Intelligent agent cooperative processing method and device, equipment and storage medium

Abstract

The invention provides an agent cooperative processing method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps that information input by a user is received, whether a workflow template matched with the information exists or not is determined based on the information, under the condition that the matched workflow template does not exist, an agent group is constructed based on an instruction to convert the information into a corresponding instruction in a corresponding field, retrieval information corresponding to retrieval of the agent group is obtained according to the instruction and the information, and the retrieval information is sent to the user. And the reply information is generated based on the retrieval information and the reply generation agent group, so that the efficiency and accuracy of reply information can be improved.

Description

Background Art

[0002] With the development of the times, large models are becoming an increasingly indispensable technology in today's society. However, in related technologies, traditional question-answering systems often do not have an adaptive multi-level question processing mechanism. When faced with multi-dimensional information requests such as cross-domain and real-time information question-answering, it is difficult to provide in-depth and accurate questions. How to improve model efficiency is an urgent problem to be solved in this field. Summary of the invention

[0003] The present disclosure provides an intelligent agent collaborative processing method, device, equipment and storage medium, which improve the efficiency of the model at least to a certain extent.

[0004] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0005] According to one aspect of the present disclosure, there is provided an agent collaborative processing method, comprising:

[0006] Receive information input by the user;

[0007] Determine, based on the information, whether there is a workflow template matching the information;

[0008] In the absence of a matching workflow template, an agent group is constructed based on instructions to convert information into corresponding instructions in the corresponding field;

[0009] According to the instructions and information, the agent group retrieves the corresponding search information;

[0010] Based on the retrieved information and the reply generation agent group, reply information is generated.

[0011] In one embodiment of the present disclosure, when there is a workflow template matching the information, the information is processed based on the matching workflow template to generate reply information.

[0012] In one embodiment of the present disclosure, an agent group is constructed based on instructions to convert information into corresponding instructions in a corresponding field, including:

[0013] The information is completed based on the general knowledge agent, the user's historical information and the pre-stored text information to obtain the completed first information;

[0014] The information is completed based on the domain agent, the user's historical information and the pre-stored text information to obtain the completed second information;

[0015] The first information and the second information are verified based on the reflection agent, and instructions are obtained when the verification passes.

[0016] In one embodiment of the present disclosure, according to the instruction and the information acquisition agent group retrieves the corresponding search information, including:

[0017] Based on the domain agent, the database and the knowledge base are called to obtain the first search information;

[0018] Performing information retrieval based on the general knowledge agent to obtain second retrieval information;

[0019] The first search information and the second search information are verified based on the reflection agent, and the search information is obtained when the verification passes.

[0020] In one embodiment of the present disclosure, the reply information is generated based on the retrieval information and the reply generation agent group, including:

[0021] Generate the search information and reply information in the domain corresponding to the information based on the domain agent, the information and the search information.

[0022] In one embodiment of the present disclosure, the reply information is generated based on the retrieval information and the reply generation agent group, including:

[0023] Generate reply information based on general agent and search information.

[0024] In one embodiment of the present disclosure, the method further includes:

[0025] Preprocessing the information to obtain preprocessed information;

[0026] Determine whether there is a workflow template matching the information based on the information, including:

[0027] Based on the pre-processed information, it is determined whether there is a workflow template that matches the information.

[0028] According to another aspect of the present disclosure, there is provided an intelligent agent collaborative processing device, comprising:

[0029] A receiving module, used for receiving information input by a user;

[0030] A determination module, used to determine whether there is a workflow template matching the information based on the information;

[0031] The conversion module is used to build an agent group based on instructions to convert information into corresponding instructions in the corresponding field when there is no matching workflow template;

[0032] The acquisition module is used to obtain the corresponding search information of the agent group according to the instructions and information;

[0033] The first generating module is used to generate reply information based on the search information and the reply generating agent group.

[0034] In one embodiment of the present disclosure, the second generating module is used to generate reply information based on the matching workflow template processing information when there is a workflow template matching the information.

[0035] In one embodiment of the present disclosure, the conversion module includes:

[0036] A first completion unit, used to complete the information based on the general knowledge agent, the user's historical information and the pre-stored text information to obtain the completed first information;

[0037] A second completion unit, used to complete the information based on the domain agent, the user's historical information and the pre-stored text information to obtain the completed second information;

[0038] The first verification unit is used to verify the first information and the second information based on the reflection agent, and obtain instructions when the verification passes.

[0039] In one embodiment of the present disclosure, the acquisition module includes:

[0040] A calling unit, used for calling a database and a knowledge base based on a domain agent to obtain first search information;

[0041] A retrieval unit, used for performing information retrieval based on the general knowledge agent to obtain second retrieval information;

[0042] The second verification unit is used to verify the first search information and the second search information based on the reflection agent, and obtain the search information when the verification passes.

[0043] In one embodiment of the present disclosure, the first generation module includes:

[0044] The first generating unit is used to generate the search information and reply information in the domain corresponding to the information based on the domain agent, the information and the search information.

[0045] In one embodiment of the present disclosure, the first generation module includes:

[0046] The second generating unit is used to generate reply information based on the general agent and the search information.

[0047] In one embodiment of the present disclosure, the device further includes:

[0048] A preprocessing module is used to preprocess the information to obtain preprocessed information;

[0049] Identify modules, including:

[0050] The determination unit is used to determine whether there is a workflow template matching the information based on the preprocessed information.

[0051] According to another aspect of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned intelligent agent collaborative processing method by executing the executable instructions.

[0052] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned intelligent agent collaborative processing method is implemented.

[0053] The intelligent agent collaborative processing method, apparatus, device and storage medium provided by the embodiments of the present disclosure receive information input by a user, determine whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, construct an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieve corresponding search information based on the instructions and information, and generate reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0054] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0056] Figure 1 An architecture diagram of an intelligent agent collaborative processing system in an embodiment of the present disclosure is shown;

[0057] Figure 2 A flow chart of an intelligent agent collaborative processing method according to an embodiment of the present disclosure is shown;

[0058] Figure 3 Another flow chart of the intelligent agent collaborative processing method in the embodiment of the present disclosure is shown;

[0059] Figure 4 A flow chart of another intelligent agent collaborative processing method according to an embodiment of the present disclosure is shown;

[0060] Figure 5 A flow chart of another intelligent agent collaborative processing method in an embodiment of the present disclosure is shown;

[0061] Figure 6 A flow chart of another intelligent agent collaborative processing method in an embodiment of the present disclosure is shown;

[0062] Figure 7 An architecture diagram of an intelligent collaborative processing device according to an embodiment of the present disclosure is shown;

[0063] Figure 8 A structural block diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0064] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0065] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0066] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0067] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0068] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0069] The current intelligent question-answering system widely uses pre-trained language models (such as BERT, GPT, etc.) or rule-driven knowledge base retrieval systems as core components, which usually include the following steps: first, receive and pre-process questions raised by users, and perform certain pre-processing operations such as text cleaning and stop word removal; second, classify or domain-identify the pre-processed questions so as to direct them to the correct knowledge base or rule module; then, use similarity matching and other technologies to retrieve relevant information from the knowledge base and output multiple related document fragments; finally, convert the retrieved information into an answer form that is easy for users to understand through template filling or generative models.

[0070] Although the above methods meet the basic question-answering needs to a certain extent, there are still significant technical bottlenecks when it comes to professional questions with complex and abstract professional vocabulary. Traditional question-answering systems often do not have an adaptive multi-level question processing mechanism. When faced with multi-dimensional information requests such as cross-domain and real-time information question-answering, it is difficult to provide in-depth and accurate answers; the accuracy of question classification and domain identification is limited by simple keyword matching and traditional machine learning algorithms, and the processing ability for complex natural language questions is limited, making it difficult to correctly understand the user's true intentions; over-reliance on a single knowledge base and fixed-mode similarity retrieval, these systems perform poorly in the dynamic integration and comprehensive processing of multi-source data, and the similarity-based retrieval mode makes it difficult for the fuzzy questions raised by users to match the knowledge base.

[0071] It should be pointed out that, in the absence of conflict, the embodiments of the present disclosure and the technical features therein may be combined with each other.

[0072] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0073] Figure 1 A schematic diagram of the structure of an intelligent agent collaborative processing system in an embodiment of the present disclosure is shown. The system can apply the intelligent agent collaborative processing method or intelligent agent collaborative processing device in each embodiment of the present disclosure.

[0074] like Figure 1As shown, the intelligent agent collaborative processing system 100 may include a data acquisition module 101 and an intelligent agent collaborative processing module 102. The data acquisition module 101 and the intelligent agent collaborative processing module 102 may be located on two different devices. The data acquisition module 101 may be a module on an electronic device with data acquisition capabilities, such as a recording device with sound collection capabilities, a photographic device with image collection capabilities, and a computer with text information collection capabilities. The intelligent agent collaborative processing module 102 may be a module on an electronic device with processing capabilities such as a computer. The data acquisition module 101 and the intelligent agent collaborative processing module 102 may be located on the same device. For example, the data acquisition module 101 and the intelligent agent collaborative processing module 102 may be an input module and a processing module on a computer or a mobile phone.

[0075] The data acquisition module 101 and the intelligent agent collaborative processing module 102 are connected via a network to achieve communication, and the network can be a wired network or a wireless network.

[0076] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged through the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0077] The following describes the situation where the data acquisition module 101 and the intelligent agent collaborative processing module 102 are located on two different devices.

[0078] The data acquisition module 101 may be located on a terminal device, which may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, etc.

[0079] Optionally, the client of the application installed in different terminal devices is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0080] The agent collaborative processing module 102 may be located on a server, which may be a server that provides various services, such as a background management server that provides support for devices operated by users using terminal devices. The background management server may analyze and process the received request and other data, and feed back the processing results to the terminal device.

[0081] Optionally, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0082] Those skilled in the art will know that Figure 1 The number of data acquisition modules and intelligent agent collaborative processing modules is only illustrative, and any number of video acquisition modules and personality recognition modules may be provided according to actual needs. The embodiments of the present disclosure are not limited to this.

[0083] In order to solve the above problems, the embodiments of the present disclosure provide an intelligent agent collaborative processing method, device, equipment and storage medium.

[0084] Figure 2 A flow chart of an intelligent agent collaborative processing method in an embodiment of the present disclosure is shown.

[0085] like Figure 2 As shown, the method may include:

[0086] S210, receiving information input by a user.

[0087] In some embodiments, the information input by the user may include natural language information.

[0088] S220: Determine, based on the information, whether there is a workflow template matching the information.

[0089] In some embodiments, the workflow template may include a pre-defined workflow template.

[0090] In some embodiments, it may be determined whether the information matches the workflow template based on the workflow template identifier or a keyword corresponding to the workflow template.

[0091] S230, in the absence of a matching workflow template, construct an agent group based on the instructions to convert the information into corresponding instructions in the corresponding field.

[0092] In some embodiments, standard instructions can be generated based on constructs, and question completion and approximate question generation can be performed based on natural language questions and historical dialogues.

[0093] S240, acquiring the corresponding search information according to the instruction and the information acquisition agent group.

[0094] In some embodiments, based on the needs of a specific field, a specific database or knowledge base can be called to complete information retrieval, and a certain text summary and polishing can be completed. Domain knowledge related vector retrieval tools, DB retrieval tools and memory modules can be called.

[0095] S250, generating reply information based on the search information and the reply generation agent group.

[0096] In some embodiments, before S210, the method may further include:

[0097] The information is preprocessed to obtain preprocessed information.

[0098] Preprocessing can include various data cleaning operations such as text cleaning and completion.

[0099] The intelligent agent collaborative processing method provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0100] Figure 3 A flow chart of another intelligent agent collaborative processing method in an embodiment of the present disclosure is shown.

[0101] like Figure 3 As shown, the method may include:

[0102] S310, receiving information input by a user;

[0103] S320, determining whether there is a workflow template matching the information based on the information;

[0104] S330: If there is a workflow template matching the information, generate reply information based on the matching workflow template processing information.

[0105] In some embodiments, when a workflow template exists, the workflow execution phase can be directly entered based on the corresponding workflow without rebuilding the workflow.

[0106] In some embodiments, execution based on a workflow may include execution based on preset execution steps or an execution template.

[0107] The intelligent agent collaborative processing method provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0108] Figure 4 A flow chart of another intelligent agent collaborative processing method in an embodiment of the present disclosure is shown.

[0109] like Figure 4 As shown, the method may include:

[0110] S410, receiving information input by a user;

[0111] S420, determining whether there is a workflow template matching the information based on the information;

[0112] S430, completing the information based on the general knowledge agent, the user's historical information and the pre-stored text information to obtain completed first information.

[0113] In some embodiments, general tasks may be processed based on a general agent, and the general tasks may include tasks in non-professional fields.

[0114] In some embodiments, information may be input into a general knowledge agent to obtain the first information.

[0115] In some embodiments, the first information may include standard information, and the general knowledge agent may complete the question based on the natural language question and the historical dialogue to obtain the standard information.

[0116] S440, completing the information based on the domain agent, the user's historical information and the pre-stored text information to obtain completed second information.

[0117] In some embodiments, a domain agent may be used to generate domain information.

[0118] In some embodiments, the second information may be annotation information.

[0119] In some embodiments, the information may be input into the domain agent so that the domain agent completes the information based on the user's historical information and pre-stored text information to obtain the completed second information.

[0120] S450, verifying the first information and the second information based on the reflection agent, and obtaining instructions when the verification passes.

[0121] In some embodiments, verifying the first information and the second information based on the reflection agent may include analyzing and verifying the first information and the second information. If the first information and the second information fail to pass the verification, the reflection agent may adjust or regenerate instructions.

[0122] S460, acquiring the corresponding search information by the agent group according to the instruction and the information;

[0123] S470, generating reply information based on the search information and the reply generation agent group.

[0124] The intelligent agent collaborative processing method provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0125] Figure 5 A flow chart of another intelligent agent collaborative processing method in an embodiment of the present disclosure is shown.

[0126] like Figure 5 As shown, the method may include:

[0127] S510, receiving information input by a user;

[0128] S520, determining whether there is a workflow template matching the information based on the information;

[0129] S530, in the absence of a matching workflow template, constructing an agent group based on the instructions to convert the information into corresponding instructions in the corresponding field;

[0130] S540, obtaining first search information based on the domain agent calling the database and the knowledge base.

[0131] In some embodiments, the first search information may be search information obtained after summarization.

[0132] In some embodiments, the domain-based agent can call a specific database or knowledge base to complete information retrieval.

[0133] In some embodiments, a summary may be performed based on the obtained search information to obtain the first search information.

[0134] S550, performing information retrieval based on the general knowledge agent to obtain second retrieval information.

[0135] In some embodiments, the general knowledge agent is used to perform general information acquisition tasks. When the user's question involves non-specific fields, general questions or real-time information questions, the general knowledge agent retrieves data from a wide range of information sources and may call web retrieval.

[0136] S560, verifying the first search information and the second search information based on the reflection agent, and obtaining the search information when the verification passes.

[0137] In some embodiments, it is responsible for verifying whether the retrieved information meets the user's intention and performing supplementary or alternative retrieval when necessary to ensure the accuracy and comprehensiveness of the information.

[0138] S570, generating reply information based on the search information and the reply generation agent group.

[0139] The intelligent agent collaborative processing method provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0140] The intelligent agent collaborative processing method provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0141] Figure 6 A flow chart of another intelligent agent collaborative processing method in an embodiment of the present disclosure is shown.

[0142] like Figure 6 As shown, the method may include:

[0143] S610, receiving information input by a user;

[0144] S620, determining whether there is a workflow template matching the information based on the information;

[0145] S630, in the absence of a matching workflow template, constructing an agent group based on the instructions to convert the information into corresponding instructions in the corresponding field;

[0146] S640, acquiring the corresponding search information by the agent group according to the instruction and the information;

[0147] S650, generating reply information in the domain corresponding to the search information and the information based on the domain agent, the information and the search information.

[0148] In some embodiments, the domain agent can use the domain LLM to generate content that conforms to the answer style of a specific domain. The domain agent will generate answers that are easy for users to understand based on the industry attributes of the question, the use of terminology, etc., where the answer can be a reply message.

[0149] In some embodiments, the method further comprises:

[0150] Generate reply information based on general agent and search information.

[0151] In some embodiments, generating reply information based on the general knowledge agent and the search information may include:

[0152] Generate general answers using the general LLM. For non-professional questions or general needs, the general knowledge agent will provide concise and intuitive answers.

[0153] Based on the same inventive concept, the disclosed embodiment also provides an intelligent collaborative processing device, such as the following embodiment. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0154] Figure 7 A structural diagram of an intelligent agent collaborative processing device in an embodiment of the present disclosure is shown.

[0155] like Figure 7 As shown, the apparatus 700 may include:

[0156] Receiving module 710, used to receive information input by a user;

[0157] A determination module 720, configured to determine, based on the information, whether there is a workflow template matching the information;

[0158] The conversion module 730 is used to construct an agent group based on the instructions to convert the information into corresponding instructions in the corresponding field when there is no matching workflow template;

[0159] An acquisition module 740 is used to acquire search information corresponding to the search of the agent group according to the instruction and information;

[0160] The first generating module 750 is used to generate reply information based on the search information and the reply generating agent group.

[0161] The intelligent agent collaborative processing device provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0162] In one embodiment of the present disclosure, the second generating module is used to generate reply information based on the matching workflow template processing information when there is a workflow template matching the information.

[0163] In one embodiment of the present disclosure, the conversion module includes:

[0164] A first completion unit, used to complete the information based on the general knowledge agent, the user's historical information and the pre-stored text information to obtain the completed first information;

[0165] A second completion unit, used to complete the information based on the domain agent, the user's historical information and the pre-stored text information to obtain the completed second information;

[0166] The first verification unit is used to verify the first information and the second information based on the reflection agent, and obtain instructions when the verification passes.

[0167] In one embodiment of the present disclosure, the acquisition module includes:

[0168] A calling unit, used for calling a database and a knowledge base based on a domain agent to obtain first search information;

[0169] A retrieval unit, used for performing information retrieval based on the general knowledge agent to obtain second retrieval information;

[0170] The second verification unit is used to verify the first search information and the second search information based on the reflection agent, and obtain the search information when the verification passes.

[0171] In one embodiment of the present disclosure, the first generation module includes:

[0172] The first generating unit is used to generate the search information and reply information in the domain corresponding to the information based on the domain agent, the information and the search information.

[0173] In one embodiment of the present disclosure, the first generation module includes:

[0174] The second generating unit is used to generate reply information based on the general agent and the search information.

[0175] In one embodiment of the present disclosure, the device further includes:

[0176] A preprocessing module is used to preprocess the information to obtain preprocessed information;

[0177] Identify modules, including:

[0178] The determination unit is used to determine whether there is a workflow template matching the information based on the preprocessed information.

[0179] The intelligent agent collaborative processing device provided by the embodiments of the present disclosure receives information input by a user, determines whether there is a workflow template that matches the information based on the information, and if there is no matching workflow template, constructs an intelligent agent group based on instructions to convert the information into corresponding instructions in the corresponding field, retrieves corresponding search information based on the instructions and information, and generates reply information based on the search information and the reply generation agent group, which can improve the efficiency and accuracy of the reply information.

[0180] The intelligent agent collaborative processing device provided in the embodiment of the present disclosure can be used to execute the positioning methods provided in the above-mentioned method embodiments. Its implementation principles and technical effects are similar and will not be described here for the sake of simplicity.

[0181] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0182] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0183] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810).

[0184] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps of various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps of the above method embodiment:

[0185] Receive information input by the user;

[0186] Determine, based on the information, whether there is a workflow template matching the information;

[0187] In the absence of a matching workflow template, an agent group is constructed based on instructions to convert information into corresponding instructions in the corresponding field;

[0188] According to the instructions and information, the agent group retrieves the corresponding search information;

[0189] Based on the retrieved information and the reply generation agent group, reply information is generated.

[0190] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0191] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0192] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0193] The electronic device 800 may also communicate with one or more external devices 840 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 8100. As shown, the network adapter 8100 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0194] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0195] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0196] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0197] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0198] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0199] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0200] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0201] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0202] Through the description of the above implementation modes, it is easy for those skilled in the art to understand that the example implementation modes described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation mode of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation mode of the present disclosure.

[0203] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. An agent collaborative processing method, characterized in that: include: Receive information input by the user; Determining, based on the information, whether there is a workflow template matching the information; In the absence of a matching workflow template, an agent group is constructed based on the instructions to convert the information into corresponding instructions in the corresponding field; According to the instructions and information acquisition agent group retrieves the corresponding search information; The reply information is generated based on the search information and the reply generation agent group.

2. The method according to claim 1, characterized in that The method further comprises: In the case that there is a workflow template matching the information, the information is processed based on the matching workflow template to generate reply information.

3. The method according to claim 1, characterized in that The instruction-based intelligent agent group converts the information into corresponding instructions in the corresponding field, including: The information is completed based on the general knowledge agent, the user's historical information and the pre-stored text information to obtain the completed first information; The information is completed based on the domain agent, the user's historical information, and the pre-stored text information to obtain completed second information; The first information and the second information are verified based on the reflection agent, and the instruction is obtained when the verification passes.

4. The method according to claim 1, characterized in that: The step of acquiring corresponding search information by the agent group according to the instruction and the information includes: Based on the domain agent, the database and the knowledge base are called to obtain the first search information; Performing information retrieval based on the general knowledge agent to obtain second retrieval information; The first search information and the second search information are verified based on the reflection agent, and the search information is obtained when the verification passes.

5. The method according to claim 1, characterized in that The generating reply information based on the search information and the reply generating agent group includes: Based on the domain agent, the information and the search information, the search information and the reply information in the domain corresponding to the information are generated.

6. The method according to claim 1, characterized in that The generating reply information based on the search information and the reply generating agent group includes: Generate reply information based on the general knowledge agent and the search information.

7. The method according to claim 1, characterized in that The method further comprises: Preprocessing the information to obtain preprocessed information; The determining, based on the information, whether there is a workflow template matching the information includes: Based on the pre-processed information, it is determined whether there is a workflow template matching the information.

8. An intelligent agent collaborative processing device, characterized in that: include: A receiving module, used for receiving information input by a user; A determination module, configured to determine whether there is a workflow template matching the information based on the information; A conversion module, used to construct an agent group based on the instructions to convert the information into corresponding instructions in the corresponding field when there is no matching workflow template; An acquisition module, used for acquiring the corresponding search information of the agent group according to the instructions and information; The generating module is used to generate the reply information based on the search information and the reply generating agent group.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the intelligent agent collaborative processing method described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent agent collaborative processing method described in any one of claims 1 to 7 is implemented.

Images