Task processing method and automatic question answering method

Abstract

Provided in the embodiments of the present specification are a task processing method and an automatic question answering method. The task processing method comprises: receiving a task processing request, the task processing request carrying target task information; and using a task processing model to analyze the target task information, and when it is determined to use a third-party plug-in to process the target task information, calling a target third-party plug-in to process the target task information, so as to obtain a task processing result corresponding to the task processing request, the task processing model being a natural language deep learning model. The combination of the task processing model and third-party plug-ins allows for processing of multimodal tasks, thus expanding the task scope of task processing; moreover, before a third-party plug-in is called, whether to process target task information by means of third-party plug-ins is determined, such that a third-party plug-in is called only when there is a calling demand, thus improving the flexibility of task processing.

Description

Task processing method and automatic question answering method

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on July 14, 2023, with application number 202310868639.0 and application name “Task Processing Method and Automatic Question Answering Method”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of this specification relate to the field of computer technology, and more particularly to a task processing method. One or more embodiments of this specification also relate to an automatic question-answering method, a task processing apparatus, an automatic question-answering apparatus, a computing device, a computer-readable storage medium, and a computer program. Background Art

[0003] With the development of computer technology, large models have begun to shine. Their remarkable capabilities in language understanding, generation, interaction, and reasoning have led to their widespread application in natural language processing, including dialogue, translation, and code generation. However, large models only support text processing and are unable to complete other complex tasks. Therefore, how to enable large models to complete complex tasks that cannot be achieved through text processing alone has gradually become a research focus.

[0004] Currently, it's possible to set up a universal interface to directly "link" large models with related components, allowing them to process complex tasks. However, this approach requires calling related components during task processing, resulting in extremely low flexibility. Therefore, a more flexible task processing solution is urgently needed.

[0005] Summary of the Invention

[0006] In view of this, embodiments of this specification provide a task processing method. One or more embodiments of this specification also relate to an automatic question-answering method, a task processing apparatus, an automatic question-answering apparatus, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0007] According to a first aspect of an embodiment of this specification, a task processing method is provided, including:

[0008] receiving a task processing request, wherein the task processing request carries target task information;

[0009] The target task information is analyzed using the task processing model. When it is determined that a third-party plug-in processes the target task information, the target third-party plug-in is called to process the target task information to obtain the task processing result corresponding to the task processing request. The task processing model is a deep learning model of natural language.

[0010] According to a second aspect of the embodiments of this specification, there is provided an automatic question-answering method, comprising:

[0011] Receive a question processing request sent by a client, wherein the question processing request carries a question to be answered;

[0012] The task processing model is used to analyze the questions to be answered. When it is determined that a third-party plug-in can handle the questions to be answered, the target third-party plug-in is called to process the questions to be answered and obtain the response result corresponding to the question processing request. The task processing model is a deep learning model of natural language.

[0013] According to a third aspect of the embodiments of this specification, there is provided a task processing device, including:

[0014] A first receiving module is configured to receive a task processing request, wherein the task processing request carries target task information;

[0015] The first processing module is configured to use a task processing model to analyze target task information. When it is determined that a third-party plug-in processes the target task information, the target third-party plug-in is called to process the target task information to obtain a task processing result corresponding to the task processing request, wherein the task processing model is a deep learning model of natural language.

[0016] According to a fourth aspect of the embodiments of this specification, an automatic question-answering device is provided, comprising:

[0017] A second receiving module is configured to receive a question processing request sent by a client, wherein the question processing request carries a question to be answered;

[0018] The second processing module is configured to use the task processing model to analyze the problem to be answered. When it is determined that a third-party plug-in handles the problem to be answered, the target third-party plug-in is called to process the problem to be answered, and a reply result corresponding to the problem processing request is obtained, wherein the task processing model is a deep learning model of natural language.

[0019] According to a fifth aspect of the embodiments of this specification, there is provided a computing device, including:

[0020] memory and processor;

[0021] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method provided in the first aspect or the second aspect are implemented.

[0022] According to a sixth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the method provided in the first or second aspect above are implemented.

[0023] According to a seventh aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the method provided in the first aspect or the second aspect above.

[0024] An embodiment of the present specification provides a task processing method, which receives a task processing request, wherein the task processing request carries target task information; uses a task processing model to analyze the target task information, and when it is determined that a third-party plug-in processes the target task information, calls the target third-party plug-in to process the target task information, and obtains a task processing result corresponding to the task processing request, wherein the task processing model is a deep learning model of natural language. By combining the task processing model with the third-party plug-in, multimodal tasks can be processed, which increases the task scope of task processing. Moreover, before calling the third-party plug-in, it is determined whether the target task information is to be processed by the third-party plug-in, so that the third-party plug-in is called only when there is a call demand, thereby increasing the flexibility of task processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] FIG1 is an architecture diagram of a task processing system provided by one embodiment of this specification;

[0026] FIG2 is an architecture diagram of another task processing system provided by one embodiment of this specification;

[0027] FIG3 is a flowchart of a task processing method provided by one embodiment of this specification;

[0028] FIG4 is a flow chart of an automatic question-answering method provided by one embodiment of this specification;

[0029] FIG5 is a flowchart of a task processing method according to an embodiment of the present invention;

[0030] FIG6 is a flowchart of another task processing method provided by one embodiment of this specification;

[0031] FIG7 a is a schematic diagram of an automatic question-and-answer interface provided in accordance with an embodiment of the present disclosure;

[0032] FIG7 b is a schematic diagram of an interface for displaying a reply result provided by an embodiment of this specification;

[0033] FIG8 is a schematic diagram of the structure of a task processing device provided by one embodiment of this specification;

[0034] FIG9 is a schematic diagram of the structure of an automatic question-answering device provided by one embodiment of this specification;

[0035] FIG10 is a structural block diagram of a computing device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0036] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0037] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0038] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0039] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0040] In one or more embodiments of this specification, a large model refers to a deep learning model with large-scale model parameters, typically containing hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than ten trillion model parameters. A large model can also be called a cornerstone model / foundation model. By pre-training a large model with large-scale unlabeled corpus, a pre-trained model with more than 100 million parameters is produced. This model can adapt to a wide range of downstream tasks and has good generalization capabilities, such as a large-scale language model (LLM) and a multi-modal pre-training model.

[0041] When large models are used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. Large models can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, they can be applied to computer vision tasks such as visual question answering (VQA), image description (IC), image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0042] First, the terms involved in one or more embodiments of this specification are explained.

[0043] Plugin: A plugin is a program written using a specific API. In practice, plugins can be called APIs or tools.

[0044] With the development of computer technology, large models have begun to shine. Their remarkable capabilities in language understanding, generation, interaction, and reasoning have led to their widespread application in natural language processing, including dialogue, translation, and code generation. However, large models only support text processing and are unable to complete other complex tasks. Therefore, how to enable large models to complete complex tasks that cannot be achieved through text processing alone has gradually become a research focus.

[0045] Currently, it is possible to set up a general interface to directly "link" large models with related components, allowing them to process complex tasks. However, this solution requires calling related components during task processing, resulting in extremely low flexibility in task processing.

[0046] To solve the above problems, the embodiments of this specification provide a task processing solution that can enable the task processing model to use a series of third-party plug-ins, combining the task processing model and the third-party plug-ins to complete a series of complex tasks that cannot be completed by text generation alone.

[0047] Specifically, a task processing request is received, wherein the task processing request carries target task information; the target task information is analyzed using a task processing model; and when it is determined that a third-party plug-in processes the target task information, the target third-party plug-in is called to process the target task information, thereby obtaining a task processing result corresponding to the task processing request, wherein the task processing model is a deep learning model of natural language. By combining the task processing model with the third-party plug-in, multimodal tasks can be processed, thereby increasing the task scope of task processing. Furthermore, before calling the third-party plug-in, it is determined whether the target task information is to be processed by the third-party plug-in, thereby realizing that the third-party plug-in is only called when there is a call demand, thereby increasing the flexibility of task processing.

[0048] In this specification, a task processing method is provided. This specification also involves an automatic question-answering method, a task processing device, an automatic question-answering device, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0049] Referring to FIG1 , FIG1 shows an architecture diagram of a task processing system provided by an embodiment of this specification. The task processing system may include a client 100 and a server 200;

[0050] The client 100 is used to send a task processing request to the server 200, wherein the task processing request carries target task information;

[0051] The server 200 is configured to analyze the target task information using the task processing model. If a third-party plug-in is determined to process the target task information, the server 200 invokes the target third-party plug-in to process the target task information and obtain a task processing result corresponding to the task processing request. The task processing model is a deep learning model for natural language processing. The server 200 then sends the task processing result to the client 100.

[0052] The client 100 is also used to receive the task processing result sent by the server 200.

[0053] By applying the solution of the embodiments of this specification, by combining the task processing model and the third-party plug-in, multimodal tasks can be processed, thereby improving the task scope of task processing. In addition, before calling the third-party plug-in, it is determined whether the target task information is to be processed through the third-party plug-in, so that the third-party plug-in is called only when there is a calling demand, thereby improving the flexibility of task processing.

[0054] Referring to FIG. 2 , FIG. 2 shows an architecture diagram of another task processing system provided in accordance with one embodiment of the present disclosure. The task processing system may include multiple clients 100 and a server 200. Multiple clients 100 may establish communication connections via the server 200. In a task processing scenario, the server 200 is used to provide task processing services between the multiple clients 100. The multiple clients 100 may act as senders or receivers, respectively, and communicate via the server 200.

[0055] Users can interact with the server 200 through the client 100 to receive data sent by other clients 100, or send data to other clients 100. In the task processing scenario, users can publish data streams to the server 200 through the client 100. The server 200 generates task processing results based on the data stream and pushes the task processing results to other clients with which communication has been established.

[0056] The client 100 and the server 200 are connected via a network. The network provides a medium for the communication link between the client 100 and the server 200. The network can include various connection types, such as wired or wireless communication links or fiber optic cables. The data transmitted by the client 100 may need to be encoded, transcoded, compressed, or other processing before being released to the server 200.

[0057] The client 100 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, Hypertext Markup Language 5) application, a light application (also known as a mini-program, a lightweight application), or a cloud application. The client 100 can be based on the software development kit (SDK) of the corresponding service provided by the server 200, such as developed based on the real-time communication (RTC) SDK. The client 100 can be deployed in an electronic device and needs to rely on the device to run or certain APPs in the device to run. For example, the electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0058] The server 200 may include servers that provide various services, such as servers that provide communication services to multiple clients, servers that provide background training to support models used on clients, and servers that process data sent by clients. It should be noted that the server 200 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server in a distributed system, or a server that is integrated with a blockchain. The server can also be a cloud server for basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0059] It is worth noting that the task processing methods provided in the embodiments of this specification are generally executed by the server. However, in other embodiments of this specification, the client may also have similar functions to the server and thus execute the task processing methods provided in the embodiments of this specification. In other embodiments, the task processing methods provided in the embodiments of this specification may also be executed jointly by the client and the server.

[0060] Referring to FIG3 , FIG3 shows a flowchart of a task processing method provided by an embodiment of this specification, which specifically includes the following steps:

[0061] Step 302: Receive a task processing request, wherein the task processing request carries target task information.

[0062] In one or more embodiments of this specification, target task information may be acquired, and task processing may be performed based on the target task information to obtain a task processing result.

[0063] Specifically, the target task information can be task information for different scenarios, such as task information for conference scenarios, task information for e-commerce scenarios, and so on. The tasks corresponding to the target task information can be different types of tasks, such as weather query tasks, image description tasks, text-to-image tasks, product query tasks, computing tasks, and so on. The target task information includes, but is not limited to, task content, task execution time, task identifier, and so on. The specific selection depends on the actual situation and is not limited in this embodiment of the present specification.

[0064] In practical applications, there are multiple ways to receive task processing requests, and the specific method is selected based on the actual situation. The embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, a task processing request sent by a user through a client can be received. In another possible implementation of this specification, a task processing request sent by a client at a scheduled time can be received.

[0065] Step 304: Use the task processing model to analyze the target task information. When it is determined that a third-party plug-in processes the target task information, call the target third-party plug-in to process the target task information to obtain the task processing result corresponding to the task processing request, wherein the task processing model is a deep learning model of natural language.

[0066] In one or more embodiments of the present specification, after receiving a task processing request, the target task information can be further analyzed using a task processing model. When it is determined that a third-party plug-in processes the target task information, the target third-party plug-in is called to process the target task information to obtain a task processing result corresponding to the task processing request.

[0067] Specifically, the task processing model is a deep learning model for natural language processing. This model can be trained based on sample text, or a pre-trained large model can be used as the task processing model. Third-party plug-ins are plug-ins developed by third-party configuration providers. These plug-ins can have different functions, such as weather query plug-ins, ticket purchase plug-ins, drawing plug-ins, and so on. The task processing result refers to the processing result corresponding to the target task information. For example, if the target task information is to query today's weather, the task processing result is "Today's weather is sunny, with a maximum temperature of 30 degrees Celsius."

[0068] It should be noted that since the task processing model processes text tasks, when using the task processing model to analyze target task information, two situations may occur: the task processing model can directly process the target task information, and the task processing model cannot directly process the target task information. In the first case, the task processing model can process the target task information. In this case, the task processing model can directly process the target task information and obtain the task processing result. When the user specifies to call a plug-in to process the target task information, the task processing model can also determine that a third-party plug-in will process the target task information. In the second case, the task processing model cannot directly process the target task information. In this case, the task processing model can determine that a third-party plug-in will process the target task information.

[0069] Furthermore, after the task processing model determines that the third-party plug-in processes the target task information, it calls the target third-party plug-in to process the target task information. There are many ways to obtain the task processing results corresponding to the task processing request, and the specific selection depends on the actual situation. The embodiments of this specification do not impose any restrictions on this.

[0070] In the first possible implementation method of this specification, the task processing model can feed back the determination result of the third-party plug-in processing the target task information to the task processing platform, and the task processing platform determines the target third-party plug-in corresponding to the target task information, and directly calls the target third-party plug-in to process the target task information to obtain the task processing result corresponding to the task processing request.

[0071] In the second possible implementation method of this specification, the task processing model can feed back the determination result of the third-party plug-in processing the target task information to the task processing platform, and the task processing platform determines the target third-party plug-in corresponding to the target task information, and sends a call instruction carrying the identification information of the target third-party plug-in to the task processing model, so that the task processing model calls the target third-party plug-in to process the target task information and obtains the task processing result corresponding to the task processing request.

[0072] In the third possible implementation method of this specification, after the task processing model determines that the third-party plug-in processes the target task information, it can determine the target third-party plug-in corresponding to the target task information, and feed back the determination result of the third-party plug-in processing the target task information and the identification information of the target third-party plug-in to the task processing platform. The task processing platform can send a call instruction to the task processing model so that the task processing model calls the target third-party plug-in to process the target task information and obtains the task processing result corresponding to the task processing request.

[0073] In a fourth possible implementation of this specification, after the task processing model determines that a third-party plug-in processes target task information, it can determine the target third-party plug-in corresponding to the target task information, directly call the target third-party plug-in to process the target task information, obtain the task processing result corresponding to the task processing request, and send the task processing result to the task processing platform. It should be noted that the task processing platform can be a processing platform on the client or on the server, and the specific selection is based on actual circumstances. This embodiment of this specification does not impose any restrictions on this.

[0074] By applying the solution of the embodiments of this specification, by combining the task processing model and the third-party plug-in, multimodal tasks can be processed, thereby improving the task scope of task processing. In addition, before calling the third-party plug-in, it is determined whether the target task information is to be processed through the third-party plug-in, so that the third-party plug-in is called only when there is a calling demand, thereby improving the flexibility of task processing.

[0075] In actual applications, there are many ways to use the task processing model to analyze target task information. The specific method is selected according to the actual situation, and the embodiments of this specification do not impose any limitations on this.

[0076] In one possible implementation of this specification, target task information may be input into a task processing model, which performs task processing to obtain a processing result. A task processing strategy is determined based on the processing result of the task processing model. That is, analyzing the target task information using the task processing model may include the following steps:

[0077] Input the target task information into the task processing model for processing;

[0078] In the event that the task processing model fails, a third-party plug-in is determined to process the target task information.

[0079] It should be noted that the target task information is input into the task processing model for processing. If the task processing model fails to process the feedback, it means that the task processing model cannot process the target task information. In this case, it can be determined that the target task information is processed by a third-party plug-in.

[0080] In actual applications, when the task processing model fails, the task processing model can directly determine the target task information processed by the third-party plug-in, or the task processing model can feed back the processing results of the failed processing to the task processing platform, and the task processing platform can determine the target task information processed by the third-party plug-in.

[0081] After determining that a third-party plug-in processes the target task information, there may or may not be a third-party plug-in that can process the target task information, and this embodiment of the specification does not impose any limitation on this.

[0082] It's worth noting that if the task processing model fails and no third-party plug-in exists that can process the target task information, a task failure notification can be directly provided to the user, ending the task processing. Furthermore, the task processing model can also provide a task failure notification to the user and retry the task processing until the target task information has been processed a preset number of times, at which point a task failure notification can be provided to the user, ending the task processing.

[0083] By applying the solution of the embodiment of this specification, the target task information is input into the task processing model for processing. If the task processing model fails to process the target task information, a third-party plug-in is determined to process the target task information. Therefore, the task processing strategy corresponding to the target task information can be determined without the need for information other than the target task information, thereby reducing the amount of data processing.

[0084] Furthermore, after the target task information is processed using the task processing model, the following steps may be further included:

[0085] When the task processing model is successfully processed, the task processing result corresponding to the task processing request is obtained.

[0086] It should be noted that the target task information is input into the task processing model for processing. If the task processing model processes successfully, the task processing model can directly generate the task processing result.

[0087] In practical applications, the task processing model can feed back the task processing results to the task processing platform. At the same time, in order to make the task processing platform clear about the source of the task processing results, the task processing strategy corresponding to the target task information can also be fed back to the task processing platform for direct processing by the task processing model.

[0088] By applying the solution of the embodiment of this specification, when the task processing model successfully processes the task, the task processing result corresponding to the task processing request is obtained. When the task processing model can process the target task information, the task processing model can be used to generate the task processing result, thereby realizing that the third-party plug-in is called only when there is a calling demand, thereby improving the flexibility of task processing.

[0089] In another possible implementation of the present specification, the task processing model may determine, based on the plug-in attribute information and the target task information, whether there is an available third-party plug-in whose plug-in performance index is greater than a preset index threshold. If there is an available third-party plug-in, it is determined that the third-party plug-in will process the target task information. That is, the above-mentioned use of the task processing model to analyze the target task information may include the following steps:

[0090] Get plugin property information of multiple third-party plugins;

[0091] Input the target task information and the plug-in attribute information of each third-party plug-in into the task processing model to obtain the plug-in performance indicators corresponding to each third-party plug-in;

[0092] When the plug-in performance indicator is greater than a preset indicator threshold, it is determined that the third-party plug-in processes the target task information.

[0093] Specifically, the plug-in attribute information is the attribute information of the third-party plug-in itself. The plug-in attribute information includes but is not limited to the plug-in HyperText Transfer Protocol (HTTP) service address, plug-in function, plug-in function description information, plug-in sample information, plug-in name, plug-in input parameters, and plug-in output parameters. The specific selection is made according to the actual situation, and the embodiments of this specification do not impose any restrictions on this. The plug-in performance index is used to describe the degree of matching between the third-party plug-in and the target task information, and also characterizes the ability of the third-party plug-in to process the target task information. The preset indicator threshold is used to determine whether there is a third-party plug-in that can process the target task information. In the case where there is a third-party plug-in that can process the target task information, the preset indicator threshold is also used to filter out the target third-party plug-in from multiple third-party plug-ins. The preset indicator threshold can be set according to the actual needs of the user, and the embodiments of this specification do not impose any restrictions on this.

[0094] In actual applications, there are many ways to obtain plug-in attribute information of multiple third-party plug-ins, and the specific selection depends on the actual situation. The embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, the plug-in attribute information actively sent by the configuration party of the third-party plug-in can be received. In another possible implementation of this specification, in order to avoid the configuration party not knowing which plug-in attribute information to send, the plug-in registration rules can be sent to the configuration party, and the plug-in attribute information sent by the configuration party based on the plug-in registration rules can be received, so that the plug-in attribute information is more accurate.

[0095] It should be noted that the target task information and the plug-in attribute information of each third-party plug-in are input into the task processing model. The task processing model can generate the target task characteristics of the target task information and the plug-in attribute characteristics of each plug-in attribute information, and further determine the plug-in performance indicators of each third-party plug-in based on the similarity between the plug-in attribute characteristics and the target task characteristics.

[0096] For example, assuming that the plug-in performance index of third-party plug-in A is 0.6, the plug-in performance index of third-party plug-in B is 0.8, and the preset index threshold is 0.7, because the plug-in performance index 0.8 of third-party plug-in B is greater than the preset index threshold 0.7, it can be determined that the task processing strategy corresponding to the target task information is the third-party plug-in processing target task information.

[0097] By applying the solution of the embodiments of this specification, plug-in attribute information of multiple third-party plug-ins is obtained; the target task information and the plug-in attribute information of each third-party plug-in are input into the task processing model to obtain the plug-in performance index corresponding to each third-party plug-in; when the plug-in performance index is greater than the preset index threshold, it is determined that the third-party plug-in processes the target task information, and the task processing strategy of the target task information is determined based on the target task information and the plug-in attribute information of each third-party plug-in by utilizing the task processing model, so that when it is determined that the target task information is processed by a third-party plug-in, there is a third-party plug-in that can process the target task information, thereby improving the stability of task processing.

[0098] In an optional embodiment of the present specification, the plug-in attribute information includes plug-in function description information; and inputting the target task information and the plug-in attribute information of each third-party plug-in into the task processing model to obtain the plug-in performance indicator corresponding to each third-party plug-in may include the following steps:

[0099] The target task information and the plug-in function description information of each third-party plug-in are input into the task processing model to obtain the plug-in performance indicators corresponding to each third-party plug-in.

[0100] Specifically, the plug-in function description information is used to describe the functions that the third-party plug-in can implement. The target task information and the plug-in function description information of each third-party plug-in are input into the task processing model. The plug-in performance index corresponding to each third-party plug-in is obtained to represent the third-party plug-in's ability to process the target task information. The larger the plug-in performance index, the stronger the plug-in's ability to process the target task information.

[0101] For example, assuming the third-party plug-in is a "knowledge base," its plug-in function description might be "Enter a series of keywords, search for documents related to these keywords in the knowledge base, and return summary text of these documents." For example, assuming the third-party plug-in is a "stable diffusion," its plug-in function description might be "Enter a string of text, generate an image that matches the text description, and return the image's Uniform Resource Locator (URL). The input text must be in English."

[0102] By applying the solution of the embodiment of this specification, the target task information and the plug-in function description information of each third-party plug-in are input into the task processing model to obtain the plug-in performance indicators corresponding to each third-party plug-in, thereby evaluating each third-party plug-in in the dimension of plug-in processing capabilities, making the task processing model's analysis of the target task information more accurate.

[0103] In another optional embodiment of the present specification, the plug-in attribute information includes plug-in sample information; and inputting the target task information and the plug-in attribute information of each third-party plug-in into the task processing model to obtain the plug-in performance indicator corresponding to each third-party plug-in may include the following steps:

[0104] The target task information and the plug-in sample information of each third-party plug-in are input into the task processing model to obtain the plug-in performance index corresponding to each third-party plug-in.

[0105] Specifically, plugin example information is used to describe the usage process of a third-party plugin. Plugin example information can be divided into positive plugin example information and negative plugin example information. Positive plugin example information includes example information where the third-party plugin can be used. Negative plugin example information includes example information where the third-party plugin cannot be used.

[0106] For example, assuming that the third-party plug-in is a "knowledge base", the positive example information of the third-party plug-in can be "Question: What are the two core doctrines of Book A? What enlightenment does it give people? Is it necessary to use this plug-in: Yes. Reason for using this plug-in (optional): The task processing platform may not have precise knowledge related to Book A, and it is necessary to query the knowledge base. Plugin input (required): The two core doctrines of Book A. Plugin return (optional): .... Expected plug-in response (optional): ....". The negative example information of the third-party plug-in can be "Question: Who are you? Is it necessary to use this plug-in: No."

[0107] Assuming the third-party plug-in is "Smart Drawing", the positive example information of the third-party plug-in can be "Question: Please draw me a picture of a busy street. Do you need this plug-in: Yes. Reason for using this plug-in (optional): .... Plugin input (required): A street full of traffic. Plugin return (optional): Hypertext Transfer Protocol service address. Expected plug-in reply (optional): Hello, I have drawn the picture for you, please check. [Picture] (Hypertext Transfer Protocol service address).". The negative example information of the third-party plug-in can be "Question: What does "bustling traffic" mean? Do you need this plug-in: No."

[0108] By applying the solution of the embodiment of this specification, the target task information and the plug-in sample information of each third-party plug-in are input into the task processing model to obtain the plug-in performance indicators corresponding to each third-party plug-in, thereby evaluating each third-party plug-in in the dimension of the plug-in usage process, making the task processing model's analysis of the target task information more accurate.

[0109] It is worth noting that the above-mentioned method of analyzing target task information using the task processing model can be run individually or in combination. When running in combination, the order of the analysis methods is selected according to the actual situation, and this embodiment of the specification does not impose any limitation on this.

[0110] In one possible implementation of this specification, obtaining plug-in attribute information of multiple third-party plug-ins may include the following steps:

[0111] Send plugin registration rules to the configuration party;

[0112] Receive plug-in attribute information of multiple third-party plug-ins sent by the configuration party based on the plug-in registration rules.

[0113] Specifically, the plug-in registration rules include the information required by the configuration party to register the third-party plug-in to the task processing platform, such as the plug-in Hypertext Transfer Protocol service address, plug-in function, plug-in function description information, plug-in sample information, plug-in name, plug-in input parameters, and plug-in output parameters. The specific selection is based on the actual situation, and the embodiments of this specification do not impose any restrictions on this.

[0114] It should be noted that after the configuration party develops and obtains a third-party plug-in, it can encapsulate the third-party plug-in as a Hypertext Transfer Protocol service or function and register the plug-in attribute information with the task processing platform. The plug-in input and output parameters can be represented as strings.

[0115] By applying the solution of the embodiment of this specification, plug-in registration rules are sent to the configuration party; plug-in attribute information of multiple third-party plug-ins sent by the configuration party based on the plug-in registration rules is received, so that the third-party plug-ins can be successfully registered on the task processing platform, ensuring the stable availability of the third-party plug-ins.

[0116] In an optional embodiment of the present specification, before calling the target third-party plug-in to process the target task information, the following steps may be further included:

[0117] A target third-party plug-in is selected from multiple third-party plug-ins according to target task information.

[0118] In actual applications, there are many ways to filter out target third-party plug-ins from multiple third-party plug-ins based on target task information. The specific selection depends on the actual situation, and the embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, the plug-in performance index of each third-party plug-in can be calculated based on the target task information and the plug-in attribute information of each third-party plug-in, and the target third-party plug-in can be filtered out from multiple third-party plug-ins based on the plug-in performance index of each third-party plug-in. In another possible implementation of this specification, the target task information and the plug-in attribute information of each third-party plug-in can be input into the task processing model to obtain the plug-in performance index corresponding to each third-party plug-in, and the target third-party plug-in can be filtered out from multiple third-party plug-ins based on the plug-in performance index of each third-party plug-in.

[0119] It should be noted that there are multiple ways to filter out target third-party plug-ins from multiple third-party plug-ins based on the plug-in performance indicators of each third-party plug-in. The specific selection depends on the actual situation, and the embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, the plug-in performance indicator can be compared with a preset indicator threshold, and the target third-party plug-in can be randomly selected from the third-party plug-ins whose plug-in performance indicators are greater than the preset indicator threshold. In another possible implementation of this specification, the plug-in performance indicators of each third-party plug-in can be sorted, and the third-party plug-in with the largest plug-in performance indicator can be used as the target third-party plug-in.

[0120] By applying the solution of the embodiments of this specification, a target third-party plug-in is screened out from multiple third-party plug-ins according to target task information, so that the task processing model and the third-party plug-in can be combined to process the target task information, thereby expanding the capabilities of the task processing model and improving the flexibility of task processing.

[0121] In an optional embodiment of the present specification, the task processing request further carries project requirement information; after the target third-party plug-in is called to process the target task information and obtains the task processing result corresponding to the task processing request, the following steps may also be included:

[0122] The project requirement information and the task processing result are input into the task processing model to obtain an updated task processing result, wherein the updated task processing result meets the project requirement information.

[0123] Specifically, the project requirement information is used to limit the task processing results according to the actual project requirements. The project requirement information includes but is not limited to the word count requirement and language requirement of the task processing results. The specific selection is based on the actual situation and is not limited in this embodiment of the specification.

[0124] For example, if the task processing result is in English and the project requirement information is in Chinese, the project requirement information and the task processing result can be input into the task processing model, and the task processing model will translate the English task processing result into the Chinese task processing result. If the task processing result is too long, the project requirement information and the task processing result can be input into the task processing model, and the task processing model will extract the main idea of ​​the task processing result to obtain an updated task processing result.

[0125] By applying the solution of the embodiment of this specification, project requirement information and task processing results are input into the task processing model to obtain updated task processing results, ensuring that the task processing results meet the project requirement information, and improving the accuracy of task processing and user experience.

[0126] In another optional embodiment of the present specification, after calling the target third-party plug-in to process the target task information and obtaining the task processing result corresponding to the task processing request, the following steps may be further included:

[0127] Send the task processing results to the client so that the client can display the task processing results to the user.

[0128] It should be noted that after invoking the target third-party plug-in to process the target task information and obtaining the task processing result corresponding to the task processing request, the task processing result can be sent to the client. Simultaneously, the corresponding processing method of the task processing result can also be sent to the client. The processing method can be obtained by direct processing or by invoking a third-party plug-in. If the processing method is obtained by invoking a third-party plug-in, the processing method can also include third-party plug-in information, such as the plug-in source, plug-in source address, etc. Furthermore, if the task processing result is an updated task processing result, both the pre-update task processing result and the updated task processing result can be sent to the client.

[0129] In actual applications, there are many ways for the client to display the task processing results to the user, which can be selected according to the actual situation. The embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, the client can only display the task processing results to the user. In another possible implementation of this specification, the client can display the task processing results and the processing method to the user at the same time, so that the user can accurately know the task processing results and the corresponding processing method. In another possible implementation of this specification, the task processing results before the update and the processing results after the update can be displayed to the user at the same time.

[0130] It is worth noting that after obtaining the task processing result corresponding to the task processing request, the task processing result can be quality checked. If the quality check passes, the task processing result is sent to the client. If the quality check fails, the task processing is performed again.

[0131] By applying the solution of the embodiment of this specification, the task processing result is sent to the client, so that the client can display the task processing result to the user, so that the user can accurately obtain the task processing result, increase the interaction with the user, and improve user satisfaction.

[0132] In an optional embodiment of the present specification, the task processing request further carries target display requirement information; and the sending of the task processing result to the client may include the following steps:

[0133] According to the target display requirement information, the task processing results are sent to the client so that the client can display the task processing results to the user.

[0134] Specifically, the target display requirement information represents the user's need to view task processing results. This target display requirement information includes, but is not limited to, displaying only task processing results, displaying task processing results and corresponding processing methods, displaying task processing results processed by a third-party plug-in and third-party plug-in information, and displaying task processing results processed by a task processing model. The target display requirement information is configured based on the user's actual needs and is not limited in this embodiment.

[0135] It should be noted that, when the processing methods corresponding to the target task information include task processing model processing and third-party plug-in processing, the task processing model can be used to generate the first task processing result, and the third-party plug-in can be used to generate the second task processing result. Then, the first task processing result and the second task processing result can be displayed to the user. Furthermore, after generating the first task processing result and the second task processing result, the user can be provided with the display options of "displaying the results obtained by third-party plug-in processing" and "displaying the results obtained by task processing model processing", and the target display option selected by the user is received, and the task processing result corresponding to the target display option is displayed.

[0136] By applying the solution of the embodiment of this specification, task processing results are sent to the client according to target display requirement information, so that the client can display the task processing results to the user, thereby increasing interaction with the user and improving user satisfaction.

[0137] In another optional embodiment of the present specification, after the client displays the task processing results to the user, the user can perform data processing based on the task processing results, or send a post-processing request based on the task processing results displayed by the client to conduct multiple rounds of question and answer. That is, after sending the task processing results to the client, the following steps may also be included:

[0138] Receive post-processing requests sent by users based on task processing results, process the post-processing requests, and obtain post-processing results corresponding to the post-processing requests.

[0139] Specifically, a post-processing request refers to a task processing request sent by a user based on the task processing results after obtaining them. The data requested for processing in a post-processing request can be new target task information or the target task information included in the task processing request. The specific choice depends on the actual situation and is not limited in this embodiment.

[0140] It should be noted that if the data requested to be processed by the post-processing request is the target task information carried by the task processing request, it means that the user is not satisfied with the task processing result and needs to reprocess the target task information. Furthermore, the post-processing request sent by the user based on the task processing result can carry the processing method specified by the user. For example, if the task display result is generated by the task processing model, the post-processing request sent by the user based on the task processing result can request the use of a third-party plug-in to process the target task information; if the task display result is generated by a third-party plug-in, the post-processing request sent by the user based on the task processing result can request the task processing model to directly process the target task information.

[0141] It should be noted that the implementation method of "processing the post-processing request and obtaining the post-processing result corresponding to the post-processing request" is the same as the implementation method of the task processing method, and will not be repeated in the embodiments of this specification.

[0142] By applying the solution of the embodiment of this specification, a post-processing request sent by a user based on a task processing result is received, and the post-processing request is processed to obtain a post-processing result corresponding to the post-processing request, thereby increasing interaction with the user and improving user satisfaction.

[0143] Referring to FIG4 , FIG4 shows a flow chart of an automatic question-answering method provided by an embodiment of this specification, which specifically includes the following steps:

[0144] Step 402: Receive a question processing request sent by the client, wherein the question processing request carries a question to be answered.

[0145] Step 404: Use the task processing model to analyze the problem to be answered. When it is determined that a third-party plug-in can handle the problem to be answered, call the target third-party plug-in to process the problem to be answered and obtain a response result corresponding to the problem processing request, wherein the task processing model is a deep learning model of natural language.

[0146] It should be noted that the question to be answered is the target task information, and the answer result is the task processing result corresponding to the task processing request. The implementation of steps 402 to 404 is the same as the implementation of steps 302 to 304 above, and will not be repeated in this embodiment.

[0147] By applying the solution of the embodiments of this specification, by combining the task processing model and the third-party plug-in, it is possible to process multimodal question-and-answer tasks, thereby improving the scope of question-and-answer tasks that can be processed. In addition, before calling the third-party plug-in, it is determined whether the question to be answered needs to be processed through the third-party plug-in, thereby realizing that the third-party plug-in is called only when there is a call demand, thereby improving the flexibility of automatic question-and-answering.

[0148] The following further illustrates the task processing method provided in this specification using the application of the task processing method in an e-commerce scenario as an example, in conjunction with FIG5 . FIG5 shows a flowchart of the processing process of a task processing method provided in one embodiment of this specification, which specifically includes the following steps:

[0149] Step 502: Receive a task processing request, wherein the task processing request carries target task information.

[0150] Step 504: Input the target task information into the task processing model for processing, wherein the task processing model is a deep learning model of natural language.

[0151] Step 506: If the task processing model is successfully processed, obtain the task processing result corresponding to the task processing request.

[0152] Step 508: When the task processing model fails, obtain plug-in function description information of multiple third-party plug-ins.

[0153] Step 510: Input the target task information and the plug-in function description information of each third-party plug-in into the task processing model to obtain the first plug-in performance indicator corresponding to each third-party plug-in.

[0154] Step 512: Filter out at least one candidate third-party plug-in corresponding to the target task information from a plurality of third-party plug-ins based on the first plug-in performance indicator corresponding to each third-party plug-in.

[0155] Step 514: Obtain plug-in sample information of each candidate third-party plug-in, input the target task information and the plug-in sample information of each candidate third-party plug-in into the task processing model, and obtain the second plug-in performance indicator corresponding to each candidate third-party plug-in.

[0156] Step 516: Determine the target third-party plug-in corresponding to the target task information based on the second plug-in performance indicator corresponding to each candidate third-party plug-in.

[0157] Step 518: Call the target third-party plug-in to process the target task information and obtain the task processing result corresponding to the task processing request.

[0158] It should be noted that the implementation of steps 502 to 518 is the same as the implementation of steps 302 to 304 described above, and will not be described in detail in this embodiment of the specification.

[0159] By applying the solution of the embodiments of this specification, by combining the task processing model and the third-party plug-in, multimodal tasks can be processed, thereby improving the task scope of task processing. In addition, before calling the third-party plug-in, it is determined whether the target task information is to be processed through the third-party plug-in, so that the third-party plug-in is called only when there is a calling demand, thereby improving the flexibility of task processing.

[0160] 6 , which shows a flowchart of another task processing method provided by an embodiment of this specification, specifically including:

[0161] Register third-party plug-ins: After the configuration party develops a third-party plug-in, it sends the plug-in attribute information of multiple third-party plug-ins based on the plug-in registration rules and registers the third-party plug-in to the task processing platform;

[0162] The task processing platform uses the plug-in attribute information of the third-party plug-in to construct instructions: For example, the instructions include plug-in function description information and plug-in sample information; Plug-in function description information: When answering user questions, you can use the following plug-ins to assist in answering: Knowledge base: Enter a series of keywords, find documents related to these keywords in the knowledge base, and return the summary text of these documents. Smart drawing: Enter a string of text, generate an image that matches the text description, and return the uniform resource locator of the image. The input text must be English text. Plug-in sample information: "

[0163] Question 1: What are the two core teachings of Book A? What enlightenment do they give to people?

[0164] Answer 1 - Think: I may not have the precise knowledge related to Book A, so I need to query the knowledge base. Third-party plugin: Knowledge base. Input plugin: The two core teachings of Book A. Observation: The results returned by the knowledge base. Think: I can now answer. Response: Answer based on the results returned by the knowledge base.

[0165] Question 2—Who are you?

[0166] Answer 2——No need to use any tools, just answer directly.

[0167] Question 3 - Draw me a picture of a busy street.

[0168] Answer 3—Thinking: I need to use a tool. Third-party plugin: Smart Map. Input plugin: A street full of traffic. Observation: The HTTP service address returned by Smart Map. Thinking: I can answer now. Response: Hello, I've already drawn the image for you. Please check it. [Image](HTTP service address).

[0169] Question 4——What does "traffic jam-packed" mean?

[0170] Answer 4 - No tools are needed, just answer directly.

[0171] It should be noted that if the input parameters and return results of the third-party plug-in are relatively complex, the JSON data can be directly regarded as a string. For example, "Question 5 - What are the arrangements for next week? Answer 5 - Thinking: I need to check the schedule. Third-party plug-in: Schedule management. Input plug-in: {"date_from":"2023 May 13th","date_to":"2023 May 20th",}. Observation: [{"2023 / 5 / 13":"I need to do something that day."},{"2023 / 5 / 14":"I need to do another thing that day."},...]. Thinking: I can answer now. Reply:...".

[0172] When processing tasks, the task processing model independently determines whether to call a third-party plug-in based on the instructions, and continues to complete the task according to the results returned by the third-party plug-in.

[0173] By applying the solution of the embodiments of this specification, the task processing model can independently determine whether to call a third-party plug-in and continue to complete the task based on the results returned by the third-party plug-in, giving the task processing model the ability to use a series of third-party plug-ins. The capability scope of the task processing model is broadened through third-party plug-ins, solving the knowledge deficiency of the task processing model itself and improving the flexibility of task processing.

[0174] See Figure 7a, which shows a schematic diagram of an automatic question-and-answer interface provided by one embodiment of this specification. The automatic question-and-answer interface is divided into a question-handling request input interface and a response result display interface. The question-handling request input interface includes a request information input box, an "OK" control, and a "Cancel" control. The response result display interface includes a response result display box.

[0175] The user enters a question-handling request containing the question to be answered in the request information input box displayed on the client and clicks the "OK" control. The server receives the question-handling request from the client, analyzes the question to be answered using the task processing model, and, if a third-party plug-in is identified as handling the question, invokes the target third-party plug-in to process the question, obtains a response result corresponding to the question-handling request, and sends the response result to the client. The client displays the response result in the response result display box.

[0176] Refer to Figure 7b, which shows an interface diagram of a reply result display interface provided by an embodiment of the present specification. Before the client displays the reply result in the reply result display box, it can also display the "Show results obtained by processing by third-party plug-in" and "Show results obtained by processing by task processing model" controls in the reply result display box. If the user clicks "Show results obtained by processing by third-party plug-in", the reply result obtained by the third-party plug-in for processing the question to be answered will be displayed in the reply result display box; if the user clicks "Show results obtained by processing by task processing model", the reply result obtained by the task processing model for processing the question to be answered will be displayed in the reply result display box; if the user clicks "Show results obtained by processing by third-party plug-in" and "Show results obtained by processing by task processing model", the reply result obtained by the third-party plug-in for processing the question to be answered and the reply result obtained by the task processing model for processing the question to be answered will be displayed in the reply result display box.

[0177] In actual applications, users can operate controls by clicking, double-clicking, touching, hovering the mouse, sliding, long pressing, voice control, or shaking, etc. The specific selection is based on the actual situation, and the embodiments of this specification do not impose any restrictions on this.

[0178] Corresponding to the above-mentioned task processing method embodiment, this specification also provides a task processing device embodiment. FIG8 shows a schematic diagram of the structure of a task processing device provided in one embodiment of this specification. As shown in FIG8 , the device includes:

[0179] The first receiving module 802 is configured to receive a task processing request, wherein the task processing request carries target task information;

[0180] The first processing module 804 is configured to analyze the target task information using a task processing model, and when it is determined that a third-party plug-in processes the target task information, call the target third-party plug-in to process the target task information to obtain a task processing result corresponding to the task processing request, wherein the task processing model is a deep learning model of natural language.

[0181] Optionally, the first processing module 804 is further configured to input the target task information into the task processing model for processing; if the task processing model fails to process the target task information, determine a third-party plug-in to process the target task information.

[0182] Optionally, the first processing module 804 is further configured to obtain a task processing result corresponding to the task processing request when the task processing model is successfully processed.

[0183] Optionally, the first processing module 804 is further configured to obtain plug-in attribute information of multiple third-party plug-ins; input the target task information and the plug-in attribute information of each third-party plug-in into the task processing model to obtain the plug-in performance indicator corresponding to each third-party plug-in; when the plug-in performance indicator is greater than a preset indicator threshold, determine that the third-party plug-in processes the target task information.

[0184] Optionally, the plug-in attribute information includes plug-in function description information; the first processing module 804 is further configured to input the target task information and the plug-in function description information of each third-party plug-in into the task processing model to obtain the plug-in performance indicators corresponding to each third-party plug-in.

[0185] Optionally, the plug-in attribute information includes plug-in sample information; the first processing module 804 is further configured to input the target task information and the plug-in sample information of each third-party plug-in into the task processing model to obtain the plug-in performance indicator corresponding to each third-party plug-in.

[0186] Optionally, the first processing module 804 is further configured to send a plug-in registration rule to the configuration party; and receive plug-in attribute information of multiple third-party plug-ins sent by the configuration party based on the plug-in registration rule.

[0187] Optionally, the task processing request also carries project requirement information; the device also includes: an input module configured to input the project requirement information and the task processing result into the task processing model to obtain an updated task processing result, wherein the updated task processing result conforms to the project requirement information.

[0188] Optionally, the device further includes: a sending module configured to send the task processing result to the client, so that the client displays the task processing result to the user.

[0189] Optionally, the sending module is further configured to send the task processing result to the client according to the target display requirement information, so that the client displays the task processing result to the user.

[0190] Optionally, the device further includes: a third processing module configured to receive a post-processing request sent by a user based on the task processing result, and process the post-processing request to obtain a post-processing result corresponding to the post-processing request.

[0191] By applying the solution of the embodiments of this specification, by combining the task processing model and the third-party plug-in, multimodal tasks can be processed, thereby improving the task scope of task processing. In addition, before calling the third-party plug-in, it is determined whether the target task information is to be processed through the third-party plug-in, so that the third-party plug-in is called only when there is a calling demand, thereby improving the flexibility of task processing.

[0192] The above is a schematic scheme of a task processing device of this embodiment. It should be noted that the technical scheme of the task processing device and the technical scheme of the task processing method described above are of the same concept. For details not described in detail in the technical scheme of the task processing device, please refer to the description of the technical scheme of the task processing method described above.

[0193] Corresponding to the above-mentioned automatic question-answering method embodiment, this specification also provides an automatic question-answering device embodiment. FIG9 shows a schematic structural diagram of an automatic question-answering device provided in one embodiment of this specification. As shown in FIG9 , the device includes:

[0194] The second receiving module 902 is configured to receive a question handling request sent by a client, wherein the question handling request carries a question to be answered;

[0195] The second processing module 904 is configured to use the task processing model to analyze the problem to be answered. When it is determined that a third-party plug-in handles the problem to be answered, the target third-party plug-in is called to process the problem to be answered, and a response result corresponding to the problem processing request is obtained, wherein the task processing model is a deep learning model of natural language.

[0196] By applying the solution of the embodiments of this specification, by combining the task processing model and the third-party plug-in, it is possible to process multimodal question-and-answer tasks, thereby improving the scope of question-and-answer tasks that can be processed. In addition, before calling the third-party plug-in, it is determined whether the question to be answered needs to be processed through the third-party plug-in, thereby realizing that the third-party plug-in is called only when there is a call demand, thereby improving the flexibility of automatic question-and-answering.

[0197] The above is a schematic diagram of an automatic question-answering device according to this embodiment. It should be noted that the technical solution of this automatic question-answering device and the technical solution of the automatic question-answering method described above are based on the same concept. For details not described in detail in the technical solution of the automatic question-answering device, please refer to the description of the technical solution of the automatic question-answering method described above.

[0198] Figure 10 shows a block diagram of a computing device according to one embodiment of the present disclosure. Components of the computing device 1000 include, but are not limited to, a memory 1010 and a processor 1020. The processor 1020 is connected to the memory 1010 via a bus 1030, and a database 1050 is used to store data.

[0199] The computing device 1000 also includes an access device 1040 that enables the computing device 1000 to communicate via one or more networks 1060. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1040 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0200] In one embodiment of the present specification, the aforementioned components of the computing device 1000 and other components not shown in FIG10 may also be connected to each other, for example, via a bus. It should be understood that the computing device structure block diagram shown in FIG10 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0201] Computing device 1000 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 1000 may also be a mobile or stationary server.

[0202] The processor 1020 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned task processing method or automatic question-answering method.

[0203] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of this computing device is based on the same concept as the technical solutions of the task processing method and the automatic question-answering method described above. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solutions of the task processing method or the automatic question-answering method described above.

[0204] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned task processing method or automatic question-answering method.

[0205] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium is based on the same concept as the technical solutions of the task processing method and the automatic question-answering method described above. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solutions of the task processing method or the automatic question-answering method described above.

[0206] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned task processing method or automatic question-answering method.

[0207] The above is a schematic diagram of a computer program according to this embodiment. It should be noted that the technical solution of this computer program is based on the same concept as the technical solutions of the task processing method and the automatic question-answering method described above. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solutions of the task processing method or the automatic question-answering method described above.

[0208] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0209] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium.

[0210] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0211] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0212] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A task processing method, comprising: receiving a task processing request, wherein the task processing request carries target task information; The target task information is analyzed using a task processing model. When it is determined that a third-party plug-in processes the target task information, the target third-party plug-in is called to process the target task information to obtain a task processing result corresponding to the task processing request, wherein the task processing model is a deep learning model of natural language.

2. According to the method of claim 1, the step of analyzing the target task information using a task processing model comprises: Inputting the target task information into the task processing model for processing; In the case where the task processing model fails to process, a third-party plug-in is determined to process the target task information.

3. The method according to claim 2, after processing the target task information using the task processing model, further comprising: When the task processing model is processed successfully, a task processing result corresponding to the task processing request is obtained.

4. The method according to claim 1, wherein the step of analyzing the target task information using a task processing model comprises: Get plugin property information of multiple third-party plugins; Inputting the target task information and the plug-in attribute information of each third-party plug-in into the task processing model to obtain the plug-in performance index corresponding to each third-party plug-in; When the plug-in performance indicator is greater than a preset indicator threshold, it is determined that a third-party plug-in processes the target task information.

5. According to the method of claim 4, the plug-in attribute information includes plug-in function description information; The step of inputting the target task information and the plug-in attribute information of each third-party plug-in into a task processing model to obtain plug-in performance indicators corresponding to each third-party plug-in includes: The target task information and the plug-in function description information of each third-party plug-in are input into the task processing model to obtain the plug-in performance indicators corresponding to each third-party plug-in.

6. The method according to claim 4, wherein the plug-in attribute information includes plug-in sample information; The step of inputting the target task information and the plug-in attribute information of each third-party plug-in into a task processing model to obtain plug-in performance indicators corresponding to each third-party plug-in includes: The target task information and plug-in sample information of each third-party plug-in are input into a task processing model to obtain plug-in performance indicators corresponding to each third-party plug-in.

7. According to the method of claim 4, the step of obtaining plug-in attribute information of a plurality of third-party plug-ins comprises: Send plugin registration rules to the configuration party; Receive plug-in attribute information of multiple third-party plug-ins sent by the configuration party based on the plug-in registration rule.

8. According to the method of claim 1, the task processing request also carries project requirement information; After calling the target third-party plug-in to process the target task information and obtaining the task processing result corresponding to the task processing request, the method further includes: The project requirement information and the task processing result are input into the task processing model to obtain an updated task processing result, wherein the updated task processing result meets the project requirement information.

9. The method according to any one of claims 1 to 8, wherein after calling the target third-party plug-in to process the target task information and obtaining the task processing result corresponding to the task processing request, the method further comprises: The task processing result is sent to the client, so that the client displays the task processing result to the user.

10. The method according to claim 9, wherein the task processing request further carries target display requirement information; The sending the task processing result to the client includes: The task processing result is sent to the client according to the target display requirement information, so that the client displays the task processing result to the user.

11. The method according to claim 9, after sending the task processing result to the client, further comprising: A post-processing request sent by a user based on the task processing result is received, and the post-processing request is processed to obtain a post-processing result corresponding to the post-processing request.

12. An automatic question-answering method, comprising: Receiving a question processing request sent by a client, wherein the question processing request carries a question to be answered; The task processing model is used to analyze the problem to be answered. When it is determined that a third-party plug-in processes the problem to be answered, the target third-party plug-in is called to process the problem to be answered, and a reply result corresponding to the problem processing request is obtained, wherein the task processing model is a deep learning model of natural language.

13. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 11 or claim 12 are implemented.

14. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method described in any one of claims 1 to 11 or claim 12.

Images