Complaint work order processing method and device, storage medium and electronic equipment

Abstract

The disclosure provides a complaint work order processing method and device, a storage medium and an electronic equipment, and relates to the technical field of Internet. The complaint work order processing method comprises the following steps: acquiring a newly added complaint work order; determining whether the newly added complaint work order has a similar historical complaint work order; if the newly added complaint work order has a similar historical complaint work order, classifying the emotion of a customer of the newly added complaint work order; determining whether the newly added complaint work order has an automatic processing condition according to the emotion classification of the customer; and outputting a complaint processing scheme of the newly added complaint work order if it is determined that the newly added complaint work order has an automatic processing condition according to the emotion classification of the customer. The embodiment of the disclosure can improve the processing efficiency of the complaint work order and reduce the labor cost.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of Internet, and particularly relates to a complaint work order processing method and device, a storage medium and an electronic device. BACKGROUND

[0002] An enterprise providing services to the outside world must face complaints, and the accepted complaints are numerous and complex. At present, the industry widely adopts intelligent classification of complaint work orders, quickly distributes the complaint work orders to professional processing teams, and then processes the complaint work orders manually. Obviously, the current method still relies heavily on manual work, and there is still a lot of redundant work, which reduces processing efficiency.

[0003] For example, a wide area broadband fault will simultaneously generate 10-20 or even more complaint work orders that cannot be self-repaired, and 2-3 people need to be arranged to manually process the 10-20 complaint work orders. The current method of distributing complaint work orders can only distribute related work orders to a complaint processing team responsible for broadband services, but still cannot reduce redundant work. SUMMARY

[0004] The present disclosure provides a complaint work order processing method, device, storage medium and electronic device, which at least partly solves the problem of low efficiency of manually processing complaint work orders in the related art.

[0005] According to a first aspect of the present disclosure, a complaint work order processing method is provided, comprising: obtaining a new complaint work order; determining whether the new complaint work order has a similar historical complaint work order; if the new complaint work order has a similar historical complaint work order, classifying the emotion of a customer of the new complaint work order; determining whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer; and outputting a complaint processing scheme of the new complaint work order if it is determined that the new complaint work order has an automatic processing condition according to the emotion classification of the customer.

[0006] Optionally, the method further comprises: after obtaining the new complaint work order, clustering the new complaint work order according to at least one feature of a business scenario, product information, complaint phenomenon, complaint content and user appeal to obtain at least two classes; determining the similarity between the class and a class of a historical complaint work order in a preset case library; and determining that the new complaint work order in the class has a similar historical complaint work order if there is a class of a historical complaint work order in the preset case library that is similar to the class with a similarity greater than a first threshold.

[0007] Optionally, the determining whether the new complaint work order has similar historical complaint work orders comprises: determining a similarity between the new complaint work order and historical complaint work orders in a preset case library; and if there is a historical complaint work order in the preset case library that has a similarity greater than a second threshold value with the new complaint work order, it is determined that the new complaint work order has similar historical complaint work orders.

[0008] Optionally, the classifying the emotion of the customer of the new complaint work order comprises: identifying an emotion state level of the customer according to the new complaint work order, wherein different emotion state levels represent degrees of non-negative or negative emotions expressed by the customer.

[0009] Optionally, the determining whether the new complaint work order has the automatic processing condition according to the emotion classification of the customer comprises: if the emotion classification of the customer belongs to non-negative or mild negative emotions, it is determined that the new complaint work order has the automatic processing condition.

[0010] Optionally, the method further comprises: after outputting the complaint processing scheme of the new complaint work order, establishing a session with the customer by calling the customer; collecting feedback information of the customer on the complaint processing scheme through the session; determining whether the new complaint work order is processed according to the feedback information; if it is determined that the new complaint work order is processed according to the feedback information, archiving the new complaint work order, and if it is determined that the new complaint work order is not processed according to the feedback information, dispatching the new complaint work order to a complaint processing node according to a preset strategy.

[0011] Optionally, the method further comprises: if the new complaint work order does not have similar historical complaint work orders or it is determined that the new complaint work order does not have the automatic processing condition according to the emotion classification of the customer, dispatching the new complaint work order to a complaint processing node according to a preset strategy; and if the new complaint work order has similar historical complaint work orders, sending information of the similar historical complaint work orders of the new complaint work order to the complaint processing node.

[0012] According to a second aspect of the present disclosure, a complaint work order processing device is also provided, comprising: an acquisition module configured to acquire a new complaint work order; a first determination module configured to determine whether the new complaint work order has similar historical complaint work orders; a classification module configured to classify an emotion of a customer of the new complaint work order if the new complaint work order has similar historical complaint work orders; a second determination module configured to determine whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer; and an output module configured to output a complaint processing scheme of the new complaint work order if it is determined that the new complaint work order has the automatic processing condition according to the emotion classification of the customer.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any of the complaint work order processing methods provided by the embodiments of the present disclosure via execution of the executable instructions.

[0014] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, having stored thereon a computer program, the computer program being executed by a processor to implement any of the complaint work order processing methods provided by the embodiments of the present disclosure.

[0015] The complaint work order processing method, device, storage medium and electronic device provided by the embodiments of the present disclosure, after obtaining the newly added complaint work order, determine whether the newly added complaint work order has a similar historical complaint work order, in the case that the newly added complaint work order has a similar historical complaint work order, further classify the emotion of the customer of the newly added complaint work order, to determine whether the newly added complaint work order meets the automatic processing condition according to the emotion classification of the customer, in the case that the newly added complaint work order meets the automatic processing condition, output the complaint processing scheme, so that the newly added complaint work order can be automatically processed based on the similarity between the newly added complaint work order and the historical complaint work order and the emotion of the customer, on the basis of improving the complaint processing efficiency, the probability of the complaint processing scheme being accepted by the customer is also improved.

[0016] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure. It is readily apparent to one of ordinary skill in the art that the accompanying drawings are merely exemplary of some embodiments of the present disclosure and are therefore not limiting of the scope of the present disclosure as encompassed by the appended claims.

[0018] Figure 1 is a flowchart of a complaint processing;

[0019] Figure 2 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure;

[0020] Figure 3 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure;

[0021] Figure 4 is a flowchart of determining whether a newly added complaint work order has a similar historical complaint work order according to one or more embodiments of the present disclosure;

[0022] Figure 5 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure;

[0023] Figure 6 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure;

[0024] Figure 7 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure;

[0025] Figure 8 is a structural schematic diagram of a complaint work order processing apparatus according to one or more embodiments of the present disclosure;

[0026] Figure 9 is a schematic diagram of processing a complaint work order by a complaint work order processing apparatus according to one or more embodiments of the present disclosure; and

[0027] Figure 10 is a structural schematic diagram of an electronic device according to one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0028] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations can be implemented in any

[0029] Moreover, the drawings represent a simplified diagram where only those components and features that are necessary to conceptually illustrate the examples are shown, and thus not all components and features of an actual implementation are necessarily shown. In addition, the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the examples. Like reference numerals can be used to denote like parts throughout the

[0030] Figure 1 is a flowchart of a complaint processing method, as Figure 1As shown, the customer 110 feeds back the complaint problem through a hotline or an Internet channel, complaint building 112 is performed according to the complaint problem and appeal fed back by the customer 110, the system stores the created complaint work order in clusters, and work order distribution 114 is performed according to a preset strategy; the complaint work order is distributed to the complaint handling personnel 116, the complaint handling personnel 116 performs work order processing 118 on the complaint work order, fills in a processing scheme, and revisits the customer according to the processing scheme; after the revisiting of the customer is completed, work order archiving 120 is performed.

[0031] As shown in the complaint handling mode, Figure 1 a large amount of manual participation is required, the labor cost consumption is large, and the efficiency is low. In view of this, the disclosure embodiment provides a complaint work order processing method.

[0032] Figure 2 is a flowchart of the complaint work order processing method according to one or more embodiments of the disclosure, as shown in Figure 2 the method comprises:

[0033] Step S202: acquiring a new complaint work order;

[0034] Optionally, the customer feeds back the complaint problem through a hotline or an Internet channel, and complaint building is performed according to the complaint problem fed back by the customer, and a new complaint work order is obtained. The new complaint work order includes but is not limited to: complaint content, business scenario, complaint phenomenon, customer appeal, and product information and the like.

[0035] Step S204: determining whether the new complaint work order has a similar historical complaint work order;

[0036] Optionally, the similarity between the new complaint work order and the historical complaint work order can be determined by comparing the characteristics of the new complaint work order with the characteristics of the historical complaint work order, to determine whether the new complaint work order has a similar historical complaint work order. The characteristics of the new complaint work order and the historical complaint work order include but are not limited to: complaint content, business scenario, complaint phenomenon, product information, and customer appeal. The historical complaint work order may be, for example, a classic historical complaint work order in a preset case library.

[0037] Step S206: if the new complaint work order has a similar historical complaint work order, classifying the emotion of the customer of the new complaint work order;

[0038] Optionally, if the new complaint work order has a similar historical complaint work order, it can be preliminarily determined that the new complaint work order can have an automatic processing solution, based on which, the emotion of the customer who sends the complaint can be further classified in combination with the information of the new complaint work order. Optionally, if the customer feeds back the complaint problem through a hotline, the emotion of the customer can be classified according to the tone, speed and words used by the customer to describe the complaint problem; if the customer feeds back the complaint problem in the form of text through an Internet channel, the text provided by the customer can be subjected to semantic recognition to identify keywords related to emotion, and the emotion of the customer can be classified based on the keywords.

[0039] Step S208: determining whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer;

[0040] Optionally, a corresponding relationship between different emotion classifications and whether the new complaint work order has an automatic processing condition can be established in advance, so that after the classification to which the emotion of the customer belongs is determined, whether the new complaint work order has an automatic processing condition can be directly determined according to the classification.

[0041] The emotion of the customer can reflect the attitude of the customer to the complaint problem he feeds back to a certain extent, if the customer's emotion is calm, the customer can be more likely to accept the automatic processing solution, if the customer's negative emotion is strong, the customer can be less likely to accept the automatic processing solution. Based on this, determining whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer can improve the probability that the complaint processing result is accepted by the customer.

[0042] Step S210: if it is determined that the new complaint work order has an automatic processing condition according to the emotion classification of the customer, outputting a complaint processing solution of the new complaint work order.

[0043] Optionally, a complaint processing model can be set in advance, which can include a complaint investigation information source system, an account period matching rule, a processing solution template and a refund execution rule, etc. The model can match the data in the preset case library according to the characteristics of the new complaint work order, so as to address to the complaint processing model, the complaint processing model can collect complaint investigation information, and the system can output a complaint processing solution according to the characteristics of the complaint processing model, wherein the characteristics of the complaint processing model include but are not limited to: complaint content keywords, work order labels, customer demands, product IDs and order numbers. The complaint processing solution can include complaint investigation information and a complaint settlement solution. The complaint investigation information required in the complaint processing process can include customer transaction record information, such as charge record, order record, etc. If the complaint involves a refund problem, the complaint investigation information can also include refund record information. The complaint settlement solution can include the processing mode, processing result, etc. of the new complaint work order.

[0044] The preset case library can store historical complaint case data, such as each record data of a historical complaint case. The data can include a business scenario, a service scenario, complaint content, customer appeal, product information, a processing scheme, a complaint work order label, and complaint archiving information, and the like. These data can be stored in a keyword granularity.

[0045] The complaint work order processing method provided in the embodiments of the present disclosure can determine whether the newly added complaint work order has a similar historical complaint work order after the newly added complaint work order is obtained. In the case that the newly added complaint work order has a similar historical complaint work order, the emotion of the customer of the newly added complaint work order is classified again to determine whether the newly added complaint work order meets the automatic processing condition according to the emotion classification of the customer. In the case that the newly added complaint work order meets the automatic processing condition, a complaint processing scheme is output, so that the newly added complaint work order can be automatically processed based on the similarity between the newly added complaint work order and the historical complaint work order and the emotion of the customer. On the basis of improving the complaint processing efficiency, the probability that the complaint processing scheme is accepted by the customer is also improved.

[0046] Figure 3 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure, as shown in Figure 3 The method can further include the following steps based on the method shown in Figure 2

[0047] Step S302: After obtaining the newly added complaint work order, the newly added complaint work order is clustered according to at least one feature in a business scenario, product information, complaint phenomenon, complaint content, and customer appeal, to obtain at least two classes.

[0048] Step S304: Determine the similarity between the class and the class of the historical complaint work order in the preset case library.

[0049] Optionally, the historical complaint work order in the preset case library can also be clustered according to at least one feature in a business scenario, product information, complaint phenomenon, complaint content, and customer appeal, to obtain a plurality of classes corresponding to the historical complaint work order. In order to improve the accuracy of the similarity between the class of the newly added complaint work order and the class of the historical complaint work order, the same feature and the same clustering algorithm can be selected to cluster the newly added complaint work order and the historical complaint work order, respectively.

[0050] The similarity between the class of the newly added complaint work order and the class of the historical complaint work order can be determined by using the existing distance calculation method between clusters, which is not described herein again.

[0051] ​Step S306: If there is a class in the preset case library that has a similarity greater than the first threshold with the class of the new complaint ticket, it is determined that the new complaint ticket has a similar historical complaint ticket in the class.

[0052] Optionally, if there is no class in the preset case library that has a similarity greater than the first threshold with the class of the new complaint ticket, the similarity between the new complaint ticket and the historical complaint ticket in the preset case library can be determined, and whether there is a similar historical complaint ticket to the new complaint ticket can be determined by determining whether there is a historical complaint ticket in the preset case library that has a similarity greater than the second threshold with the new complaint ticket.

[0053] For example, the second threshold can be the same as the first threshold, or the second threshold can be greater than the first threshold. For example, the first threshold can be 85%, and the second threshold can be set based on the value of the first threshold.

[0054] In one or more embodiments of the present disclosure, as shown in Figure 4 determining whether the new complaint ticket has a similar historical complaint ticket can include:

[0055] Step S1042: determining the similarity between the new complaint ticket and the historical complaint ticket in the preset case library;

[0056] Optionally, the similarity between the new complaint ticket and the historical complaint ticket in the preset case library can be determined according to the characteristics of the new complaint ticket, such as business scenarios, complaint products, complaint phenomena, complaint content, and customer demands.

[0057] Step S1044: If there is a historical complaint ticket in the preset case library that has a similarity greater than the second threshold with the new complaint ticket, it is determined that the new complaint ticket has a similar historical complaint ticket.

[0058] Optionally, the preset case library can store clustered historical complaint tickets, or store unclustered historical complaint tickets, or can simultaneously store part of the clustered historical complaint tickets and part of the unclustered historical complaint tickets.

[0059] In one or more embodiments of the present disclosure, if the new complaint ticket has a similar historical complaint ticket, classifying the emotion of the customer of the new complaint ticket can include:

[0060] According to the new complaint ticket, the emotional state level of the customer is identified, wherein different emotional state levels represent the degree of non-negative or negative emotions expressed by the customer.

[0061] Optionally, the customer complaint content can be provided in the form of a voice message or in the form of text information. If the complaint content is provided in the form of a voice message, semantic recognition can be performed on the voice message to obtain text information, the emotion-related words contained in the text information are recognized to obtain a keyword recognition result, and at the same time, speech speed recognition and tone recognition are performed on the voice message to obtain a speech speed recognition result and a tone recognition result, respectively. The keyword recognition result, the speech speed recognition result, and the tone recognition result can be weighted and summed according to the weights corresponding to the keyword recognition result, the weights corresponding to the speech speed recognition result, and the weights corresponding to the tone recognition result, to obtain an index for representing the customer emotion classification, and the customer emotion state level is determined. If the customer complaint content is provided in the form of text information, semantic recognition can be performed on the text information to recognize the emotion-related words contained in the text information to obtain a keyword recognition result, and the customer emotion state level is determined according to the keyword recognition result.

[0062] Alternatively, when the customer emotion state level is recognized, the emotion-related features in the new complaint work order, such as the emotion-related keywords, the speech speed, and the tone, can be extracted, and these features can be input into a pre-trained emotion recognition model. The emotion recognition model can output an emotion state level, which can include light joy, general, light aversion, aversion, or strong negative emotion.

[0063] In one or more embodiments of the present disclosure, determining whether the new complaint work order meets the automatic processing condition according to the customer emotion classification can include:

[0064] If the customer emotion classification belongs to a non-negative emotion or a light negative emotion, it is determined that the new complaint work order meets the automatic processing condition.

[0065] Optionally, the non-negative emotion can include light joy and general in the above emotion state level, and the light negative emotion can include light aversion in the above emotion state level. If the customer emotion classification belongs to a negative emotion, such as aversion and strong negative emotion in the above emotion classification, it is determined that the new complaint work order does not meet the automatic processing condition.

[0066] Optionally, after it is determined that the new complaint work order meets the automatic processing condition, a complaint processing scheme for the new complaint work order can be further generated according to the features of the new complaint work order and in combination with the processing flow of a historical complaint work order similar to the new complaint work order. If the complaint problem in the new complaint work order needs to be processed, for example, the complaint problem is a network failure, the processing of the complaint problem in the new complaint work order can be performed by referring to the processing flow of the historical complaint work order similar to the new complaint work order.

[0067] Figure 5is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure, as shown in Figure 5 The method can further include, based on the method shown in Figure 2 The method can further include, based on the method shown in

[0068] Step S502: After outputting the complaint processing solution of the new complaint work order, a session is established with the customer by calling the customer;

[0069] Optionally, the customer of the new complaint order can be called to establish a voice call or an instant chat session to inquire whether the customer accepts the complaint processing solution and whether the complaint problem is solved.

[0070] Step S504: Feedback information of the customer on the complaint processing solution is collected through the session;

[0071] Step S506: Whether the new complaint work order is processed is determined according to the feedback information;

[0072] Optionally, the session content of the customer can be text extracted and semantically recognized to determine whether the customer accepts the complaint processing solution and whether the complaint problem of the customer is solved. If it is determined according to the feedback information of the user that the customer accepts the complaint processing solution or the complaint problem of the customer is solved, it can be determined that the new complaint work order is processed. In addition, the emotion of the customer can be determined based on the session with the customer. If the customer expresses dissatisfaction or emotional fluctuation, the complaint work order of the customer can be assigned to the complaint processing personnel for secondary complaint processing. The recognition of the emotion of the customer can still be realized by using the emotion recognition model described above, which will not be described here.

[0073] Step S508: If it is determined according to the feedback information that the new complaint work order is processed, the new complaint work order is archived. If it is determined according to the content of the feedback information that the new complaint work order is not processed, the new complaint work order is assigned to a complaint processing node according to a preset strategy.

[0074] Optionally, if it is determined according to the feedback information of the customer that the new complaint work order is processed, the work order and the complaint processing solution corresponding to the work order can be stored in a preset case library. Thus, the case library can be enriched, more automatic processing solutions for complaint problems can be quickly put online, and the operation cost can be reduced.

[0075] Optionally, if it is determined according to the feedback information of the customer that the customer does not accept the complaint processing scheme or the problem complained by the customer is not solved, it is determined that the newly added complaint work order is not processed. In this case, according to a preset strategy for distributing complaint work orders in the system, the newly added complaint work order can be distributed to a complaint processing node for manual processing of the newly added complaint order, so that the complaint work order can be effectively processed. The complaint processing node can be an electronic device used by a complaint processing personnel to process the complaint work order. The preset strategy can distribute the complaint work order to the electronic device of the corresponding complaint processing personnel according to the characteristics of the newly added complaint work order.

[0076] Figure 6 is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure, as shown in Figure 6 , the method comprises:

[0077] Step S602: If the newly added complaint work order does not have a similar historical complaint work order or it is determined according to the emotional classification of the customer that the newly added complaint work order does not have automatic processing conditions, the newly added complaint work order is distributed to a complaint processing node according to a preset strategy.

[0078] When it is determined according to the emotional classification of the customer that the newly added complaint work order does not have automatic processing conditions, the newly added complaint work order is distributed to the complaint processing node according to the preset strategy, so that the difficult complaint work order that cannot be automatically processed can be distributed to the complaint processing personnel for processing of the complaint by the complaint processing personnel. It can be seen that the complaint work order processing method based on the embodiments of the present disclosure can only manually process part of the newly added complaint work orders that do not have automatic processing conditions, and the rest of the complaint work orders can be automatically processed, which can effectively improve the processing efficiency of the complaint work orders.

[0079] Step S604: If the newly added complaint work order has a similar historical complaint work order, the information of the historical complaint work order similar to the newly added complaint work order is sent to the complaint processing node.

[0080] Optionally, after it is determined according to the emotional classification of the customer of the newly added complaint work order that the newly added complaint work order does not have automatic processing conditions, the information of the historical complaint work order similar to the newly added complaint work order can be sent to the complaint processing node together with the newly added complaint work order. For example, when the complaint processing personnel of the complaint processing node opens the newly added complaint work order, the system prompts that the newly added complaint work order has a similar historical complaint work order, so that the complaint processing personnel can refer to the complaint processing scheme of the historical complaint work order when processing the newly added complaint work order, thereby improving the efficiency of manually processing the newly added complaint work order. The information of the historical complaint work order may, for example, include the case number of the historical complaint work order.

[0081] Figure 7is a flowchart of a complaint work order processing method according to one or more embodiments of the present disclosure, as shown in Figure 7 The method can include a work order clustering pre-judgment stage, an automatic execution judgment stage, and a complaint processing automation stage.

[0082] As shown in Figure 7 The work order clustering pre-judgment stage includes: step S702: clustering the complaint work order by a work order intelligent classification model to form a data warehouse, the data warehouse including at least two types of complaint work orders;

[0083] The automatic execution judgment stage includes: step S704: determining whether there is a similar historical complaint work order in the case library; if so, configuring the automatic processing parameters for the complaint work order, so that the complaint work order can be automatically processed; step S706: determining the classification to which the customer emotion belongs according to the complaint work order, and determining whether the complaint work order meets the automatic processing condition according to the classification to which the customer emotion belongs.

[0084] Among them, determining the classification to which the customer emotion belongs can include: performing semantic recognition on the voice message of the customer to obtain text information, recognizing the emotion-related words contained in the text information to obtain a keyword recognition result, and simultaneously performing speech speed recognition and tone recognition on the voice message to obtain a speech speed recognition result and a tone recognition result, respectively. According to the keyword recognition result, the speech speed recognition result, and the tone recognition result, the classification to which the customer emotion belongs is determined; or performing semantic recognition on the text information in the user complaint content, recognizing the emotion-related words contained in the text information to obtain a keyword recognition result, and determining the classification to which the customer emotion belongs according to the keyword recognition result. According to the classification to which the customer emotion belongs, it is determined whether the complaint work order meets the automatic processing condition.

[0085] The complaint processing automation stage includes: step S708: if the complaint work order meets the automatic processing condition, automatically processing the complaint work order;

[0086] Step S710: outputting a complaint processing scheme and actively calling the customer;

[0087] Step S712: if the customer accepts the complaint processing scheme, closing and archiving the complaint work order.

[0088] Step S714: if the complaint work order does not meet the automatic processing condition, returning the complaint work order to the original processing flow for work order processing (i.e., a process of manually processing the complaint work order).

[0089] Figure 8 is a structural schematic diagram of a complaint work order processing device according to one or more embodiments of the present disclosure, as shown in Figure 8 The device 810 includes:

[0090] The acquisition module 812 is configured to acquire a newly added complaint work order.

[0091] The first determination module 814 is configured to determine whether the newly added complaint work order has a similar historical complaint work order.

[0092] The classification module 816 is configured to, if the newly added complaint work order has a similar historical complaint work order, classify the emotion of a customer of the newly added complaint work order.

[0093] The second determination module 818 is configured to determine whether the newly added complaint work order has an automatic processing condition according to the emotion classification of the customer.

[0094] The output module 820 is configured to, if it is determined that the newly added complaint work order has an automatic processing condition according to the emotion classification of the customer, output a complaint processing scheme of the newly added complaint work order.

[0095] In one or more embodiments of the present disclosure, the apparatus can further include:

[0096] The clustering module is configured to, after acquiring the newly added complaint work order, cluster the newly added complaint work order according to at least one feature in a business scenario, product information, a complaint phenomenon, complaint content, and user appeal, to obtain at least two classes.

[0097] The third determination module is configured to determine a similarity between the class and a class of a historical complaint work order in a preset case library.

[0098] The fourth determination module is configured to, if there is a class of a historical complaint work order in the preset case library that is similar to the class and has a similarity greater than a first threshold value, determine that the newly added complaint work order in the class has a similar historical complaint work order.

[0099] In one or more embodiments of the present disclosure, the first determination module can be specifically configured to:

[0100] Determine a similarity between the newly added complaint work order and a historical complaint work order in a preset case library.

[0101] If there is a historical complaint work order in the preset case library that is similar to the newly added complaint work order and has a similarity greater than a second threshold value, determine that the newly added complaint work order has a similar historical complaint work order.

[0102] In one or more embodiments of the present disclosure, the classification module can be specifically configured to:

[0103] Identify an emotion state level of the customer in the newly added complaint work order, wherein different emotion state levels represent degrees of non-negative or negative emotions expressed by the customer.

[0104] In one or more embodiments of the present disclosure, the second determining module can be specifically used for:

[0105] If the emotion classification of the customer belongs to non-negative emotion or mild negative emotion, it is determined that the new complaint work order has an automatic processing condition.

[0106] In one or more embodiments of the present disclosure, the device can further include:

[0107] A session module, configured to establish a session with the customer by calling the customer after outputting the complaint processing scheme of the new complaint work order;

[0108] A collection module, configured to collect feedback information of the customer on the complaint processing scheme through the session;

[0109] A fifth determining module, configured to determine whether the new complaint work order is processed according to the feedback information;

[0110] A control module, configured to archive the new complaint work order if it is determined that the new complaint work order is processed according to the feedback information, and dispatch the new complaint work order to a complaint processing node according to a preset strategy if it is determined that the new complaint work order is not processed according to the feedback information.

[0111] In one or more embodiments of the present disclosure, the device can further include:

[0112] A dispatching module, configured to dispatch the new complaint work order to a complaint processing node according to a preset strategy if the new complaint work order does not have a similar historical complaint work order or it is determined that the new complaint work order does not have an automatic processing condition according to the emotion classification of the customer;

[0113] A sending module, configured to send information of the historical complaint work order similar to the new complaint work order to the complaint processing node if the new complaint work order has a similar historical complaint work order.

[0114] Figure 9 is a schematic diagram of a complaint work order processing device according to one or more embodiments of the present disclosure, which processes a complaint work order, as shown in Figure 9 The complaint work order processing flow can include that a customer 912 initiates a complaint, performs complaint order building 914, an automatic processing module 916 performs automatic processing on the complaint work order, performs work order dispatching 918 on the complaint work order if the complaint work order cannot be automatically processed, a complaint processing personnel 920 processes the complaint work order 922, and archives the complaint work order 924 after the complaint work order is processed.

[0115] The automatic processing module 916 can be used to determine whether the complaint work order meets the conditions for automatic processing, and to automatically process the complaint work order when the complaint work order meets the conditions for automatic processing.

[0116] As shown in Figure 9 The complaint work order processing device includes an automatic processing module 916, a case library module 926, an emotion recognition module 928, an automatic execution module 930, an intelligent outbound call module 932, and a model module 934.

[0117] The case library module 926 is used to store complaint case data, determine whether the complaint work order has a similar case and whether it meets the conditions for automatic processing. After the complaint work order 914 is obtained, the complaint work order can be matched with historical cases (including historical complaint work orders and processing information of the historical complaint work orders) in the case library module 926 to determine whether the complaint work order has a similar historical complaint work order. If there is no similar historical complaint work order in the case library module, it is determined that the complaint work order is not an automatically executable case, and the complaint work order is sent to the work order assignment 918.

[0118] The emotion recognition module 928 identifies the emotional state of the customer of the complaint work order based on a customer emotion recognition model, and determines whether the complaint work order can be automatically executed according to the emotional state of the customer. If the customer's emotions fluctuate greatly, the customer is determined to be a sensitive customer, and the complaint work order is sent to the work order assignment 918, so that the complaint work order returns to the original complaint processing flow and is assigned to a complaint processing personnel.

[0119] The automatic execution module 930 is used to generate a complaint processing scheme according to a preset rule.

[0120] The intelligent outbound call module 932 is used to make outbound calls according to the complaint processing scheme output by the automatic execution module 930 and collect customer feedback information. If it is determined that the customer accepts the complaint processing scheme according to the customer feedback information, the complaint work order is archived 924. If the customer expresses dissatisfaction or emotional fluctuations, the complaint work order is sent to the work order assignment 918 so that the complaint work order returns to the original complaint processing flow for secondary complaint processing.

[0121] The model module 934 stores models for intelligent classification of operation management work orders, emotion recognition, automatic execution of work orders, and intelligent outbound calls. The intelligent classification model can be used to cluster the new complaint work order according to at least one of the features of a business scenario, product information, complaint phenomenon, complaint content, and user demand, to obtain at least two classes. The function of the emotion recognition model is described in detail above and will not be repeated here. The automatic execution model of the work order is used to automatically process the complaint work order according to the features of the complaint work order and the processing flow of a historical complaint case similar to the complaint work order. The intelligent outbound call model is used to actively call the customer after outputting the complaint processing scheme to collect feedback from the customer.

[0122] The electronic device 1000 according to this embodiment of the present application will be described below with reference to Figure 10 Figure 10 The electronic device 1000 shown is merely an example and should not limit the function and scope of use of the embodiments of the present application.

[0123] As shown in Figure 10 , the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 can include, but are not limited to, the at least one processing unit 1010 described above, the at least one storage unit 1020 described above, and a bus 1030 connecting different system components, including the storage unit 1020 and the processing unit 1010.

[0124] The storage unit stores program code that can be executed by the electronic device 1000, so that the electronic device 1000 performs the steps described in the above "Exemplary Method" section according to various exemplary embodiments of the present application.

[0125] The storage unit 1020 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 10201 and / or a cache memory unit 10202, and can further include a read-only memory (ROM) 10203.

[0126] The storage unit 1020 can also include a program / utility 10204 having a set of program modules 10205, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof can include implementation of a network environment.

[0127] ​Bus 1030 can be one of several types of bus structure, including a storage bus or bus for a storage controller, a peripheral bus, a graphics acceleration port, a processor bus, or a local bus using any of a variety of bus architectures.

[0128] Electronic device 1000 can also communicate with one or more external devices 1100, such as a keyboard or a pointing device, using one or more input / output (I / O) interfaces 1050. I / O interfaces 1050 can include, for example, a serial port, parallel port, and / or a USB port.

[0129] In exemplary embodiments of the present disclosure, a computer readable storage medium having stored thereon a program product capable of implementing the above-described methods of the specification is also provided. In some possible implementations, various aspects of the present disclosure can also be implemented in the form of a program product including a program code that, when run on a terminal device, causes the terminal device to perform the steps described in the above "Exemplary Methods" section according to various exemplary embodiments of the present disclosure.

[0130] A program product for implementing the above-described methods according to embodiments of the present disclosure is described, which can take the form of a portable compact disc read-only memory (CD-ROM) and include program code and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in the present document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0131] The program product can take any combination of one or more computer-readable media. The computer-readable media can be a computer-readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] The computer-readable signal medium can include a computer-readable storage medium that is propagated as a carrier wave. The computer-readable signal medium can further be any computer-readable medium that is not a storage medium. The computer-readable signal medium can be a computer-readable storage medium that is a propagated signal on a computer-readable storage medium.

[0133] The program code embodied on the computer-readable media can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0134] The program code can be executed by one or more programmable processors, which can be individual or grouped processors, to perform the operations of the embodiments. The program code can execute entirely on a user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider (ISP).

[0135] It should be noted that, although the above detailed description refers to several modules or units of the device for action execution, such a division is not mandatory. Indeed, according to an embodiment of the present disclosure, features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, features and functionalities of one module or unit described above can be further divided into several modules or units embodied.

[0136] Moreover, although individual steps of the methods in the present disclosure are described in a particular order in the drawings, this is not required or implied as to the order of the steps, nor is it required that all of the steps be performed to achieve the desired result. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, one step can be broken into multiple steps, etc.

[0137] From the above description of the embodiments, those skilled in the art will readily perceive that the example embodiments described herein can be implemented by software and / or by software in combination with the necessary hardware. Thus, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0138] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure following the general principles thereof and including such departures from the present disclosure that come within known use or custom in the art to which the present disclosure pertains. The specification and examples are to be regarded as illustrative only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A complaint ticket processing method, characterized by, The method comprises the following steps: acquiring a new complaint work order; determining whether the new complaint work order has a similar historical complaint work order; if the new complaint work order has a similar historical complaint work order, classifying the emotion of a customer of the new complaint work order; determining whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer; if it is determined that the new complaint work order has an automatic processing condition according to the emotion classification of the customer, outputting a complaint processing scheme of the new complaint work order; wherein classifying the emotion of the customer of the new complaint work order comprises: if the customer feeds back a complaint problem through a hotline, classifying the emotion of the customer according to the tone, speed and words used by the customer in narrating the complaint problem; if the customer feeds back a complaint problem in the form of text through an Internet channel, performing semantic recognition on the text provided by the customer, identifying emotion-related keywords, and classifying the emotion of the customer based on the keywords; wherein determining whether the new complaint work order has a similar historical complaint work order comprises: clustering the new complaint work order according to at least one feature of a business scenario, product information, a complaint phenomenon, complaint content and user demand to obtain at least two classes; determining the similarity between the class and a class of a historical complaint work order in a preset case library; if there is a class of a historical complaint work order in the preset case library that is similar to the class and has a similarity greater than a first threshold value, it is determined that the new complaint work order in the class has a similar historical complaint work order; if there is no class of a historical complaint work order in the preset case library that is similar to the class and has a similarity greater than the first threshold value, the similarity between the new complaint work order and a historical complaint work order in the preset case library is determined; if there is a historical complaint work order in the preset case library that is similar to the new complaint work order and has a similarity greater than a second threshold value, it is determined that the new complaint work order has a similar historical complaint work order.

2. The method of claim 1, wherein, Classifying the emotion of the customer of the new complaint work order comprises: identifying the emotion state level of the customer according to the new complaint work order, wherein different emotion state levels represent the degree of non-negative or negative emotion expressed by the customer.

3. The method of claim 2, wherein, Determining whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer comprises: if the emotion classification of the customer belongs to non-negative emotion or mild negative emotion, it is determined that the new complaint work order has an automatic processing condition.

4. The method of claim 1, wherein, The method further comprises: after outputting the complaint processing scheme of the new complaint work order, establishing a session with the customer by calling the customer; collecting feedback information of the customer on the complaint processing scheme through the session; determining whether the new complaint work order is processed according to the feedback information; if it is determined that the new complaint work order is processed according to the feedback information, archiving the new complaint work order; if it is determined that the new complaint work order is not processed according to the feedback information, distributing the new complaint work order to a complaint processing node according to a preset strategy.

5. The method of claim 1, wherein, The method further comprises: If the new complaint work order does not have a similar historical complaint work order or is determined not to have an automatic processing condition according to the emotion classification of the customer, the new complaint work order is dispatched to a complaint processing node according to a preset strategy; If the new complaint work order has a similar historical complaint work order, information of the similar historical complaint work order of the new complaint work order is sent to the complaint processing node.

6. A complaint ticket processing apparatus characterized by comprising: The method comprises: an acquisition module, configured to acquire a new complaint work order; a first determination module, configured to determine whether the new complaint work order has a similar historical complaint work order; a classification module, configured to, if the new complaint work order has a similar historical complaint work order, classify an emotion of a customer of the new complaint work order; a second determination module, configured to determine whether the new complaint work order has an automatic processing condition according to the emotion classification of the customer; an output module, configured to, if the new complaint work order is determined to have an automatic processing condition according to the emotion classification of the customer, output a complaint processing scheme of the new complaint work order; wherein the classification module is further configured to, if the customer feeds back a complaint problem through a hotline, classify the emotion of the customer according to a tone, a speed and words used by the customer in narrating the complaint problem; and if the customer feeds back a complaint problem in the form of text through an Internet channel, perform semantic recognition on the text provided by the customer, identify emotion-related keywords, and classify the emotion of the customer based on the keywords; wherein the first determination module is further configured to cluster the new complaint work order according to at least one feature in a business scenario, product information, a complaint phenomenon, complaint content and user appeal, to obtain at least two classes; determine a similarity between the class and a class of a historical complaint work order in a preset case library; if there is a class of a historical complaint work order in the preset case library that is similar to the class and has a similarity greater than a first threshold value, it is determined that the new complaint work order in the class has a similar historical complaint work order; if there is no class of a historical complaint work order in the preset case library that is similar to the class and has a similarity greater than the first threshold value, a similarity between the new complaint work order and a historical complaint work order in the preset case library is determined; and if there is a historical complaint work order in the preset case library that is similar to the new complaint work order and has a similarity greater than a second threshold value, it is determined that the new complaint work order has a similar historical complaint work order.

7. An electronic device, comprising: The method comprises: a processor; and a memory, configured to store executable instructions of the processor; wherein the processor is configured to execute the complaint work order processing method of any one of claims 1-5 by executing the executable instructions.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the complaint work order processing method of any one of claims 1-5.

Images