User complaint accountability method, device, storage medium and apparatus

Abstract

The application discloses a user complaint responsibility determination method and device, a storage medium and an apparatus, and relates to the technical field of user complaint responsibility determination.The method comprises the following steps: acquiring user complaint data, and performing complaint service tracing according to the user complaint data to determine a complained service, judging whether a service handling file corresponding to the complained service exists in a preset database, when the service handling file exists, performing standard identification on the service handling file to obtain an identification result, and determining the responsibility for a user complaint corresponding to the user complaint data according to the identification result.Compared with the prior art that relies on manual identification of the responsibility subject of a user complaint, the application can automatically trace the complained service corresponding to the user complaint data, detect the service handling file of the complained service, and determine the responsibility based on the detection result, so that the efficiency of complaint responsibility determination is improved and the accuracy of responsibility determination is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a user complaint responsibility determination method, device, storage medium and apparatus. BACKGROUND

[0002] At present, the responsibility subject of user complaint is mainly determined by manual identification. However, the manual identification method has defects of high cost and low processing efficiency, and the subjective factor of manual identification is strong, and a unified identification standard cannot be formed, and misjudgment is prone to occur.

[0003] The above content is only used to assist in understanding the technical solutions of the present application, and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a user complaint responsibility determination method, device, storage medium and apparatus, which aims to solve the technical problems of high cost, low processing efficiency and easy misjudgment in the prior art by relying on manual identification of the responsibility subject of user complaint.

[0005] To achieve the above purpose, the present application provides a user complaint responsibility determination method, which comprises the following steps:

[0006] Obtaining user complaint data, and performing complaint business traceability according to the user complaint data to determine a complained business;

[0007] Judging whether a business handling file corresponding to the complained business exists in a preset database;

[0008] When the business handling file exists, performing standard identification on the business handling file to obtain an identification result;

[0009] According to the identification result, responsibility of a user complaint corresponding to the user complaint data is determined.

[0010] Optionally, the step of performing standard identification on the business handling file to obtain an identification result when the business handling file exists specifically comprises:

[0011] When the business handling file exists, extracting a business handling audio and a business handling agreement from the business handling file;

[0012] Performing audio extraction on the business handling audio to obtain audio content corresponding to the business handling audio;

[0013] Performing character recognition on the business handling agreement to obtain agreement text corresponding to the business handling agreement;

[0014] The recording content and the protocol text are subjected to normative recognition to obtain a recognition result.

[0015] Optionally, the step of subjecting the recording content and the protocol text to normative recognition to obtain a recognition result specifically comprises:

[0016] A recording keyword is extracted from the recording content, and the recording content is subjected to normative recognition based on the recording keyword to obtain a recording normative recognition result.

[0017] A protocol signature is extracted from the protocol text, and the protocol signature is matched with a user name to obtain a protocol normative recognition result.

[0018] The recognition result is generated according to the recording normative recognition result and the protocol normative recognition result.

[0019] Optionally, after the step of subjecting the business handling file to normative recognition to obtain a recognition result when the business handling file exists, the user complaint responsibility determination method further comprises:

[0020] The user complaint data is subjected to data extraction to obtain actual product information of a user.

[0021] Product design information corresponding to the complained business is searched for, and it is determined whether the complained business has a design defect according to the product design information and the actual product information to obtain a determination result.

[0022] Correspondingly, the step of determining responsibility for a user complaint corresponding to the user complaint data according to the recognition result specifically comprises:

[0023] The user complaint corresponding to the user complaint data is subjected to responsibility determination according to the determination result and the recognition result.

[0024] Optionally, the step of searching for product design information corresponding to the complained business, and determining whether the complained business has a design defect according to the product design information and the actual product information to obtain a determination result specifically comprises:

[0025] The product design information corresponding to the complained business is searched for, and the product design information is matched with the actual product information to obtain a matching result.

[0026] The number of complaints corresponding to the complained business is searched for, and it is determined whether the number of complaints is greater than a preset threshold to obtain a number of complaints determination result.

[0027] It is determined whether the complained business has a design defect according to the matching result and the number of complaints determination result to obtain a determination result.

[0028] Optionally, after the step of identifying the responsibility of the user complaint corresponding to the user complaint data according to the identification result, the complaint processing method further comprises:

[0029] determining the responsible subject of the complained business and the rectification information to be made according to the responsibility identification result;

[0030] sending the rectification information to be made to the terminal device corresponding to the responsible subject.

[0031] Optionally, after the step of sending the complaint investigation result to the terminal device corresponding to the responsible subject, the complaint processing method further comprises:

[0032] receiving the responsibility evaluation score fed back by the responsible subject according to the rectification information to be made, and generating a responsibility optimization strategy according to the responsibility evaluation score;

[0033] establishing a corresponding relationship between the responsibility optimization strategy and the complained business, and storing the corresponding relationship in the preset database.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a user complaint responsibility determination device, which comprises a memory, a processor and a user complaint responsibility determination program stored in the memory and executable on the processor. The user complaint responsibility determination program is configured to implement the steps of the user complaint responsibility determination method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which stores a user complaint responsibility determination program. When the user complaint responsibility determination program is executed by a processor, it implements the steps of the user complaint responsibility determination method as described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a user complaint responsibility determination device, which comprises a traceability module, a judgment module, an identification module and an identification module.

[0037] The traceability module is configured to obtain user complaint data and perform complaint business traceability according to the user complaint data to determine the complained business.

[0038] The judgment module is configured to determine whether the business handling file corresponding to the complained business exists in the preset database.

[0039] The identification module is configured to, when the business handling file exists, perform normative identification on the business handling file to obtain an identification result.

[0040] The determining module is configured to determine the responsibility for the user complaint corresponding to the user complaint data according to the identification result.

[0041] The present application can automatically trace the complained business corresponding to the user complaint data, and detect the business handling file of the complained business, and determine the responsibility based on the detection result, thereby improving the efficiency of complaint determination of responsibility and ensuring the accuracy of responsibility determination. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 is a structural schematic diagram of a user complaint determination device of a hardware running environment related to the embodiment scheme of the present application.

[0043] Figure 2 is a flowchart of a first embodiment of the user complaint determination method of the present application.

[0044] Figure 3 is a flowchart of a second embodiment of the user complaint determination method of the present application.

[0045] Figure 4 is a flowchart of a third embodiment of the user complaint determination method of the present application.

[0046] Figure 5 is a structural block diagram of a first embodiment of the user complaint determination device of the present application.

[0047] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0049] Reference Figure 1 , Figure 1 is a structural schematic diagram of a user complaint determination device of a hardware running environment related to the embodiment scheme of the present application.

[0050] As Figure 1As shown, the user complaint responsibility determination device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection communication between the components. The user interface 1003 can include a display screen (Display), and the optional user interface 1003 can further include a standard wired interface, a wireless interface. The wired interface of the user interface 1003 can be a USB interface in the present application. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 can be a high-speed random access memory (RAM) memory, and can also be a stable memory (Non-volatile Memory, NVM), such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0051] Those skilled in the art can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the user complaint responsibility determination device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0052] As Figure 1 As shown, the memory 1005, which is a computer storage medium, can include an operating system, a network communication module, a user interface module, and a user complaint responsibility determination program.

[0053] In Figure 1 In the user complaint responsibility determination device shown, the network interface 1004 is mainly used to connect to a background server and communicate data with the background server; the user interface 1003 is mainly used to connect to a user device; the user complaint responsibility determination device calls the user complaint responsibility determination program stored in the memory 1005 through the processor 1001, and executes the user complaint responsibility determination method provided by the embodiment of the present application.

[0054] Based on the above hardware structure, an embodiment of the user complaint responsibility determination method of the present application is proposed.

[0055] Referring to Figure 2 , Figure 2 The flowchart of the first embodiment of the user complaint responsibility determination method of the present application is proposed.

[0056] Step S10: Obtain user complaint data, and perform complaint service traceability according to the user complaint data to determine the complained service.

[0057] It should be understood that the execution subject of the embodiment can be the user complaint accountability device described above, wherein the user complaint accountability device can be a computing service device with data processing, network communication and program running functions, such as a tablet computer and a personal computer, and the execution subject can also be other electronic devices that can realize the same or similar functions, and the embodiment does not limit this. In the embodiment and each of the following embodiments, the user complaint accountability method of the application is described by taking the user complaint accountability device as an example.

[0058] It should be noted that the user complaint data includes complaint user information, user complaint time, and a complained business number, etc. The complained business number is used to identify the specific business complained by the user.

[0059] It can be understood that the user complaint data can be obtained through a complaint request uploaded by a complaint platform. The complaint platform can be an information platform that has established a communication connection with the user complaint accountability device in advance, and the user can initiate a complaint request through the complaint platform.

[0060] It should be understood that the complaint business traceability according to the user complaint data is to determine the complained business, which can be to extract the complained business number from the user complaint data and determine the complained business according to the complained business number.

[0061] Step S20: determining whether the business handling file corresponding to the complained business exists in the preset database.

[0062] It should be noted that the business handling file can be various process files of the user when handling the business, for example, the business handling file can be at least one of a business handling recording, a business handling agreement and a business handling image. In the embodiment and other embodiments, the business handling recording and the business handling agreement are taken as examples for description.

[0063] The business handling recording can be a call recording of the user when handling the business, the business handling agreement can be a business agreement signed by the user when handling the business, and the business handling image can be a verification picture taken by the user when handling the business.

[0064] It should be understood that whether the business handling file exists in the preset database is an important reference basis for determining whether the user handles the business independently. Therefore, it is necessary to determine whether the business handling organization handling the complained business is accountable by judging whether the business handling file corresponding to the complained business exists in the preset database.

[0065] It should be noted that the business handling organization can be a service organization for handling the business of the user, for example, an online customer service organization and a store customer service organization, etc.

[0066] It can be understood that the complained business can be determined to correspond to a business handling channel through complaint business traceability, and a business handling organization handling the complained business can be determined according to the business handling channel. The business handling channel can be a channel used by the user to handle the business, for example, an online handling channel and an offline handling channel.

[0067] It should be understood that when the business handling document does not exist, it indicates that the business handling organization may have handled the business for the user without the user's knowledge, and at this time, the business handling organization handling the complained business can be directly determined as the responsible subject.

[0068] In a specific implementation, for example, it is determined whether the business handling audio corresponding to the complained business exists in the preset database, and it is determined whether the business handling agreement corresponding to the complained business exists in the preset database. When the business handling audio or the business handling agreement does not exist, it indicates that the business handling process of the business handling organization does not conform to the specification, and the business handling organization handling the complained business is determined as the responsible subject of the complained business, and the business handling process is rectified as the to-be-rectified information.

[0069] Step S30: When the business handling document exists, performing specification identification on the business handling document to obtain an identification result.

[0070] It should be understood that when the business handling document exists, the business handling organization handling the complained business cannot be directly determined as not responsible. This is because there is also a situation that the business handling content of the business handling organization does not conform to the specification, and therefore, the business handling document needs to be subjected to specification identification to obtain an identification result.

[0071] It can be understood that the specification identification on the business handling document to obtain the identification result can be matching the business handling document with a preset file template, and performing specification identification on the business handling document according to a matching result to obtain the identification result. The preset file template can be preset by a management personnel of the user complaint responsibility determination device.

[0072] Further, in order to be able to adaptively perform specification identification on the business handling document, the step S30 comprises:

[0073] Step S301: When the business handling document exists, extracting a business handling audio and a business handling agreement from the business handling document;

[0074] Step S302: Performing audio extraction on the business handling audio to obtain audio content corresponding to the business handling audio;

[0075] Step S303: Performing character recognition on the business handling agreement to obtain agreement text corresponding to the business handling agreement;

[0076] Step S304: performing standardization identification on the recording content and the protocol text to obtain an identification result.

[0077] It should be noted that the service handling recording can be a call recording of the user when handling the service, and the service handling protocol can be a service protocol signed by the user when handling the service.

[0078] It should be understood that the audio extraction on the service handling recording to obtain the recording content of the service handling recording can be audio extraction on the service handling recording by a preset speech recognition model to obtain the recording content. The preset speech recognition model is used to convert audio into text.

[0079] It can be understood that the character recognition on the service handling protocol to obtain the protocol text corresponding to the service handling protocol can be character recognition on the service handling protocol by a preset character recognition model to obtain the protocol text corresponding to the service handling protocol. The preset character recognition model can be a Convolutional Recurrent Neural Network (CRNN) model.

[0080] The character recognition on the service handling protocol to obtain the protocol text corresponding to the service handling protocol can also be character recognition on the service handling protocol by an Optical Character Recognition (OCR) program through an Application Programming Interface (API) of the OCR program, to obtain the protocol text, which is not limited in the embodiment.

[0081] It should be understood that the standardization identification on the recording content and the protocol text to obtain the identification result can be to judge whether the recording content conforms to a preset service handling standard to obtain a recording judgment result, to judge whether the protocol text matches a preset text template to obtain a protocol matching result, and to generate the identification result according to the recording judgment result and the protocol matching result. The preset service handling standard and the preset text template can be preset by a management personnel of the user complaint responsibility determination device.

[0082] It can be understood that when the recording content conforms to the preset service handling standard and the protocol text matches the preset text template, it is determined that the identification result is that the service handling conforms to the standard; when the recording content does not conform to the preset service handling standard or the protocol text does not match the preset text template, it is determined that the identification result is that the service handling does not conform to the standard.

[0083] Further, in order to further improve the accuracy of the standardization identification, the step S304 specifically includes:

[0084] Step S3041: extracting a recording keyword from the recording content, and performing standard identification on the recording content based on the recording keyword to obtain a recording standard identification result;

[0085] Step S3042: extracting a protocol signature from the protocol text, and matching the protocol signature with a user name to obtain a protocol standard identification result;

[0086] Step S3043: generating an identification result according to the recording standard identification result and the protocol standard identification result.

[0087] It should be noted that the recording keyword can be other words in the recording content except for regular words. The regular words can be mood auxiliaries and the like.

[0088] It should be understood that the standard identification on the recording content based on the recording keyword to obtain the recording standard identification result can be matching the recording keyword with a preset sensitive word, and performing standard identification on the recording content according to a matching result to obtain the recording standard identification result. The preset business keyword can be preset by a management personnel of the user complaint responsibility determination device, and the preset sensitive word can be a word that is not allowed to appear in the business handling process, for example, an insulting word.

[0089] It can be understood that when the recording keyword matches the preset sensitive word successfully, it is determined that the recording content does not conform to the standard; and when the recording keyword fails to match the preset sensitive word, it is determined that the recording content conforms to the standard.

[0090] It should be noted that the protocol signature can be a signature signed on a business handling protocol, and the user name can be a name in user information.

[0091] It should be understood that matching the protocol signature with the user name is to determine whether the protocol signature is signed by the user himself / herself. When the protocol signature fails to match the user name, it is determined that the signature on the business handling protocol is not signed by the user himself / herself, and thus it is determined that the protocol text does not conform to the standard.

[0092] It can be understood that generating the identification result according to the recording standard identification result and the protocol standard identification result can be determining that the identification result is that the business handling conforms to the standard when the recording standard identification result is that the standard is met and the protocol standard identification result is that the standard is met; and determining that the identification result is that the business handling does not conform to the standard when the recording standard identification result is that the standard is not met or the protocol standard identification result is that the standard is not met.

[0093] Step S40: determining responsibility for the user complaint corresponding to the user complaint data according to the identification result.

[0094] It should be noted that the responsibility identification can be identification of the responsible subject of the complained business and the information to be rectified. The responsible subject can be an organization responsible for the complaint, and the information to be rectified can be the content of the business that needs to be rectified.

[0095] It should be understood that when the identification result is that the business handling conforms to the standard, it indicates that the business handling content of the business handling organization conforms to the standard, and at this time, it is determined that the business handling organization of the complained business is not responsible.

[0096] It can be understood that when the identification result is that the business handling does not conform to the standard, it indicates that the business handling content of the business handling organization does not conform to the standard, and at this time, it is determined that the business handling organization of the complained business is the responsible subject of the complained business, and the rectification of the business handling content is the information to be rectified.

[0097] The embodiment obtains user complaint data, traces the complained business according to the user complaint data to determine the complained business, judges whether the business handling file corresponding to the complained business exists in the preset database, when the business handling file exists, performs standard identification on the business handling file to obtain an identification result, and performs responsibility identification on the user complaint corresponding to the user complaint data according to the identification result. Compared with the existing way of relying on manual judgment of the responsible subject of the user complaint, since the present application can automatically trace the complained business corresponding to the user complaint data and detect the business handling file of the complained business, and performs responsibility identification based on the detection result, the efficiency of complaint responsibility determination can be improved, and the accuracy of responsibility identification can be ensured.

[0098] Reference Figure 3 , Figure 3 The flowchart of the second embodiment of the user complaint responsibility determination method of the present application is shown based on the first embodiment shown in the above Figure 2 The second embodiment of the user complaint responsibility determination method of the present application is proposed based on the first embodiment shown in the above

[0099] In the second embodiment, after the step S30, the method further comprises:

[0100] Step S310: data extraction is performed on the user complaint data to obtain actual product information of the user.

[0101] It should be noted that the actual product information can be actual charge amount, actual business link, actual preferential amount, etc.

[0102] It should be understood that the data extraction on the user complaint data to obtain the actual product information of the user can be extraction of complaint user information and complained business number from the user complaint data, and determination of the actual product information of the user according to the complaint user information and the complained business number.

[0103] Step S320: searching for product design information corresponding to the complained service, and judging whether the complained service has design defects according to the product design information and actual product information, to obtain a judgment result.

[0104] It should be understood that, considering the actual situation, there are also cases where the design service of the product design department is unreasonable, resulting in user complaints. Therefore, it is also necessary to search for product design information corresponding to the complained service, and judge whether the complained service has design defects according to the product design information and actual product information.

[0105] It should be noted that the product design information can be a design charge amount, a design service link, a design discount amount, etc.

[0106] It can be understood that searching for product design information corresponding to the complained service can be searching for product design information corresponding to the complained service in a preset design information table. The preset design information table contains the correspondence between service products and product design information, and the correspondence between service products and product design information can be pre-recorded by the management personnel of the user complaint responsibility determination device.

[0107] It should be understood that judging whether the complained service has design defects according to the product design information and actual product information can be matching the product design information with the actual product information, and judging whether the complained service has design defects according to the matching result.

[0108] It can be understood that when the product design information and the actual product information fail to match, it is determined that the complained service has design defects; when the product design information and the actual product information match successfully, it is determined that the complained service does not have design defects.

[0109] Further, considering the actual situation, there can be a situation where a certain user has an occasional error. In order to avoid incorrect judgment, the step S320 comprises:

[0110] Searching for product design information corresponding to the complained service, and matching the product design information with the actual product information to obtain a matching result;

[0111] Searching for the number of complaints corresponding to the complained service, and judging whether the number of complaints is greater than a preset threshold to obtain a number of complaints judgment result;

[0112] Judging whether the complained service has design defects according to the matching result and the number of complaints judgment result to obtain a judgment result.

[0113] It should be noted that the preset threshold can be pre-set by the management personnel of the user complaint responsibility determination device.

[0114] It should be understood that when the number of complaints is greater than the preset threshold, it means that the complained business is complained more frequently and the problem is more common. When the number of complaints is less than or equal to the preset threshold, it means that the complained business is complained less frequently and the problem is less common.

[0115] It can be understood that whether the complained business has design defects is determined according to the matching result and the number of complaints determination result. The determination result can be that when the product design information and the actual product information fail to match, and the number of complaints is greater than the preset threshold, it is determined that the complained business has design defects; or when the product design information and the actual product information match successfully, or the number of complaints is less than or equal to the preset threshold, it is determined that the complained business does not have design defects.

[0116] In a specific implementation, for example, whether there is overcharge is determined by comparing the designed charge amount with the actual charge amount; whether there is business link duplication is determined by comparing the designed business link with the actual business link; whether there is overcharge is determined by comparing the designed discount amount with the actual discount amount, and then whether the complained business has design defects is determined according to the above determination results. If the complained business has design defects and a certain number of user complaints occur, it is determined that the product design department is the responsibility subject of the customer complaint.

[0117] Correspondingly, the step S40 comprises:

[0118] Step S40': determining the responsibility of the user complaint corresponding to the user complaint data according to the determination result and the identification result.

[0119] It should be understood that the responsibility of the user complaint corresponding to the user complaint data can be determined according to the determination result and the identification result. When the determination result is that the complained business has design defects, it is determined that the product design department of the complained business is the responsibility subject of the complained business, and the product design content to be rectified is the rectification information; when the identification result is that the business handling does not conform to the standard, it is determined that the business handling organization of the complained business is the responsibility subject of the complained business, and the business handling content to be rectified is the rectification information.

[0120] In the second embodiment, the user's actual product information is obtained by data extraction on the user complaint data, the product design information corresponding to the complained business is found, whether the complained business has design defects is determined according to the product design information and the actual product information, the determination result is obtained, and the responsibility of the user complaint corresponding to the user complaint data is determined according to the determination result and the identification result. Since not only whether the business handling document of the complained business conforms to the standard is verified, but also whether the complained business has design defects is verified in this example, the responsibility can be determined from multiple business aspects, and the reliability of the responsibility determination result is improved.

[0121] Referring to Figure 4 , Figure 4 FIG. 3 is a flowchart illustrating a third embodiment of a method for determining responsibility for a user complaint according to the present application; Figure 2 The third embodiment of a method for determining responsibility for a user complaint according to the present application is provided based on the first embodiment shown in FIG. 2.

[0122] In the third embodiment, the step S40 is followed by further comprising:

[0123] Step S50: determining a responsible subject of the complained business and rectification information to be rectified according to the responsibility determination result.

[0124] It should be noted that the responsible subject can be an organization responsible for the complaint, and the rectification information to be rectified can be the content of the business that needs to be rectified.

[0125] It should be understood that determining a responsible subject of the complained business and rectification information to be rectified according to the responsibility determination result can be extracting the responsible subject of the complained business and the rectification information to be rectified from the responsibility determination result.

[0126] Step S60: sending the rectification information to be rectified to a terminal device corresponding to the responsible subject.

[0127] It should be understood that in order to be able to rectify the complained business proposed by the user in a timely manner, the embodiment sends the rectification information to be rectified to the terminal device corresponding to the responsible subject.

[0128] It can be understood that after receiving the rectification information to be rectified, the responsible subject can be reviewed by the responsible person of the responsible subject, and the rectification is supervised after it is determined that there is no objection.

[0129] Step S70: receiving a responsibility determination evaluation score fed back by the responsible subject according to the rectification information to be rectified, and generating a responsibility determination optimization strategy according to the responsibility determination evaluation score.

[0130] It should be understood that considering that there can be a situation in which the responsibility determination result is inaccurate in actual situations. In order to be able to adaptively correct the responsibility determination result, the responsibility determination evaluation score fed back by the responsible subject according to the rectification information to be rectified can be received, and a responsibility determination optimization strategy can be generated according to the responsibility determination evaluation score.

[0131] It should be noted that the responsibility determination evaluation score is used to evaluate the accuracy of the user complaint responsibility determination, and the higher the responsibility determination evaluation score, the more accurate the user complaint responsibility determination.

[0132] It should be understood that after receiving the rectification information to be rectified, the responsible subject can be reviewed by the responsible person of the responsible subject, and the accuracy score can be scored according to the review result to obtain the responsibility determination evaluation score.

[0133] It can be understood that generating the responsibility optimization strategy according to the responsibility evaluation score can be searching for the responsibility optimization strategy corresponding to the responsibility evaluation score in the preset optimization strategy table. The preset optimization strategy table contains the correspondence between the responsibility evaluation score and the responsibility optimization strategy, and the correspondence between the responsibility evaluation score and the responsibility optimization strategy can be preset by the manager of the device for user complaint responsibility.

[0134] Step S80: establishing the correspondence between the responsibility optimization strategy and the complained business, and storing the correspondence in the preset database.

[0135] It should be understood that the correspondence between the responsibility optimization strategy and the complained business can be established, and the correspondence can be stored in the preset database, so that the next time the user complaint responsibility is performed, the user complaint responsibility result is adaptively corrected by using the correspondence.

[0136] In the third embodiment, by determining the responsibility subject of the complained business and the rectification information to be rectified according to the responsibility determination result, sending the rectification information to be rectified to the terminal device corresponding to the responsibility subject, receiving the responsibility evaluation score fed back by the responsibility subject according to the rectification information to be rectified, generating the responsibility optimization strategy according to the responsibility evaluation score, establishing the correspondence between the responsibility optimization strategy and the complained business, and storing the correspondence in the preset database, the responsibility determination can be automatically iteratively optimized, and the accuracy of the determination result is improved.

[0137] In addition, the embodiment of the present application also provides a storage medium, the storage medium stores a user complaint responsibility program, and the user complaint responsibility program is executed by a processor to realize the steps of the user complaint responsibility method as described above.

[0138] In addition, with reference to Figure 5 , the embodiment of the present application also provides a user complaint responsibility device, which comprises: a traceability module 10, a judgment module 20, an identification module 30 and a determination module 40.

[0139] The traceability module 10 is used for acquiring user complaint data, and performing complaint business traceability according to the user complaint data to determine the complained business.

[0140] It should be noted that the user complaint data includes complaint user information, user complaint time and complained business number, etc. The complained business number is used to identify the specific business of user complaint.

[0141] It can be understood that the user complaint data can be obtained through a complaint request uploaded by a complaint platform. The complaint platform can be an information platform that has established a communication connection with the user complaint accountability device in advance, and the user can initiate a complaint request through the complaint platform.

[0142] It should be understood that the complaint business traceability according to the user complaint data to determine the complained business can be to extract the complained business number from the user complaint data, and determine the complained business according to the complained business number.

[0143] The judgment module 20 is configured to determine whether the business handling file corresponding to the complained business exists in the preset database.

[0144] It should be noted that the business handling file can be various process files of the user when handling the business, for example, the business handling file can be at least one of a business handling recording, a business handling agreement and a business handling image. In this embodiment and other embodiments, the business handling recording and the business handling agreement are taken as examples for illustration.

[0145] The business handling recording can be a call recording of the user when handling the business, the business handling agreement can be a business agreement signed by the user when handling the business, and the business handling image can be a verification picture taken by the user when handling the business.

[0146] It should be understood that whether the business handling file exists in the preset database is an important reference basis for determining whether the user handles the business independently. Therefore, it is necessary to determine whether the business handling organization responsible for handling the complained business is responsible by judging whether the business handling file corresponding to the complained business exists in the preset database.

[0147] It should be noted that the business handling organization can be a service organization for handling the business of the user, for example, an online customer service organization and a store customer service organization.

[0148] It can be understood that the business handling channel corresponding to the complained business can be determined through the complaint business traceability, and the business handling organization responsible for handling the complained business can be determined according to the business handling channel. The business handling channel can be a channel used by the user when handling the business, for example, an online handling channel and an offline handling channel.

[0149] It should be understood that when the business handling file does not exist, it means that the business handling organization may have handled the business for the user without the user's knowledge, and at this time, the business handling organization responsible for handling the complained business can be directly determined as the responsible subject.

[0150] In a specific implementation, for example, it is determined whether the service handling audio corresponding to the complained service exists in the preset database, and it is determined whether the service handling agreement corresponding to the complained service exists in the preset database. When the service handling audio or the service handling agreement does not exist, it indicates that the service handling process of the service handling organization does not conform to the standard, the service handling organization of the complained service is determined as the responsible subject of the complained service, and the service handling process is corrected as the to-be-corrected information.

[0151] The identification module 30 is configured to perform standard identification on the service handling document when the service handling document exists, and obtain an identification result.

[0152] It should be understood that when the service handling document exists, the service handling organization of the complained service cannot be directly determined as not responsible. This is because the service handling content of the service handling organization may not be standard, and therefore, the service handling document needs to be subjected to standard identification to obtain an identification result.

[0153] It can be understood that the standard identification on the service handling document to obtain the identification result can be matching the service handling document with a preset file template, and performing standard identification on the service handling document according to the matching result to obtain the identification result. The preset file template can be preset by a management personnel of the user complaint responsibility determination device.

[0154] Further, in order to adaptively perform standard identification on the service handling document, the identification module 30 is further configured to extract a service handling audio and a service handling agreement from the service handling document when the service handling document exists.

[0155] The service handling audio is subjected to audio extraction to obtain audio content corresponding to the service handling audio.

[0156] The service handling agreement is subjected to character recognition to obtain agreement text corresponding to the service handling agreement.

[0157] The audio content and the agreement text are subjected to standard identification to obtain an identification result.

[0158] It should be noted that the service handling audio can be a call recording of a user when handling a service, and the service handling agreement can be a service agreement signed by the user when handling a service.

[0159] It should be understood that the audio extraction on the service handling audio to obtain the audio content of the service handling audio can be audio extraction on the service handling audio by a preset speech recognition model to obtain the audio content. The preset speech recognition model is configured to convert audio into text.

[0160] It can be understood that the character recognition of the service handling agreement to obtain the agreement text corresponding to the service handling agreement can be character recognition of the service handling agreement by a preset character recognition model to obtain the agreement text corresponding to the service handling agreement. The preset character recognition model can be a convolutional recurrent neural network (CRNN) model.

[0161] The character recognition of the service handling agreement to obtain the agreement text corresponding to the service handling agreement can also be character recognition of the service handling agreement by an optical character recognition (OCR) program through an application programming interface (API) call of the OCR program to obtain the agreement text, which is not limited in the embodiment.

[0162] It should be understood that the standard recognition of the recording content and the agreement text to obtain the recognition result can be to judge whether the recording content conforms to the preset service handling standard to obtain a recording judgment result, to judge whether the agreement text matches the preset text template to obtain an agreement matching result, and to generate a recognition result according to the recording judgment result and the agreement matching result. The preset service handling standard and the preset text template can be set by the management personnel of the user complaint accountability device in advance.

[0163] It can be understood that when the recording content conforms to the preset service handling standard and the agreement text matches the preset text template, it is determined that the recognition result is that the service handling conforms to the standard; when the recording content does not conform to the preset service handling standard or the agreement text does not match the preset text template, it is determined that the recognition result is that the service handling does not conform to the standard.

[0164] Further, in order to further improve the accuracy of the standard recognition, the recognition module 30 is also used to extract a recording keyword from the recording content, and perform standard recognition on the recording content based on the recording keyword to obtain a recording standard recognition result.

[0165] extract an agreement signature from the agreement text, and match the agreement signature with a user name to obtain an agreement standard recognition result;

[0166] generate a recognition result according to the recording standard recognition result and the agreement standard recognition result.

[0167] It should be noted that the recording keyword can be other words in the recording content except for conventional words. The conventional words can be mood auxiliaries and the like.

[0168] It should be understood that the standard identification of the recording content based on the recording keyword can be that the recording keyword is matched with the preset sensitive word, and the standard identification of the recording content is performed according to the matching result to obtain the recording standard identification result. The preset business keyword can be set by the management personnel of the user complaint responsibility determination device in advance, and the preset sensitive word can be a word that is not allowed to appear in the business handling process, for example, an insulting word.

[0169] It can be understood that when the recording keyword is successfully matched with the preset sensitive word, it is determined that the recording content is not standard; when the recording keyword fails to match the preset sensitive word, it is determined that the recording content is standard.

[0170] It should be noted that the protocol signature can be a signature signed on the business handling agreement, and the user name can be the name in the user profile.

[0171] It should be understood that the matching of the protocol signature and the user name is to determine whether the protocol signature is signed by the user himself. When the protocol signature and the user name fail to match, it indicates that the signature on the business handling agreement is not signed by the user himself, and therefore, it can be determined that the protocol text is not standard.

[0172] It can be understood that the generation of the identification result according to the recording standard identification result and the protocol standard identification result can be that when the recording standard identification result is standard and the protocol standard identification result is standard, it is determined that the identification result is that the business handling is standard; when the recording standard identification result is not standard or the protocol standard identification result is not standard, it is determined that the identification result is that the business handling is not standard.

[0173] The determination module 40 is configured to determine the responsibility of the user complaint corresponding to the user complaint data according to the identification result.

[0174] It should be noted that the responsibility determination can be to determine the responsible subject of the complained business and the information to be rectified. The responsible subject can be an organization responsible for the complaint, and the information to be rectified can be the content to be rectified in the business.

[0175] It should be understood that when the identification result is that the business handling is standard, it indicates that the business handling content of the business handling organization is standard, and at this time, it is determined that the business handling organization of the complained business is not responsible.

[0176] It can be understood that when the identification result is that the business handling is not standard, it indicates that the business handling content of the business handling organization is not standard, and at this time, it is determined that the business handling organization of the complained business is the responsible subject of the complained business, and the rectified business handling content is the information to be rectified.

[0177] The embodiment obtains user complaint data, and performs complaint business traceability according to the user complaint data to determine the complained business, judges whether the business handling file corresponding to the complained business exists in the preset database, when the business handling file exists, performs normative identification on the business handling file to obtain an identification result, and performs responsibility identification on the user complaint corresponding to the user complaint data according to the identification result; compared with the existing way of relying on manual identification of the responsibility subject of the user complaint, since the application can automatically trace the complained business corresponding to the user complaint data and detect the business handling file of the complained business, and performs responsibility identification based on the detection result, the efficiency of complaint responsibility determination can be improved, and the accuracy of responsibility identification is ensured.

[0178] Other embodiments or specific implementations of the user complaint responsibility determination device described in the application can refer to the above-mentioned method embodiments, which will not be described here.

[0179] It should be noted that in this paper, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or system. Without more limitations, the element defined by the sentence "includes a" does not exclude the presence of another identical element in the process, method, article or system including the element.

[0180] The above-mentioned embodiment numbers of the application are only for description, not representing the advantages and disadvantages of the embodiments. In the unit claims of several devices, several of these devices can be embodied by the same hardware item. The use of the words first, second, and third does not represent any order, and these words can be interpreted as names.

[0181] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by software and necessary general hardware platform, of course, they can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the application can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (Read Only Memory image, ROM) / random access memory (Random Access Memory, RAM), a magnetic disk, an optical disk), including a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) execute the method described in each embodiment of the application.

[0182] The above merely describes the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application, and any equivalent structure or equivalent process conversion, or direct or indirect application in other related technical fields, which are made by using the content of the present application specification and drawings, are also included in the patent protection scope of the present application.

Claims

1. A method for determining liability in user complaints, characterized in that, The user complaint responsibility determination method comprises the following steps: Obtaining user complaint data, and performing complaint business traceability according to the user complaint data to determine a complained business; Judging whether a business handling file corresponding to the complained business exists in a preset database; When the business handling file exists, performing standard identification on the business handling file to obtain an identification result; According to the identification result, determining the responsibility of the user complaint corresponding to the user complaint data; The step of performing standard identification on the business handling file to obtain an identification result when the business handling file exists specifically comprises: When the business handling file exists, extracting a business handling recording and a business handling agreement from the business handling file; Performing audio extraction on the business handling recording to obtain recording content corresponding to the business handling recording; Performing character recognition on the business handling agreement to obtain agreement text corresponding to the business handling agreement; Performing standard identification on the recording content and the agreement text to obtain an identification result; After the step of performing standard identification on the business handling file to obtain an identification result when the business handling file exists, the user complaint responsibility determination method further comprises: Extracting data from the user complaint data to obtain actual product information of a user; Finding product design information corresponding to the complained business, and judging whether the complained business has a design defect according to the product design information and the actual product information to obtain a judgment result, wherein the product design information comprises a design deduction amount, a design business link, and a design discount amount; Correspondingly, the step of determining the responsibility of the user complaint corresponding to the user complaint data according to the identification result specifically comprises: Determining the responsibility of the user complaint corresponding to the user complaint data according to the judgment result and the identification result.

2. The method of claim 1, wherein, The step of performing standard identification on the recording content and the agreement text to obtain an identification result specifically comprises: Extracting a recording keyword from the recording content, and performing standard identification on the recording content based on the recording keyword to obtain a recording standard identification result; Extracting an agreement signature from the agreement text, and matching the agreement signature with a user name to obtain an agreement standard identification result; Generating an identification result according to the recording standard identification result and the agreement standard identification result.

3. The method of claim 1, wherein the step of determining the cause of the user complaint is performed by a computer system. The step of finding product design information corresponding to the complained business, and judging whether the complained business has a design defect according to the product design information and the actual product information to obtain a judgment result specifically comprises: Finding product design information corresponding to the complained business, and matching the product design information with the actual product information to obtain a matching result; Finding a complaint frequency corresponding to the complained business, and judging whether the complaint frequency is greater than a preset threshold to obtain a complaint frequency judgment result; Judging whether the complained business has a design defect according to the matching result and the complaint frequency judgment result to obtain a judgment result.

4. The user complaint attribution method of any one of claims 1-3, wherein, The user complaint responsibility determination method further includes the following steps after the step of determining the responsibility of the user complaint corresponding to the user complaint data according to the identification result: determining the responsible subject of the complained business and the information to be rectified according to the responsibility determination result; sending the information to be rectified to the terminal device corresponding to the responsible subject.

5. The method of claim 4, wherein the step of determining the cause of the user complaint is performed by a computer system. The user complaint responsibility determination method further includes the following steps after the step of sending the information to be rectified to the terminal device corresponding to the responsible subject: receiving the responsibility evaluation score fed back by the responsible subject according to the information to be rectified, and generating a responsibility optimization strategy according to the responsibility evaluation score; establishing the corresponding relationship between the responsibility optimization strategy and the complained business, and storing the corresponding relationship in the preset database.

6. A user complaint assignment apparatus, characterized by comprising: The user complaint responsibility determination device includes a memory, a processor, and a user complaint responsibility determination program stored in the memory and executable on the processor, and the user complaint responsibility determination program implements the steps of the user complaint responsibility determination method of any one of claims 1 to 5 when executed by the processor.

7. A storage medium, characterized by The storage medium stores a user complaint responsibility determination program, and the user complaint responsibility determination program implements the steps of the user complaint responsibility determination method of any one of claims 1 to 5 when executed by the processor.

8. A user complaint attribution apparatus, characterized by, The user complaint responsibility determination device includes a traceability module, a judgment module, an identification module, and a determination module. The traceability module is configured to obtain user complaint data, perform complaint business traceability according to the user complaint data, and determine a complained business. The judgment module is configured to determine whether a business handling file corresponding to the complained business exists in a preset database. The identification module is configured to, when the business handling file exists, perform standard identification on the business handling file to obtain an identification result. The determination module is configured to determine the responsibility of the user complaint corresponding to the user complaint data according to the identification result. The identification module is further configured to, when the business handling file exists, extract a business handling recording and a business handling agreement from the business handling file, perform audio extraction on the business handling recording to obtain recording content corresponding to the business handling recording, perform character recognition on the business handling agreement to obtain agreement text corresponding to the business handling agreement, and perform standard identification on the recording content and the agreement text to obtain an identification result. The user complaint responsibility determination device further includes the following steps after the step of, when the business handling file exists, performing standard identification on the business handling file to obtain an identification result: The user complaint data is subjected to data extraction to obtain actual product information of the user; product design information corresponding to the complained service is searched, and whether the complained service has a design defect is judged according to the product design information and the actual product information to obtain a judgment result, the product design information including a designed deduction amount, a designed service link and a designed preferential amount; correspondingly, the responsibility identification of the user complaint corresponding to the user complaint data according to the recognition result includes: the responsibility identification of the user complaint corresponding to the user complaint data according to the judgment result and the recognition result.

Images