Question processing method and device, electronic equipment and storage medium

Abstract

The invention provides a problem processing method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a to-be-processed problem through a problem diagnosis agent, and determining a problem type of the problem; processing the problem according to the type of the problem by using a problem solving agent and / or an expert agent to obtain a response result of the problem; outputting feedback information based on the question and the response result of the question by using a question feedback agent; wherein the output feedback information comprises knowledge used for updating a knowledge base, and the knowledge is obtained by summarizing the question feedback agent based on the question and the response result. Through the method, the problem processing efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of problem processing, and in particular, to a problem processing method and device, an electronic device, and a storage medium. BACKGROUND

[0002] After a customer experiences a product, or purchases and uses a product, there can be some problems that need to be solved, and customer support is a key link for enterprises to improve user experience and promote business growth, and is also a core hub for promoting technology accumulation and upgrading product competitiveness. The traditional manual support mode relies on a large number of human resources, and has the pain points of response delay, long solution period, and difficulty in accumulating technical experience. SUMMARY

[0003] To overcome the problems in the related art, the present disclosure provides a problem processing method and device, an electronic device, and a storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a problem processing method is provided, and the method comprises: determining a problem to be processed and determining a problem type of the problem by using a problem diagnosis agent; processing the problem according to the problem type by using a problem solving agent and / or an expert agent, to obtain a response result of the problem; outputting feedback information based on the problem and the response result of the problem by using a problem feedback agent; wherein the outputted feedback information comprises knowledge for updating a knowledge base, and the knowledge is obtained by the problem feedback agent based on the problem and the response result.

[0005] In some embodiments, the determining, by the problem diagnosis agent, of the problem type of the problem comprises: determining, by the problem diagnosis agent, whether an object focused on by the problem is a preset target object, and determining a technical field to which the problem belongs in a case where the object focused on by the problem is the target object; the processing, by the problem solving agent and / or the expert agent, of the problem according to the problem type to obtain the response result of the problem comprises: processing, by the problem solving agent and / or the expert agent, the problem according to the technical field to which the problem belongs to obtain the response result.

[0006] In some embodiments, the determining, by the problem diagnosis agent, of the problem type of the problem comprises: determining, by the problem diagnosis agent, whether the problem is a problem in a problem library; The problem solving agent and / or the expert agent processes the problem according to the problem type to obtain a response result of the problem, including: In response to the problem not being in the problem library, the problem diagnosis agent saves the problem to the problem library, and the problem solving agent and / or the expert agent processes the problem and identifies a processing state of the problem in the problem library; wherein the processing state indicates whether the problem is solved.

[0007] In some embodiments, the method further includes: In response to the problem not being in the problem library, the problem diagnosis agent saves the problem to the problem library, and the problem solving agent and / or the expert agent processes the problem and identifies a processing state of the problem in the problem library; wherein the processing state indicates whether the problem is solved.

[0008] In some embodiments, the problem diagnosis agent determines the problem type of the problem, including: The problem diagnosis agent queries a user database to determine a priority of a user associated with the problem; The problem solving agent and / or the expert agent processes the problem according to the problem type to obtain a response result of the problem, including: In response to the priority of the user being higher than or equal to a preset priority threshold, the expert agent processes the problem according to the problem type to obtain the response result; In response to the priority of the user being lower than the preset priority threshold, the problem solving agent processes the problem according to the problem type to obtain the response result.

[0009] In some embodiments, the problem diagnosis agent determines the problem to be processed and determines the problem type of the problem, including: The problem diagnosis agent obtains dialogue information of the user from a dialogue library, and generates the problem to be processed based on the dialogue information and determines the problem type of the problem.

[0010] In some embodiments, the problem solving agent processes the problem according to the problem type to obtain a response result of the problem, including: The problem solving agent detects whether necessary information is missing for solving the problem based on the dialogue information in the dialogue library, and sends prompt information for supplementing the necessary information based on the dialogue library in the case that the necessary information is missing; The problem solving agent obtains the necessary information from the dialogue library, and processes the problem according to the problem type and the necessary information to obtain a response result of the problem.

[0011] In some embodiments, the problem solving agent and / or the expert agent processes the problem according to the problem type to obtain a response result of the problem, including at least one of: The problem solving agent and / or the expert agent retrieves and generates the response result of the problem in the knowledge base according to the problem type; The problem solving agent and / or the expert agent retrieves and generates the response result of the problem in the knowledge base according to the problem type.

[0012] In some embodiments, the expert agent processes the problem according to the problem type to obtain a response result of the problem, including: In response to the expert agent obtaining the help information in the dialogue library, the expert agent processes the problem according to the problem type to obtain a response result of the problem; or, In response to the expert agent determining that the response result of the problem solving agent does not meet the preset quality condition, the expert agent optimizes the response result of the problem according to the problem type to obtain an optimized response result.

[0013] In some embodiments, in response to the expert agent obtaining the help information in the dialogue library, the expert agent processes the problem according to the problem type to obtain a response result of the problem, including: In response to the problem solving agent not solving the problem and sending first help information to the dialogue library, the expert agent processes the problem according to the problem type to obtain the response result in the case of obtaining the first help information in the dialogue library.

[0014] In some embodiments, the problem feedback agent outputs feedback information based on the problem and the response result of the problem, including: The problem feedback agent determines that the problem is not solved from the problem library, or determines that the user is not satisfied with the response result of the problem based on the dialogue library and the user interaction, and sends second help information to the dialogue library; In response to the case that the expert agent acquires the help information in the dialogue library, the problem is processed according to the problem type by using the expert agent to obtain a response result of the problem, which includes: In response to the case that the expert agent acquires the help information in the dialogue library, the problem is processed according to the problem type by using the expert agent to obtain a response result of the problem, which includes:

[0015] In some embodiments, the feedback information output module is configured to output feedback information based on the problem and the response result of the problem by using the problem feedback agent, which includes: The feedback information output module is configured to summarize the problem and the response result of the problem by using the problem feedback agent, and output the knowledge to update the knowledge base in response to the case that a preset update condition is met.

[0016] In some embodiments, the feedback information output module is configured to output feedback information based on the problem and the response result of the problem by using the problem feedback agent, which includes: The feedback information output module is configured to summarize the problem and the response result of the problem by using the problem feedback agent, and output the knowledge to update the knowledge base in response to the case that a preset update condition is met. The feedback information output module is configured to summarize the problem and the response result of the problem by using the problem feedback agent, and output the knowledge to update the knowledge base in response to the case that a preset update condition is met.

[0017] According to a second aspect of the embodiments of the present disclosure, a problem processing device is provided, which includes: The determination module is configured to determine a problem to be processed and determine a problem type of the problem by using a problem diagnosis agent. The processing module is configured to process the problem according to the problem type by using a problem solving agent and / or an expert agent to obtain a response result of the problem. The feedback information output module is configured to output feedback information based on the problem and the response result of the problem by using the problem feedback agent. The output feedback information includes knowledge for updating a knowledge base, and the knowledge is obtained by summarizing the problem and the response result by using the problem feedback agent.

[0018] In some embodiments, the determining module is further configured to use the problem diagnosis agent to determine whether the object of concern of the problem is a preset target object, and if the object of concern of the problem is the target object, to determine the technical field to which the problem belongs; the processing module is further configured to use the problem solving agent and / or the expert agent to process the problem according to the technical field to which the problem belongs, and to obtain the response result.

[0019] In some embodiments, the determining module is further configured to use the problem diagnosis agent to determine whether the problem is a problem in the problem library; the processing module is further configured to, in response to the problem not being a problem in the problem library, use the problem solving agent and / or the expert agent to process the problem according to the problem type to obtain the response result.

[0020] In some embodiments, the apparatus further includes: The saving module is configured to, in response to a problem not being a problem in the problem database, use the problem diagnosis agent to save the problem to the problem database, and use the problem solving agent and / or the expert agent to process the problem and then mark the processing status of the problem in the problem database; wherein, the processing status indicates whether the problem has been solved.

[0021] In some embodiments, the determining module is further configured to use the problem diagnosis agent to query a user database to determine the priority of the user associated with the problem; the processing module is further configured to, in response to the user's priority being higher than or equal to a preset priority threshold, use the expert agent to process the problem according to the problem type to obtain the response result; in response to the user's priority being lower than the preset priority threshold, use the problem solving agent to process the problem according to the problem type to obtain the response result.

[0022] In some embodiments, the determining module is further configured to use the problem diagnosis agent to obtain user dialogue information from a dialogue library, generate the problem to be processed based on the dialogue information, and determine the problem type of the problem.

[0023] In some embodiments, the processing module is further configured to use the problem-solving agent to detect whether necessary information is missing to solve the problem based on the dialogue information in the dialogue library, and send a prompt message to supplement the necessary information based on the dialogue library if the necessary information is missing; use the problem-solving agent to obtain the necessary information from the dialogue library, and process the problem according to the problem type and the necessary information to obtain a response result for the problem.

[0024] In some embodiments, the processing module is further configured to perform at least one of the following processes: Based on the question type, retrieve and generate the response result for the question from the knowledge base; The system searches the network based on the question type and generates a response result for the question.

[0025] In some embodiments, the processing module is further configured to, in response to the expert agent obtaining help information from the dialogue database, utilize the expert agent to process the problem according to the problem type to obtain a response result for the problem; or, in response to the expert agent determining that the response result of the problem-solving agent does not meet preset quality conditions, utilize the expert agent to optimize the response result of the problem according to the problem type to obtain an optimized response result.

[0026] In some embodiments, the processing module is further configured to respond to the problem-solving agent failing to solve the problem and sending a first request for help to the dialogue library, wherein, when the expert agent obtains the first request for help from the dialogue library, it processes the problem according to the problem type to obtain the response result.

[0027] In some embodiments, the feedback information output module is further configured to send a second help request to the dialogue library if it is determined from the question library that the question has not been resolved, or if it is determined from the dialogue library and user interaction that the user is not satisfied with the response to the question; the processing module is further configured to reprocess the question according to the question type when the second help request is obtained from the dialogue library by the expert agent, so as to obtain the response result of the question.

[0028] In some embodiments, the feedback information output module is further configured to utilize the problem feedback agent to summarize based on the problem and the response results of the problem, and output the knowledge to update the knowledge base when a preset update condition is met.

[0029] In some embodiments, the feedback information output module is further configured to use the problem feedback agent to output the knowledge to the dialogue library, and use the expert agent to obtain the knowledge from the dialogue library for accuracy judgment; in response to the expert agent judging that the accuracy of the knowledge meets the preset accuracy condition, a notification message supporting the updating of the knowledge base is sent to the dialogue library, so that the problem feedback agent can use the knowledge to update the knowledge base.

[0030] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; Memory used to store computer programs or instructions; The processor executes the computer program or instructions to implement the steps of the method described in the first aspect above.

[0031] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, the storage medium storing a computer program or instructions that, when executed by a processor, implement the steps of the method described in the first aspect above.

[0032] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program or instructions, which, when executed by a processor, implement the steps of the method described in the first aspect above.

[0033] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: In this embodiment, multi-agent collaboration is employed. A problem diagnosis agent acquires and diagnoses the problem, determining its type. Problem-solving agents and / or expert agents then process the problem based on its type to obtain a response. This significantly reduces reliance on manual intervention and improves problem-solving efficiency. Furthermore, a problem feedback agent outputs feedback information based on the problem and its response to update the knowledge base. This allows knowledge to be accumulated and retained, enabling the system to obtain a response when encountering the same problem again. This approach helps improve problem-solving efficiency, and the continuous learning and enrichment of the knowledge base fosters a self-evolving problem-solving ecosystem.

[0034] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0035] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0036] Figure 1 This is a flowchart illustrating a problem-solving method according to an exemplary embodiment; Figure 2 This is an architecture diagram of a problem-solving system that supports question processing in this embodiment of the disclosure; Figure 3 This is a flowchart illustrating a problem-solving method according to an embodiment of this disclosure; Figure 4This is a block diagram of a problem processing apparatus according to an exemplary embodiment; Figure 5 This is a structural block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0037] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses consistent with some aspects of this disclosure as detailed in the appended claims.

[0038] The customer support technologies in related technologies mainly include the following three types: (1) Document support: Standardized answers are provided through static technical documents (such as product manuals, technical white papers, etc.), and users need to search and filter the content themselves; (2) Community forum support: Relying on open source communities and forums, customer questions are answered through user mutual assistance and expert manual answers; (3) Artificial Intelligence (AI) question answering system based on Retrieval-Augmented Generation (RAG) uses retrieval-augmented generation technology to answer customer questions.

[0039] The above technologies have the following shortcomings: (1) Document support: poor cross-version and cross-product line knowledge correlation, significant information silos, high maintenance costs and lack of interactivity; (2) Community forum support: relies on manual intervention, high information redundancy, delayed response and long cold start cycle; (3) AI question answering system based on RAG has unstable question answer quality, insufficient ability to handle complex questions, and lack of question closed-loop optimization mechanism.

[0040] Based on this, the present disclosure proposes a problem-solving method. Figure 1 This is a flowchart illustrating a problem-solving method according to an exemplary embodiment. For example... Figure 1 As shown, the method mainly includes the following steps: S101. Using a problem diagnosis agent, determine the problem to be processed and the problem type of the problem; S102. Using a problem-solving intelligent agent and / or an expert intelligent agent, the problem is processed according to the problem type to obtain the response result of the problem; S103. Using a problem feedback agent, output feedback information based on the problem and the response result of the problem; wherein, the output feedback information includes knowledge for updating the knowledge base, and the knowledge is summarized by the problem feedback agent based on the problem and the response result.

[0041] In this embodiment of the disclosure, the problem-solving method can be applied to an electronic device, which can be a server or a terminal device. For example, the terminal device includes a mobile terminal or a fixed terminal. The mobile terminal can include mobile phones, tablets, laptops, wearable devices, etc.; the fixed terminal can include scanners or printers, etc. As a type of computer, the server can provide computing or application services to other clients (such as computers, smartphones, and other terminal devices, or even large factory equipment) in the network.

[0042] The problem-solving method in this embodiment can be configured in a problem-solving device, which can be located in an electronic device. This embodiment does not limit this.

[0043] It should be noted that the execution entity of the embodiments of this disclosure may be, for example, a central processing unit (CPU) in an electronic device in terms of hardware, and may be, for example, a related background service in an electronic device in terms of software, without limitation.

[0044] This disclosure involves multiple intelligent agents, including a problem diagnosis intelligent agent, a problem solving intelligent agent, an expert intelligent agent, and a problem feedback intelligent agent. Each intelligent agent can be understood as a software functional module in an electronic device. The electronic device forms a problem solving system through the above multiple intelligent agents, and the problem solving system is a software service in the electronic device.

[0045] In this embodiment, each intelligent agent can be implemented using the same or different machine learning models, but the functions or capabilities of different agents differ. The machine learning model can be a recurrent neural network model, a convolutional neural network model, or a large language model (LLM), etc. Taking a large language model as an example, a deep neural network is trained using massive amounts of text to obtain a large language model capable of understanding and generating natural language. This large language model can then perform various complex language tasks based on instructions. In this embodiment, each intelligent agent possesses language understanding and analysis capabilities, enabling multiple agents to collaborate and solve problems. Specifically, the problem diagnosis agent can analyze the problem based on its own language understanding and analysis capabilities, allowing the problem-solving agent and / or expert agent to better solve the problem by combining their own language understanding and analysis capabilities; the problem feedback agent can summarize knowledge based on its own language understanding and analysis capabilities.

[0046] In step S101, the electronic device utilizes a problem diagnosis agent to determine the problem to be processed and its type. The problem to be processed can be any product-related issue, such as product price, product-related technical issues, or pre-sales and after-sales services related to the product. The problem type may involve factors such as the service stage associated with the problem (e.g., pre-sales or after-sales), the technical field to which the problem belongs, whether the problem has been previously processed, or the problem's priority, etc. This disclosure does not limit the type of problem or the specific problem.

[0047] In some embodiments of this disclosure, when acquiring a problem and determining its type, the electronic device may receive a problem input by a user, such as through voice or other text input, control clicks, etc., and assign the problem to a problem diagnosis agent via a central processing unit, so that the problem diagnosis agent can determine the problem type. In other embodiments, the process of using the problem diagnosis agent to determine the problem to be processed and to determine the problem type includes: The problem diagnosis agent obtains user dialogue information from the dialogue database, generates the problem to be processed based on the dialogue information, and determines the problem type.

[0048] In this embodiment, the problem diagnosis agent is associated with a dialogue library in the electronic device. The dialogue library is a database in the electronic device used to record and process customer interactions. After detecting that a user has initiated a dialogue, the electronic device can notify the problem diagnosis agent, enabling the agent to retrieve the user's dialogue information from the dialogue library and generate a problem to be processed based on the dialogue information, determining the problem type. The user's dialogue information includes information input unidirectionally by the user, and may also include dialogue interaction information between the problem-solving system and the user; this embodiment does not limit this aspect.

[0049] It should be noted that the problem diagnosis agent can be an agent based on a large language model, possessing semantic understanding and analysis capabilities. It can determine the problem and its type based on one or more dialogue messages in a dialogue database. For example, the problem diagnosis agent can analyze each dialogue message currently input by the user, and if the analysis determines that the problem is difficult to determine, it outputs a question from the dialogue database to guide the user to further refine the information and thus regenerate the question. However, if the problem can be determined based on the initial dialogue message input by the user, the problem diagnosis agent directly determines the problem type based on the acquired question.

[0050] It is understood that in this embodiment of the disclosure, the problem diagnosis agent can connect to a dialogue library to achieve dialogue interaction with the user, thereby helping the problem diagnosis agent to obtain more comprehensive information to generate questions and determine the question type, which helps to improve the accuracy of question acquisition, and there is no need to transmit the final question or transmit dialogue information through the central processor to generate questions, which can improve the efficiency of the problem diagnosis agent in acquiring questions.

[0051] In step S102, the electronic device utilizes a problem-solving agent and / or an expert agent to process the problem according to its type, thereby obtaining a response. Both the problem-solving agent and the expert agent can be agents generated based on a large language model. Furthermore, the expert agent and the problem-solving agent can differ not only in the accuracy and / or efficiency of their problem processing but also in the range of problems they can handle. For example, an expert agent may only process specific problem types, while a problem-solving agent may be applicable to all problems.

[0052] In some embodiments of this disclosure, a problem-solving agent or an expert agent may be selected to solve the problem based on its priority or the technical field it belongs to. Furthermore, when the problem type is uncommon, two agents may work together to process the problem and obtain a more accurate response. In other embodiments of this disclosure, the problem-solving agent and / or expert agent may also optimize the problem based on its type, such as making the problem expression more accurate, to obtain a more accurate response.

[0053] Furthermore, in this embodiment of the disclosure, the problem-solving agent and / or expert agent can retrieve the response to the problem based on knowledge stored in an internal knowledge base, or they can obtain the response through a network search. The internal knowledge base can be a database stored in the electronic device, which organizes knowledge related to various aspects of the product; alternatively, the internal knowledge base can be a knowledge base stored in a device associated with the electronic device (such as a server device associated with the problem-solving system in a mobile phone).

[0054] In step S103, the electronic device utilizes a problem feedback agent to output feedback information based on the problem and its response structure. This feedback information includes at least knowledge summarized based on the problem and response results to update the knowledge base. For example, in embodiments of this disclosure, the problem feedback agent can directly access the knowledge base to update the knowledge therein, or the problem feedback agent can feed the knowledge back to the central processing unit (CPU) for updating the knowledge base.

[0055] In some embodiments, the feedback information output by the problem feedback agent may also include the problem and the response result of the problem. The feedback information including the problem and the response result can be fed back to relevant personnel, such as sales personnel, technical support personnel, or managers of the project to which the product involved in the problem belongs, through electronic devices, so that relevant personnel can track the product status in real time and realize closed-loop management.

[0056] In some embodiments, the problem feedback agent may also feed back the problem and the response to the problem to an expert agent, such as enabling the expert agent to further optimize the response.

[0057] It is understood that, in this embodiment of the disclosure, through multi-agent collaboration, a problem diagnosis agent is used to acquire and diagnose problems, determine the problem type, and a problem-solving agent and / or expert agent are used to process the problem based on the problem type to obtain a response result. This greatly reduces reliance on manual intervention and improves the efficiency of problem-solving. In addition, a problem feedback agent is used to output feedback information based on the problem and the response result to update the knowledge base, so that knowledge can be accumulated and deposited. This allows the response result to be obtained based on the knowledge in the knowledge base when the same problem is acquired in the future. In this way, it helps to improve the efficiency of problem-solving, and through continuous learning to enrich the knowledge base, a self-evolving problem-solving ecosystem can be formed.

[0058] In some embodiments, determining the problem type using a problem diagnostic agent includes: Using the problem diagnosis agent, it is determined whether the object of the problem's concern is a preset target object, and if the object of the problem's concern is the target object, the technical field to which the problem belongs is determined; The process of utilizing a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes: The problem is processed using the problem-solving agent and / or the expert agent, according to the technical field to which the problem belongs, to obtain the response result.

[0059] In this embodiment of the disclosure, the problem type includes the technical field to which the problem belongs. The electronic device uses a problem diagnosis agent to determine whether the object of the problem is a preset target object, including determining whether the problem is a technical problem or whether the product associated with the problem is a product that the current problem-solving system can support.

[0060] In this embodiment of the disclosure, when the electronic device determines that the object of interest in the problem is the target object using a problem diagnosis agent, it further determines the technical field to which the problem belongs. This guides the problem-solving agent and / or expert agent to process the problem according to the technical field to which the problem belongs. For example, the problem-solving agent and the expert agent may be models for different technical fields, so a model for the corresponding field can be selected based on the technical field to which the problem belongs. Another example is that both the problem-solving agent and the expert agent have different sub-processing modules for different technical fields, so the corresponding sub-processing modules can be invoked to process the problem, thereby improving the accuracy of problem processing.

[0061] It is understood that in this embodiment of the disclosure, the problem diagnosis agent acts as an "intelligent router". By defining the domain, the problem is guided to the corresponding agent or sub-module for processing, thereby optimizing the allocation of processing resources and improving the accuracy and efficiency of problem processing.

[0062] In some embodiments, determining the problem type using a problem diagnostic agent includes: The problem diagnosis agent is used to determine whether the problem is a problem in the problem database; The process of utilizing a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes: In response to the fact that the problem is not in the problem library, the problem-solving agent and / or the expert agent are used to process the problem according to the problem type to obtain the response result.

[0063] In this embodiment of the disclosure, the problem type includes whether the problem is a problem that has been processed in the past. Problems that have been processed in the past are stored in the problem database. If the current problem is a problem in the problem database, then the response result corresponding to the problem stored in the problem database can be used directly, without having to use the problem-solving agent and / or expert agent to process the problem according to the problem type.

[0064] Understandably, this approach can reduce the duplication of problem-solving, save resources, and improve problem-solving efficiency.

[0065] In this embodiment of the disclosure, the problem diagnosis agent can directly access the problem database to determine whether the problem is a problem that has already been processed and is recorded in the problem database.

[0066] In some embodiments, the method further includes: In response to the fact that the problem is not a problem in the problem database, the problem diagnosis agent saves the problem to the problem database, and the problem solving agent and / or the expert agent process the problem and mark the processing status of the problem in the problem database; wherein, the processing status indicates whether the problem has been solved.

[0067] In this embodiment, if the problem is not in the problem database, the electronic device uses a problem diagnosis agent to save the problem to the problem database, which is equivalent to creating a new problem ticket in the database. The problem-solving agent and / or expert agent can also retrieve the currently saved problem from the problem database and process it. Furthermore, after processing the problem, the problem-solving agent and / or expert agent can also mark the processing status of the problem in the problem database to record whether the problem has been resolved. It should be noted that if a response result is obtained based on the problem-solving agent and / or expert agent, the response result can also be saved to the problem database, and the problem database can also store the problem type, etc.

[0068] It is understood that, in this embodiment of the disclosure, by recording issues in the issue database and identifying the processing status of issues, the management of issues becomes more comprehensive, making it easier for customers and relevant parties to trace the source, and demonstrating good intelligence.

[0069] In some embodiments, determining the problem type using a problem diagnostic agent includes: The problem diagnosis agent is used to query the user database to determine the priority of users associated with the problem; The process of utilizing a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes: In response to the user's priority being higher than or equal to a preset priority threshold, the expert agent processes the problem according to the problem type to obtain the response result. In response to the user's priority being lower than the preset priority threshold, the problem-solving agent processes the problem according to the problem type to obtain the response result.

[0070] In this embodiment of the disclosure, the question type includes the question priority, and the question priority is determined based on the priority of the user associated with the question. The higher the user's priority, the higher the question's priority. For example, users are divided into VIP users and regular users, and questions raised by VIP users have a higher priority than questions raised by regular users.

[0071] As mentioned above, expert agents can outperform problem-solving agents in terms of accuracy and / or efficiency in problem handling. Therefore, for high-priority problems, expert agents can handle them based on problem type; while for relatively low-priority problems, problem-solving agents can handle them based on problem type. In this embodiment, the problem-solving agent and / or expert agent can obtain the priority of the problem (the priority of the user associated with the problem) from the problem database to determine whether the problem needs to be handled. Alternatively, in this embodiment, the problem diagnosis agent can determine the priority of the user associated with the problem and then directly send the problem and problem type to the corresponding agent for processing.

[0072] It is understood that, in this embodiment of the disclosure, the hierarchical processing mechanism can achieve optimized resource allocation and improve the quality and efficiency of problem processing.

[0073] In some embodiments, the process of utilizing a problem-solving agent to handle the problem according to the problem type and obtain a response result for the problem includes: The problem-solving agent uses dialogue information in the dialogue database to detect whether necessary information is missing in order to solve the problem, and if the necessary information is missing, it sends a prompt message to supplement the necessary information based on the dialogue database. The problem-solving agent obtains the necessary information from the dialogue library and processes the problem according to the problem type and the necessary information to obtain the response result of the problem.

[0074] As previously mentioned, the problem diagnosis agent can obtain dialogue information from a dialogue database to generate questions. Although the problem diagnosis agent can generate questions based on dialogue information, the information input by the user may be incomplete, resulting in a lack of necessary information for solving the problem. In this embodiment of the disclosure, the problem-solving agent can also interact with the dialogue database, obtain dialogue information from the database, and detect whether necessary information for solving the problem is missing. If necessary information is detected to be missing, a prompt message for supplementing the necessary information is sent to the dialogue database so that the user can supplement it.

[0075] After obtaining the necessary information from the dialogue database, the problem-solving agent can process the problem according to the problem type and the necessary information, thereby obtaining the response result.

[0076] It is understood that, in the embodiments of this disclosure, by having the problem-solving agent interact with the user based on a dialogue library to obtain the necessary information for solving the problem, the accuracy of the problem-solving agent in handling the problem can be improved.

[0077] In some embodiments, the process of using a problem-solving agent and / or an expert agent to process the problem according to the problem type and obtain a response result for the problem includes at least one of the following: Using the problem-solving agent and / or the expert agent, the response result for the problem is retrieved from the knowledge base and generated according to the problem type; The problem-solving agent and / or the expert agent are used to search the network and generate response results for the problem according to the problem type.

[0078] In this embodiment of the disclosure, the problem-solving intelligent agent and / or expert intelligent agent can retrieve and generate response results for the problem from a knowledge base based on the problem type. The knowledge in the knowledge base includes information derived from historical problems and summaries of their responses, as well as knowledge obtained by administrators integrating internal technical documents and community resources. The problem-solving intelligent agent and / or expert intelligent agent can also search for relevant domain knowledge in the knowledge base based on the problem type, such as the technical field to which the problem belongs. Furthermore, by combining the found knowledge with the problem and utilizing the analytical processing capabilities of the problem-solving intelligent agent and / or expert intelligent agent, they can generate response results for the problem.

[0079] Furthermore, electronic devices support network-based searches, allowing problem-solving agents and / or expert agents to retrieve and generate responses based on the problem type. It should be noted that the information obtained from network searches may be relatively fragmented; problem-solving agents and / or expert agents can integrate and summarize the retrieved information to generate responses.

[0080] It is understood that, in the embodiments of this disclosure, the dual RAG architecture based on the knowledge base and supporting network retrieval enables the problem-solving agent and / or expert agent to obtain more accurate response results to the problem, improves the ability to solve complex problems, and also makes the content of the knowledge base update more accurate and efficient.

[0081] In some embodiments, the step of using the expert agent to process the problem according to the problem type and obtain a response result for the problem includes: In response to the expert agent obtaining a request for help from the dialogue database, the expert agent processes the problem according to the problem type to obtain a response result for the problem; or, In response to the expert agent determining that the response result of the problem-solving agent does not meet the preset quality conditions, the expert agent is used to optimize the response result of the problem according to the problem type to obtain an optimized response result.

[0082] In this embodiment, the help request information obtained by the expert agent from the dialogue database can be either a help request posted by a problem-solving agent or a help request posted by a problem feedback agent. Furthermore, the expert agent can utilize its language analysis and understanding capabilities to analyze whether the response output by the problem-solving agent explains the cause of the problem and the solution, whether the solution is detailed, or whether the response matches the problem. If the cause and solution are not explained, or the solution is not detailed, or the response does not match the problem, then it is determined that the preset quality conditions are not met, and the expert agent re-optimizes the response. For example, if the response is not detailed, the expert agent can process the problem based on the response output by the problem-solving agent and the problem type, where the response output by the problem-solving agent guides the expert agent in processing the problem. If the response does not match the problem, or lacks the cause of the problem or the solution, the expert agent can process the problem based on the problem type to obtain a re-optimized response.

[0083] It should be noted that in this embodiment of the disclosure, the expert agent can access the dialogue database at preset time intervals to determine whether there is a request for help or whether the response result of the problem-solving agent meets the preset quality conditions. Alternatively, the expert agent can be notified to access the dialogue database through the central processing unit.

[0084] It is understood that in this embodiment of the disclosure, the expert intelligent agent intervenes when there is a request for help, or performs a forced upgrade process when a low-quality response is determined, so as to improve the accuracy of the final response result.

[0085] In some embodiments, when the expert agent obtains a request for help from the dialogue database, the expert agent processes the problem according to the problem type to obtain a response result for the problem, including: In response to the problem-solving agent failing to solve the problem and sending a first request for help to the dialogue database, if the expert agent obtains the first request for help from the dialogue database, it processes the problem according to the problem type to obtain the response result.

[0086] In this embodiment, both the problem-solving agent and the expert agent can interact with the dialogue library to collaboratively handle the problem. The electronic device first uses the problem-solving agent to process the problem according to the problem type and outputs the output of the problem-solving agent to the dialogue library. If the output indicates that the problem is not solved, such as the problem-solving agent outputting "no answer found", then the problem-solving agent sends a first request for help to the dialogue library, such as "please help from an expert". After the expert agent obtains the first request for help from the dialogue library, it processes the problem according to the problem type.

[0087] It is understood that in this embodiment of the disclosure, the expert intelligent agent can not only correct, supplement and optimize the response results of the problem-solving intelligence, but also solve the problems that were not solved on the first attempt based on the help information of the problem-solving intelligence. It belongs to a closed-loop feedback collaborative mechanism. Through this collaborative mechanism, dynamic problem processing and optimization can be achieved, which helps to improve the accuracy of problem processing and is conducive to solving complex problems.

[0088] In some embodiments, the step of utilizing a problem feedback agent to output feedback information based on the problem and the response result includes: If the problem feedback agent determines from the problem database that the problem has not been resolved, or if it determines from the dialogue database and user interaction that the user is not satisfied with the response to the problem, it sends a second help request to the dialogue database. When the expert agent obtains a request for help from the dialogue database, the expert agent processes the problem according to the problem type to obtain a response result for the problem, including: When the expert agent obtains the second request for help from the dialogue database, it reprocesses the problem according to the problem type to obtain a response result for the problem.

[0089] In this embodiment of the disclosure, the problem feedback agent can access both the problem database and the dialogue database to interact with the user. When it is determined through the problem database that the problem has not been resolved, or when it is determined through interaction with the user that the user is not satisfied with the response, a second help request is sent to the dialogue database. This allows the expert agent to process the problem and obtain a response result after obtaining the second help request from the dialogue database.

[0090] It should be noted that, as mentioned above, the processing status of a problem in the problem database is identified after the problem-solving agent or expert agent processes the problem. If the problem was initially processed by the problem-solving agent but no response was received, the problem can be reprocessed using any submodule of the expert agent. Conversely, if the problem was initially processed by the expert agent but no response was received, the expert agent can switch submodules to reprocess the problem. The expert agent can record the submodules used for the same problem and delete the record after a response is received. Furthermore, in this embodiment, the first and second requests for help can use different phrases to distinguish the publisher of the request.

[0091] It is understood that in this embodiment of the disclosure, the problem feedback agent can not only provide updated knowledge to the knowledge base, but also publish a second request for help to the dialogue database so that the expert agent can reprocess the problem, thus forming a dual-closed-loop optimized problem-solving system (knowledge base optimization and problem processing optimization), which helps to improve the system's adaptability and long-term reliability.

[0092] In some embodiments, the step of utilizing a problem feedback agent to output feedback information based on the problem and the response result includes: The problem feedback agent summarizes the problem and the response results, and updates the knowledge base when preset update conditions are met.

[0093] In this embodiment of the disclosure, when the problem feedback agent outputs feedback to update the knowledge base based on the problem and the response result, it does not update the knowledge simply by summarizing the knowledge; it also determines whether preset update conditions are met. For example, if there are similar historical problems and corresponding historical knowledge in the knowledge base, the knowledge corresponding to the problem in the knowledge base will only be added if the current knowledge is different from the historical knowledge, or the historical knowledge will be replaced with the currently summarized knowledge if the quality is better.

[0094] It is understood that in this embodiment of the disclosure, by updating the knowledge base only when preset update conditions are met, invalid updates can be reduced and instruction consumption can be reduced.

[0095] In some embodiments, the step of outputting the knowledge to update the knowledge base when a preset update condition is met includes: The knowledge is output to the dialogue database using the question feedback agent, and the knowledge is retrieved from the dialogue database by the expert agent to determine its accuracy. In response to the expert agent determining that the accuracy of the knowledge meets a preset accuracy condition, a notification message supporting the updating of the knowledge base is sent to the dialogue database, so that the question feedback agent can use the knowledge to update the knowledge base.

[0096] In this embodiment, the problem feedback agent outputs the summarized knowledge to a dialogue database, enabling the expert agent to retrieve knowledge from the database and assess its accuracy using its language understanding and analytical capabilities. For example, the expert agent may invoke a domain knowledge graph to review the knowledge, or use its language understanding and semantic analysis to evaluate the logical coherence and contextual rationality of the knowledge to determine its accuracy. If the accuracy meets a preset accuracy condition, the expert agent sends a notification message to the dialogue database to update the knowledge base.

[0097] It is understood that in this embodiment of the disclosure, the knowledge base is only updated when the accuracy of the knowledge is determined by the expert intelligent agent, so that the knowledge base can continuously iterate to obtain higher quality knowledge, thereby gradually improving the problem-solving system's processing quality and efficiency over time.

[0098] Figure 2 This is an architecture diagram of a problem-solving system supporting question processing in this embodiment of the disclosure, as shown in Figure 2. The problem-solving system provides an environment for problem-solving, wherein the customer information database A is the aforementioned user database; the internal knowledge base B is the aforementioned knowledge base; the question list and information C is the aforementioned question database; and the historical dialogues D is the aforementioned dialogue database. Questions raised by users and the information they provide are stored in the historical dialogues C. The problem diagnosis agent 21 observes information from the historical dialogues C and creates new questions and classifies them, i.e., generates questions and determines the question type. The newly created questions are saved in the question list and information C. During this process, the problem diagnosis agent 21 accesses the question list and information C, and only creates and stores a new question in the question list and information C if it determines that the current question does not belong to a historical question in the question list and information C. Furthermore, the problem diagnosis agent 21 also confirms which technical modules the question involves and accesses the customer information database A to determine the user's priority, so that the problem-solving agent 21 and the expert agent 24 can be better utilized to process the problem subsequently. Figure 2In this process, problem-solving agent 23 can retrieve problems from the problem list and information C, and process them by searching the internal knowledge base B and / or the internet. During this process, problem-solving agent 23 can access historical dialogues D to interact with the user and obtain necessary information for problem-solving. After processing a problem and obtaining a response, problem-solving agent 23 updates the processing status of the problem in the problem list and information C. If problem-solving agent 23 fails to obtain a response, it can send a first request for help to expert agent 24 through historical dialogues D. Figure 2 In the process, the problem feedback agent 22 accesses the problem-solving process in historical dialogues D, and accesses the problem list and information C to obtain the problem's processing status to track the progress. If it determines through the problem list and information C that the problem is unresolved, or confirms with the user through historical dialogues D that the problem is unresolved, it then issues a second request for help through historical dialogues D to allow the expert agent to handle the problem. When providing feedback, the problem diagnosis agent 21 first summarizes knowledge based on the problem and its response results, and accesses the internal knowledge base B to determine whether to update it. For example, it obtains the knowledge update suggestions from expert agent 24 from historical dialogues D, and updates the internal knowledge base B if it determines that an update is needed. In addition, the problem feedback agent 22 also synchronizes the response results after problem processing to relevant personnel, such as the corresponding salesperson and project manager. Figure 2 In this context, expert agent 24 can retrieve the problem-solving process from historical dialogues D and check the reasonableness of the response output by problem-solving agent 23, correcting and supplementing it if necessary. As mentioned earlier, expert agent 24 intervenes in the problem based on the first and second help requests in historical dialogues D, and updates the problem list and the processing status of the problem in information C after obtaining a response. Furthermore, expert agent 24 can also retrieve the knowledge summarized by problem feedback agent 22 from historical dialogues D and judge the accuracy of the knowledge, thereby sending a notification message to historical dialogues D to inform problem feedback agent 22 whether to update the internal knowledge base B.

[0099] In this embodiment, the problem diagnosis agent 21, problem feedback agent 22, problem resolution agent 23, and expert agent 24 can all be agents based on a large language model. Through interaction between these agents and the environment, collaboration among multiple agents is achieved, thereby automating the problem-solving process. This significantly reduces the human costs of problem-solving, project management, information communication, and document maintenance, while simultaneously improving the efficiency of user problem-solving and knowledge base updates. Furthermore, closed-loop problem management is achieved through multi-agent collaboration. During the processing, historical dialogues (D), problem lists, and information (C) are recorded and archived, supporting real-time traceability for customers and relevant parties.

[0100] It should be noted that, in this embodiment of the disclosure, it also supports seeking help from humans based on the first help request information and the second help request information, and humans can also confirm the accuracy of the knowledge and the quality of the response results of the problem-solving intelligent agent 23.

[0101] Figure 3 This is a flowchart illustrating a problem-solving method according to an embodiment of this disclosure, such as... Figure 3 As shown, it includes the following steps: S301, User Input.

[0102] In this embodiment of the disclosure, the user can input a problem and a description of the associated problem to handle the problem through multi-agent collaboration.

[0103] S302, Problem Diagnosis: The intelligent agent diagnoses the problem.

[0104] In this embodiment of the disclosure, the problem diagnosis agent truly diagnoses the problem, that is, determines the problem type.

[0105] S303. Is it related to product technology? If so, proceed to step S304.

[0106] In this embodiment of the disclosure, determining the type of problem includes determining whether the problem is related to product technology. If it is related, the problem handling process continues; otherwise, the subsequent problem handling process is not executed.

[0107] S304, Problem-solving intelligent agents handle problems.

[0108] In this embodiment of the disclosure, problems can be addressed primarily through a problem-solving agent, such as by searching a knowledge base or searching online.

[0109] S305. Do we need to ask the user? If yes, proceed to step S301; if no, continue processing the problem.

[0110] In this embodiment of the disclosure, the problem-solving agent first determines whether it needs to ask the user for the necessary information to solve the problem before processing the problem. If necessary, it receives the necessary information input by the user before processing the problem.

[0111] S306. Do you need to seek help from an expert? If yes, proceed to step S307; if no, proceed to step S308.

[0112] In this embodiment of the disclosure, if the problem-solving agent cannot solve the problem, it can seek help from the expert agent to execute the steps of the expert agent in S307 to handle the problem; otherwise, it executes the feedback from the problem feedback agent in S308.

[0113] S307, Expert intelligent agents handle problems.

[0114] S308, Problem Feedback Intelligent Agent Feedback.

[0115] In this embodiment of the disclosure, the problem feedback agent can provide feedback to relevant personnel on the response results of the problem-solving agent, and can also provide feedback on whether the user is satisfied with the response results of the problem-solving agent.

[0116] S309. Has the problem been resolved? If not, return to step S307.

[0117] In this embodiment of the disclosure, if the user is not satisfied with the response result of the problem-solving agent, the problem is processed by an expert agent to obtain a response result.

[0118] S310, the expert agent provides knowledge base update suggestions.

[0119] In this embodiment of the disclosure, the problem feedback agent can also summarize knowledge based on the problem and response results. The expert agent analyzes the summarized knowledge and, if it is determined that the knowledge meets the preset accuracy conditions, provides update suggestions so that the problem feedback agent can update the knowledge base.

[0120] It is understood that, in the embodiments of this disclosure, multi-agent collaboration can greatly reduce reliance on human intervention, improve the efficiency of problem solving, and form a self-evolving problem-solving ecosystem through knowledge accumulation.

[0121] Figure 4 This is a block diagram illustrating a problem-solving apparatus according to an exemplary embodiment. Figure 4 As shown, the device mainly includes: The determination module 401 is configured to use a problem diagnosis agent to determine the problem to be processed and the problem type of the problem. Processing module 402 is configured to use a problem-solving agent and / or an expert agent to process the problem according to the problem type and obtain the response result of the problem; The feedback information output module 403 is configured to use a problem feedback agent to output feedback information based on the problem and the response result of the problem; wherein, the output feedback information includes knowledge for updating the knowledge base, and the knowledge is summarized by the problem feedback agent based on the problem and the response result.

[0122] In some embodiments, the determining module 401 is further configured to use the problem diagnosis agent to determine whether the object of concern of the problem is a preset target object, and if the object of concern of the problem is the target object, to determine the technical field to which the problem belongs; the processing module 402 is further configured to use the problem solving agent and / or the expert agent to process the problem according to the technical field to which the problem belongs, and to obtain the response result.

[0123] In some embodiments, the determining module 401 is further configured to use the problem diagnosis agent to determine whether the problem is a problem in the problem library; the processing module 402 is further configured to, in response to the problem not being a problem in the problem library, use the problem solving agent and / or the expert agent to process the problem according to the problem type to obtain the response result.

[0124] In some embodiments, the apparatus further includes: The saving module is configured to, in response to a problem not being a problem in the problem database, use the problem diagnosis agent to save the problem to the problem database, and use the problem solving agent and / or the expert agent to process the problem and then mark the processing status of the problem in the problem database; wherein, the processing status indicates whether the problem has been solved.

[0125] In some embodiments, the determining module 401 is further configured to use the problem diagnosis agent to query the user database to determine the priority of the user associated with the problem; the processing module 402 is further configured to, in response to the user's priority being higher than or equal to a preset priority threshold, use the expert agent to process the problem according to the problem type to obtain the response result; in response to the user's priority being lower than the preset priority threshold, use the problem solving agent to process the problem according to the problem type to obtain the response result.

[0126] In some embodiments, the determining module 401 is further configured to use the problem diagnosis agent to obtain user dialogue information from a dialogue library, generate the problem to be processed based on the dialogue information, and determine the problem type of the problem.

[0127] In some embodiments, the processing module 402 is further configured to use the problem-solving agent to detect whether necessary information is missing to solve the problem based on the dialogue information in the dialogue library, and send a prompt message to supplement the necessary information based on the dialogue library if the necessary information is missing; use the problem-solving agent to obtain the necessary information from the dialogue library, and process the problem according to the problem type and the necessary information to obtain the response result of the problem.

[0128] In some embodiments, the processing module 402 is further configured to perform at least one of the following processes: Based on the question type, retrieve and generate the response result for the question from the knowledge base; The system searches the network based on the question type and generates a response result for the question.

[0129] In some embodiments, the processing module 402 is further configured to, in response to the expert agent obtaining help information in the dialogue database, utilize the expert agent to process the problem according to the problem type to obtain a response result for the problem; or, in response to the expert agent determining that the response result of the problem-solving agent does not meet preset quality conditions, utilize the expert agent to optimize the response result of the problem according to the problem type to obtain an optimized response result.

[0130] In some embodiments, the processing module 402 is further configured to respond to the problem-solving agent failing to solve the problem and sending a first help request to the dialogue library, and in the case that the expert agent obtains the first help request from the dialogue library, process the problem according to the problem type to obtain the response result.

[0131] In some embodiments, the feedback information output module 403 is further configured to send a second help request to the dialogue library if it is determined from the question library that the question has not been resolved, or if it is determined from the dialogue library and user interaction that the user is not satisfied with the response to the question; the processing module 402 is further configured to reprocess the question according to the question type when the second help request is obtained from the dialogue library by the expert agent, so as to obtain the response result of the question.

[0132] In some embodiments, the feedback information output module 403 is further configured to utilize the problem feedback agent to summarize based on the problem and the response results of the problem, and output the knowledge to update the knowledge base when a preset update condition is met.

[0133] In some embodiments, the feedback information output module 403 is further configured to use the problem feedback agent to output the knowledge to the dialogue library, and use the expert agent to obtain the knowledge from the dialogue library for accuracy judgment; in response to the expert agent judging that the accuracy of the knowledge meets the preset accuracy condition, a notification message supporting the updating of the knowledge base is sent to the dialogue library, so that the problem feedback agent can use the knowledge to update the knowledge base.

[0134] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0135] Figure 5 This is a structural block diagram of an electronic device according to an exemplary embodiment. For example, electronic device 500 may be a mobile phone, tablet computer, wearable device, etc.

[0136] Reference Figure 5 The electronic device 500 may include one or more of the following components: processing component 502, memory 504, power supply component 506, multimedia component 508, audio component 510, input / output (I / O) interface 55, sensor component 514, and communication component 516.

[0137] Processing component 502 typically controls the overall operation of electronic device 500, such as operations associated with at least one of display, telephone call, data communication, camera operation, and recording operation. Processing component 502 may include one or more processors 520 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 502 may include one or more modules to facilitate interaction between processing component 502 and other components. For example, processing component 502 may include a multimedia module to facilitate interaction between multimedia component 508 and processing component 502.

[0138] Memory 504 is configured to store various types of data to support operation on electronic device 500. Examples of such data include at least one of the following: instructions for any application or method operating on electronic device 500, contact data, phonebook data, messages, pictures, and videos. Memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0139] Power supply component 506 provides power to various components of electronic device 500. Power supply component 506 may include at least one of the following: a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 500.

[0140] Multimedia component 508 includes a screen that provides an output interface between electronic device 500 and user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a Touch Panel, the screen may be implemented as a touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 508 includes a front-facing camera and / or a rear-facing camera. When electronic device 500 is in an operating mode, such as a shooting mode or video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0141] Audio component 510 is configured to output and / or input audio signals. For example, audio component 510 includes a microphone (MIC) configured to receive external audio signals when electronic device 500 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 504 or transmitted via communication component 516. In some embodiments, audio component 510 also includes a speaker for outputting audio signals.

[0142] I / O interface 55 provides an interface between processing component 502 and peripheral interface modules, such as keyboards, click wheels, and buttons. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0143] Sensor assembly 514 includes one or more sensors for providing state assessments of various aspects of electronic device 500. For example, sensor assembly 514 may detect the on / off state of electronic device 500, the relative positioning of components such as the display and keypad of electronic device 500, changes in position of electronic device 500 or one of its components, the presence or absence of user contact with electronic device 500, orientation or acceleration / deceleration of electronic device 500, and temperature changes of electronic device 500. Sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 514 may also include an optical sensor, such as a complementary metal-oxide-semiconductor (CMOS) or charge-coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, sensor assembly 514 may also include, but is not limited to, at least one of the following: an accelerometer, a gyroscope, a magnetometer, a pressure sensor, and a temperature sensor.

[0144] Communication component 516 is configured to facilitate wired or wireless communication between electronic device 500 and other devices. Electronic device 500 can access wireless networks based on communication standards, such as Wi-Fi, 4G, 5G, or combinations thereof. In one exemplary embodiment, communication component 516 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 516 also includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth (BT), and other technologies.

[0145] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components.

[0146] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including executable instructions or a computer program, which can be executed by a processor 520 of an electronic device 500 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0147] A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform any of the problem-solving methods described above in the embodiments of this disclosure.

[0148] This disclosure provides a computer program product comprising a computer program or executable instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer program or executable instructions from the computer-readable storage medium and executes the computer program or executable instructions, causing the computer device to perform any of the problem-solving methods described in this disclosure.

[0149] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0150] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A problem-solving method, characterized in that, include: Using a problem diagnosis agent, identify the problem to be addressed and determine the problem type. Using a problem-solving agent and / or an expert agent, the problem is processed according to the problem type to obtain the response result for the problem; A problem feedback agent is used to output feedback information based on the problem and the response result; wherein, the output feedback information includes knowledge for updating the knowledge base, and the knowledge is summarized by the problem feedback agent based on the problem and the response result.

2. The method according to claim 1, characterized in that, The process of using a problem diagnosis agent to determine the problem type includes: Using the problem diagnosis agent, it is determined whether the object of the problem's concern is a preset target object, and if the object of the problem's concern is the target object, the technical field to which the problem belongs is determined; The process of utilizing a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes: The problem is processed using the problem-solving agent and / or the expert agent, according to the technical field to which the problem belongs, to obtain the response result.

3. The method according to claim 1, characterized in that, The process of using a problem diagnosis agent to determine the problem type includes: The problem diagnosis agent is used to determine whether the problem is a problem in the problem database; The process of utilizing a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes: In response to the fact that the problem is not in the problem library, the problem-solving agent and / or the expert agent are used to process the problem according to the problem type to obtain the response result.

4. The method according to claim 3, characterized in that, The method further includes: In response to the fact that the problem is not a problem in the problem database, the problem diagnosis agent saves the problem to the problem database, and the problem solving agent and / or the expert agent process the problem and mark the processing status of the problem in the problem database; wherein, the processing status indicates whether the problem has been solved.

5. The method according to claim 1, characterized in that, The process of using a problem diagnosis agent to determine the problem type includes: The problem diagnosis agent is used to query the user database to determine the priority of users associated with the problem; The process of utilizing a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes: In response to the user's priority being higher than or equal to a preset priority threshold, the expert agent processes the problem according to the problem type to obtain the response result. In response to the user's priority being lower than the preset priority threshold, the problem-solving agent processes the problem according to the problem type to obtain the response result.

6. The method according to claim 1, characterized in that, The process of using a problem diagnosis agent to identify the problem to be addressed and to determine the problem type includes: The problem diagnosis agent obtains user dialogue information from the dialogue database, generates the problem to be processed based on the dialogue information, and determines the problem type.

7. The method according to claim 6, characterized in that, The method of utilizing a problem-solving agent to process the problem according to the problem type and obtain a response result for the problem includes: The problem-solving agent uses dialogue information in the dialogue database to detect whether necessary information is missing in order to solve the problem, and if the necessary information is missing, it sends a prompt message to supplement the necessary information based on the dialogue database. The problem-solving agent obtains the necessary information from the dialogue library and processes the problem according to the problem type and the necessary information to obtain the response result of the problem.

8. The method according to claim 1, characterized in that, The process of using a problem-solving agent and / or an expert agent to handle the problem according to the problem type and obtain a response result for the problem includes at least one of the following: Using the problem-solving agent and / or the expert agent, the response result for the problem is retrieved from the knowledge base and generated according to the problem type; The problem-solving agent and / or the expert agent are used to search the network and generate response results for the problem according to the problem type.

9. The method according to claim 1, characterized in that, The process of using the expert agent to process the problem according to the problem type and obtain the response result for the problem includes: In response to the expert agent obtaining a request for help from the dialogue database, the expert agent processes the problem according to the problem type to obtain a response result for the problem; or, In response to the expert agent determining that the response result of the problem-solving agent does not meet the preset quality conditions, the expert agent is used to optimize the response result of the problem according to the problem type to obtain an optimized response result.

10. The method according to claim 9, characterized in that, When the expert agent obtains a request for help from the dialogue database, the expert agent processes the problem according to the problem type to obtain a response result for the problem, including: In response to the problem-solving agent failing to solve the problem and sending a first request for help to the dialogue database, if the expert agent obtains the first request for help from the dialogue database, it processes the problem according to the problem type to obtain the response result.

11. The method according to claim 9, characterized in that, The method of utilizing a problem feedback agent to output feedback information based on the problem and the response result includes: If the problem feedback agent determines from the problem database that the problem has not been resolved, or if it determines from the dialogue database and user interaction that the user is not satisfied with the response to the problem, it sends a second help request to the dialogue database. When the expert agent obtains a request for help from the dialogue database, the expert agent processes the problem according to the problem type to obtain a response result for the problem, including: When the expert agent obtains the second request for help from the dialogue database, it reprocesses the problem according to the problem type to obtain a response result for the problem.

12. The method according to claim 1, characterized in that, The method of utilizing a problem feedback agent to output feedback information based on the problem and the response result includes: The problem feedback agent summarizes the problem and the response results, and outputs the knowledge to update the knowledge base when the preset update conditions are met.

13. The method according to claim 12, characterized in that, The step of outputting the knowledge to update the knowledge base when preset update conditions are met includes: The knowledge is output to the dialogue database using the question feedback agent, and the knowledge is retrieved from the dialogue database by the expert agent to determine its accuracy. In response to the expert agent determining that the accuracy of the knowledge meets a preset accuracy condition, a notification message supporting the updating of the knowledge base is sent to the dialogue database, so that the question feedback agent can use the knowledge to update the knowledge base.

14. A problem-solving device, characterized in that, include: The module is configured to use a problem diagnosis agent to identify the problem to be addressed and determine the problem type. The processing module is configured to use a problem-solving agent and / or an expert agent to process the problem according to the problem type and obtain the response result of the problem; The feedback information output module is configured to use a problem feedback agent to output feedback information based on the problem and the response result of the problem; wherein, the output feedback information includes knowledge for updating the knowledge base, and the knowledge is summarized by the problem feedback agent based on the problem and the response result.

15. An electronic device, characterized in that, include: processor; Memory used to store computer programs or instructions; The processor executes the computer program or instructions to implement the steps of the method according to any one of claims 1 to 13.

16. A non-transitory computer-readable storage medium storing a computer program or instructions, characterized in that, When the computer program or instructions in the storage medium are executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

Images