Complaint pushing method and device based on e-commerce platform, computer equipment, readable storage medium and program product

Abstract

The invention relates to a complaint pushing method and device based on an e-commerce platform, computer equipment, a computer readable storage medium and a computer program product, relates to the technical field of information, and can improve the user complaint processing efficiency. The method comprises the steps of obtaining at least one piece of user complaint information of the same user account in an e-commerce platform; for each piece of user complaint information, determining at least one complaint theme involved in the user complaint information according to an analysis result of the user complaint information; according to various complaint themes involved in the user complaint information, merging and / or splitting the at least one piece of user complaint information to obtain at least one complaint document; wherein the same complaint document corresponds to the same business customer service type, and different complaint documents correspond to different business customer service types; and according to the business customer service type corresponding to each complaint document, pushing each complaint document to a customer service account related to the business customer service type.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular, to a complaint push method, device, computer device, computer-readable storage medium, and computer program product based on an e-commerce platform. Background Art

[0002] With the development of computer technology, when an abnormality occurs in a business, a user can conveniently submit relevant complaints on an e-commerce platform.

[0003] In related technologies, when the complaint content of a user involves multiple business lines, it is mainly for the user to separately find customer service for multiple business lines. For example, when the complaint content involves product quality and logistics, the user needs to contact different customer services and describe the complaint content multiple times before it can be resolved, which greatly prolongs the response time to user complaints. It can be seen that when a user complaint involves multiple business lines, the complaint handling efficiency of related technologies is low. Summary of the Invention

[0004] Based on this, it is necessary to provide a complaint push method, device, computer device, computer-readable storage medium, and computer program product based on an e-commerce platform for the above technical problems.

[0005] In a first aspect, the present application provides a complaint push method based on an e-commerce platform, including:

[0006] Obtain at least one user complaint information of the same user account in the e-commerce platform;

[0007] For each of the user complaint information, determine at least one complaint theme involved in the user complaint information according to the analysis result of the user complaint information;

[0008] According to various complaint themes involved in each of the user complaint information, merge and / or split the at least one user complaint information to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service;

[0009] Push each of the complaint documents to the customer service account related to the type of business customer service according to the type of business customer service corresponding to each of the complaint documents.

[0010] In one of the embodiments, the step of merging and / or splitting the at least one user complaint information according to various complaint themes involved in each of the user complaint information to obtain at least one complaint document includes:

[0011] For each of the complaint themes involved in each of the user complaint information, obtain the complaint information under the complaint theme from the user complaint information;

[0012] Determine the type of business customer service associated with each of the complaint topics;

[0013] If the type of business customer service associated with the complaint topic includes different types of business customer service, then generate complaint documents for different types of business customer service respectively according to the first complaint information under each of the complaint topics associated with different types of business customer service;

[0014] If the type of business customer service associated with the complaint topic includes the same type of business customer service, then merge the second complaint information under each of the complaint topics associated with the same type of business customer service, and obtain the complaint document for the same type of business customer service according to the result of the merged complaint information.

[0015] In one embodiment, before obtaining at least one user complaint information of the same user account in the e-commerce platform, it further includes:

[0016] Obtain multiple historical user complaint information under each of the complaint topics;

[0017] Determine the target customer service account of each of the multiple historical user complaint information according to the complaint handling record of each of the multiple historical user complaint information; the target customer service account is the customer service account that actually solves the historical user complaint information;

[0018] Determine the type of business customer service associated with the complaint topic according to the type of business customer service of the target customer service account.

[0019] In one embodiment, obtaining the complaint information under the complaint topic from the user complaint information includes:

[0020] Divide the user complaint information into multiple text chunks, and determine the text chunks associated with the complaint topic;

[0021] Determine the complaint description rule preset for the complaint topic, and adjust the text information of the text chunks associated with the complaint topic according to the complaint description rule, and use the adjusted text information as the complaint information under the complaint topic.

[0022] In one embodiment, determining at least one complaint topic involved in the user complaint information according to the analysis result of the user complaint information includes:

[0023] Obtain the key information associated with the complaint content in the user complaint information;

[0024] Match the key information with the topic keywords under various preset complaint topics, and determine at least one of the complaint topics involved in the user complaint information according to the matching result.

[0025] In one embodiment, obtaining at least one user complaint information of the same user account in the e-commerce platform includes:

[0026] Obtaining the submitted complaint information of multiple user accounts in the e-commerce platform;

[0027] For each of the submitted complaint information, determining the text associated with the user complaint in the submitted complaint information, and when the number of characters in the text is greater than the character number threshold, using the submitted complaint information as one user complaint information of the same user account; and / or;

[0028] For each of the user accounts, if the number of the submitted complaint information of the user account within a preset time is greater than the submission times threshold, using each of the submitted complaint information of the user account as multiple user complaint information of the same user account.

[0029] In a second aspect, the present application further provides a complaint push device based on an e-commerce platform, including:

[0030] A complaint acquisition module, configured to obtain at least one user complaint information of the same user account in the e-commerce platform;

[0031] A complaint theme determination module, configured to determine at least one complaint theme involved in the user complaint information according to the analysis result of each user complaint information;

[0032] A complaint document acquisition module, configured to merge and / or split the at least one user complaint information according to various complaint themes involved in each user complaint information to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service;

[0033] A complaint document push module, configured to push each complaint document to the customer service account related to the type of business customer service according to the type of business customer service corresponding to each complaint document.

[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Obtaining at least one user complaint information of the same user account in the e-commerce platform;

[0036] For each of the user complaint information, determining at least one complaint theme involved in the user complaint information according to the analysis result of the user complaint information;

[0037] Merge and / or split the at least one user complaint information according to various complaint topics involved in each user complaint information, to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service;

[0038] Push each complaint document to the customer service account related to the type of business customer service according to the type of business customer service corresponding to each complaint document.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Obtain at least one user complaint information of the same user account in the e-commerce platform;

[0041] For each user complaint information, determine at least one complaint topic involved in the user complaint information according to the analysis result of the user complaint information;

[0042] Merge and / or split the at least one user complaint information according to various complaint topics involved in each user complaint information, to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service;

[0043] Push each complaint document to the customer service account related to the type of business customer service according to the type of business customer service corresponding to each complaint document.

[0044] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0045] Obtain at least one user complaint information of the same user account in the e-commerce platform;

[0046] For each user complaint information, determine at least one complaint topic involved in the user complaint information according to the analysis result of the user complaint information;

[0047] Merge and / or split the at least one user complaint information according to various complaint topics involved in each user complaint information, to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service;

[0048] Push each of the complaint documents to the customer service account related to the business customer service type corresponding to each complaint document.

[0049] The above-mentioned complaint push method, device, computer device, computer-readable storage medium, and computer program product based on an e-commerce platform can obtain at least one user complaint information of the same user account in the e-commerce platform; for each user complaint information, according to the analysis result of the user complaint information, determine at least one complaint theme involved in the user complaint information; then, according to various complaint themes involved in each user complaint information, merge and / or split at least one user complaint information to obtain at least one complaint document; where the same complaint document corresponds to the same business customer service type, and different complaint documents correspond to different business customer service types; furthermore, each complaint document can be pushed to the customer service account related to the business customer service type according to the business customer service type corresponding to each complaint document. In this embodiment, by determining at least one complaint theme involved in the user complaint information, and then merging and / or splitting at least one user complaint information according to various complaint themes involved in each user complaint information to obtain at least one complaint document, it is possible to automatically and reasonably split and merge the user complaint information, and automatically allocate the split or merged complaint documents to the relevant customer service accounts, avoiding contacting the customer service of each business line one by one through the user method, realizing efficient automatic identification and accurate push, reducing the time and error rate of manual allocation, and also enabling user complaints to reach the appropriate customer service for processing faster, significantly improving the processing efficiency and accuracy of user complaints. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a schematic flowchart of a complaint push method based on an e-commerce platform in an embodiment;

[0052] Figure 2 It is a schematic flowchart of another complaint push method based on an e-commerce platform in an embodiment;

[0053] Figure 3 It is a structural block diagram of a complaint push device based on an e-commerce platform in an embodiment;

[0054] Figure 4 It is an internal structure diagram of a computer device in an embodiment. Detailed Implementation Modes

[0055] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] In one embodiment, as Figure 1 shown, a complaint push method based on an e-commerce platform is provided. In this embodiment, the method is exemplified by being applied to a server. It can be understood that the method can also be applied to a system including a terminal and a server and implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0057] S101, obtain at least one user complaint information of the same user account in the e-commerce platform.

[0058] In specific implementation, the server can obtain one or more user complaint information from the same user account in the e-commerce platform. Among them, the user complaint information can be the complaint information submitted by the user account of the e-commerce platform, and can be the specific content and relevant detailed information feedback by the user account to the e-commerce platform due to dissatisfaction or problems for one or more reasons.

[0059] In some exemplary embodiments, the e-commerce platform can collect user complaint information. For example, when a user account submits a complaint on the e-commerce trading platform, the e-commerce platform can record the detailed content of the complaint, including one or more of text descriptions, pictures, audio, and video.

[0060] S102, for each user complaint information, determine at least one complaint theme involved in the user complaint information according to the analysis result of the user complaint information.

[0061] In specific implementation, in each user complaint information, multiple complaint themes may be involved. For example, a user account may simultaneously complain about product quality problems and logistics delays through its user complaint information. In this regard, in this embodiment, for each user complaint information, the content of the user complaint information can be analyzed, and one or more complaint themes involved in the user complaint information can be determined according to the analysis result of the user complaint information.

[0062] S103, according to various complaint themes involved in each user complaint information, merge and / or split at least one user complaint information to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service.

[0063] In the related art, it mainly relies on manual identification of complaint content and complaint themes (such as product quality, logistics delay, system suggestions, etc.), and then distributes complaint information to the corresponding customer service for processing manually. This processing method may lead to misjudgment and low processing efficiency, resulting in poor handling or incorrect handling of user complaints, thus generating more complaints. At the same time, when dealing with complaints involving multiple business lines, only e-commerce platform staff or the user himself / herself can contact the customer service of each business line one by one. While it is possible to contact an inappropriate business customer service, it also lengthens the complaint response time of the user, and the complaint handling efficiency is low.

[0064] In this regard, in this embodiment, after obtaining various complaint themes involved in each user complaint information provided by the same user account, various user complaint information can be merged and / or split according to the various complaint themes involved in the user complaint information to obtain one or more complaint documents to be assigned to the customer service account. By merging or splitting complaint information according to the complaint theme, it is possible to automatically merge the complaint information of various complaint themes corresponding to the same type of business customer service into the same complaint document, and automatically split the complaint information of complaint themes corresponding to different types of business customer service into different complaint documents.

[0065] S104, according to the business customer service type corresponding to each complaint document, push each complaint document to the customer service account related to the business customer service type.

[0066] Furthermore, one or more complaint documents can be pushed to the customer service account related to the business customer service type according to the business customer service type corresponding to each complaint document.

[0067] For example, the scope of responsibilities of different types of business customer service can be predefined in advance, and it can be set which complaint themes' complaint information each type of business customer service needs to handle. As shown in Table 1 below, the complaint themes associated with each type of business customer service are provided:

[0068] Table 1

[0069] Business customer service type Complaint theme Merchant customer service Commodity quality Logistics customer service Logistics distribution After-sales customer service After-sales service Platform customer service Others

[0070] Then, according to the complaint theme classification result of the user complaint information, the corresponding complaint documents can be merged or split, and the complaint documents can be automatically pushed to the customer service account under the corresponding business customer service type.

[0071] In the above complaint push method based on an e-commerce platform, at least one user complaint information of the same user account in the e-commerce platform can be obtained; for each user complaint information, at least one complaint theme involved in the user complaint information is determined according to the analysis result of the user complaint information; then, according to various complaint themes involved in each user complaint information, at least one user complaint information is merged and / or split to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service; furthermore, according to the type of business customer service corresponding to each complaint document, each complaint document can be pushed to the customer service account related to the type of business customer service. In this embodiment, by determining at least one complaint theme involved in the user complaint information, and then merging and / or splitting at least one user complaint information according to various complaint themes involved in each user complaint information to obtain at least one complaint document, it is possible to automatically and reasonably split and merge the user complaint information, and automatically assign the split or merged complaint document to the relevant customer service account, avoiding contacting the customer service of each business line one by one in the user's way, realizing efficient automatic identification and accurate push, reducing the time and error rate of manual assignment, and also enabling the user complaint to reach the appropriate customer service for processing faster, significantly improving the processing efficiency and accuracy of user complaints.

[0072] In addition, through the solution of the present application, accurate complaint push and fast processing feedback can be achieved, effectively improving the satisfaction of users with the e-commerce platform; moreover, by automatically splitting and merging complaint documents, duplicate processing and omission are avoided, the resources consumed in the platform operation process are reduced, and the operation cost is reduced.

[0073] In one embodiment, in step S103, according to various complaint themes involved in each user complaint information, at least one user complaint information is merged and / or split to obtain at least one complaint document, which may include the following steps:

[0074] S1031, for each complaint theme involved in each user complaint information, obtain the complaint information under the complaint theme from the user complaint information.

[0075] In specific implementation, for each complaint theme involved in each user complaint information, the complaint information under the complaint theme can be obtained from the user complaint information. For example, through one or more methods such as semantic analysis and keyword matching, the complaint information related to the complaint theme can be extracted from the user complaint information.

[0076] S1032, determine the type of business customer service associated with each complaint theme.

[0077] In a specific implementation, the business customer service types associated with various complaint topics can be set in advance. For example, according to the pre-established correspondence between complaint topics and business customer service types, the business customer service types associated with each complaint topic involved in the user's complaint information can be determined.

[0078] S1033. If the business customer service types associated with a complaint topic include different business customer service types, then according to the first complaint information under each complaint topic associated with different business customer service types, complaint documents are generated for different business customer service types respectively.

[0079] S1034. If the business customer service types associated with a complaint topic include the same business customer service type, then the second complaint information under each complaint topic associated with the same business customer service type is merged, and according to the result of the merged complaint information, a complaint document for the same business customer service type is obtained.

[0080] For example, when the user's complaint information involves multiple business customer service types (also known as business lines), for each business customer service type, the complaint information under each complaint topic associated with that business customer service type, that is, the first complaint information, can be automatically determined, and then split into multiple independent complaint documents according to the first complaint information under each complaint topic, so as to be separately pushed to the corresponding business customer service for processing. For example, if the user complains about "product quality problems and logistics delays", it can be split into two complaint documents and pushed to the merchant and the logistics customer service respectively.

[0081] Another example is that if the business customer service types associated with a complaint topic include the same business customer service type, for example, multiple users' complaint information involves the same problem or the same user, then for the same certain business customer service type, the complaint information (that is, the second complaint information) under each complaint topic associated with the same business customer service type can be merged to avoid duplicate processing. For example, if the user complains about the same product quality problem multiple times, these complaints can be merged and pushed to the merchant for unified processing.

[0082] In this embodiment, by splitting the first complaint information under different business customer service types, when the user's complaint involves multiple business customer service types, relevant complaint information can be accurately and efficiently pushed to the relevant customer service respectively, improving the efficiency and accuracy of complaint handling; at the same time, by merging the second complaint information under the same business customer service type, duplicate processing of user complaints can be avoided, saving platform resources.

[0083] In an exemplary embodiment, before step S101, the following steps may further be included:

[0084] Obtain multiple historical user complaint information under each complaint theme; determine the target customer service accounts of multiple historical user complaint information according to the complaint handling records of multiple historical user complaint information respectively; the target customer service account is the customer service account that actually resolves the historical user complaint information; determine the business customer service type associated with the complaint theme according to the business customer service type of the target customer service account.

[0085] In specific implementation, user complaint information that has been processed under each complaint theme can be collected. For the convenience of distinction, this user complaint information is called historical user complaint information. Then, the complaint handling records of multiple historical user complaint information can be obtained. Among them, the complaint handling record can record the process of at least one customer service handling the historical user complaint information after the user submits the historical user complaint information. The at least one customer service involved in the complaint handling process can be a customer service of one or more business customer service types. After that, the target customer service account of each historical user complaint information can be determined according to the complaint handling records of multiple historical user complaint information, which can be understood as the customer service account that finally successfully resolves or handles the corresponding historical complaint information. Furthermore, for each complaint theme, the business customer service type associated with the complaint theme can be determined according to the business customer service type of the multiple target customer service accounts of the complaint theme. For example, for each complaint theme, the number of target customer service accounts under multiple business customer service types can be counted, and the business customer service type with the highest number of accounts, or one or more business customer service types whose number of accounts exceeds the account number threshold, can be used as the business customer service type associated with the complaint theme.

[0086] In this embodiment, the business customer service type associated with each complaint theme can be determined according to the complaint handling records of multiple historical user complaint information, which can accurately determine the appropriate business customer service type under each complaint theme based on past complaint handling experience, help accurately assign the merged or split complaint documents to the appropriate personnel for processing in the future, and improve the accuracy of complaint handling.

[0087] In an exemplary embodiment, in step S1031, obtaining the complaint information under the complaint theme from the user complaint information may include the following steps:

[0088] Divide the user complaint information into multiple text chunks, and determine the text chunks associated with the complaint theme; determine the complaint description rules preset for the complaint theme, and adjust the text information of the text chunks associated with the complaint theme according to the complaint description rules, and use the adjusted text information as the complaint information under the complaint theme.

[0089] In some embodiments, text segmentation techniques in Natural Language Processing (NLP) can be used to identify natural paragraphs or logical separation points in user complaint information, thereby dividing it into multiple text chunks. For example, for the user complaint information "The quality of the product is poor and it was already damaged when received. The logistics is also very slow and I waited for a long time.", after processing, it is divided into two text chunks, including "The quality of the product is poor and it was already damaged when received." and "The logistics is also very slow and I waited for a long time.".

[0090] Then, the text chunks associated with the complaint theme can be determined. For example, in combination with a predefined complaint theme thesaurus, at least one text chunk associated with the complaint theme can be determined according to the matching result between the text information in the text chunk and the thesaurus.

[0091] On the other hand, corresponding complaint description rules can be preset in advance for various complaint themes, and the complaint description rules are used to indicate the standardized description method of complaint information under the complaint theme. Furthermore, the text information of the text chunks associated with the complaint theme can be adjusted according to the complaint description rules, and the adjusted text information is used as the complaint information under the complaint theme. Exemplarily, semantic analysis in NLP technology can be used to normalize different expression ways of user complaint information into predefined complaint information. For example, user complaint information can include "The product is broken", "The product is damaged", "There is a problem with the quality of the product", which describe the same problem through different expression ways, and the server can unify and normalize them into "There is a problem with the quality of the product" according to the requirements of the complaint description rules.

[0092] In this embodiment, by adjusting the text information of the text chunks associated with the complaint theme according to the complaint description rules and using the adjusted text information as the complaint information under the complaint theme, the complaint information under each complaint theme can be represented in a standardized manner, which helps to improve the efficiency and accuracy of subsequent splitting or merging of complaint information.

[0093] In one embodiment, in step S102, according to the analysis result of user complaint information, determining at least one complaint theme involved in the user complaint information may include the following steps:

[0094] S1021, obtaining key information associated with the complaint content in the user complaint information.

[0095] In specific implementation, after obtaining the user complaint information, the server can initially organize the user complaint information, remove irrelevant information, and extract key content to prepare for subsequent analysis.

[0096] In some exemplary embodiments, a keyword extraction algorithm in natural language processing technology can be used to identify the core words and phrases related to complaints in the user complaint information, and the identified core words and phrases can be used as key information.

[0097] In some exemplary embodiments, before obtaining the key information in the user complaint information, the obtained user complaint information can be preprocessed first, and then the preprocessed user complaint information can be used to obtain the key information associated with the complaint content. Exemplarily, the collected user complaint information can be first subjected to text formatting processing to remove redundant spaces, line breaks, special symbols, etc.; then, natural language processing technology can be used to identify the interfering content unrelated to the complaint theme through text classification and keyword extraction. Exemplarily, the interfering content can include the user's chatting content, irrelevant background information. For example, the user may mention "I'm in a bad mood today because..." in the user complaint information, and this part of the content is irrelevant to the complaint theme and can be removed.

[0098] S1022, match the key information with the theme keywords under various preset complaint themes, and determine at least one complaint theme involved in the user complaint information according to the matching result.

[0099] In practical applications, various complaint themes and complaint keywords under each complaint theme can be preset to form a complaint theme thesaurus. The complaint theme thesaurus can provide a clear reference framework for the server to help the server quickly identify and classify user complaint content. Through predefined keywords and phrases, the natural language description of the user can be converted into a standardized complaint theme, thus realizing accurate automated processing.

[0100] In some examples, the complaint themes can be classified according to the business characteristics of the e-commerce platform and common complaint types. For example, the following table 2 shows various complaint themes and their corresponding classification descriptions:

[0101] Table 2

[0102] Theme classification Description Commodity quality Quality problems related to the commodity itself, such as damage, defects, inconsistent with the description, etc. Logistics distribution Problems related to logistics, such as delay, package loss, delivery error, etc. After-sales service Problems related to after-sales service, such as difficulty in returning and exchanging goods, slow customer service response, etc. Labor protection supplies problems Problems related to the quality, compliance, use of labor protection supplies, etc. Welfare-related problems Problems related to welfare distribution, inconsistent welfare content, etc. Book-related problems Problems related to book content, printing quality, inconsistent version, etc. Others Other complaint contents not belonging to the above classifications.

[0103] Then, relevant keywords and phrases can be collected for each complaint theme classification, and these keywords and phrases should be able to cover various expressions that the user may use. The following table 3 shows the theme keywords (including keywords and phrases) under various complaint themes:

[0104] Table 3

[0105] Theme classification Keywords and phrases Commodity quality Commodity damage, poor quality, defects, inconsistent with the description, commodity problems, quality problems, etc. Logistics distribution Logistics delay, package loss, delivery error, slow express delivery, logistics problems, etc. After-sales service Difficulty in returning and exchanging goods, slow customer service response, poor after-sales service, after-sales problems, etc. Labor protection supplies problems Labor protection supplies damage, labor protection supplies quality, labor protection supplies not meeting the standards, etc. Welfare-related problems Welfare not distributed, inconsistent welfare content, welfare problems, etc. Book-related problems Book content error, poor printing quality, inconsistent version, book problems, etc. Others System problems, platform usage problems, other problems, etc.

[0106] Furthermore, the extracted key information can be matched with the topic keywords under various preset complaint topics, and at least one complaint topic involved in the user complaint information can be determined according to the matching result. For example, for the complaint topic with successful matching between the topic keyword and the key information, it can be used as the complaint topic involved in the user complaint information.

[0107] In this embodiment, on the one hand, by obtaining the key information associated with the complaint content in the user complaint information, the interference information in the complaint topic recognition process can be reduced. On the other hand, by matching the key information with the topic keywords of each complaint topic, the complaint topics involved in the user complaint information can be quickly determined by means of text matching, improving the recognition efficiency of the complaint topics.

[0108] In an exemplary embodiment, step S101 may include the following steps:

[0109] Obtain the submitted complaint information of multiple user accounts in the e-commerce platform; for each submitted complaint information, determine the text associated with the user complaint in the submitted complaint information, and when the number of characters in the text is greater than the character number threshold, regard the submitted complaint information as a user complaint information of the same user account; and / or; for each user account, if the number of submitted complaint information within the preset time is greater than the submission times threshold, regard each submitted complaint information of the user account as multiple user complaint information of the same user account.

[0110] In this embodiment, the complaint information submitted by multiple user accounts in the e-commerce platform can be obtained. For the convenience of distinction, this complaint information is called the submitted complaint information, and the submitted complaint information can be understood as the complaint information submitted or uploaded to the e-commerce platform by any user account.

[0111] Then, the complaint information can be screened based on the dimension of a single submitted complaint information or a single user account. Specifically, for each submitted complaint information, the content of the submitted complaint information can be parsed to remove the interfering text content irrelevant to the user complaint, and the text associated with the user complaint in the submitted complaint information can be determined. In some examples, in combination with natural language processing techniques, through a pre-trained semantic understanding model, the text associated with the user complaint in the submitted complaint information can be extracted. Furthermore, the number of characters of the extracted text can be counted, and when the number of characters of the text is greater than the character number threshold, the submitted complaint information can be used as a user complaint information of the same user account. By using, as a user complaint information of the same user account, the text associated with the user complaint when the number of characters thereof exceeds the character number threshold, and pushing the complaint through the method of the present application, it is possible to timely discover user complaints that may be associated with multiple complaint topics and related to the business customer service type, avoiding the need for the user to contact the customer service of other different business lines after submitting the user complaint, and improving the response efficiency and processing efficiency of the e-commerce platform for user complaints while reducing user operations. In some embodiments, the complaint information submitted for the first time for a business order among multiple submitted complaint information can be determined, so that the information can be timely pushed to the customer service of each business line when the user makes the first complaint, improving the complaint processing efficiency after the user's first complaint.

[0112] In other embodiments, the user account can be used as the processing dimension, the submitted complaint information submitted by each user account to the e-commerce platform within a preset time can be counted, and it can be determined whether the number of submitted complaint information is greater than the submission times threshold. For example, whether the number of submitted complaint information by a user account within three days is greater than 5 times. If the number of submitted complaint information by a user account within the preset time is greater than the submission times threshold, it is possible that the user account has made multiple complaints about the same complaint content. At this time, each submitted complaint information of the user account can be used as multiple user complaint information of the same user account. Thus, in the case where the user makes frequent complaints within a short period of time, the associated complaint information can be merged, reducing the resources consumed by the e-commerce platform in the process of handling user complaints.

[0113] To enable those skilled in the art to better understand the above steps, the following will be combined with Figure 2 An example is used to exemplarily illustrate the embodiments of the present application, but it should be understood that the embodiments of the present application are not limited thereto. In this example, the following steps can be included:

[0114] S201, obtain at least one user complaint information of the same user account in the e-commerce platform.

[0115] S202. For each user complaint information, divide the user complaint information into multiple text chunks, and determine the text chunks associated with the complaint theme.

[0116] S203. Determine the complaint description rules preset for the complaint theme, and adjust the text information of the text chunks associated with the complaint theme according to the complaint description rules. Use the text information obtained after adjustment and conforming to the complaint description rules as the complaint information under the complaint theme.

[0117] S204. For each complaint theme involved in the user complaint information, obtain the complaint information under the complaint theme from the user complaint information.

[0118] S205. Determine the business customer service types associated with each complaint theme.

[0119] S206. If the business customer service types associated with the complaint theme include different business customer service types, generate complaint documents for different business customer service types respectively according to the first complaint information under each complaint theme associated with different business customer service types.

[0120] S207. If the business customer service types associated with the complaint theme include the same business customer service type, merge the second complaint information under each complaint theme associated with the same business customer service type, and obtain the complaint document for the same business customer service type according to the complaint information merging result.

[0121] S208. Push each complaint document to the customer service account related to the business customer service type according to the business customer service type corresponding to each complaint document.

[0122] By automatically identifying the specific content of user complaints, the complaints are accurately pushed to different processing roles. At the same time, when a complaint involves multiple business lines, the system can automatically split or merge complaint documents to ensure that each problem can be effectively processed. Compared with the prior art, this solution can more accurately understand the complaint content, improve the complaint handling efficiency, and enhance the user experience.

[0123] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0124] Based on the same inventive concept, an embodiment of the present application further provides a complaint pushing device based on an e-commerce platform for implementing the above-mentioned complaint pushing method based on an e-commerce platform. The implementation solutions provided by this device to solve problems are similar to those described in the above method. Therefore, the specific limitations in one or more embodiments of the complaint pushing device based on an e-commerce platform provided below can refer to the limitations on the complaint pushing method based on an e-commerce platform in the above text, and will not be elaborated here.

[0125] In an exemplary embodiment, as Figure 3 shown, a complaint pushing device based on an e-commerce platform is provided, including:

[0126] A complaint acquisition module 301, configured to acquire at least one user complaint information of the same user account in the e-commerce platform;

[0127] A complaint theme determination module 302, configured to, for each of the user complaint information, determine at least one complaint theme involved in the user complaint information according to the analysis result of the user complaint information;

[0128] A complaint document acquisition module 303, configured to merge and / or split the at least one user complaint information according to various complaint themes involved in each of the user complaint information, to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service;

[0129] A complaint document pushing module 304, configured to push each of the complaint documents to the customer service account related to the type of business customer service according to the type of business customer service corresponding to each of the complaint documents.

[0130] In an embodiment, the complaint document acquisition module 303 is configured to:

[0131] For each complaint theme involved in each of the user complaint information, acquire the complaint information under the complaint theme from the user complaint information;

[0132] Determine the type of business customer service associated with each of the complaint themes;

[0133] If the type of business customer service associated with the complaint theme includes different types of business customer service, generate complaint documents for different types of business customer service respectively according to the first complaint information under each complaint theme associated with different types of business customer service;

[0134] If the business customer service types associated with the complaint topics include the same business customer service type, the second complaint information under each of the complaint topics associated with the same business customer service type is merged, and according to the complaint information merging result, a complaint document for the same business customer service type is obtained.

[0135] In one embodiment, the apparatus further includes an association relationship determination module, and the association relationship determination module is configured to:

[0136] Obtain multiple historical user complaint information under each of the complaint topics;

[0137] According to the complaint handling records of the multiple historical user complaint information respectively, determine the target customer service accounts of the multiple historical user complaint information respectively; the target customer service account is the customer service account that actually resolves the historical user complaint information;

[0138] According to the business customer service type of the target customer service account, determine the business customer service type associated with the complaint topic.

[0139] In one embodiment, the complaint document acquisition module 303 is configured to, including:

[0140] Divide the user complaint information into multiple text blocks, and determine the text blocks associated with the complaint topic;

[0141] Determine the complaint description rule preset for the complaint topic, and perform text information adjustment on the text blocks associated with the complaint topic according to the complaint description rule, and use the adjusted text information as the complaint information under the complaint topic.

[0142] In one embodiment, the complaint topic determination module 302 is configured to:

[0143] Obtain the key information associated with the complaint content in the user complaint information;

[0144] Match the key information with the topic keywords under various preset complaint topics, and according to the matching result, determine at least one of the complaint topics involved in the user complaint information.

[0145] In one embodiment, the complaint acquisition module 301 is configured to:

[0146] Obtain the submitted complaint information of multiple user accounts in the e-commerce platform;

[0147] For each of the submitted complaint information, determine the text associated with the user complaint in the submitted complaint information, and when the number of characters in the text is greater than the character number threshold, use the submitted complaint information as a user complaint information of the same user account; and / or;

[0148] For each of the user accounts, if the number of submitted complaint messages of the user account within a preset time is greater than the submission times threshold, then each of the submitted complaint messages of the user account is used as multiple user complaint messages of the same user account.

[0149] Each module in the above-mentioned complaint push device based on an e-commerce platform can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0150] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store complaint data of user accounts. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a complaint push method based on an e-commerce platform.

[0151] Those skilled in the art can understand that Figure 4 the structure shown in

[0152] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0153] In an embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above method embodiments.

[0154] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the steps in the foregoing method embodiments.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0156] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0157] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0158] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A complaint pushing method based on an e-commerce platform, characterized in that, The method includes: Obtaining at least one user complaint information of the same user account in the e-commerce platform; For each of the user complaint information, according to the analysis result of the user complaint information, determining at least one complaint theme involved in the user complaint information; According to various complaint themes involved in each of the user complaint information, merging and / or splitting the at least one user complaint information to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service; According to the type of business customer service corresponding to each of the complaint documents, pushing each of the complaint documents to the customer service account related to the type of business customer service.

2. The method according to claim 1, characterized in that The step of merging and / or splitting the at least one user complaint information according to various complaint themes involved in each of the user complaint information to obtain at least one complaint document includes: For each complaint theme involved in each of the user complaint information, obtaining the complaint information under the complaint theme from the user complaint information; Determining the type of business customer service associated with each of the complaint themes; If the type of business customer service associated with the complaint theme includes different types of business customer service, generating complaint documents for different types of business customer service respectively according to the first complaint information under each of the complaint themes associated with different types of business customer service; If the type of business customer service associated with the complaint theme includes the same type of business customer service, merging the second complaint information under each of the complaint themes associated with the same type of business customer service, and obtaining a complaint document of the same type of business customer service according to the merged result of the complaint information.

3. The method according to claim 2, characterized in that, Before obtaining at least one user complaint information of the same user account in the e-commerce platform, it further includes: Obtaining multiple historical user complaint information under each of the complaint themes; According to the complaint handling records of each of the multiple historical user complaint information, determining the target customer service account of each of the multiple historical user complaint information; the target customer service account is the customer service account that actually solves the historical user complaint information; According to the type of business customer service of the target customer service account, determining the type of business customer service associated with the complaint theme.

4. The method according to claim 2, wherein The step of obtaining the complaint information under the complaint theme from the user complaint information includes: Dividing the user complaint information into multiple text chunks, and determining the text chunks associated with the complaint theme; Determining a preset complaint description rule for the complaint theme, and adjusting the text information of the text chunks associated with the complaint theme according to the complaint description rule, and using the adjusted text information as the complaint information under the complaint theme.

5. The method according to any one of claims 1 to 4, characterized in that, The step of determining at least one complaint theme involved in the user complaint information according to the analysis result of the user complaint information includes: Obtaining the key information associated with the complaint content in the user complaint information; Matching the key information with the theme keywords under various preset complaint themes, and determining at least one of the complaint themes involved in the user complaint information according to the matching result.

6. The method according to any one of claims 1 to 4, characterized in that The step of obtaining at least one user complaint information of the same user account in the e-commerce platform includes: Obtain the submitted complaint information of multiple user accounts in the e-commerce platform; For each of the submitted complaint information, determine the text associated with the user complaint in the submitted complaint information, and when the number of characters in the text is greater than the character number threshold, regard the submitted complaint information as a user complaint information of the same user account; and / or; For each of the user accounts, if the number of the submitted complaint information of the user account within a preset time is greater than the submission times threshold, regard each of the submitted complaint information of the user account as multiple user complaint information of the same user account.

7. A complaint push device based on an e-commerce platform, characterized in that, The device includes: A complaint acquisition module, configured to obtain at least one user complaint information of the same user account in the e-commerce platform; A complaint theme determination module, configured to, for each of the user complaint information, determine at least one complaint theme involved in the user complaint information according to the analysis result of the user complaint information; A complaint document acquisition module, configured to merge and / or split the at least one user complaint information according to various complaint themes involved in each of the user complaint information, to obtain at least one complaint document; wherein, the same complaint document corresponds to the same type of business customer service, and different complaint documents correspond to different types of business customer service; A complaint document push module, configured to push each of the complaint documents to the customer service account related to the type of business customer service according to the type of business customer service corresponding to each of the complaint documents.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images