Summary of the invention

[0003] In view of the shortcomings of the prior art described above, an object of the present invention is to provide a method, device and medium for generating rectification tasks in response to customer feedback, so as to at least solve one technical problem in the above-mentioned background technology.

[0004] To achieve the above purpose, the present invention adopts the following technical solution.

[0005] A first aspect of the present invention provides a method for generating a rectification task in response to customer feedback, comprising: Collect feedback data from customers, which at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; Performing sentiment analysis on the feedback data to obtain negative feedback data, and performing topic identification on the negative feedback data to obtain topic categories; Dimensional processing is performed on the negative feedback data based on the negative feedback data and the corresponding subject categories to obtain a rectification-specific dimension; The corresponding rectification tasks are automatically generated based on the special rectification dimension.

[0006] As an optional implementation, the feedback data sent by customers is collected, and the feedback data includes at least one or more of telephone recordings, texts, order reviews and order complaint channels, and is finally converted into text data, including: Obtain text and non-text data generated from phone recordings, texts, order reviews, and order complaint channels; The non-text data is processed into text, and the text data and the non-text data after the text processing are merged into feedback data.

[0007] As an optional implementation, the negative feedback data is dimensionally processed based on the negative feedback data and the corresponding subject categories to obtain a rectification-specific dimension, including: mapping the negative feedback data into at least one thematic category; In the topic category, extracting a preset number of semantic features from the negative feedback data, and mapping the semantic features to a preset number of preset levels; The rectification dimension corresponding to the preset level mapped by the semantic feature is indexed in the rectification dimension dictionary.

[0008] As an optional implementation, before indexing the rectification special dimension corresponding to the preset level mapped by the semantic feature in the rectification dimension dictionary, the following steps are included: Establishing a rectification dimension dictionary, the rectification dimension dictionary including subject categories, a preset number of preset levels corresponding to each subject category, and rectification special dimensions corresponding to a preset number of preset levels corresponding to each subject category; When mapping the negative feedback data into at least one thematic category, further comprising: Traverse the rectification dimension dictionary, and if the topic category to which the negative feedback data can be mapped cannot be indexed in the rectification dimension dictionary, set the first topic category; Extracting a preset number of semantic features from the negative feedback data, and setting a preset number of first-class custom levels; mapping the extracted semantic features to the corresponding preset number of first-class custom levels, and obtaining corresponding rectification special dimensions; The first topic category and the first custom level are updated to the rectification dimension dictionary.

[0009] As an optional implementation, after mapping the negative feedback data to at least one topic category, the method further includes: Extracting a preset number of semantic features from the negative feedback data; Traversing the rectification dimension dictionary, if the preset level that can map all semantic features to the preset number of corresponding subject categories cannot be indexed in the rectification dimension dictionary, then setting the second type of custom level for the semantic features that are not mapped to the preset level of the corresponding subject category, and obtaining the corresponding rectification special dimension; The preset levels of a part of the preset number that have been mapped to the corresponding subject categories are set as the third type of preset levels, and the subject categories, the second type of custom levels and the third type of preset levels are updated to rectify the dimension dictionary.

[0010] As an optional implementation, the subject categories include at least hygiene, service quality, price and facilities and equipment.

[0011] A second aspect of the present invention provides a method for generating rectification tasks in response to customer feedback, comprising: Collect feedback data from customers, which at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; Performing sentiment analysis on the feedback data to obtain feedback data, and performing topic identification on the feedback data to obtain topic categories; Dimensional processing is performed on the feedback data based on the feedback data and the corresponding subject category to obtain a response-specific dimension, wherein the response-specific dimension at least includes a rectification-specific dimension when the feedback data is negative feedback data; Based on the response-specific dimension, a corresponding response task is automatically generated, and the response task at least includes a rectification task when the feedback data is negative feedback data.

[0012] A third aspect of the present invention provides a rectification task generation system in response to customer feedback, comprising: A collection unit, at least used to collect feedback data from customers, wherein the feedback data at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; An analysis and identification unit, at least used to perform sentiment analysis on the feedback data to obtain negative feedback data, and perform topic identification on the negative feedback data to obtain a topic category; A dimensional processing unit performs dimensional processing on the negative feedback data based on the negative feedback data and the corresponding subject category to obtain a rectification special dimension; The execution unit is at least used to automatically generate corresponding rectification tasks based on the rectification special dimension.

[0013] The fourth aspect of the present invention provides an electronic device, comprising: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the steps of the method for generating rectification tasks in response to customer feedback as described in the first aspect of the present invention.

[0014] A fifth aspect of the present invention provides a readable storage medium storing a computer program, wherein a processor executes the steps of the method for generating rectification tasks in response to customer feedback as described in the first aspect of the present invention.

[0015] The present invention starts from the feedback data sent by the customers, undergoes sentiment analysis and theme recognition, and finally automatically realizes corresponding rectification, thereby improving the feedback sensitivity to the negative voices of the users, which is beneficial to improving the accommodation experience of the users and the service quality of the hotel itself. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a flowchart of a method for generating rectification tasks in response to customer feedback according to a specific embodiment of the present invention.

[0018] Figure 2 It is a flowchart of another method for generating rectification tasks in response to customer feedback according to a specific embodiment of the present invention.

[0019] Figure 3 It is a flowchart of another method for generating rectification tasks in response to customer feedback according to a specific embodiment of the present invention.

[0020] Figure 4 It is a block diagram of a method for generating rectification tasks in response to customer feedback according to a specific embodiment of the present invention.

[0021] Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application. In addition, it should be understood that the specific implementation methods described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0023] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments of the present application. In addition, in the following embodiments, the description of each embodiment has its own emphasis, and for parts not described in detail in one embodiment, reference can be made to the relevant description of other embodiments.

[0024] like Figure 1 As shown, the first aspect of the present invention provides a method for generating rectification tasks in response to customer feedback, comprising the following steps.

[0025] Step S100: Collecting feedback data from customers, wherein the feedback data at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels.

[0026] Specifically, with the development of intelligent society and interactive technology, customer feedback data is presented to merchants in different forms and through different channels, wherein the channel types may be telephone recordings, texts, order reviews, and order complaint channels, and the forms thereof are various, for example, text data or non-text data, such as picture data, voice data, video data, and label data, wherein the label data may be data of a specific "#XXXX" type, such as "#PillowUncomfortable", and for the non-text data generated in telephone recordings, texts, order reviews, and order complaint channels, the present invention proposes to perform text processing on the non-text data, and merge the text data and the text-processed non-text data into feedback data.

[0027] Through this step, the feedback data can be collected into a unified text data language, which is conducive to the subsequent sentiment analysis and topic identification of the feedback data.

[0028] Step S200: sentiment analysis is performed on the feedback data to obtain negative feedback data, and topic identification is performed on the negative feedback data to obtain topic categories, wherein the topic categories at least include hygiene, service quality, price, and facilities and equipment. Specifically, text sentiment analysis is a technology that analyzes text data and determines the sentiment tendency or state. With the development of Natural Language Processing (NLP), as an important branch in the field of artificial intelligence, it can understand, interpret, and generate human language through computers to achieve sentiment analysis.

[0029] Specifically, topic identification is a technology that processes and analyzes large-scale data to obtain research topics. Among them, in the prior art, there are technologies such as using the Latent Dirichlet Allocation (LDA) model for topic identification.

[0030] Optionally, the feedback data can be analyzed according to sentiment to obtain positive feedback data and neutral feedback data. Taking the negative voice of the responding user as an example, the present invention further describes the negative feedback data.

[0031] like Figure 2 As shown, in one embodiment of the present invention, the negative feedback data is dimensionally processed based on the negative feedback data and the corresponding subject categories to obtain a rectification special dimension, including: mapping the negative feedback data into at least one thematic category; In the topic category, extracting a preset number of semantic features from the negative feedback data, and mapping the semantic features to a preset number of preset levels; The rectification dimension corresponding to the preset level mapped by the semantic feature is indexed in the rectification dimension dictionary.

[0032] Specifically, before indexing the rectification special dimension corresponding to the preset level mapped by the semantic feature in the rectification dimension dictionary, it includes: establishing a rectification dimension dictionary, the rectification dimension dictionary including subject categories, a preset number of preset levels corresponding to each subject category, and rectification special dimensions corresponding to the preset number of preset levels corresponding to each subject category.

[0033] Exemplarily, as shown in Table 1, the rectification dimension dictionary can be stored in the form of a database or table. Considering the actual user feedback needs, there may be more than one subject category for user feedback. For example, user comments: There is a peculiar smell in the room I live in, and the tables and chairs are damaged. The corresponding subject categories involved are hygiene and facilities. Therefore, the negative feedback data needs to be mapped to the hygiene subject category and the setting subject category. Among them, the substantive names of each preset level can be repeated according to the actual situation, which still does not affect the technical content to be protected by the present invention. Table 1

[0034] Further, taking the subject category of hygiene as an example, in this subject category, a preset number of preset levels can be involved in establishing a rectification dimension dictionary. The preset number is designed according to the minimum granularity that can be rectified. The present invention shows a rectification dimension dictionary consisting of a subject category, a preset number of 5 preset levels (Level1-Level5) and rectification special dimensions.

[0035] Step S300: Dimensioning the negative feedback data based on the negative feedback data and the corresponding subject categories to obtain a rectification-specific dimension.

[0036] Step S400: Automatically generate corresponding rectification tasks based on the rectification special dimension.

[0037] In this way, the present invention starts from the feedback data sent by the customers, undergoes sentiment analysis and theme recognition, and finally automatically realizes corresponding rectification, thereby improving the feedback sensitivity to the negative voices of the users, which is beneficial to improving the accommodation experience of the users and improving the service quality of the hotel itself.

[0038] like Figure 2 As shown, in one embodiment of the present invention, when mapping negative feedback data to at least one topic category, it also includes: Traverse the rectification dimension dictionary. If the subject category to which the negative feedback data can be mapped cannot be indexed in the rectification dimension dictionary, set the first subject category. For example, the first subject category is a subject category other than the sanitation, service quality, price, and facilities and equipment subject categories, such as a geographical area, which is reflected in the feedback data, such as near a subway, near a station, near an urban area, etc.; Extracting a preset number of semantic features from the negative feedback data, and setting a preset number of first-class custom levels; mapping the extracted semantic features to the corresponding preset number of first-class custom levels, and obtaining corresponding rectification special dimensions; The first topic category and the first custom level are updated to the rectification dimension dictionary.

[0039] Here, in this way, the present invention can achieve targeted solutions to new negative problems and update the rectification dimension dictionary, and can flexibly and closed-loop respond to rectification tasks fed back by customers.

[0040] like Figure 2 As shown, in one embodiment of the present invention, after mapping the negative feedback data to at least one topic category, it also includes: Extracting a preset number of semantic features from the negative feedback data; Traversing the rectification dimension dictionary, if the preset level that can map all semantic features to the preset number of corresponding subject categories cannot be indexed in the rectification dimension dictionary, then setting the second type of custom level for the semantic features that are not mapped to the preset level of the corresponding subject category, and obtaining the corresponding rectification special dimension; Let the preset levels of some preset numbers that have been mapped to the corresponding subject categories be the third type of preset levels, and update the dimensional dictionary of subject categories, second type of custom levels and third type of preset levels, wherein the second type of preset levels and the third type of preset levels are combined together to form the preset levels of the original preset number.

[0041] Exemplarily, if it is impossible to index a preset level in the rectification dimension dictionary that can map all semantic features to a preset number of corresponding subject categories (for example, currently it can only be mapped to a certain subject category in the rectification dimension dictionary, such as matching the subject category of "facilities"), but cannot match any group of preset number of preset level contents under the subject category, then the preset level of some preset number that has been mapped to the corresponding subject category is retained as the third type of preset level (for example, it can only be mapped to Level 1 guest rooms-Level 2 electrical appliances), and the second type of custom level is set for the semantic features that are not mapped to the preset level of the corresponding subject category (for example, it is not mapped to Level 3 Class I electrical appliances-Level 4 cookers-Level 5 microwave ovens), and the corresponding rectification special dimension is obtained.

[0042] Based on this, the present invention can improve the adaptability to feedback data at different levels, and further realize a flexible and closed-loop generation solution for rectification tasks in response to customer feedback.

[0043] A second aspect of the present invention provides a method for generating rectification tasks in response to customer feedback, comprising: Collect feedback data from customers, which at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; the feedback data includes positive feedback data, neutral feedback data and negative feedback data; Performing sentiment analysis on the feedback data to obtain feedback data, and performing topic identification on the feedback data to obtain topic categories; Dimensional processing is performed on the feedback data based on the feedback data and the corresponding subject category to obtain a response-specific dimension, wherein the response-specific dimension at least includes a rectification-specific dimension when the feedback data is negative feedback data; Based on the response-specific dimension, a corresponding response task is automatically generated, and the response task at least includes a rectification task when the feedback data is negative feedback data.

[0044] Specifically, the rectification task generation method for responding to customer feedback provided in the second aspect of the present invention can also be applied to omnipolar feedback data. In addition to timely rectification of negative voices (negative feedback data), positive voices will also be fed back accordingly. In a feasible manner, referring to the processing method of negative voices, the present invention can achieve work incentives for hotel staff by obtaining the incentive dimension dictionary corresponding to positive voices (positive feedback data), such as setting the same theme category and preset level, and finally indexing to the responsible person or responsible hotel (if the hotel is a chain hotel) based on the housing information associated with the user, implementing a corresponding reward mechanism, improving the overall hotel service level, and creating hotel service characteristics.

[0045] In addition, even for neutral feedback information, it can, together with positive and negative voices, provide a certain reference or reference for evaluating the overall operating level of the hotel.

[0046] like Figure 3 As shown, in an application scenario of the present invention, in order to better demonstrate the overall synergy of the rectification tasks, after the rectification tasks are generated, it also includes: if it is confirmed that the task is to be rectified, it is necessary to improve the rectification plan and submit a rectification completion plan until the rectification is completed; or in the rectification stage, an application for inability to rectify is raised and enters the pending review state. If the application is approved, all tasks cannot be rectified, that is, no rectification is required for this feedback; if the application is approved, some tasks cannot be rectified, then a rectification plan is submitted, and a rectification completion plan is submitted until the rectification is completed; or if the application is not approved, the application for inability to rectify is rejected.

[0047] like Figure 4As shown, the third aspect of the present invention provides a rectification task generation system in response to customer feedback, comprising: a collection unit 21, at least for collecting feedback data sent by customers, the feedback data at least including textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; An analysis and identification unit 22, at least used for performing sentiment analysis on the feedback data to obtain negative feedback data, and performing topic identification on the negative feedback data to obtain a topic category; A dimensionalization processing unit 23 performs dimensionalization processing on the negative feedback data based on the negative feedback data and the corresponding subject category to obtain a rectification special dimension; The execution unit 24 is at least used to automatically generate a corresponding rectification task based on the rectification special dimension.

[0048] In one embodiment of the present invention, a task push and transfer unit 25 is further included. The task push and transfer module can push the rectification task generated by the execution unit to the corresponding hotel or the relevant department of the platform, and monitor the execution status of the task.

[0049] This system uses technologies such as intelligent speech recognition, speech-to-text, and natural language processing (NLP) analysis to achieve unified analysis and processing of voice feedback from telephone, text, order reviews, and order complaints. This system can accurately identify problems existing in the hotel and generate corresponding rectification tasks, thereby promoting the hotel or platform department to make effective rectifications and improving customer stay experience.

[0050] like Figure 5 As shown, the fourth aspect of the present invention provides an electronic device, comprising: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the steps of the method described in any one of the above embodiments.

[0051] A fifth aspect of the present invention discloses a readable storage medium storing a computer program, wherein the computer program is executed by a processor to perform the steps of the method described in any one of the above embodiments.

[0052] Computer-readable storage media may include: any entity or device capable of carrying a computer program, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc. A computer program includes a computer program code. The computer program code may be in source code form, object code form, an executable file, or some intermediate form, etc. A computer-readable storage medium may include: any entity or device capable of carrying a computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc.

[0053] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0054] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0055] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating rectification tasks in response to customer feedback, characterized in that: include: Collect feedback data from customers, which at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; Performing sentiment analysis on the feedback data to obtain negative feedback data, and performing topic identification on the negative feedback data to obtain topic categories; Dimensional processing is performed on the negative feedback data based on the negative feedback data and the corresponding subject categories to obtain a rectification-specific dimension; The corresponding rectification tasks are automatically generated based on the special rectification dimension.

2. The method for generating rectification tasks in response to customer feedback according to claim 1, characterized in that: The collected feedback data from customers includes at least one or more of the data generated in telephone recordings, texts, order reviews and order complaints channels, and is ultimately converted into textual data, including: Obtain text and non-text data generated from phone recordings, texts, order reviews, and order complaint channels; The non-text data is processed into text, and the text data and the non-text data after the text processing are merged into feedback data.

3. The method for generating rectification tasks in response to customer feedback according to claim 1, characterized in that: Based on the negative feedback data and the corresponding subject categories, the negative feedback data is dimensionalized to obtain rectification-specific dimensions, including: mapping the negative feedback data into at least one thematic category; In the topic category, extracting a preset number of semantic features from the negative feedback data, and mapping the semantic features to a preset number of preset levels; The rectification dimension corresponding to the preset level mapped by the semantic feature is indexed in the rectification dimension dictionary.

4. The method for generating rectification tasks in response to customer feedback according to claim 3, characterized in that: Before indexing the rectification special dimension corresponding to the preset level mapped by the semantic feature in the rectification dimension dictionary, it includes: Establishing a rectification dimension dictionary, the rectification dimension dictionary including subject categories, a preset number of preset levels corresponding to each subject category, and rectification special dimensions corresponding to a preset number of preset levels corresponding to each subject category; When mapping the negative feedback data into at least one thematic category, further comprising: Traverse the rectification dimension dictionary, and if the topic category to which the negative feedback data can be mapped cannot be indexed in the rectification dimension dictionary, set the first topic category; Extracting a preset number of semantic features from the negative feedback data, and setting a preset number of first-class custom levels; Mapping the extracted semantic features to a corresponding preset number of first-class custom levels, and obtaining corresponding rectification special dimensions; The first topic category and the first custom level are updated to the rectification dimension dictionary.

5. The method for generating rectification tasks in response to customer feedback according to claim 4, characterized in that: After mapping the negative feedback data into at least one thematic category, further comprising: Extracting a preset number of semantic features from the negative feedback data; Traversing the rectification dimension dictionary, if the preset level that can map all semantic features to the preset number of corresponding subject categories cannot be indexed in the rectification dimension dictionary, then setting the second type of custom level for the semantic features that are not mapped to the preset level of the corresponding subject category, and obtaining the corresponding rectification special dimension; The preset levels of a part of the preset number that have been mapped to the corresponding subject categories are set as the third type of preset levels, and the subject categories, the second type of custom levels and the third type of preset levels are updated to rectify the dimension dictionary.

6. The method for generating rectification tasks in response to customer feedback according to claim 1, characterized in that: The subject categories include at least hygiene, service quality, price and facilities and equipment.

7. A method for generating rectification tasks in response to customer feedback, characterized in that: include: Collect feedback data from customers, which at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; Performing sentiment analysis on the feedback data to obtain feedback data, and performing topic identification on the feedback data to obtain topic categories; Dimensional processing is performed on the feedback data based on the feedback data and the corresponding subject category to obtain a response-specific dimension, wherein the response-specific dimension at least includes a rectification-specific dimension when the feedback data is negative feedback data; Based on the response-specific dimension, a corresponding response task is automatically generated, and the response task at least includes a rectification task when the feedback data is negative feedback data.

8. A rectification task generation system in response to customer feedback, characterized in that: include: A collection unit, at least used to collect feedback data from customers, wherein the feedback data at least includes textual data generated and composed in telephone recordings, texts, order reviews and order complaint channels; An analysis and identification unit, at least used to perform sentiment analysis on the feedback data to obtain negative feedback data, and perform topic identification on the negative feedback data to obtain a topic category; A dimensional processing unit performs dimensional processing on the negative feedback data based on the negative feedback data and the corresponding subject category to obtain a rectification special dimension; The execution unit is at least used to automatically generate corresponding rectification tasks based on the rectification special dimension.

9. An electronic device, characterized in that: include: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the steps of the method for generating rectification tasks in response to customer feedback as described in any one of claims 1-6.

10. A readable storage medium storing a computer program, characterized in that: The computer program is executed by a processor to execute the steps of the method for generating rectification tasks in response to customer feedback as described in any one of claims 1-6.

Images