Method and device for processing client side problem, equipment and storage medium

Abstract

According to the embodiment of the invention, a method, a device and equipment for processing a client side problem and a storage medium are provided. The method includes determining at least one information acquisition function block from a plurality of information acquisition function blocks based on a received user input, the user input indicating a client-side problem associated with a client of a user, different information acquisition function blocks of the plurality of information acquisition function blocks being configured to acquire different types of client-side information; obtaining target information, related to the client side problem, of the client side by using at least one information obtaining function block; and based on the user input and the target information, providing a response to the client-side question by using the first machine learning model. In the embodiment of the invention, the method is applied to a digital assistant (such as an IT intelligent customer service assistant). Therefore, a user can be helped to better solve IT faults or safety problems.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for handling client-side issues. Background Art

[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. The terminal device presents the corresponding content through the user interface of the application and implements question-and-answer interaction with the user to meet various needs of the user. The terminal device or application can provide users with digital assistant functions to support better interaction with the user. For example, in the information technology (IT) customer service scenario, an IT intelligent customer service assistant can be provided to users to answer questions during the use of the IT system. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for handling client-side issues is provided. The method includes: determining at least one information acquisition function block from a plurality of information acquisition function blocks based on received user input, the user input indicating a client-side issue related to a user's client, and different information acquisition function blocks in the plurality of information acquisition function blocks being configured to acquire different types of client-side information; acquiring target information of the client related to the client-side issue using at least one information acquisition function block; and providing a response to the client-side issue using a first machine learning model based on the user input and the target information.

[0004] In a second aspect of the present disclosure, a device for handling client-side problems is provided. The device includes: a determination module configured to determine at least one information acquisition function block from a plurality of information acquisition function blocks based on received user input, the user input indicating a client-side problem related to the user's client, and different information acquisition function blocks in the plurality of information acquisition function blocks being configured to acquire different types of client-side information; an acquisition module configured to acquire target information of the client related to the client-side problem using at least one information acquisition function block; and a providing module configured to provide a response to the client-side problem using a first machine learning model based on the user input and the target information.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figure 2 An architectural diagram showing an example of a client-side problem handling system according to some embodiments of the present disclosure;

[0011] Figure 3 A flowchart illustrating a process for handling client-side issues according to some embodiments of the present disclosure;

[0012] Figure 4 A block diagram showing an apparatus for handling client-side issues according to some embodiments of the present disclosure; and

[0013] Figure 5 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0014] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0015] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0016] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0017] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0018] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0021] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0022] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0023] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", which are used interchangeably in this article. A model may also include different types of processing units or networks.

[0024] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In the example environment 100, a digital assistant 130 having an application 120 is installed in a terminal device 110. A user 140 can interact with the application 120 via the terminal device 110 and / or an attached device of the terminal device 110. Exemplarily, the application 120 can be a chat application (also called an instant messaging application), a document application, an audio and video conferencing application, an email application, a task application, a calendar application, an objectives and key results (OKR) application, and the like. It can be understood that although Figure 1 A single application 120 is shown in the figure, but in fact, multiple applications 120 may be installed on the terminal device 110. In some embodiments, the application 120 may include a multi-functional collaboration platform, such as an office collaboration platform (also called an office suite) that can provide integration of multiple types of applications to facilitate people to carry out office work, communication and other activities. In the multi-functional collaboration platform, people can start different business components as needed to complete corresponding information processing, sharing, communication and the like.

[0025] The digital assistant 130 may be configured to have an intelligent conversation function. Figure 1 In the example shown, the digital assistant 130 can be configured as an independently running application, such as a web application or other types of applications. In other examples, the digital assistant 130 can be integrated into the application 120. In some embodiments, the digital assistant 130 interacts with the application 120 to obtain the operating data of the application 120 (for example, the network configuration information of the application 120, the operating log information of the application 120, etc.). The digital assistant 130 can also obtain the device information of the terminal device (for example, CPU occupancy, CPU temperature, etc.) through the application 120. The user determines the operating status of the application 120 and the terminal device 110 by interacting with the digital assistant 130.

[0026] The user can interact with the digital assistant 130 through the client. During the interaction, the user inputs an interactive message, and the digital assistant 130 provides a reply message in response to the user input. Generally, the digital assistant 130 can support the user to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability. In some embodiments, depending on the configuration of the application 120, the interactive message with the application 120 may include a multimodal message, such as a text message (e.g., natural language text), a voice message, an image message, a video message, and the like.

[0027] exist Figure 1 In the environment 100, the terminal device 110 can present the user interface 150 of the application 120. The user interface 150 may include various interfaces that the application 120 can provide, such as an interactive interface between the user 140 and the digital assistant 130. The interactive interface may include, for example, a conversation window between the user 140 and the digital assistant 130.

[0028] In some embodiments, the digital assistant 130 may be associated with a corresponding database, which stores data or information required for the digital assistant 130 to answer user interaction information. Exemplarily, the digital assistant 130 may obtain information indicated by the user from a database connected to the application 120 (e.g., a knowledge base for storing historical interaction information between the user 140 and the digital assistant, or a database for storing guidance information or instruction information) in response to user input. The digital assistant 130 may provide the user with corresponding answers based on the acquired operating data and device information and the questions or needs raised by the user.

[0029] In some embodiments, the terminal device 110 communicates with the server 160 to provide the service of the application 120. The terminal device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface for the user (such as "wearable" circuits, etc.). The server 160 can be various types of computing systems / servers that can provide computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0030] It should be understood that the structure and function of each element in the environment 100 are described for exemplary purposes only, and do not imply any limitation on the scope of the present disclosure. For example, the embodiments of the present disclosure can be applied to any suitable one or more applications, and are not limited to office suites.

[0031] As briefly mentioned above, in IT customer service scenarios, digital assistants (e.g., IT intelligent customer service assistants) can be provided to users to answer questions during the use of IT systems. For example, in an enterprise office scenario, it is expected that digital assistants can provide solutions to problems related to user systems (such as equipment failures, account management, etc.) input by users.

[0032] Conventionally, digital assistants are implemented based on the Natural Language Processing (NLP) model. Digital assistants understand user needs through the NLP model and answer questions based on preset rules and a preset knowledge base. Due to the poor performance of the NLP model, there are problems such as insufficient context understanding, insufficient interactivity and flexibility. Often, manual customer service intervention is required to truly solve the problem.

[0033] With the development of language models, digital assistants based on language models have been introduced. However, such digital assistants often lack in-depth understanding when dealing with individual user feedback issues, which is particularly evident in technical troubleshooting. Such digital assistants usually directly provide root cause analysis and general solutions based on the user's simple description. General solutions have a low match with actual problems and cannot really solve actual problems. For example, when a user reports that the computer is stuck, there are many reasons for this problem, such as the computer temperature is too high, the central processing unit (CPU) occupancy rate is too high, etc. In this case, digital assistants can usually only provide general solutions, such as guiding users to view information such as CPU resource usage and process calls. However, these measures often fail to completely solve the problem, but require manual customer service to intervene for detailed troubleshooting and resolution, which increases labor and time costs.

[0034] Embodiments of the present disclosure propose a solution for handling client-side issues. According to various embodiments of the present disclosure, based on received user input, at least one information acquisition function block is determined from multiple information acquisition function blocks. At least one information acquisition function block is used to obtain target information of the client related to the client-side issue. Based on the user input and the target information, a response to the client-side issue is provided using a first machine learning model.

[0035] In an embodiment of the present disclosure, when a user raises a client-side problem related to the user's client, the information acquisition function block is used to obtain client-side information related to the client-side problem to obtain the information required to solve the client-side problem. In this way, a solution to the client-side problem is provided based on the client-side information and the user input. In this way, the response provided is more targeted to the client-side problem indicated by the user, that is, a problem solution with higher accuracy and matching can be provided to the user. As a result, users can be helped to better solve IT-related failures or security issues.

[0036] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0037] Figure 2 FIG. 1 shows an example architecture diagram of a client-side problem handling system according to some embodiments of the present disclosure. Figure 2 As shown, the system 200 may be implemented or include the server 160 . Alternatively, the system 200 may be implemented by the server 160 and the terminal device 110 in collaboration.

[0038] In some embodiments, the server 160 may determine at least one information acquisition functional block from a plurality of information acquisition functional blocks based on the received user input 210. The user input 210 indicates a client-side problem. As an example, Figure 2 A first information acquisition function block 230-1, a second information acquisition function block 230-2, a third information acquisition function block 230-3, a fourth information acquisition function block 230-4 and a fifth information acquisition function block 230-5 are shown, which are individually or collectively referred to as information acquisition function blocks 230. It should be understood that Figure 2 The number of information acquisition function blocks shown in is merely exemplary and is not intended to be limiting. The information acquisition function block 230 is configured to acquire a predetermined type of client-side information.

[0039] In some embodiments, the client may be implemented in the terminal device 110. For example, the client may be an application of a digital assistant running in the terminal device 110. User input 210 indicates a client-side problem that the user needs to solve. In an embodiment of the present disclosure, a client-side problem may refer to any type of problem related to the use of the client, including but not limited to hardware problems, software problems, account problems, and the like. As an example, client-side problems may include problems related to a terminal device running a client, such as operating problems of the terminal device, networking problems of the terminal device, and the like. As another example, client-side problems may include problems related to an application that implements the client, such as version problems of the application, operating errors of the application, and the like. As yet another example, client-side problems may include problems related to an account that logs into the client, such as account login problems, account permission problems, and the like.

[0040] like Figure 2 As shown, user input 210 indicates different types of client-side questions. Client-side question types 220 include at least a first client-side question type 220-1, a second client-side question type 220-2, a third client-side question type 220-3, a fourth client-side question type 220-4, and a fifth client-side question type 220-5, which may be individually or collectively referred to as client-side question types 220.

[0041] In some embodiments, the client-side problem type 220 may include technical support and troubleshooting types to help users solve problems with office equipment, software, and systems, such as computer, printer, network connection, and other equipment failures, operating system problems, software installation and update usage problems, etc., to provide users with fast and accurate technical support and reduce system downtime. Exemplarily, the user input 210 may be "My computer is stuck."

[0042] In some embodiments, the client-side question type 220 may include a system and software guidance training type, which is used to provide operation guides for specific software and systems, training and usage guidance for new systems and software. Exemplarily, the user input 210 may be "I cannot use application A".

[0043] In some embodiments, the client-side problem type 220 may include a type of security problem handling, which is used to help users deal with various security incidents, such as virus infection, data leakage, etc., and guide users to perform security settings, such as strong password management, data backup, etc. Exemplarily, the user input 210 may be "there is a security vulnerability on the client side".

[0044] In some embodiments, the client-side question type 220 may include user account management and permission management types, which are used to help users set up and manage accounts, solve login problems, etc., and ensure that users have appropriate permissions. Exemplarily, the user input 210 may be "Create a system account for me."

[0045] In some embodiments, the client-side problem type 220 may include the type of network configuration and connection, which is used to solve the user's network connection problem, help with network configuration, assist the user in setting up and using VPN, ensure secure remote access, etc. Exemplarily, the user input 210 may be "My computer cannot connect to the Internet", etc.

[0046] The server 160 can use multiple different types of information acquisition function blocks 230 to obtain client-side operation information. Each type of information acquisition function block 230 is used to obtain corresponding types of operation information. For example, the first information acquisition function block 230-1 is used to obtain network card configuration information and data transmission information, and the second information acquisition function block 230-2 is used to obtain guidance tutorials, etc.

[0047] In some embodiments, the server 160 may determine the type of client-side question indicated by the user input 210 using a second machine learning model (e.g., a language model) based on the user input 210 and the plurality of client-side question types 220. Subsequently, the server 160 may determine one or more data acquisition functional blocks based on the determined type of the client-side question and the correspondence between the plurality of client-side question types 220 and the plurality of information acquisition functional blocks 230. The first machine learning model and the second machine learning model may be the same model (e.g., the first machine learning model and the second machine learning model are the same language model). The first machine learning model and the second machine learning model may be different models.

[0048] As an example, a language model can be used to process user input 210 and multiple client-side problems to determine the type of client-side problem. The language model is used to parse the user input 210, and combined with the historical conversation content, determine the type of client-side problem indicated in the user input 210. For example, if the user says "My computer is very slow", it is necessary to determine that this is a technical support and troubleshooting type of problem. Through such detailed classification, the functional blocks used in subsequent steps can be selected more accurately. Exemplarily, the server 160 can generate prompt information based on the user input 210 and the description of multiple client-side problem types 220. The prompt information is provided to the second machine learning model to obtain the output of the second machine learning model. Based on the output of the second machine learning model, the type of client-side problem indicated by the user input 210 is determined from the multiple client-side problem types 220.

[0049] In some embodiments, the prompt information provided to the second machine learning model may include one or more of the following: skills used by the second machine learning model, a process for classifying client-side questions into multiple client-side question types (also referred to as a classification process), or user input examples and corresponding classification result examples. The following will refer to Table 1 to illustrate the generation of prompt information, which is an example of prompt information.

[0050] Table 1

[0051]

[0052]

[0053] As shown in Table 1, lines 8 to 10 in the prompt information show the skills used by the second machine learning model, lines 12 to 14 show the classification process, and lines 22 to 25 show example user inputs and corresponding model outputs. For example, when the user inputs "My computer is stuck", the type of client-side problem output is "Intent Category": "Service Technical Support and Troubleshooting".

[0054] In addition, the prompt information may also include a description of the role of the second machine learning model (for example, lines 1 to 2 in Table 1), task objectives (for example, lines 4 to 6 in Table 1) and constraints (for example, lines 16 to 20 in Table 1), etc.

[0055] Alternatively or additionally, the type of user input 210 may be determined based on historical interaction information between user 140 and the digital assistant. For example, user input 210 and historical interaction information may be provided to the second machine learning model as part of the prompt information. In this way, the second machine learning model may determine the type of user input 210 based on the prompt information.

[0056] After the type of the client-side question indicated by the user input 210 is determined, the corresponding information acquisition function block 230 may be determined based on a preset correspondence between the type of the client-side question and a plurality of information acquisition function blocks.

[0057] In some embodiments, the server 160 uses at least one information acquisition function block 230 to acquire target information related to the client-side problem on the client side. As an example, after determining the problem type corresponding to the user input 210, the corresponding client-side information is acquired by calling the determined information acquisition function block 230. The information acquisition function block 230 can be an information acquisition tool, an information acquisition plug-in and / or an interface for querying and collecting client-side operation information. For example, in the scenario of network troubleshooting, the WIFI strength detection plug-in is called to measure the current signal strength to assist the subsequent large model in determining the user's intention.

[0058] Exemplarily, the target information may include operation information generated during the operation of the client (e.g., log information of the client, configuration information of the client, etc.). The target information may include information of the terminal device 110 where the client is located (e.g., CPU occupancy of the terminal device 110, CPU temperature of the terminal device 110, configuration information of the terminal device, and network connection status of the terminal device 110, etc.). Alternatively or additionally, the target information may include information related to the user account (e.g., account authority information, etc.) or other information related to the client. In some embodiments, the user may predetermine the range of target information corresponding to each type of question. Subsequently, the target information corresponding to the user input 210 is acquired through the information acquisition function block 230.

[0059] The process of determining the information acquisition function block 230 will be described below with reference to Table 2, which is an example of determining the information acquisition function block 230.

[0060] Table 2

[0061]

[0062] In order to ensure the security of the client-side system, the user's permission needs to be obtained before the operation information is obtained by using the information acquisition function block 230. If the user's permission is not obtained, the information acquisition function block 230 is stopped from being called. In some embodiments, at the client receiving the user input 210, the range of information to be obtained by at least one information acquisition function block 230 is presented. Subsequently, in response to receiving an indication of permission to obtain information, the client-side information is determined by using at least one information acquisition function block 230.

[0063] Exemplarily, if the information acquisition function block 230 needs to obtain the client-side CPU occupancy rate and the client-side temperature information, the information acquisition function block 230 presents the information to be obtained at the client so that the user can view the scope of the information to be obtained. If the user allows the information acquisition operation to be performed, an indication of permission is sent to the client. Subsequently, in response to receiving the indication of permission to obtain information, the digital assistant uses the corresponding information acquisition function block 230 to determine the client-side CPU occupancy rate and temperature information.

[0064] In some embodiments, in order to further improve the security of the system, it is possible to determine whether the user has the corresponding information acquisition authority before the information acquisition function block 230 presents the scope of the information to be acquired. If the user does not have the information acquisition authority, the task of acquiring the operation information is terminated.

[0065] In some embodiments, server 160 provides a response to the client-side problem using the first machine learning model based on user input 210 and target information. For example, the response may include providing a solution to the client-side problem in natural language. For another example, the response may include performing an action to solve the client-side problem.

[0066] In some embodiments, the server 160 determines reference information 240 associated with the client-side question from the knowledge base based on the user input 210 and the target information. Accordingly, providing a response to the client-side question using the first machine learning model includes: providing a response to the client-side question using the first machine learning model based on the user input 210, the target information and the reference information 240.

[0067] Exemplarily, after the server 110 obtains the target information on the client side, it integrates it with the client-side question indicated by the user input 210 and the historical interaction information between the user and the digital assistant to form the input of Retrieval Augmented Generation (RAG).

[0068] After the server 110 obtains the user-side information, it vectorizes it with the user's questions and historical conversation data to obtain the corresponding retrieval token. Subsequently, the retrieval token is used as input data for the RAG retrieval technology to filter out documents, solutions and information fragments related to the user's questions from the pre-selected knowledge base. The filtered documents are used as reference information 240. In this way, it is ensured that the RAG technology can comprehensively consider all relevant information and improve the accuracy of the retrieval results.

[0069] After obtaining the RAG search results, the reference information 240 is analyzed and summarized using the language model to determine a specific problem solution (ie, a response to the client-side problem).

[0070] In some embodiments, in order to select an action execution function block to be used from a plurality of action execution function blocks, prompt information may be provided to the first machine learning model. The prompt information provided to the first machine learning model may include one or more of the following: a process for selecting an action execution function block from a plurality of action execution function blocks (also referred to as an action recommendation process), or a user input example and a corresponding action execution function block selection example. The following will refer to Table 3 to illustrate the generation of a response to a client-side question, which is an example of generating a response to a client-side question.

[0071] Table 3

[0072]

[0073]

[0074] As shown in Table 3, the 6th to 9th lines in the prompt information show the recommended process, and the 10th to 12th lines show the example user input and the corresponding model output. For example, when the user inputs "My computer is very slow", the output client-side problem solution is "Solution": "After analysis, the CPU occupancy rate is high", and it is recommended to call "tools": 'Close ** process'. In addition, the prompt information can also include a description of the role of the first machine learning model (for example, lines 1 to 5 in Table 3), etc.

[0075] In some embodiments, the response to the client-side problem may be a solution to the client-side problem, and the solution indicates the operation that the user needs to perform. For example, if the client-side problem is that the CPU usage is too high, the solution may be "ask the user to close some background processes". The user solves the client-side problem by executing the solution.

[0076] In some embodiments, the response to the client-side problem may be to call and execute a corresponding tool or plug-in to solve the client-side problem. For example, if the client-side problem is that the CPU usage is too high due to "process C", then the plug-in "close process C" is called to solve the client-side problem.

[0077] In some embodiments, the server 160 determines at least one action execution function block from a plurality of action execution function blocks based on the user input 210 and the target information, and different action execution function blocks in the plurality of action execution function blocks are configured to execute different types of actions related to the operation of the object. Subsequently, the determined action execution function blocks are used to execute one or more target actions 250 for solving the client-side problem. Figure 2 As shown, the system 200 includes at least a first action execution block 260 - 1 , a second action execution block 260 - 2 , a third action execution block 260 - 3 , a fourth action execution block 260 - 4 and a fifth action execution block 260 - 5 , which may be individually or collectively referred to as action execution blocks 260 . Figure 2 The number of action execution blocks 260 shown in FIG. 2 is exemplary only and is not intended to be limiting.

[0078] In some embodiments, based on user input 210 and target information, a second machine learning model is used to determine at least one action for solving the client-side problem. Subsequently, based on the predetermined type of action configured for at least one action and multiple action execution function blocks, at least one action execution function block is determined. Exemplarily, the server 160 can determine the action to be performed based on the response to the client-side problem. Subsequently, based on the corresponding relationship between the action and the action execution function block, the corresponding predetermined action execution function block is determined. Alternatively or additionally, the server 160 can determine the action execution function block related to the solution based on the response (i.e., the solution) to the client-side problem.

[0079] In some embodiments, in order to further improve the security of the system, an action for solving a problem on the client side can be performed after obtaining user permission. Exemplarily, in response to the predetermined type of action configured by at least one action execution function block requiring manipulation of the client receiving the user input 210, a description of one or more target actions 250 to be performed is presented at the client. The description information can be in the form of text. If an indication is received that the user allows the execution of the action, then in response to this indication, at least one action execution function block is called to execute the one or more target actions 250.

[0080] In some embodiments, after calling the action execution function block to execute the target action 250 , the system 200 may also present the corresponding client-side problem solving result 270 to the user to improve the user's usage experience.

[0081] It can be seen that, on the one hand, this solution uses language models to conduct in-depth analysis of user input questions and historical conversations, accurately identify user intentions, and thus provide customized solutions. This not only greatly improves the efficiency of problem solving, but also significantly improves user satisfaction. On the other hand, by building a large number of information acquisition function blocks and action execution blocks suitable for different scenarios. After the user feedbacks the problem, the system calls the relevant information acquisition tool set according to the classified user intentions to obtain more user-side information and provide more accurate and personalized problem solutions. After determining the solution, the system can directly call the action execution block to solve the user problem. In this way, the system can diagnose and handle the user's personalized needs more accurately and solve the user's problems thoroughly. The frequency of manual intervention is reduced, time and cost are significantly saved, and the user experience is improved.

[0082] Figure 3 A flowchart of a process for handling client-side issues according to some embodiments of the present disclosure is shown. Figure 3 As shown, the method for handling client-side issues may be implemented or included in the server 160 .

[0083] In box 310, based on the received user input, at least one information acquisition function block is determined from a plurality of information acquisition function blocks, the user input indicates a client-side problem related to the user's client, and different information acquisition function blocks in the plurality of information acquisition function blocks are configured to obtain different types of client-side information.

[0084] In some embodiments, determining at least one information acquisition functional block from multiple information acquisition functional blocks includes: based on user input and multiple client-side problem types, using a second machine learning model to determine the type of client-side problem indicated by the user input; and based on the determined type of client-side problem, determining one or more information acquisition functional blocks according to the correspondence between multiple client-side problem types and multiple information acquisition functional blocks.

[0085] In some embodiments, using a second machine learning model to determine the type of client-side problem indicated by user input includes: generating prompt information based on the user input and descriptions of multiple client-side problem types; providing the prompt information to the second machine learning model to obtain an output of the second machine learning model; and determining the type of client-side problem indicated by the user input from multiple client-side problem types based on the output of the second machine learning model.

[0086] In some embodiments, the prompt information includes at least one of the following: the skills used by the second machine learning model, the process of classifying the client-side question into multiple client-side question types, or a user input example and a corresponding classification result example.

[0087] At block 320 , target information of the client related to the client-side problem is obtained using at least one information obtaining function.

[0088] In some embodiments, obtaining target information related to client-side issues of a user's client includes: presenting, at the client, a range of information to be obtained by at least one information acquisition function block; and obtaining the target information using at least one information acquisition function block in response to receiving an indication allowing information to be obtained.

[0089] At block 330 , a response to the question on the client side is provided using a first machine learning model based on the user input and the target information.

[0090] In some embodiments, using a first machine learning model to provide a response to a client-side problem includes: based on user input and target information, using the first machine learning model to determine at least one action execution function block from a plurality of action execution function blocks, wherein different action execution function blocks among the plurality of action execution function blocks are configured to perform different types of actions related to client-side operation; and using at least one action execution function block to execute one or more target actions for solving the client-side problem.

[0091] In some embodiments, the prompt information provided to the first machine learning model includes at least one of the following: a process for selecting an action execution function block from multiple action execution function blocks, or a user input example and a corresponding action execution function block selection example.

[0092] In some embodiments, determining at least one action execution function block from multiple action execution function blocks includes: based on user input and target information, using a first machine learning model, determining at least one action for solving a client-side problem; and determining at least one action execution function block based on at least one action and predetermined types of actions to which the multiple action execution function blocks are respectively configured.

[0093] In some embodiments, providing a response to a client-side question includes: in response to at least one action execution function block being configured with a predetermined type of action requiring manipulation of the client, presenting at the client a description of one or more target actions to be performed; and in response to receiving an indication that execution of the action is allowed, calling at least one action execution function block to perform the one or more target actions.

[0094] In some embodiments, process 300 also includes: determining reference information associated with the client-side question from a knowledge base based on user input and target information, and wherein providing a response to the client-side question includes: providing a response to the client-side question based on user input, target information and reference information.

[0095] Figure 4 A block diagram of an apparatus for handling operational issues according to some embodiments of the present disclosure is shown. Figure 4 As shown, the method for handling operation problems may be implemented or included in the server 160. Each module / component in the apparatus 400 may be implemented by hardware, software, firmware or any combination thereof.

[0096] like Figure 4As shown, the device 400 includes a determination module 410, which is configured to determine at least one information acquisition function block from multiple information acquisition function blocks based on the received user input, the user input indicates a client-side problem related to the user's client, and different information acquisition function blocks in the multiple information acquisition function blocks are configured to obtain different types of client-side information. The device 400 also includes an acquisition module 420, which is configured to use at least one information acquisition function block to obtain target information related to the client-side problem of the client. The device 400 also includes a providing module 430, which is configured to use a first machine learning model to provide a response to the client-side problem based on the user input and the target information.

[0097] In some embodiments, the determination module 410 is also configured to determine the type of client-side problem indicated by the user input based on the user input and multiple client-side problem types using a second machine learning model; and based on the determined type of client-side problem, determine one or more information acquisition functional blocks according to the correspondence between multiple client-side problem types and multiple information acquisition functional blocks.

[0098] In some embodiments, the determination module 410 is also configured to generate prompt information based on user input and descriptions of multiple client-side problem types; provide the prompt information to a second machine learning model to obtain an output of the second machine learning model; and determine the type of client-side problem indicated by the user input from multiple client-side problem types based on the output of the second machine learning model.

[0099] In some embodiments, the acquisition module 420 is further configured to present, at the client, a range of information to be acquired by at least one information acquisition function block; and in response to receiving an indication allowing acquisition of information, acquire target information using at least one information acquisition function block.

[0100] In some embodiments, the providing module 430 is also configured to determine at least one action execution function block from multiple action execution function blocks based on user input and target information using a first machine learning model, and different action execution function blocks in the multiple action execution function blocks are configured to perform different types of actions related to client-side operation; and use at least one action execution function block to execute one or more target actions for solving client-side problems.

[0101] In some embodiments, the providing module 430 is also configured to determine at least one action for solving the client-side problem based on user input and target information using a first machine learning model; and determine at least one action execution functional block based on predetermined types of actions in which at least one action and multiple action execution functional blocks are respectively configured.

[0102] In some embodiments, the providing module 430 is also configured to present descriptive information about one or more target actions to be performed at the client in response to at least one action execution function block being configured with a predetermined type of action requiring manipulation of the client; and in response to receiving an indication allowing execution of the action, call at least one action execution function block to perform one or more target actions.

[0103] In some embodiments, the device 400 also includes a reference information determination module, which is configured to determine reference information associated with the client-side question from a knowledge base based on user input and target information, and wherein providing a response to the client-side question includes: providing a response to the client-side question based on user input, target information and reference information.

[0104] Figure 5 A block diagram of an electronic device 500 is shown in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 5 The electronic device 500 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can be used to implement Figure 1 An electronic device 110.

[0105] like Figure 5 As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0106] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.

[0107] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0108] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0109] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0110] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0111] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0112] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0113] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0114] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0115] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for handling client-side issues, the method being applied to a digital assistant and comprising: determining at least one information acquisition function block from a plurality of information acquisition function blocks based on received user input indicating a client-side problem associated with a client of the user, different ones of the plurality of information acquisition function blocks being configured to acquire different types of client-side information; Using the at least one information acquisition function block, acquiring target information of the client related to the client-side problem; as well as Based on the user input and the target information, a response to the client-side question is provided using a first machine learning model.

2. The method of claim 1 , wherein providing a response to the client-side question using a first machine learning model comprises: Based on the user input and the target information, using the first machine learning model, determine at least one action execution function block from a plurality of action execution function blocks, where different action execution function blocks in the plurality of action execution function blocks are configured to perform different types of actions related to the client side; as well as Using the at least one action execution function block, one or more target actions for solving the client-side problem are executed.

3. The method according to claim 1, wherein determining at least one information acquisition functional block from a plurality of information acquisition functional blocks comprises: Determining, using a second machine learning model, a type of client-side problem indicated by the user input based on the user input and a plurality of client-side problem types; as well as Based on the determined type of the client-side problem, the one or more information acquisition function blocks are determined according to the correspondence between the multiple client-side problem types and the multiple information acquisition function blocks.

4. The method of claim 3, wherein determining, using a second machine learning model, the type of client-side problem indicated by the user input comprises: Generate prompt information based on the user input and descriptions of the multiple client-side problem types; Providing the prompt information to the second machine learning model to obtain an output of the second machine learning model; as well as Based on the output of the second machine learning model, determine the type of client-side question indicated by the user input from the multiple client-side question types.

5. The method according to claim 1, wherein obtaining target information of the client related to the client-side problem comprises: At the client, presenting a range of information to be acquired by the at least one information acquisition function block; as well as In response to receiving an indication of permission to obtain information, the target information is obtained using the at least one information obtaining function block.

6. The method according to claim 1, further comprising: determining reference information associated with the client-side question from a knowledge base based on the user input and the target information, and Providing a response to the client-side question includes: A response to the client-side question is provided based on the user input, the target information, and the reference information.

7. The method according to claim 2, wherein determining at least one action execution function block from a plurality of action execution function blocks comprises: Determine, based on the user input and the target information, at least one action for solving the client-side problem using the first machine learning model; as well as The at least one action execution function block is determined based on the predetermined types of actions to which the at least one action and the plurality of action execution function blocks are respectively configured.

8. The method of claim 2, wherein providing a response to the client-side question comprises: In response to the predetermined type of action configured by the at least one action execution function block requiring manipulation of the client, presenting description information about the one or more target actions to be performed at the client; as well as In response to receiving the indication that execution of the action is allowed, the at least one action execution function block is called to execute the one or more target actions.

9. The method according to claim 4, wherein the prompt information includes at least one of the following: The skill used by the second machine learning model, a process of classifying the client-side problem into the plurality of client-side problem types, or Examples of user input and corresponding classification results.

10. The method according to claim 2, wherein the prompt information provided to the first machine learning model includes at least one of the following: a process of selecting an action execution function block from the plurality of action execution function blocks, or Example of user input and corresponding selection of action execution function block.

11. An apparatus for handling client-side problems, the apparatus being applied to a digital assistant and comprising: a determination module configured to determine at least one information acquisition function block from a plurality of information acquisition function blocks based on received user input indicating a client-side problem related to a client of a user, different information acquisition function blocks in the plurality of information acquisition function blocks being configured to acquire different types of client-side information; an acquisition module, configured to acquire target information of the client related to the client-side problem by using the at least one information acquisition function block; as well as A module is provided, configured to provide a response to the client-side question using a first machine learning model based on the user input and the target information.

12. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 10.

Images