Feedback processing method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a feedback processing method and device, electronic equipment and storage medium, relates to the technical field of computers, in particular to the technical field of artificial intelligence such as natural language processing, large language model and deep learning, and can be used in application scenarios such as generative search, intelligent assistant, virtual assistant and intelligent e-commerce. The specific implementation scheme is as follows: obtaining target feedback information to be processed; determining a first label chain corresponding to the target feedback information; matching the first label chain with each historical label chain in a historical feedback database respectively to obtain a reference label chain matched with the first label chain and a first client identifier corresponding to the reference label chain; and sending the target feedback information to the first client.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of artificial intelligence technology such as natural language processing, large language models, and deep learning, specifically to a feedback processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] During the user experience of an application, customer complaints often arise due to application malfunctions at different stages. Timely handling of these complaints and maintenance of application functionality are crucial for driving continuous product and service optimization and for upholding the company's brand image. Since different personnel are typically responsible for maintaining functionality at different stages, quickly identifying the responsible party for user feedback is key to improving the efficiency of feedback processing. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, the purpose of this disclosure is to provide a feedback processing method, apparatus, electronic device and storage medium to automate the transfer of user feedback issues to specific personnel, thereby reducing the time spent in the feedback transfer process and improving the efficiency of feedback processing.

[0005] According to a first aspect of this disclosure, a feedback processing method is provided, comprising:

[0006] Obtain the target feedback information to be processed;

[0007] Determine the first tag chain corresponding to the target feedback information;

[0008] The first tag chain is matched with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain.

[0009] The target feedback information is sent to the first client.

[0010] According to a second aspect of this disclosure, a feedback processing apparatus is provided, comprising:

[0011] The acquisition module is used to acquire the target feedback information to be processed;

[0012] The first determining module is used to determine the first tag chain corresponding to the target feedback information;

[0013] The second determining module is used to match the first tag chain with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and a first client identifier corresponding to the reference tag chain.

[0014] The sending module is used to send the target feedback information to the first client.

[0015] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the feedback processing method as described in the first aspect.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the feedback processing method as described in the first aspect.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the feedback processing method as described in the first aspect.

[0021] The feedback processing method, apparatus, electronic device, and storage medium provided in this disclosure have the following beneficial effects:

[0022] By performing multi-level classification of the target feedback information, a first tag chain is obtained. Then, based on this first tag chain, the client identifier corresponding to the historical tag chain matching the target feedback information is obtained. The target feedback information is then sent to the client corresponding to the client identifier, completing the distribution of the feedback information. This approach enables rapid location and automatic dispatch of personnel handling user feedback, reduces the time consumed in the feedback flow process, improves the efficiency of feedback processing, and optimizes the user experience.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, which are provided for a better understanding of the present invention and are not intended to limit the scope of this disclosure, wherein:

[0025] Figure 1 This is a schematic flowchart of a feedback processing method according to an embodiment of the present disclosure;

[0026] Figure 2 This is a schematic flowchart of a feedback processing method according to another embodiment of the present disclosure;

[0027] Figure 3 This is a schematic flowchart of a feedback processing method according to another embodiment of the present disclosure;

[0028] Figure 4 This is a schematic flowchart of a feedback processing method according to another embodiment of the present disclosure;

[0029] Figure 5 This is a schematic diagram of the structure of a feedback processing device according to an embodiment of the present disclosure;

[0030] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0031] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0032] This disclosure relates to the fields of artificial intelligence technologies such as natural language processing, large language models, and deep learning.

[0033] Natural Language Understanding (NLU) is a general term for all methods, models, or tasks that support machines in understanding text content. NLU plays a crucial role in text information processing systems and is an essential module for systems such as recommendation, question answering, and search.

[0034] Large Language Models (LLMs) are deep learning models trained on large amounts of text data that can generate natural language text or understand the meaning of language text. LLMs can handle various natural language tasks, such as text classification, question answering, and dialogue, and are an important pathway to artificial intelligence.

[0035] Deep learning learns the inherent patterns and hierarchical representations of sample data. The information gained during this learning process greatly aids in interpreting data such as text, images, and sound. Its ultimate goal is to enable machines to possess analytical and learning capabilities like humans, allowing them to recognize data such as text, images, and sound.

[0036] Artificial Intelligence (AI) is an important component of the field of intelligence. It attempts to understand the nature of intelligence and to produce new intelligent machines that can react in a way similar to human intelligence. AI is a broad science encompassing robotics, speech recognition, image recognition, natural language processing, expert systems, machine learning, and computer vision.

[0037] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0038] The feedback processing method, apparatus, electronic device, and storage medium of this disclosure are described below with reference to the accompanying drawings.

[0039] It should be noted that the execution subject of the feedback processing method in this embodiment is a feedback processing device, which can be implemented by software and / or hardware. The device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc.

[0040] Figure 1 This is a schematic flowchart of a feedback processing method according to an embodiment of the present disclosure.

[0041] like Figure 1 As shown, the feedback processing method includes:

[0042] S101: Obtain the target feedback information to be processed.

[0043] The target feedback information may include feedback content that provides a detailed description of the specific problem, as well as a feedback title that summarizes or generalizes the feedback content. The feedback title may be a title that is summarized and entered by the customer service representative after the customer receives the feedback content entered by the user in the chat window.

[0044] In this embodiment, when a customer service representative stores feedback information in the user feedback pool, the target feedback information to be processed can be determined and processed directly. Alternatively, a thread can be established on the server to periodically query the user feedback pool for unprocessed feedback information and use it as the target feedback information for processing. The time interval between two queries can be determined according to the actual application maintenance needs, such as 3 minutes.

[0045] S102: Determine the first tag chain corresponding to the target feedback information.

[0046] The first label chain refers to a chain structure composed of multi-level labels used to represent the classification of target feedback information. The number of levels in the first label chain can be determined according to the complexity of the feedback problem, the accuracy requirements of the feedback processing, etc. For example, the number of levels can be 3, 5, etc., and this disclosure does not limit it.

[0047] Furthermore, within multi-level tags, the scope described by the tag decreases as the tag level increases. For example, a level 1 tag could be a scenario tag, such as transmission, storage, account, or activity; a level 2 tag could be a function tag, such as upload, backup, or decompression; and a level 3 tag could be a problem tag, such as upload failure or backup failure.

[0048] In this embodiment of the disclosure, the target feedback information can be classified step by step according to the pre-set multi-level tags to obtain each level tag that matches the target feedback information. Then, each level tag is formed into a chain structure according to its corresponding level to determine the first tag chain corresponding to the target feedback information.

[0049] Optionally, multi-level candidate tags and the relationships between them can be obtained first. Then, the target feedback information is matched with each level of candidate tags to determine the tags that match the target feedback information. Afterward, based on the relationships between the candidate tags at each level, the tags that match the target feedback information at each level can be concatenated to obtain the first tag chain.

[0050] In this embodiment of the disclosure, a tag database can be pre-built. The tag database can contain multi-level candidate tags, each level can contain multiple candidate tags, and a higher-level candidate tag can be associated with one or more lower-level candidate tags.

[0051] In this embodiment, semantic analysis of the target feedback information can be performed using various methods (such as large language models and other models or algorithms for semantic recognition) to determine which label the target feedback label matches level by level, thereby completing the matching between the target feedback information and each level of candidate labels. Then, the matched candidate labels can be organized into a chain structure according to their association relationship in the label database to obtain the first label chain.

[0052] For example, if the target feedback information matches the label "transmission" in the level 1 candidate labels, the label "backup" in the level 2 candidate labels, and the label "backup failure" in the level 3 candidate labels, then the first label chain can be obtained as "transmission-backup-backup failure" based on the relationship between these three labels.

[0053] It should be noted that the target feedback information can match multiple candidate tags at the same level, and the final first tag chain may have one or more, and in the case of multiple first tag chains, the level of the tags contained in any two first tag chains can also be different.

[0054] In this embodiment of the disclosure, by matching the target feedback information with candidate tags, and then linking the matched candidate tags in the order of their association to obtain the first tag chain, the accuracy and efficiency of target feedback information classification can be improved, providing a more accurate basis for determining the flow direction of target feedback information.

[0055] S103: Match the first tag chain with each historical tag chain in the historical feedback database to obtain the reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain.

[0056] The historical feedback database is used to store data generated after processing historical user feedback. It may include historical tag chains that classify and label historical user feedback, as well as the content, reproduction path, cause of the problem, and solution of the historical user feedback.

[0057] The first client identifier refers to the identifier of the client used by R&D engineers and other staff responsible for resolving user feedback.

[0058] In this embodiment of the disclosure, the staff member responsible for handling user feedback corresponding to each historical tag chain can be recorded by storing the first client identifier corresponding to each historical tag chain in the historical feedback database. It should be noted that the first client identifiers corresponding to two historical tag chains may be the same or different.

[0059] In this embodiment of the disclosure, the first tag chain can be matched with each historical tag chain in the historical feedback database level by level. If the tags in any historical tag chain match the tags in the first tag chain, the any historical tag chain is determined as a reference tag chain. Thus, the first client identifier corresponding to the reference tag chain can be determined in the historical feedback database.

[0060] S104: Send the target feedback information to the first client.

[0061] In this embodiment of the disclosure, after obtaining the first client identifier corresponding to the reference tag chain, since the reference tag chain matches the first tag chain corresponding to the target feedback information, the processing methods of the target feedback information and the historical feedback corresponding to the reference tag chain should be similar. Therefore, the first client identifier can be determined as the identifier of the client used by the staff responsible for processing the target feedback information, thereby sending the target feedback information to the first client to complete the rapid distribution of the target feedback information.

[0062] It should be noted that when there are multiple reference tag chains, the first client identifiers corresponding to the reference tag chains may be the same or different. Therefore, when there are multiple first client identifiers corresponding to a reference tag chain, one first client identifier corresponding to a reference tag chain can be selected to send the target feedback information. Alternatively, the target feedback information can be sent to multiple first clients separately based on all the first client identifiers; this disclosure does not limit this approach.

[0063] In this embodiment, the target feedback information to be processed is first obtained, and then the first tag chain corresponding to the target feedback information is determined. Next, the first tag chain is matched with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and a first client identifier corresponding to the reference tag chain. Then, the target feedback information is sent to the first client. Thus, by performing multi-level classification of the target feedback information, the first tag chain is obtained, and based on the first tag chain, the client identifier corresponding to the historical tag chain matching the target feedback information is obtained. The target feedback information is then sent to the client corresponding to the client identifier, completing the distribution of the feedback information. This achieves rapid location and automatic dispatch of personnel handling user feedback, reduces the time consumed in the feedback flow process, improves the efficiency of feedback processing, and optimizes the user experience.

[0064] Figure 2 This is a schematic flowchart of a feedback processing method proposed in another embodiment of this disclosure.

[0065] like Figure 2 As shown, the feedback processing method includes:

[0066] S201: Obtain the target feedback information to be processed.

[0067] For a detailed description of S201 above, please refer to other embodiments of this disclosure, which will not be repeated here.

[0068] S202: Input the first prompt information and the target feedback information into the large language model respectively to obtain the first-level target label output by the large language model.

[0069] The first prompt information is used to instruct the large language model to select the first-level target label that semantically matches the target feedback information from the first-level candidate labels.

[0070] In this embodiment, all level 1 tags in the tag database can be obtained first as first-level candidate tags. Then, first prompt information is generated based on the first-level candidate tags.

[0071] For example, the first-level candidate tags are transmission, storage, account, activity, and value-added services. The first prompt message could be "Among the candidate tags shown below: transmission, storage, account, activity, and value-added services, filter for tags that match the target feedback information: ...", etc. This disclosure does not limit this.

[0072] Understandably, if the first-level candidate labels in the label database remain unchanged, the first prompt information used to filter out the first-level target labels in the large language model is also fixed.

[0073] In this embodiment of the disclosure, the first prompt information and the target feedback information can be input into the large language model. The large language model uses its natural language analysis capabilities to determine which candidate tags in the first prompt information are semantically consistent with the target feedback information, thereby outputting the first-level target tags.

[0074] It should be noted that the first-level target label output by the large language model may be one or multiple.

[0075] S203: Obtain the next-level candidate label associated with the first-level target label.

[0076] In this embodiment of the disclosure, the tag database may contain the association relationship between candidate tags at all levels. Therefore, it is possible to query the next-level candidate tags associated with each first-level target tag in the tag database.

[0077] S204: Generate a second prompt message based on the first-level target label and the next-level candidate labels.

[0078] The second prompt information is used to instruct the large language model to select the next-level target label from the next-level candidate labels that semantically matches the target feedback information.

[0079] In this embodiment of the disclosure, a second prompt message can be generated by utilizing the first-level target label and the association between the first-level target label and the next-level candidate label.

[0080] For example, the first-level target tags include transmission, storage, and account; the next-level candidate tags associated with transmission include upload and backup; the next-level candidate tags associated with storage include file and decompression; and the next-level candidate tag associated with account is account ban. The first prompt message could be something like, "From the following candidate tags: transmission, transmission-upload, transmission-backup, storage, storage-file, storage-decompression, account, account-account ban, filter for tags that match the target feedback information: ...", etc. This disclosure does not limit this.

[0081] S205: Input the second prompt information and the target feedback information into the large language model respectively to obtain the second-level target label output by the large language model.

[0082] In this embodiment of the disclosure, the second prompt information and the target feedback information can be input into the large language model. The large language model uses its natural language analysis capabilities to determine which candidate labels in the second prompt information are semantically consistent with the target feedback information, thereby outputting the second-level target labels.

[0083] As in the example above, the second-level target labels output by the large language model can be transmission-upload, transmission-backup, and storage-file.

[0084] S206: Based on the second-level target label, return to obtain the associated next-level candidate label, and repeat the above operation until the target labels corresponding to the target feedback information at each level are obtained.

[0085] In this embodiment of the disclosure, the operation of determining the next-level candidate label associated with the second-level target label in the label database can be returned, i.e., S203. Then, the following S204 and S205 are repeated to determine the next-level target label step by step until the label database does not contain the next-level candidate label associated with the target label, and the target labels at each level corresponding to the target feedback information are obtained.

[0086] S207: Concatenate the target labels at each level to obtain the first label chain.

[0087] In this embodiment of the disclosure, the target tags at each level can be spliced ​​together in ascending order of level number according to the pre-set association relationship between target tags at each level in the tag database to obtain the first tag chain.

[0088] For example, the first-level target tags include "transfer" and "storage," the second-level target tags include "upload," "backup," and "file," and the third-level target tags include "upload failure," "new upload function," and "backup failure." Furthermore, "upload" and "backup" are the next-level tags associated with "transfer," "file" is the next-level tag associated with "storage," "upload failure" and "new upload function" are the next-level tags associated with "upload," and "backup failure" is the next-level tag associated with "backup." Therefore, the first tag chain can include: transfer-upload-upload failure, transfer-upload-new upload function, transfer-backup-backup failure, and storage-file.

[0089] S208: Match the first tag chain with each historical tag chain in the historical feedback database to obtain the reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain.

[0090] S209: Send the target feedback information to the first client.

[0091] For detailed descriptions of S208 and S209 above, please refer to other embodiments of this disclosure, which will not be repeated here.

[0092] In this embodiment, by using a large language model to intelligently classify the target feedback information, the determination efficiency of the first tag chain is improved, which provides conditions for reducing the time consumption of automatic dispatch and improving the efficiency of feedback processing.

[0093] Figure 3 This is a schematic flowchart of a feedback processing method proposed in another embodiment of this disclosure.

[0094] like Figure 3 As shown, the feedback processing method includes:

[0095] S301: Obtain the target feedback information to be processed.

[0096] S302: Determine the first tag chain corresponding to the target feedback information.

[0097] S303: Match the first tag chain with each historical tag chain in the historical feedback database to obtain the reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain.

[0098] For detailed descriptions of S301 to S303 above, please refer to other embodiments of this disclosure, which will not be repeated here.

[0099] It should be noted that in this disclosure, after using the first tag chain to match and filter the historical tag chains to obtain the parameter tag chain, the parameter tag chain can be further filtered using the parameter information of the client sending the feedback information and the similarity between the feedback information, so as to improve the credibility of the reference tag chain.

[0100] S304: Obtain the first parameter information of the second client that sent the target feedback information.

[0101] The second client refers to the client used by the user when entering the target feedback information in the customer service window.

[0102] The client's parameter information may include the client's platform, such as iOS, Android, PC, web, etc., and the software version installed on the client at the time; this disclosure does not limit this. In other words, the first parameter information refers to the specific platform and software version of the second client.

[0103] S305: Match the first parameter information with the second parameter information of the first client to obtain the first client identifier corresponding to the second parameter information that matches the first parameter information.

[0104] The second parameter information of the first client refers to the parameter information corresponding to the feedback issues that the processor can handle on the first client, and may also include the platform and software version.

[0105] In this embodiment of the disclosure, if any second parameter information is the same as the first parameter information, it can be determined that the historical feedback information and the target feedback information corresponding to the reference tag chain are fed back from the same platform client and / or the same software version. Therefore, their solutions may be similar and the processing personnel are the same. Then, the first client identifier corresponding to the matching second parameter information can be determined as the identifier of the first client to which the target feedback information is to be sent.

[0106] S306: Send the target feedback information to the first client.

[0107] For a detailed description of S306 above, please refer to other embodiments of this disclosure, which will not be repeated here.

[0108] In this embodiment, by utilizing the parameter information of the client, the first client identifier corresponding to the selected reference tag chain is further filtered, thereby improving the reliability of the first client for distributing target feedback information and providing conditions for improving the efficiency of feedback processing.

[0109] Figure 4 This is a schematic flowchart of a feedback processing method proposed in another embodiment of this disclosure.

[0110] like Figure 4 As shown, the feedback processing method includes:

[0111] S401: Obtain the target feedback information to be processed.

[0112] S402: Determine the first tag chain corresponding to the target feedback information.

[0113] S403: Match the first tag chain with each historical tag chain in the historical feedback database to obtain the reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain.

[0114] For detailed descriptions of S401 to S403 above, please refer to other embodiments of this disclosure, which will not be repeated here.

[0115] S404: When there are multiple first clients, determine the similarity between the target feedback information and the historical feedback information corresponding to the reference tag chain.

[0116] In this embodiment, if the first client identifiers corresponding to any two reference tag chains are different, it can be determined that there are multiple first clients. Then, a large language model can be used to summarize the target feedback information to obtain summary text. This summary text is then vectorized to obtain the vector corresponding to the target feedback information. Next, the cosine distance between the vector corresponding to the target feedback information and the vector of historical feedback information corresponding to each reference tag chain can be calculated to obtain the similarity between the target feedback information and the historical feedback information corresponding to the reference tag chains.

[0117] Alternatively, similarity can be obtained by directly matching the target feedback information with historical feedback information, etc. This disclosure does not limit this.

[0118] S405: Send the target feedback information to the first client corresponding to the reference tag chain with the highest similarity.

[0119] In this embodiment of the disclosure, when any historical feedback information has the highest similarity to the target feedback information, it can be determined that the processing scheme of the historical feedback information is more suitable for the target feedback information. Then, the first client corresponding to the reference tag chain with the highest similarity can be determined as the first client for sending the target feedback information.

[0120] It should be noted that there may be two reference tag chains with the same similarity. Therefore, if there is more than one reference tag chain with the highest similarity and the first client identifier corresponding to each reference tag chain is different, it is necessary to use other conditions to further sort the priority of these two reference tag chains.

[0121] Optionally, if the number of reference tag chains with the highest similarity is greater than 1, the level of the highest-level tag that matches the first tag chain can be determined for each of the multiple reference tag chains. Then, based on the level, the target feedback information is sent to the first client corresponding to the reference tag chain with the highest level.

[0122] For example, the reference tag chains with the highest similarity are reference tag chain A and reference tag chain B, and the first client identifier corresponding to reference tag chain A is 'a', while the first client identifier corresponding to reference tag chain B is 'b'. The level of the highest-level tag matching reference tag chain A with the first tag chain is determined to be 4, and the level of the highest-level tag matching reference tag chain B with the first tag chain is determined to be 3. Since 4 > 3, it can be determined that the target feedback information is sent to the first client 'a'.

[0123] In this embodiment of the disclosure, when multiple reference tag chains have the same similarity, the first client for sending a target feedback information is determined by comparing the level of the highest-level tag that matches the first tag chain in each reference tag chain. This further improves the reliability and efficiency of feedback distribution.

[0124] It should be noted that, in this disclosure, in addition to sending the target feedback information to the first client, historical processing data of historical feedback can also be used to provide processing personnel with reference processing solutions, thereby further improving the efficiency of feedback processing.

[0125] Optionally, the processing data of the historical feedback information corresponding to the reference tag chain can be obtained, and then the processing data and the target feedback information can be sent to the first client.

[0126] The processed data of historical feedback information may include the reproduction path, problem attribution, and solution.

[0127] In this embodiment of the disclosure, the processing data of historical feedback information corresponding to all reference tag chains can be sent to the first client together with the target feedback information to provide feedback processing personnel with a reference processing solution, thereby further improving the efficiency of feedback processing and reducing the workload of feedback processing personnel.

[0128] It should be noted that since there can be multiple reference tag chains, there may also be multiple processing data for the historical feedback information corresponding to each reference tag chain. If all the processing data is sent to the first client without processing, it will not provide feedback processing personnel with a good processing solution reference, which may cause confusion among processing personnel and affect processing efficiency.

[0129] Optionally, when there are multiple data to process, the weight value corresponding to each reference tag chain can be determined first based on the similarity of each reference tag chain, and then the multiple processed data and target feedback information can be sent to the first client in sequence according to the weight value.

[0130] The weight value corresponding to the reference tag chain is used to represent the credibility of the processed data corresponding to the reference tag chain when processing target feedback information.

[0131] In this embodiment, the similarity of each reference tag chain can be determined first based on the similarity between the target feedback information and the historical feedback information corresponding to the reference tag chain. Then, the weight value of each reference tag chain can be determined based on the magnitude of the similarity; the greater the similarity, the greater the weight value. After obtaining the weight value of each reference tag chain, the corresponding processing data is sorted in descending order of weight value, and the sorted processing data and the target feedback information are sent to the first client together.

[0132] It should be noted that in this disclosure, a similarity threshold can also be set. If the similarity of any reference tag chain is less than the similarity threshold, the processing data corresponding to that reference tag chain is deleted and not sent to the first client.

[0133] In this embodiment of the disclosure, by determining the similarity corresponding to each reference tag chain, the order in which the processed data is sent to the first client is sorted, making the data sent to the first client more organized, facilitating the processing personnel to quickly and accurately obtain the reference processing solution, and further improving the efficiency of feedback processing.

[0134] In this embodiment, the most reliable first client is determined from multiple first client identifiers based on the similarity between the historical feedback information corresponding to the reference tag chain and the target feedback information, and the target feedback information is sent, which further improves the accuracy and reliability of feedback dispatch and improves the efficiency of feedback processing.

[0135] Figure 5 This is a schematic diagram of the structure of a feedback processing device proposed in an embodiment of this disclosure.

[0136] like Figure 5 As shown, the feedback processing device 500 includes:

[0137] The acquisition module 501 is used to acquire the target feedback information to be processed;

[0138] The first determining module 502 is used to determine the first tag chain corresponding to the target feedback information;

[0139] The second determining module 503 is used to match the first tag chain with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain.

[0140] The sending module 504 is used to send the target feedback information to the first client.

[0141] Optionally, the first determining module 502 can be specifically used for:

[0142] Obtain multi-level candidate tags and the relationships between each candidate tag;

[0143] Match the target feedback information with each level of candidate labels to determine the labels at each level that match the target feedback information;

[0144] Based on the correlation between candidate tags at each level, the tags at each level that match the target feedback information are concatenated to obtain the first tag chain.

[0145] Optionally, the first determining module 502 can be specifically used for:

[0146] The first prompt information and the target feedback information are respectively input into the large language model to obtain the first-level target label output by the large language model;

[0147] Retrieve the next-level candidate tags associated with the first-level target tag;

[0148] Based on the first-level target label and the next-level candidate label, generate the second prompt message;

[0149] The second prompt information and the target feedback information are input into the large language model respectively to obtain the second-level target label output by the large language model;

[0150] Based on the second-level target label, return to obtain the associated next-level candidate label, and repeat the above operation until the target labels at all levels corresponding to the target feedback information are obtained;

[0151] By splicing together the target labels at each level, the first label chain is obtained.

[0152] Optionally, the second determining module 503 can also be used for:

[0153] Obtain the first parameter information of the second client that sent the target feedback information;

[0154] The first parameter information is matched with the second parameter information of the first client to obtain the first client identifier corresponding to the second parameter information that matches the first parameter information.

[0155] Optionally, the sending module 504 can be specifically used for:

[0156] When there are multiple first clients, determine the similarity between the target feedback information and the historical feedback information corresponding to the reference tag chain;

[0157] The target feedback information is sent to the first client corresponding to the reference tag chain with the highest similarity.

[0158] Optionally, the sending module 504 can be specifically used for:

[0159] If the number of reference tag chains with the highest similarity is greater than 1, determine the level of the highest-level tag that the multiple reference tag chains match with the first tag chain.

[0160] Based on the level, the target feedback information is sent to the first client corresponding to the reference tag chain with the highest level.

[0161] Optionally, the sending module 504 can be specifically used for:

[0162] Retrieve processing data for historical feedback information corresponding to the reference tag chain;

[0163] The processed data and target feedback information are sent to the first client.

[0164] Optionally, the sending module 504 can be specifically used for:

[0165] When there are multiple data points to process, the weight value of each reference tag chain is determined based on the similarity of each reference tag chain.

[0166] Based on the weight values, multiple processed data and target feedback information are sent sequentially to the first client.

[0167] It should be noted that the foregoing explanation of the feedback processing method also applies to the feedback processing device of this embodiment, and will not be repeated here.

[0168] In this embodiment, the target feedback information to be processed is first obtained, and then the first tag chain corresponding to the target feedback information is determined. Next, the first tag chain is matched with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and a first client identifier corresponding to the reference tag chain. Then, the target feedback information is sent to the first client. Thus, by performing multi-level classification of the target feedback information, the first tag chain is obtained, and based on the first tag chain, the client identifier corresponding to the historical tag chain matching the target feedback information is obtained. The target feedback information is then sent to the client corresponding to the client identifier, completing the distribution of the feedback information. This achieves rapid location and automatic dispatch of personnel handling user feedback, reduces the time consumed in the feedback flow process, improves the efficiency of feedback processing, and optimizes the user experience.

[0169] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0170] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0171] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0172] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0173] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the topic generation method. For example, in some embodiments, the topic generation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the topic generation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the topic generation method by any other suitable means (e.g., by means of firmware).

[0174] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0175] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0176] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0177] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0178] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0179] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0180] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0181] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. In the description of this disclosure, the words "if" and "suppose" as used may be interpreted as "when," "when," "in response to determination," or "in the circumstances."

[0182] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A feedback processing method, characterized in that, include: Obtain the target feedback information to be processed; Determine the first tag chain corresponding to the target feedback information; The first tag chain is matched with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain. The target feedback information is sent to the first client.

2. The method as described in claim 1, characterized in that, Determining the first tag chain corresponding to the target feedback information includes: Obtain multi-level candidate tags and the relationships between each candidate tag; The target feedback information is matched with each level of candidate labels to determine each level of label that matches the target feedback information; Based on the correlation between the candidate tags at each level, the tags at each level that match the target feedback information are concatenated to obtain the first tag chain.

3. The method as described in claim 1, wherein determining the first tag chain corresponding to the target feedback information includes: The first prompt information and the target feedback information are respectively input into the large language model to obtain the first-level target label output by the large language model; Obtain the next-level candidate tag associated with the first-level target tag; Based on the first-level target label and the next-level candidate label, a second prompt message is generated; The second prompt information and the target feedback information are respectively input into the large language model to obtain the second-level target label output by the large language model; Based on the second-level target label, return to the process of obtaining the associated next-level candidate label, and repeat the above operation until the target labels at each level corresponding to the target feedback information are obtained; The target labels at each level are spliced ​​together to obtain the first label chain.

4. The method as described in claim 1, characterized in that, After obtaining the reference tag chain that matches the first tag chain and the first client identifier corresponding to the reference tag chain, the method further includes: Obtain the first parameter information of the second client that sent the target feedback information; The first parameter information is matched with the second parameter information of the first client to obtain the first client identifier corresponding to the second parameter information that matches the first parameter information.

5. The method as described in claim 1, characterized in that, Sending the target feedback information to the first client includes: When there are multiple first clients, determine the similarity between the target feedback information and the historical feedback information corresponding to the reference tag chain; The target feedback information is sent to the first client corresponding to the reference tag chain with the highest similarity.

6. The method as described in claim 5, characterized in that, Sending the target feedback information to the first client corresponding to the reference tag chain with the highest similarity includes: If the number of reference tag chains with the highest similarity is greater than 1, determine the level of the highest-level tag that the multiple reference tag chains match with the first tag chain. Based on the magnitude of the level, the target feedback information is sent to the first client corresponding to the reference tag chain with the largest level.

7. The method as described in any one of claims 5-6, characterized in that, Sending the target feedback information to the first client includes: Processing data for obtaining historical feedback information corresponding to the reference tag chain; The processed data and the target feedback information are sent to the first client.

8. The method as described in claim 7, characterized in that, Sending the processed data and the target feedback information to the first client includes: When there are multiple pieces of data to be processed, a weight value corresponding to each reference tag chain is determined based on the similarity corresponding to each reference tag chain. Based on the weight values, the processed data and the target feedback information are sequentially sent to the first client.

9. A feedback processing device, characterized in that, include: The acquisition module is used to acquire the target feedback information to be processed; The first determining module is used to determine the first tag chain corresponding to the target feedback information; The second determining module is used to match the first tag chain with each historical tag chain in the historical feedback database to obtain a reference tag chain that matches the first tag chain and a first client identifier corresponding to the reference tag chain. The sending module is used to send the target feedback information to the first client.

10. The apparatus as claimed in claim 9, characterized in that, The first determining module is specifically used for: Obtain multi-level candidate tags and the relationships between each candidate tag; The target feedback information is matched with each level of candidate labels to determine each level of label that matches the target feedback information; Based on the correlation between the candidate tags at each level, the tags at each level that match the target feedback information are concatenated to obtain the first tag chain.

11. The apparatus of claim 9, wherein the first determining module is specifically configured to: The first prompt information and the target feedback information are respectively input into the large language model to obtain the first-level target label output by the large language model; Obtain the next-level candidate tag associated with the first-level target tag; Based on the first-level target label and the next-level candidate label, a second prompt message is generated; The second prompt information and the target feedback information are respectively input into the large language model to obtain the second-level target label output by the large language model; Based on the second-level target label, return to the process of obtaining the associated next-level candidate label, and repeat the above operation until the target labels at each level corresponding to the target feedback information are obtained; The target labels at each level are spliced ​​together to obtain the first label chain.

12. The apparatus as claimed in claim 9, characterized in that, The second determining module is further configured to: Obtain the first parameter information of the second client that sent the target feedback information; The first parameter information is matched with the second parameter information of the first client to obtain the first client identifier corresponding to the second parameter information that matches the first parameter information.

13. The apparatus as claimed in claim 9, characterized in that, The sending module is specifically used for: When there are multiple first clients, determine the similarity between the target feedback information and the historical feedback information corresponding to the reference tag chain; The target feedback information is sent to the first client corresponding to the reference tag chain with the highest similarity.

14. The apparatus as claimed in claim 13, characterized in that, The sending module is specifically used for: If the number of reference tag chains with the highest similarity is greater than 1, determine the level of the highest-level tag that the multiple reference tag chains match with the first tag chain. Based on the magnitude of the level, the target feedback information is sent to the first client corresponding to the reference tag chain with the largest level.

15. The apparatus as described in any one of claims 13-14, characterized in that, The sending module is specifically used for: Processing data for obtaining historical feedback information corresponding to the reference tag chain; The processed data and the target feedback information are sent to the first client.

16. The apparatus as claimed in claim 15, characterized in that, The sending module is specifically used for: When there are multiple pieces of data to be processed, a weight value corresponding to each reference tag chain is determined based on the similarity corresponding to each reference tag chain. Based on the weight values, the processed data and the target feedback information are sequentially sent to the first client.

17. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the feedback processing method according to any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to execute the feedback processing method according to any one of claims 1-8.

19. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the feedback processing method according to any one of claims 1-8.

Images