Data processing method and device, electronic equipment and storage medium

Abstract

The invention relates to a data processing method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a business scene and an information type to which each piece of feedback information belongs for an obtained feedback information set in a preset time period; aggregating the feedback information according to the service scenes to which the feedback information belongs so as to obtain feedback information subsets corresponding to the service scenes, and when the service scenes comprise a target service scene, determining target feedback information of which the information type is a target information type in the feedback information subsets corresponding to the target service scene, the target information type is a non-consulting type, and feedback prompting is performed on the service processing node associated with the target service scene based on the target feedback information of the target information type, so that the processing efficiency of a large amount of feedback information is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a data processing method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of business, the amount of data reflecting feedback information of business interaction process is increasing day by day. This feedback information is usually presented in the form of questions, such as consulting questions, technical questions, product questions, etc.

[0003] In the related art, the processing method for the increasing amount of feedback information mainly relies on manual work, which leads to low efficiency in processing problems involved in a large amount of feedback information, such as technical problems, product problems, etc. Summary of the invention

[0004] The present disclosure provides a data processing method, device, electronic device and storage medium to at least solve the problem of low efficiency in processing a large amount of feedback information in the related art. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided a data processing method, including:

[0006] Obtain feedback information within a preset time period to obtain a feedback information set;

[0007] Based on each piece of feedback information in the feedback information set, determining a business scenario and an information type to which each piece of feedback information belongs;

[0008] Aggregating the feedback information in the feedback information set according to the business scenarios to which the feedback information belongs, to obtain feedback information subsets corresponding to the business scenarios;

[0009] In the case where each of the business scenarios includes a target business scenario, determining, in a feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type; and the target information type is a non-consulting type;

[0010] Based on the target feedback information of the target information type, feedback prompts are given to the business processing node associated with the target business scenario.

[0011] In some exemplary embodiments, when each of the business scenarios includes a target business scenario, determining, in a feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type includes:

[0012] Based on the preset scene prompt mapping information, determining the scene prompt level corresponding to each of the business scenarios; the preset scene prompt mapping information represents the correspondence between the preset business scenarios and the scene prompt level;

[0013] If there is a target scenario prompt level, determining the business scenario corresponding to the target scenario prompt level as the target business scenario; the target scenario prompt level indicates that a prompt is required;

[0014] Determine, in the feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type.

[0015] In some exemplary implementations, the target feedback information based on the target information type, providing feedback prompts to the business processing node associated with the target business scenario, includes:

[0016] Determine the total amount of target feedback information of the target information type;

[0017] When the total quantity exceeds a preset quantity threshold, a feedback prompt is given to the business processing node associated with the target business scenario based on the target feedback information of the target information type.

[0018] In some exemplary embodiments, after determining the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set, the method further includes:

[0019] Find out whether there is a new information type in each of the determined information types;

[0020] If the newly added information type is found, a feedback prompt is given to the business processing node associated with the business scenario corresponding to the newly added information type based on the feedback information corresponding to the newly added information type.

[0021] In some exemplary implementations, after obtaining the feedback information subsets corresponding to the business scenarios, the method further includes:

[0022] For each of the feedback information subsets, determine the number of feedback information corresponding to each of the information types in the feedback information subset, and obtain the total number of feedbacks corresponding to each information type in each of the business scenarios;

[0023] Based on the total number of feedbacks of each information type corresponding to each of the business scenarios, an information type distribution diagram is generated.

[0024] In some exemplary implementations, generating an information type distribution diagram based on the total number of feedbacks corresponding to each information type in each business scenario includes:

[0025] For each of the business scenarios, based on the total number of feedbacks for each information type corresponding to the business scenario, the information types are arranged in descending order;

[0026] A preset number of information types ranked first are selected as key information types, and based on the total number of feedbacks corresponding to the preset number of key information types, an information type distribution diagram corresponding to the business scenario is generated.

[0027] In some exemplary implementations, generating an information type distribution diagram based on the total number of feedbacks corresponding to each information type in each business scenario includes:

[0028] For each information type, determine the sum of the total number of feedbacks of the information type corresponding to each business scenario, and obtain the total number of type feedbacks of each information type;

[0029] Based on the total number of type feedbacks of each of the information types, an information type distribution diagram of the information type dimension is generated.

[0030] In some exemplary implementations, generating an information type distribution diagram based on the total number of feedbacks corresponding to each information type in each business scenario includes:

[0031] For each information type, based on the feedback time of the feedback information of the information type corresponding to each business scenario, determine the total number of time feedbacks corresponding to the preset time granularity of the preset time period;

[0032] Based on the total number of time feedbacks corresponding to the preset time granularity of each information type in the preset time period, a distribution graph of the information type in the time dimension is generated.

[0033] In some exemplary implementations, determining the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set includes:

[0034] Each piece of feedback information in the feedback information set is input into a large language model respectively, and the business scenario and information type to which each piece of feedback information belongs are determined by the large language model.

[0035] According to a second aspect of an embodiment of the present disclosure, there is provided a data processing device, including:

[0036] A feedback information acquisition unit, configured to acquire feedback information within a preset time period to obtain a feedback information set;

[0037] A scenario and type determination unit, configured to determine the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set;

[0038] an aggregation unit, configured to aggregate the feedback information in the feedback information set according to the business scenarios to which the feedback information belongs, to obtain feedback information subsets corresponding to the business scenarios respectively;

[0039] A target feedback determination unit is configured to determine, when each of the business scenarios includes a target business scenario, target feedback information whose information type is a target information type in a feedback information subset corresponding to the target business scenario; and the target information type is a non-consulting type;

[0040] The feedback prompt unit is configured to execute target feedback information based on the target information type and provide feedback prompts to the business processing node associated with the target business scenario.

[0041] In some exemplary embodiments, the target feedback determination unit is configured to execute:

[0042] Based on the preset scene prompt mapping information, determining the scene prompt level corresponding to each of the business scenarios; the preset scene prompt mapping information represents the correspondence between the preset business scenarios and the scene prompt level;

[0043] If there is a target scenario prompt level, determining the business scenario corresponding to the target scenario prompt level as the target business scenario; the target scenario prompt level indicates that a prompt is required;

[0044] Determine, in the feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type.

[0045] In some exemplary embodiments, the feedback prompt unit is configured to execute:

[0046] Determine the total amount of target feedback information of the target information type;

[0047] When the total quantity exceeds a preset quantity threshold, a feedback prompt is given to the business processing node associated with the target business scenario based on the target feedback information of the target information type.

[0048] In some exemplary embodiments, the apparatus further comprises:

[0049] A newly added information type searching unit is configured to search and determine whether there is a newly added information type in each of the information types;

[0050] The new information feedback prompt unit is configured to perform feedback prompts to the business processing node associated with the business scenario corresponding to the new information type based on the feedback information corresponding to the new information type when the new information type is found.

[0051] In some exemplary embodiments, the apparatus further comprises:

[0052] A first quantity determination unit is configured to determine, for each of the feedback information subsets, the quantity of feedback information corresponding to each of the information types in the feedback information subset, to obtain a total quantity of feedback corresponding to each of the information types in each of the business scenarios;

[0053] The distribution graph generating unit is configured to generate an information type distribution graph based on the total number of feedbacks corresponding to each information type in each of the business scenarios.

[0054] In some exemplary embodiments, the distribution map generating unit is configured to execute:

[0055] For each of the business scenarios, based on the total number of feedbacks for each information type corresponding to the business scenario, the information types are arranged in descending order;

[0056] A preset number of information types ranked first are selected as key information types, and based on the total number of feedbacks corresponding to the preset number of key information types, an information type distribution diagram corresponding to the business scenario is generated.

[0057] In some exemplary embodiments, the distribution map generating unit is configured to execute:

[0058] For each information type, determine the sum of the total number of feedbacks of the information type corresponding to each business scenario, and obtain the total number of type feedbacks of each information type;

[0059] Based on the total number of type feedbacks of each of the information types, an information type distribution diagram of the information type dimension is generated.

[0060] In some exemplary embodiments, the distribution map generating unit is configured to execute:

[0061] For each information type, based on the feedback time of the feedback information of the information type corresponding to each business scenario, determine the total number of time feedbacks corresponding to the preset time granularity of the preset time period;

[0062] Based on the total number of time feedbacks corresponding to the preset time granularity of each information type in the preset time period, a distribution graph of the information type in the time dimension is generated.

[0063] In some exemplary embodiments, the scenario and type determination unit is configured to execute: inputting each piece of feedback information in the feedback information set into a large language model respectively, and determining the business scenario and information type to which each piece of feedback information belongs through the large language model.

[0064] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0065] processor;

[0066] a memory for storing instructions executable by the processor;

[0067] Wherein, the processor is configured to execute the instructions to implement the data processing method of the first aspect mentioned above.

[0068] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the data processing method of the first aspect described above.

[0069] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the data processing method of the first aspect described above is implemented.

[0070] The embodiment of the present disclosure obtains feedback information within a preset time period to obtain a feedback information set, and determines the business scenario and information type to which each piece of feedback information belongs, and then aggregates the feedback information according to the business scenario to which each piece of feedback information belongs to obtain a feedback information subset corresponding to each business scenario, and in a case where each of the above-mentioned business scenarios includes a target business scenario, in the feedback information subset corresponding to the target business scenario, target feedback information of a target information type is determined, and the target information type is a non-consultation type, and based on the target feedback information of the target information type, feedback prompts are given to the business processing node associated with the target business scenario, thereby improving the processing efficiency of the feedback information.

[0071] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0073] Figure 1 is a schematic diagram of an application environment of a data processing method according to an exemplary embodiment;

[0074] Figure 2 is a flowchart of a data processing method according to an exemplary embodiment;

[0075] Figure 3 is a flowchart of another data processing method according to an exemplary embodiment;

[0076] Figure 4 is a flowchart of another data processing method according to an exemplary embodiment;

[0077] Figure 5 is an example of an information type distribution diagram according to an exemplary embodiment;

[0078] Figure 6 is a schematic diagram of a system architecture for implementing a data processing method according to an exemplary embodiment;

[0079] Figure 7 is a structural block diagram of a data processing device according to an exemplary embodiment;

[0080] Figure 8 It is a structural block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0081] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0082] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0083] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0084] See also Figure 1, which is a schematic diagram of an application environment according to an exemplary embodiment, the application environment may include a data processing server 110 and multiple business processing nodes 120, and the multiple business processing nodes 120 may correspond to different business scenarios. The data processing server 110 and each business processing node 120 may communicate via a wired or wireless network connection.

[0085] Among them, the data processing server 110 can collect feedback information from multiple business channels. The feedback information is usually presented in the form of questions, and the questions involved include but are not limited to different question types such as consulting questions, technical questions, and product questions. The data processing method implemented in the present disclosure is executed based on the collected feedback information, and then through interaction with multiple business processing nodes 120, efficient, accurate, and comprehensive processing of the problems involved in the feedback information is achieved.

[0086] It should be noted that the node in the embodiment of the present disclosure can be an independent Server process, which can be distinguished by IP port. The node can be deployed on one or more servers. Generally speaking, one physical server independently deploys one node to achieve high availability. Among them, the server mentioned in the embodiment of the present disclosure can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or an edge computing node, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0087] Figure 2 is a flow chart of a data processing method according to an exemplary embodiment. The data processing method can be applied to Figure 1 The data processing server shown, specifically, Figure 2 As shown, the method may include the following steps S201-S209:

[0088] In step S201, feedback information within a preset time period is obtained to obtain a feedback information set.

[0089] The feedback information represents the problems reported by the user during the interaction with the service, so the feedback information can also be referred to as problem feedback data. The embodiment of the present disclosure does not limit the interaction mode with the service, which can be a conversational interaction mode or other interaction modes.

[0090] The preset time period can be set based on actual needs, for example, one day, three days or one week, etc. Feedback information within the preset time period can be obtained from multiple channels, so that the feedback information set can contain richer information, which is conducive to improving the accuracy and comprehensiveness of data processing.

[0091] In step S203, based on each piece of feedback information in the feedback information set, the business scenario and information type to which each piece of feedback information belongs are determined.

[0092] Among them, the information type of the feedback information can be reflected by the problem type of the problem involved in the feedback information. For example, the information type can include consulting type (for example, when to ship, etc.), product type (for example, suggestions for product improvement, etc.), technical type (for example, system optimization suggestions, etc.), among which other information types except consulting type can be considered as non-consulting type.

[0093] Exemplarily, based on each piece of feedback information in a feedback information set, determining the business scenario and information type to which each piece of feedback information belongs may include: inputting each piece of feedback information in the feedback information set into a large language model respectively, and determining the business scenario and information type to which each piece of feedback information belongs through the large language model.

[0094] Among them, the large language model is based on deep learning and neural network technology. Its specific functions include natural language understanding, text generation, dialogue system, language translation, text summarization, etc. Through the training of massive text data, it can predict contextual relationships and achieve semantic understanding and generation. The large language model is used to determine the business scenario and information type to which each feedback information belongs, which can improve the accuracy of determining the business scenario and information type to which each feedback information belongs.

[0095] In the disclosed embodiments, the information types determined by the large language model may include consulting types (e.g., when to ship, etc.), product types (e.g., suggestions for product improvements, etc.), and technical types (e.g., suggestions for system optimization, etc.), among which information types other than consulting information types may be considered non-consulting types.

[0096] In a specific implementation, a corresponding scenario prompt text may be pre-constructed for a business scenario, and the scenario prompt text is used to indicate that a business scenario classification task is performed according to a business scenario classification example to output a business scenario. For example, a business scenario may include a live broadcast scenario, a short video scenario, a merchant scenario, etc. Then, when the business scenario to which each feedback information belongs is determined by a large language model, the classification function of the large language model and the above-mentioned scenario prompt text may be used to enable the large language model to perform a business scenario classification task on the input feedback information based on the scenario prompt text to output the business scenario corresponding to the feedback information. A corresponding information type prompt text may be pre-constructed for an information type, and the information type prompt text is used to indicate that an information type classification task is performed according to an information type classification example to output an information type. For example, an information type may include a consulting question type, a product question type, a technical question type, etc. Then, when the information type to which each feedback information belongs is determined by a large language model, the classification function of the large language model and the above-mentioned information type prompt text may be used to enable the large language model to perform an information type classification task on the input feedback information based on the information type prompt text to output the information type corresponding to the feedback information.

[0097] In other examples, the above-mentioned scenario prompt text and information type prompt text can both be in the text form of a thinking chain. For example, the scenario thinking chain prompt text can be used to prompt reasoning in multiple steps to gradually determine the business scenario of the input feedback information, and the information type thinking chain prompt text can be used to prompt reasoning in multiple steps to gradually determine the information type of the input feedback information. Since the text prompt of the thinking chain ensures a logical and traceable reasoning process, it further improves the accuracy of determining the business scenario and information type of each feedback information, which is conducive to further improving the accuracy of data processing.

[0098] In step S205, the feedback information in the feedback information set is aggregated according to the business scenarios to which the feedback information belongs, so as to obtain feedback information subsets corresponding to the business scenarios.

[0099] Specifically, for each determined business scenario, feedback information belonging to the business scenario is aggregated to form a feedback information subset corresponding to the business scenario.

[0100] In step S207, when each of the business scenarios includes a target business scenario, it is determined that in a feedback information subset corresponding to the target business scenario, the information type is target feedback information of a target information type, and the target information type is a non-consulting type.

[0101] Among them, the target business scenario can be set based on multiple business scenarios involved in the business. For example, the target business scenario can be a business scenario that needs to be focused on among multiple business scenarios, such as a live broadcast scenario.

[0102] This public embodiment takes into account that the problems involved in non-consulting feedback information are usually handled with low efficiency by customer service. Therefore, when there is a target business scenario in the determined business scenarios, it is further determined that the information type in the feedback information subset corresponding to the target business scenario is target feedback information of a non-consulting type. The target information type can be any non-consulting type, such as a technical problem type, a product problem type, etc.

[0103] In some exemplary embodiments, the above-mentioned step S207 may include: determining the scene prompt level corresponding to each of the business scenarios based on preset scene prompt mapping information, and the preset scene prompt mapping information represents the correspondence between the preset business scenarios and the scene prompt level; if there is a target scene prompt level, determining the business scenario corresponding to the target scene prompt level as the target business scenario, and the target scene prompt level indicates that a prompt is required; determining the target feedback information whose information type is the target information type in the feedback information subset corresponding to the target business scenario.

[0104] Specifically, the server can maintain preset scene prompt mapping information that characterizes the correspondence between preset business scenarios and scene prompt levels, wherein the preset business scenarios can be set based on actual business conditions, for example, they can include live broadcast scenarios, short video scenarios, etc., wherein the live broadcast scenarios can also be subdivided into more business scenarios, and the number and granularity of the preset business scenarios are not specifically limited in the embodiments of the present disclosure. The scene prompt level corresponding to each preset business scenario can be set based on the actual business situation, for example, the scene prompt level can be set to level 0 and level 1, wherein level 0 means that no prompt is required, and level 1 means that a prompt is required. Of course, more levels can be set as needed, and the embodiments of the present disclosure do not specifically limit the setting method of the scene prompt level. It can be understood that the preset scene prompt mapping information can also be adjusted according to the needs of actual applications, such as adding corresponding relationships, adjusting corresponding relationships, and deleting corresponding relationships, etc. In the above implementation, the target business scenario that needs to be prompted is determined based on the preset scene prompt mapping information, which improves the flexibility of data processing in the embodiments of the present disclosure.

[0105] In step S209, based on the target feedback information of the target information type, a feedback prompt is given to the business processing node associated with the target business scenario.

[0106] In the disclosed embodiment, each business scenario corresponds to a business processing node, and the business processing node can be used to process the feedback information of the corresponding business scenario, such as processing the problems involved in the feedback information. Problem description information can be generated based on the target feedback information of the target information type corresponding to the target business scenario, and problem feedback prompt information can be generated based on the problem description information, and then the problem feedback prompt information is sent to the business processing node associated with the target business scenario, so that the business processing node processes the problem described in the problem description information after receiving the problem feedback prompt information.

[0107] Taking the target business scenario as the live broadcast scenario and the target information type as the technical type as an example, if the feedback information is "improving the fluency of the live broadcast interface", then the business scenario corresponding to the feedback information is the live broadcast scenario, and the information type is a technical problem. Then, based on the feedback information, feedback prompts can be given to the business processing node associated with the live broadcast scenario. For example, problem feedback prompt information representing "improving the fluency of the live broadcast interface" can be directly sent to the business processing node associated with the live broadcast scenario, so that the technical problem can be promptly delivered to the business processing node, and the technical problem can be handled quickly and accurately.

[0108] In some exemplary embodiments, in order to further improve the processing efficiency of feedback information, the above-mentioned step S209, when providing feedback prompts to the business processing node associated with the target business scenario based on the target feedback information of the target information type, may include: determining the total number of target feedback information of the target information type; and when the total number exceeds a preset number threshold, providing feedback prompts to the business processing node associated with the target business scenario.

[0109] Among them, the preset quantity threshold can be set based on the actual application situation, and different business scenarios and different target information types can be set differently.

[0110] Specifically, for the feedback information subset corresponding to the target business scenario, the total number of target feedback information of the target information type in the feedback information subset can be counted. When the total number exceeds the preset number threshold, it indicates that there are many problems of the target information type in the target business scenario and they need to be dealt with promptly and effectively. At this time, based on the target feedback information of the target information type, feedback prompts are given to the business processing nodes associated with the target business scenario, which is conducive to improving the timeliness and effectiveness of handling key issues in key business scenarios.

[0111] The above technical solutions of the embodiments of the present disclosure improve the processing efficiency, processing accuracy and processing coverage of issues involved in a large amount of feedback information, especially non-consulting issues such as technical issues, product issues, etc.

[0112] In some exemplary embodiments, Figure 3 As shown, after determining the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set in the aforementioned step S203, the method may further include:

[0113] In step S301, it is checked whether there is a newly added information type in the determined information types.

[0114] Specifically, the server can maintain a list of existing information types. After the large language model determines the information type to which each feedback information belongs for the current feedback information set, it can search based on the existing information type list to see whether each currently determined information type is in the existing information type list. If a currently determined information type is not in the existing information type list, it indicates that the information type is a newly added information type, and the following step S303 can be executed at this time.

[0115] In step S303, if the newly added information type is found, feedback is given to the business processing node associated with the business scenario corresponding to the newly added information type based on the feedback information corresponding to the newly added information type.

[0116] Among them, the business scenario corresponding to the newly added information type can be an existing business scenario or a new business scenario. The determination method is similar to that of the new information type. The server can search the list of existing business scenarios based on the dimension to see whether the business scenario corresponding to the newly added information type is a new business scenario.

[0117] In the above implementation mode, new information types are usually searched for, and when new information types exist, feedback prompts are given to the business processing nodes associated with the business scenarios corresponding to the new information types based on the feedback information corresponding to the new information types, thereby improving the processing efficiency, accuracy and comprehensiveness of the feedback information.

[0118] In some exemplary embodiments, Figure 4 As shown, after obtaining the feedback information subsets corresponding to the business scenarios in step S205, the method further includes:

[0119] In step S401, for each of the feedback information subsets, the number of feedback information corresponding to each of the information types in the feedback information subset is determined to obtain the total number of feedbacks corresponding to each information type in each of the business scenarios.

[0120] In step S403, an information type distribution diagram is generated based on the total number of feedbacks corresponding to each information type in each of the business scenarios.

[0121] Specifically, for each feedback information subset of each business scenario, the number of feedback information corresponding to each information type in the feedback information subset is determined. For example, the number of feedback information corresponding to the technical problem type in the feedback information subset and the number of feedback information corresponding to the product problem type in the feedback information subset can be determined respectively. Then, based on the total number of feedbacks of each information type corresponding to the business scenario, an information type distribution map can be generated, which is conducive to intuitively displaying the distribution of information types for each business scenario, improving the effectiveness of data processing results, and further improving the processing efficiency and accuracy of feedback information.

[0122] The information type distribution graph in the embodiment of the present disclosure may include an information type distribution graph of at least one dimension, and the at least one dimension may include a business scenario dimension, an information type dimension, and a time dimension to further improve the effectiveness of the data processing results.

[0123] Based on this, in some exemplary embodiments, the above-mentioned step S403, when generating an information type distribution map based on the total number of feedbacks corresponding to each information type in each business scenario, may include: for each business scenario, based on the total number of feedbacks corresponding to each information type in the business scenario, arranging each information type in descending order; selecting a preset number of information types ranked first as key information types, and generating an information type distribution map corresponding to the business scenario based on the total number of feedbacks corresponding to the preset number of key information types.

[0124] See also Figure 5 , which shows an example of an information type distribution diagram provided by an embodiment of the present disclosure, such as Figure 5 (1) in the figure shows the information type distribution diagram of the business scenario dimension, which involves three business scenarios, including the information type distribution diagram corresponding to each business scenario, and the information type distribution diagram of each business scenario is used to highlight the total number of feedbacks corresponding to the top three key information types under the business scenario, and the top three key information types are consulting question type, product question type and technical question type. By generating the information type distribution diagram of the business scenario dimension, key issues can be highlighted from the perspective of the business scenario, which is conducive to improving the processing efficiency and accuracy of each business scenario for the issues involved in the feedback information.

[0125] In some exemplary embodiments, when generating an information type distribution diagram based on the total number of feedbacks corresponding to each information type in each of the business scenarios, the above-mentioned step S403 may include: for each information type, determining the sum of the total number of feedbacks corresponding to the information type in each of the business scenarios, and obtaining the total number of type feedbacks for each of the information types; and generating an information type distribution diagram of the information type dimension based on the total number of type feedbacks for each of the information types.

[0126] Specifically, the sum of the total number of type feedbacks of each information type can be calculated first, and then the proportion of each information type can be determined based on the quotient of the total number of type feedbacks of each information type and the sum, and then an information type distribution diagram of the information type dimension can be generated based on the proportion of each information type.

[0127] Continue to see Figure 5 , where (2) is an information type distribution diagram of the information type dimension, and the information types involved include product problem types, technical problem types, consulting problem types and other problem types. The information type distribution diagram of the information type dimension shows the proportion of the above-mentioned information types, highlighting key issues from the perspective of information type, which is conducive to improving the processing efficiency and accuracy of the issues involved in the feedback information.

[0128] In some exemplary embodiments, when generating an information type distribution map based on the total number of feedbacks for each information type corresponding to each of the business scenarios, the above-mentioned step S403 may include: for each information type, determining the total number of time feedbacks corresponding to the preset time granularity of the preset time period based on the feedback time of the feedback information of the information type corresponding to each of the business scenarios; and generating an information question type distribution map in the time dimension based on the total number of time feedbacks corresponding to the preset time granularity of each of the information types in the preset time period.

[0129] Each feedback information corresponds to an information feedback time, which represents the time for feeding back the corresponding feedback information within the aforementioned preset time period. The preset time granularity of the preset time period can be determined based on the preset time period. For example, when the preset time period is 1 day, the preset time granularity can be 1 hour; when the preset time period is 1 week, the preset time granularity can be 1 day.

[0130] Specifically, for each information type, at the preset time granularity of the preset time period, for the feedback information corresponding to the information type in all business scenarios, the sum of the feedback information of the information type with feedback time at the same preset time granularity is counted to obtain the total number of time feedbacks corresponding to the preset time granularity, and then based on the total number of time feedbacks corresponding to the preset time granularity of each information type in the preset time period, a distribution diagram of the information type in the time dimension can be generated.

[0131] Continue to see Figure 5, where (3) shows the information type distribution diagram in the time dimension. The preset time period is from October 4, year A to October 10, year A, and the preset time granularity is 1 day. It shows the distribution trends of product problem types, consulting problem types, technical problem types, and other problem types in the preset time period, highlighting the changes of each information type from a time perspective, which is conducive to improving the processing efficiency and accuracy of the problems involved in the feedback information.

[0132] It can be understood that, in the embodiments of the present disclosure, after the information type distribution map is generated, the information type distribution map can also be displayed based on the associated terminals.

[0133] Figure 6 FIG. 1 is a schematic diagram of the overall system architecture for implementing the data processing method provided by the embodiment of the present disclosure. Figure 6 As shown, the overall system architecture may include a display layer, a service layer, a data layer, and a storage layer. The display layer can display the process data and results of data processing in the form of charts and lists through a visual interface to help each business processing node intuitively understand the data; the service layer is used to implement the data processing method of the embodiment of the present disclosure; the data layer is used to collect feedback information from multiple channels, and can also perform data cleaning on the collected feedback information, remove noise and duplicate data, so as to improve data quality and ensure the real-time, comprehensiveness, and effectiveness of the data; the storage layer is used to store feedback information, data processing results, etc. through a database.

[0134] Figure 7 is a structural block diagram of a data processing device according to an exemplary embodiment. Figure 7 , the data processing device 700 comprises:

[0135] The feedback information acquisition unit 710 is configured to acquire feedback information within a preset time period to obtain a feedback information set;

[0136] The scenario and type determination unit 720 is configured to determine the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set;

[0137] The aggregation unit 730 is configured to aggregate the feedback information in the feedback information set according to the business scenarios to which the feedback information belongs, to obtain feedback information subsets corresponding to the business scenarios respectively;

[0138] The target feedback determination unit 740 is configured to determine, when each of the business scenarios includes a target business scenario, target feedback information whose information type is a target information type in a feedback information subset corresponding to the target business scenario; and the target information type is a non-consultation type;

[0139] The feedback prompting unit 750 is configured to execute target feedback information based on the target information type and provide feedback prompts to the business processing node associated with the target business scenario.

[0140] In some exemplary embodiments, the target information determination unit 740 is configured to execute:

[0141] Based on the preset scene prompt mapping information, determining the scene prompt level corresponding to each of the business scenarios; the preset scene prompt mapping information represents the correspondence between the preset business scenarios and the scene prompt level;

[0142] If there is a target scenario prompt level, determining the business scenario corresponding to the target scenario prompt level as the target business scenario; the target scenario prompt level indicates that a prompt is required;

[0143] Determine, in the feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type.

[0144] In some exemplary implementations, the problem feedback prompting unit 750 is configured to execute:

[0145] Determine the total amount of target feedback information of the target information type;

[0146] When the total quantity exceeds a preset quantity threshold, a feedback prompt is given to the business processing node associated with the target business scenario based on the target feedback information of the target information type.

[0147] In some exemplary embodiments, the apparatus 700 further includes:

[0148] A newly added information type searching unit is configured to search and determine whether there is a newly added information type in each of the information types;

[0149] The new information feedback prompt unit is configured to perform feedback prompts to the business processing node associated with the business scenario corresponding to the new information type based on the feedback information corresponding to the new information type when the new information type is found.

[0150] In some exemplary embodiments, the apparatus 700 further includes:

[0151] A first quantity determination unit is configured to determine, for each of the feedback information subsets, the quantity of feedback information corresponding to each of the information types in the feedback information subset, to obtain a total quantity of feedback corresponding to each of the information types in each of the business scenarios;

[0152] The distribution graph generating unit is configured to generate an information type distribution graph based on the total number of feedbacks corresponding to each information type in each of the business scenarios.

[0153] In some exemplary embodiments, the distribution map generating unit is configured to execute:

[0154] For each of the business scenarios, based on the total number of feedbacks for each information type corresponding to the business scenario, the information types are arranged in descending order;

[0155] A preset number of information types ranked first are selected as key information types, and based on the total number of feedbacks corresponding to the preset number of key information types, an information type distribution diagram corresponding to the business scenario is generated.

[0156] In some exemplary embodiments, the distribution map generating unit is configured to execute:

[0157] For each information type, determine the sum of the total number of feedbacks of the information type corresponding to each business scenario, and obtain the total number of type feedbacks of each information type;

[0158] Based on the total number of type feedbacks of each of the information types, an information type distribution diagram of the information type dimension is generated.

[0159] In some exemplary embodiments, the distribution map generating unit is configured to execute:

[0160] For each information type, based on the feedback time of the feedback information of the information type corresponding to each business scenario, determine the total number of time feedbacks corresponding to the preset time granularity of the preset time period;

[0161] Based on the total number of time feedbacks corresponding to the preset time granularity of each information type in the preset time period, a distribution graph of the information type in the time dimension is generated.

[0162] In some exemplary embodiments, the scenario and type determination 720 unit is configured to execute: inputting each piece of feedback information in the feedback information set into a large language model respectively, and determining the business scenario and information type to which each piece of feedback information belongs through the large language model.

[0163] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0164] In addition, the device provided in the above embodiment, when implementing its function, only uses the division of the above-mentioned functional modules as an example. In actual application, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0165] In an exemplary embodiment, an electronic device is also provided, including a processor; a memory for storing instructions executable by the processor; wherein, when the processor is configured to execute the instructions stored in the memory, it implements the data processing method provided in any of the above embodiments.

[0166] The electronic device may be a terminal, a server or a similar computing device. For example, the computer running on a server Figure 8 is a hardware structure block diagram of a server running a data processing method provided by an embodiment of the present invention, such as Figure 8 As shown, the server 900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 810 (the processor 810 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 830 for storing data, and one or more storage media 820 (such as one or more mass storage devices) for storing application programs 823 or data 822. Among them, the memory 830 and the storage medium 820 can be short-term storage or permanent storage. The program stored in the storage medium 820 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 810 can be configured to communicate with the storage medium 820 and execute a series of instruction operations in the storage medium 820 on the server 800. The server 800 may also include one or more power supplies 860, one or more wired or wireless network interfaces 850, one or more input and output interfaces 840, and / or one or more operating systems 821, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0167] The input / output interface 840 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 800. In one example, the input / output interface 840 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 840 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0168] It can be understood by those skilled in the art that Figure 8 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 8 More or fewer components as shown, or with Figure 8 Different configurations are shown.

[0169] In an exemplary embodiment, a computer-readable storage medium is also provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the data processing method provided in any of the above embodiments.

[0170] In an exemplary embodiment, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the data processing method provided in any of the above embodiments is implemented.

[0171] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0172] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A data processing method, characterized in that: include: Obtain feedback information within a preset time period to obtain a feedback information set; Based on each piece of feedback information in the feedback information set, determining a business scenario and an information type to which each piece of feedback information belongs; Aggregating the feedback information in the feedback information set according to the business scenarios to which the feedback information belongs, to obtain feedback information subsets corresponding to the business scenarios; In a case where each of the business scenarios includes a target business scenario, determining, in a feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type; The target information type is a non-consulting type; Based on the target feedback information of the target information type, feedback prompts are given to the business processing node associated with the target business scenario.

2. The method according to claim 1, characterized in that In the case where each of the business scenarios includes a target business scenario, determining the target feedback information of the target information type in the feedback information subset corresponding to the target business scenario includes: Based on the preset scene prompt mapping information, determining the scene prompt level corresponding to each of the business scenarios; the preset scene prompt mapping information represents the correspondence between the preset business scenarios and the scene prompt level; If there is a target scenario prompt level, determining the business scenario corresponding to the target scenario prompt level as the target business scenario; the target scenario prompt level indicates that a prompt is required; Determine, in the feedback information subset corresponding to the target business scenario, target feedback information whose information type is a target information type.

3. The method according to claim 1 or 2, characterized in that: The target feedback information based on the target information type, providing feedback prompts to the business processing node associated with the target business scenario, includes: Determine the total amount of target feedback information of the target information type; When the total quantity exceeds a preset quantity threshold, a feedback prompt is given to the business processing node associated with the target business scenario based on the target feedback information of the target information type.

4. The method according to claim 1, characterized in that After determining the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set, the method further includes: Find out whether there is a new information type in each of the determined information types; If the newly added information type is found, a feedback prompt is given to the business processing node associated with the business scenario corresponding to the newly added information type based on the feedback information corresponding to the newly added information type.

5. The method according to claim 1, characterized in that: After obtaining the feedback information subsets corresponding to the business scenarios, the method further includes: For each of the feedback information subsets, determine the number of feedback information corresponding to each of the information types in the feedback information subset, and obtain the total number of feedbacks corresponding to each information type in each of the business scenarios; Based on the total number of feedbacks of each information type corresponding to each of the business scenarios, an information type distribution diagram is generated.

6. The method according to claim 5, characterized in that The generating of the information type distribution diagram based on the total number of feedbacks corresponding to each information type in each business scenario includes: For each of the business scenarios, based on the total number of feedbacks for each information type corresponding to the business scenario, the information types are arranged in descending order; A preset number of information types ranked first are selected as key information types, and based on the total number of feedbacks corresponding to the preset number of key information types, an information type distribution diagram corresponding to the business scenario is generated.

7. The method according to claim 5, characterized in that The generating of the information type distribution diagram based on the total number of feedbacks corresponding to each information type in each business scenario includes: For each information type, determine the sum of the total number of feedbacks of the information type corresponding to each business scenario, and obtain the total number of type feedbacks of each information type; Based on the total number of type feedbacks of each of the information types, an information type distribution diagram of the information type dimension is generated.

8. The method according to claim 5, characterized in that The generating of the information type distribution diagram based on the total number of feedbacks corresponding to each information type in each business scenario includes: For each information type, based on the feedback time of the feedback information of the information type corresponding to each business scenario, determine the total number of time feedbacks corresponding to the preset time granularity of the preset time period; Based on the total number of time feedbacks corresponding to the preset time granularity of each information type in the preset time period, a distribution graph of the information type in the time dimension is generated.

9. The method according to claim 1, characterized in that: The determining, based on each piece of feedback information in the feedback information set, a business scenario and an information type to which each piece of feedback information belongs includes: Each piece of feedback information in the feedback information set is input into a large language model respectively, and the business scenario and information type to which each piece of feedback information belongs are determined by the large language model.

10. A data processing device, characterized in that: include: A feedback information acquisition unit, configured to acquire feedback information within a preset time period to obtain a feedback information set; A scenario and type determination unit, configured to determine the business scenario and information type to which each piece of feedback information belongs based on each piece of feedback information in the feedback information set; an aggregation unit, configured to aggregate the feedback information in the feedback information set according to the business scenarios to which the feedback information belongs, to obtain feedback information subsets corresponding to the business scenarios respectively; a target feedback determination unit configured to determine, when each of the business scenarios includes a target business scenario, target feedback information whose information type is a target information type in a feedback information subset corresponding to the target business scenario; The target information type is a non-consulting type; The feedback prompt unit is configured to execute target feedback information based on the target information type and provide feedback prompts to the business processing node associated with the target business scenario.

11. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the data processing method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the data processing method as claimed in any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 9 is implemented.

Images