Method, apparatus, electronic device, and medium for constructing an agent

Abstract

The present disclosure provides a method, device, electronic equipment and medium for constructing an agent, relating to the field of artificial intelligence, and particularly relating to the field of large language models and agents. The method can include obtaining a first user input, the first user input being a natural language text containing an agent construction requirement; determining one or more fields based on the first user input; obtaining a second user input associated with the one or more fields; obtaining a prompt sentence based on the one or more fields and the second user input; and constructing an agent according to the prompt sentence.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more particularly to large language models and intelligent agents, specifically to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for constructing intelligent agents. Background Technology

[0002] With the rapid development of artificial intelligence technology, large-scale pre-trained models and agent technology have demonstrated significant application value in multiple fields. However, existing technical solutions still face many technical bottlenecks in agent construction and large-scale model applications, especially in agent construction.

[0003] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for constructing intelligent agents.

[0005] According to one aspect of this disclosure, a method for constructing an intelligent agent is provided, comprising: obtaining first user input, the first user input being natural language text containing intelligent agent construction requirements; determining one or more fields based on the first user input; obtaining second user input associated with the one or more fields; obtaining a prompt statement based on the one or more fields and the second user input; and constructing an intelligent agent based on the prompt statement.

[0006] According to another aspect of this disclosure, an apparatus for constructing an intelligent agent is provided, comprising: a first input unit for obtaining first user input, the first user input being natural language text containing intelligent agent construction requirements; a field determination unit for determining one or more fields based on the first user input; an associated input unit for obtaining second user input associated with the one or more fields; a prompt statement unit for obtaining a prompt statement based on the one or more fields and the second user input; and a construction unit for constructing an intelligent agent according to the prompt statement.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method for constructing an intelligent agent according to one or more embodiments of this disclosure.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform a method for constructing an intelligent agent according to one or more embodiments of this disclosure.

[0009] According to another aspect of this disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, implements a method for constructing an intelligent agent according to one or more embodiments of this disclosure.

[0010] According to one or more embodiments of this disclosure, intelligent agents can be intelligently assisted in their construction.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A schematic diagram of an exemplary system in which the various methods described herein may be implemented according to embodiments of the present disclosure is shown;

[0014] Figure 2 A flowchart of a method for constructing an intelligent agent according to an embodiment of the present disclosure is shown;

[0015] Figure 3 An exemplary system architecture diagram according to an embodiment of the present disclosure is shown;

[0016] Figure 4 A schematic diagram of a data flow for a method for an intelligent agent according to an embodiment of the present disclosure is shown;

[0017] Figure 5 A structural block diagram of an apparatus for constructing an intelligent agent according to an embodiment of the present disclosure is shown;

[0018] Figure 6 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0021] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0022] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0023] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0024] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of methods for constructing intelligent agents according to this disclosure.

[0025] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105, and / or 106 under a Software as a Service (SaaS) model.

[0026] exist Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0027] Users can interact using client devices 101, 102, 103, 104, 105, and / or 106, for example, by building or interacting with intelligent agents. The client devices can provide interfaces that enable users to interact with them. The client devices can also output information to the user through these interfaces. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.

[0028] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices are capable of executing various applications, such as various internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and can use various communication protocols.

[0029] Network 110 can be any type of network well known to those skilled in the art, and can use any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0030] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0031] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0032] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0033] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0034] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.

[0035] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.

[0036] Figure 1The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0037] The following is for reference. Figure 2 A method 200 for constructing an intelligent agent according to an exemplary embodiment of the present disclosure is described.

[0038] In step S201, a first user input is obtained, which is natural language text containing the agent construction requirements.

[0039] In step S202, one or more fields are determined based on the first user input.

[0040] For example, one or more fields related to the agent construction requirements can be determined based on the first user input. For instance, the one or more fields may be fields used to normalize the description of the agent construction requirements. For instance, the one or more fields may be fields associated with the data required to construct the agent, such as some fields from a pre-determined set of fields for constructing the agent.

[0041] At step S203, a second user input associated with the one or more fields is obtained.

[0042] For example, the second user input can be used to generate requirement information, such as more standardized requirement information.

[0043] At step S204, a prompt statement is obtained based on the one or more fields and the second user input.

[0044] A prompt can be used to prompt a large language model. For example, prompts and a large model can be used to build an agent.

[0045] In step S205, an intelligent agent is constructed based on the prompt statement.

[0046] The method described according to embodiments of this disclosure can intelligently assist in constructing intelligent agents. In particular, it can determine corresponding fields based on user-provided requirement descriptions. For example, one or more fields corresponding to a category can be obtained based on the category of the requirement description. Thus, the requirement description can be formatted and standardized, eliminating the need for users to fully describe all information; instead, users can input information in association with the generated fields, facilitating user operation and generating standardized prompts.

[0047] According to some embodiments, determining one or more fields based on a first user input includes: obtaining a requirement form based on the first user input, the requirement form including the one or more fields.

[0048] For example, a requirement form can be interactive. For instance, a requirement form can be obtained and displayed to users, allowing them to easily refine their requirements.

[0049] In some examples, the requirements form can be pre-filled, for example, one or more field values ​​have been automatically generated based on the requirements description statement. The generated field values ​​can be modified.

[0050] According to some embodiments, obtaining a demand form based on the first user input includes: determining a demand category based on the first user input; and selecting a form corresponding to the demand category from a predetermined form library as the demand form.

[0051] For example, templates or forms corresponding to different categories can be maintained in advance. For instance, determining at least a portion of the identified requirement content based on the requirement category includes obtaining a form associated with the requirement category, the form including at least one field associated with the requirement category. Exemplarily, but not limitingly, the requirement category can be content extraction, content retrieval, content generation, etc., and different requirement categories can be described using different normalized fields.

[0052] According to some embodiments, the method may further include obtaining an identified field value corresponding to at least one of the one or more fields based on the first user input.

[0053] In such an embodiment, a portion of the field content can be extracted to convert the user description into a standardized form format.

[0054] According to some embodiments, the second user input includes modifications to at least a portion of the identified field values.

[0055] Users can supplement, modify, or confirm the generated field values, and the format of the fields and field values ​​makes it convenient for users to modify or supplement them.

[0056] According to some embodiments, the second user input includes confirmation of at least a portion of the identified field values.

[0057] Users can provide explicit or implicit confirmation. As a concrete example, if all the required field values ​​have been extracted from the requirements text and the user has no further additions, the user can confirm the field values ​​by clicking "Generate Prompt," "Next," "Build," etc.

[0058] According to some embodiments, the one or more fields include a requirement category field, and wherein a modification to the requirement category field is used to trigger the presentation of a different category of form to the user as an updated requirement form.

[0059] The automatically extracted categories may be incorrect, or the user may want to use a different type of requirement. In such cases, user input includes modifications to the field values ​​of the requirement category fields. By modifying the requirement category, different field values ​​(i.e., different forms) can be presented. In such cases, the method may exemplary include re-extracting based on the updated form to pre-fill the field values ​​of at least some of the fields.

[0060] According to some embodiments, the second user input includes field value input corresponding to at least a portion of the one or more fields.

[0061] For fields that were not successfully retrieved or are optional, users can enter their input. The standardized form format for fields and field values ​​makes it easy for users to fill in the information.

[0062] According to some embodiments, obtaining a prompt statement based on the one or more fields and the second user input includes: in response to determining that the second user input indicates confirmation of a corresponding field value for at least one of the one or more fields, determining demand information based on the at least one field and the corresponding field value; and obtaining the prompt statement based on the demand information.

[0063] According to such an embodiment, standardized requirement information can be obtained. For example, when the fields are organized into a requirement form, the second user input can indicate confirmation of the corresponding field value for at least one field of the requirement form. In such an embodiment, the determined requirement information can be, for example, standardized requirement information, such as form-based requirement information.

[0064] According to some embodiments, the method may further include determining a data source corresponding to the first user input, wherein constructing an agent based on the prompt statement includes constructing the agent based on the prompt statement and the data source.

[0065] In addition to generating prompts, it can also match corresponding data sources based on user needs descriptions, thereby enabling the construction of intelligent agents that are more targeted and better suited to user needs.

[0066] According to some embodiments, determining the data source corresponding to the first user input includes determining a data domain based on the first user input and then determining the data source corresponding to the data domain.

[0067] Therefore, it is possible to determine the corresponding domain based on the user's needs and to identify the data source in a targeted manner.

[0068] According to some embodiments, the method may further include obtaining an enhanced dataset based on the data domain as the data source.

[0069] Therefore, enhancements can be made based on the data domain, making the constructed intelligent agents more targeted.

[0070] According to some embodiments, the method may further include: determining a data range; and constructing the agent based on data corresponding to the data range.

[0071] Therefore, the data range can be determined based on user selection, such as the most popular data, ordinary data, or all data, and an intelligent agent can be constructed based on the data range. This allows for different effects to be achieved by constructing the agent based on data from different ranges, according to user needs.

[0072] With the rapid development of artificial intelligence technology, intelligent agents have been widely used in many fields. However, in existing technologies, the construction of intelligent agents often faces problems such as high cost, long cycle, and poor user experience. According to one or more embodiments of this disclosure, a large model system architecture scheme that supports real-time updates is provided.

[0073] As a specific, non-limiting embodiment, reference is made to Figure 3 A smart agent construction system 300 according to one or more embodiments of the present disclosure is described. For example... Figure 3 As shown, the system architecture for building intelligent agents can include, for example, prompt generation, data export, and optional updates and training.

[0074] The Prompt generation module, also known as the intelligent prompt generation module, is a programming language used to transform raw queries (first user input) into large-scale models. For example, it can automatically generate structured prompts through steps such as business requirement profiling, information extraction and backfilling, advanced configuration interaction, and prompt synthesis and validation.

[0075] Business requirement profiling can be built based on the user's original query, using a classifier to select a matching Agent template. The template library can pre-load structured tables corresponding to various business types. For example, the first level of the table is a domain classification identifier. For instance, key background information from the business system can be used to generate business requirement profiles.

[0076] Information extraction and backfilling can utilize natural language processing technology to extract key information from user input, including but not limited to: entity recognition components extracting core parameters, semantic analysis components parsing format requirements, sentiment analysis modules determining tone and style, and automatically filling the extracted results into predefined table fields. For unrecognized fields, the following processing strategies can be adopted: triggering highlight suggestions for required fields, providing default parameters for optional fields, and generating interactive options for extended fields.

[0077] Advanced configuration interactions can provide multimodal interaction interfaces for complex scenarios, such as adding optional extra boxes to cater to personalized needs. For example, a conditional branch selector can be used to provide an interactive selection interface with preset options. Exemplarily, a multi-turn dialogue engine can be used, which can be implemented, for example, through a requirement recognition model. Exemplarily, the dialogue engine can provide contextual guidance, such as guiding style requirements through multi-turn dialogue, outputting "Which style do you want to choose from these?" to the user. It is understood that this disclosure is not limited thereto. User-defined parameter input modules can be used to support open-ended parameter supplementation.

[0078] Prompt synthesis and validation can convert structured tabular data into standard Prompt format, including but not limited to: Role definition domain: containing identity identifiers, skill descriptions, and constraint rules; Workflow domain: defining the task execution logic chain; Tool call domain: declaring accessible APIs and usage specifications. The generated results can be submitted to the execution engine after compliance checks by a syntax validator.

[0079] Thus, users can complete the construction of an intelligent agent by selecting a template, filling out a form, configuring advanced settings (optional), and submitting their requirements.

[0080] As a specific, non-restrictive example, the final output could be information in the following format:

[0081]

[0082]

[0083]

[0084] Data export can be achieved through an intelligent data export module or subsystem, which may include a data import layer, a hierarchical storage layer, and an intelligent export engine. This subsystem can utilize large amounts of high-quality data from search scenarios to generate business-domain sharded data. It can automatically export public database data to the search data center, and then export and use the core data from the data center for users. To improve professionalism and effectiveness, based on the example format of this disclosure, the industry-required data can be fine-tuned, refined, and subjected to RAG retrieval. For example, based on the original query, i.e., the first user input, data domains and / or industry classifications can be extracted, which will serve as the industry classifications for the required data.

[0085] The data ingestion layer can include a real-time crawling component: acquiring raw data from multiple sources based on a distributed crawling framework; and a streaming processing pipeline: including deduplication filters, format normalizers, and quality assessment models. For example, the core could be data provided by a search engine.

[0086] For example, the data import layer may include a search data acquisition module and a data cleaning and preprocessing module. The search data acquisition module can collect raw data from the search engine in real time. The data cleaning and preprocessing module can clean, deduplicate, and standardize the format of the collected data to ensure data quality.

[0087] Data can be stored through a data storage layer. As an example, data can be categorized and stored in various ways. For instance, it can be stored by industry, such as secondary industry categories including broad and narrow classifications. Another example is categorizing data by quality or popularity; for instance, each data point could be classified as "hottest," "average," or "cold" based on user clicks and search behavior.

[0088] For example, the data storage layer may include a public data warehouse and business domain sub-databases. The public data warehouse can store cleaned, high-quality data, serving as a centralized data management center. The business domain sub-databases can store public data according to different business needs, categorizing it by domain to form multiple business sub-databases.

[0089] Tiered storage can be implemented using a layered storage architecture: Public data warehouse: stores the basic dataset and establishes a unified metadata standard; Business-specific database cluster: establishes physically isolated sub-databases according to industry classification; Dynamic tiering system: classifies data quality based on user behavior analysis models (click-through rate, dwell time, conversion rate) and establishes hot data indexes.

[0090] For example, in addition to user content data, the collected and stored data may also include user feedback data, search behavior, user clicks, browsing, etc.

[0091] For example, the data export layer may include an automatic export agent module and an access control and security control module. The automatic export agent module can automatically export the corresponding business database data according to preset rules or user needs. The access control and security control module can ensure the access control and security of the data export, preventing unauthorized data access.

[0092] The intelligent export engine of the data export layer can include a demand parser: linking user queries with business databases through semantic matching algorithms; an access control gateway: implementing attribute-based access control (ABAC) policies; and an adaptive transmission module: providing differentiated transmission schemes based on data hierarchy.

[0093] Differentiated transmission schemes may include, for example, an economic mode that transmits only a subset of thermal data; a standard mode that transmits thermal data plus regular data; and a full mode that transmits all data.

[0094] For example, a data center layer and a user service layer may also be provided.

[0095] The data center layer may include: a search data center, which aggregates data from all business databases and provides users with a unified data service interface; and a core data processing module, which performs in-depth processing and analysis on imported data to enhance its value.

[0096] For example, the user service layer may include: a data sales platform for providing sales services for sharded data, supporting users to purchase the business domain data they need; and a user interface module for users to request and obtain the required datasets through APIs or interfaces.

[0097] Return to reference Figure 3 For decision-intensive scenarios, it also provides optional intelligent model training, which includes, for example, a training sample generator, a hybrid training controller, and a deployment monitoring system. For instance, in certain domains, such as those with strong decision-making attributes, a subset of high-quality data can be exported for decision-making.

[0098] The training sample generator may include: a template parsing unit: deconstructing the semantic framework of the original Prompt; a data augmentation unit: generating derived samples using a random replacement strategy; and a distribution equalizer: ensuring consistency of feature distribution through a chi-square test.

[0099] The hybrid training controller may include: a full training unit: for model initialization based on the base dataset; an incremental update unit: for handling new data using a sliding window mechanism; and a validation feedback loop: for implementing K-fold cross-validation and online A / B testing.

[0100] Deploying a monitoring system can include: a version management repository to maintain the model iteration history; an anomaly detector to monitor inference result offsets; and a rollback mechanism to automatically switch to the previous version when the accuracy drops below a threshold.

[0101] A combination of full and incremental SFT can be used, randomly shuffling and replacing the original template information and core data to intelligently generate diverse training samples, thereby achieving rapid and effective model updates and training.

[0102] By combining full and incremental SFT (Structured Fine-Tuning) techniques, the amount of data and training time required can be significantly reduced while ensuring the effectiveness of model training. Full SFT is used for comprehensive initial model training, while incremental SFT quickly adapts to new or changed data, improving the model's flexibility and real-time performance.

[0103] For example, a strategy for intelligently generating training samples can be provided, which involves randomly shuffling and replacing the original template information with core data to automatically generate diverse training samples. This method not only increases the diversity of training data but also effectively avoids overfitting and improves the model's generalization ability.

[0104] As an optional exemplary embodiment, to maintain data diversity when generating training samples, data distribution checks and statistical tests (such as chi-square test and Kolmogorov-Smirnov test) can be performed during data extraction to quantitatively assess whether the feature distribution is consistent across different datasets. Then, stratified sampling is performed to ensure that categories have the same proportion across different datasets. Finally, a validation method (K-fold cross-validation) is used to ensure that the data during model training is representative of all data.

[0105] Figure 4 A schematic diagram of a data flow according to one or more exemplary non-limiting embodiments of the present disclosure is shown. Figure 4 As shown, the data export layer is responsible for exporting data. The Prompt intelligent system generates a basic training template and interacts with the data intelligence system. After data export, it undergoes a data filtering and generation process, followed by template filling and replacement. The processed data is then submitted for training. Furthermore, the user service layer (data intelligence system) can perform data cross-validation to ensure data quality. For example, a data verification / confirmation step can also be included between template filling / replacement and the submission of training data.

[0106] According to one or more embodiments of this disclosure, the entire process of intelligent agent construction is optimized.

[0107] According to one or more embodiments of this disclosure, fully automated data export is achieved, reducing manual intervention and improving data processing efficiency.

[0108] According to one or more embodiments of this disclosure, large amounts of data are innovatively managed by dividing them into databases according to business domains to meet the customized needs of different users.

[0109] According to one or more embodiments of this disclosure, the entire process from data acquisition and processing to export and sale is automated, improving system response speed.

[0110] According to one or more embodiments of this disclosure, the authenticity, accuracy, and completeness of the large amount of data obtained from search scenarios can be ensured. All data is scored using full website base data and user behavior click models, and the scoring rules for business data are further optimized based on the user's profile and reverse click recommendation behavior.

[0111] Now for reference Figure 5 An apparatus 500 for constructing an intelligent agent according to embodiments of the present disclosure is described. The apparatus 500 may include a first input unit 501, a field determination unit 502, a second input unit 503, a prompt statement unit 504, and a construction unit 505. The first input unit 501 may be used to obtain first user input, which is natural language text containing intelligent agent construction requirements. The field determination unit 502 may be used to determine one or more fields based on the first user input. The second input unit 503 may be used to obtain second user input associated with the one or more fields. The prompt statement unit 504 may be used to obtain a prompt statement based on the one or more fields and the second user input. The construction unit 505 may be used to construct an intelligent agent according to the prompt statement.

[0112] The apparatus described in the embodiments of this disclosure is capable of intelligently assisting in the construction of intelligent agents.

[0113] The collection, acquisition, storage, use, processing, transmission, provision, and public application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0114] According to embodiments of this disclosure, an electronic device, a readable storage medium, and a computer program product are also provided.

[0115] refer to Figure 6The present invention describes a structural block diagram of an electronic device 600 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0116] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0117] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to electronic device 600. Input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device, and can include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 607 can be any type of device capable of presenting information, and can include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 608 can include, but is not limited to, disk and optical disk. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and can include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0118] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as method 200 and its variations. For example, in some embodiments, method 200 and its variations may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of method 200 and its variations described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute method 200 and its variations by any other suitable means (e.g., by means of firmware).

[0119] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0121] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0124] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0125] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0126] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A method for constructing an intelligent agent, comprising: Obtain first user input, which is natural language text containing the agent construction requirements; Determining one or more fields based on the first user input includes: determining a requirement category based on the first user input; selecting a structured table corresponding to the requirement category from a predetermined form library as a requirement form, the requirement form including the one or more fields; and extracting key information from the first user input using natural language processing technology, and automatically filling the extracted results into the fields of the requirement form. Obtain second user input associated with the one or more fields; Obtaining a prompt statement based on one or more fields and the second user input includes: converting the one or more fields and the second user input into structured tabular data; and synthesizing the prompt statement based on the structured tabular data, wherein the prompt statement includes a role definition domain, a workflow domain, and a tool call domain, wherein the role definition domain includes identity identifiers, skill descriptions, and constraint rules; Determine the data domain corresponding to the first user input; Determining a business domain sub-database corresponding to the data domain as the data source includes: classifying the data quality based on a user behavior analysis model and establishing a hot data index; and providing differentiated transmission schemes according to the data classification to export data from the business domain sub-database. The differentiated transmission schemes include: an economical mode that transmits only a subset of hot data, a standard mode that transmits both hot and ordinary data, or a complete mode that transmits all data. Construct an intelligent agent based on the prompt statement and the data source.

2. The method according to claim 1, further comprising obtaining an identified field value corresponding to at least one of the one or more fields based on the first user input.

3. The method according to claim 2, wherein, The second user input includes modifications to at least a portion of the identified field values.

4. The method according to claim 2, wherein, The second user input includes confirmation of at least a portion of the identified field values.

5. The method according to any one of claims 1-4, wherein, The one or more fields include a requirement category field, and wherein a modification to the requirement category field is used to trigger the presentation of a different category of form to the user as an updated requirement form.

6. The method according to any one of claims 1-4, wherein, The second user input includes field value input corresponding to at least a portion of the one or more fields.

7. The method according to any one of claims 1-4, wherein, The prompt statement obtained based on the one or more fields and the second user input includes: In response to determining that the second user input indicates confirmation of a corresponding field value for at least one of the one or more fields, demand information is determined based on the at least one field and the corresponding field value; and The prompt statement is obtained based on the aforementioned requirement information.

8. The method of claim 1, further comprising obtaining an enhanced dataset based on the data domain as the data source.

9. The method according to any one of claims 1-4, further comprising: Determine the data range; And construct the intelligent agent based on the data corresponding to the data range.

10. An apparatus for constructing intelligent agents, comprising: The first input unit is used to obtain the first user input, which is natural language text containing the agent construction requirements; A field determination unit is configured to determine one or more fields based on the first user input, including: determining a requirement category based on the first user input; selecting a structured table corresponding to the requirement category from a predetermined form library as a requirement form, the requirement form including the one or more fields; and extracting key information from the first user input using natural language processing technology, and automatically filling the extracted results into the fields of the requirement form. The second input unit is used to obtain second user input associated with the one or more fields; A prompt statement unit is used to obtain a prompt statement based on one or more fields and the second user input, including: converting the one or more fields and the second user input into structured tabular data; and synthesizing the prompt statement based on the structured tabular data, wherein the prompt statement includes a role definition domain, a workflow domain, and a tool invocation domain, wherein the role definition domain includes identity identifiers, skill descriptions, and constraint rules; and The construction unit is used to determine the data domain corresponding to the first user input and to determine the business domain sub-database corresponding to the data domain as the data source. This includes: classifying the data based on a user behavior analysis model to establish a hot data index; providing differentiated transmission schemes according to the data classification; exporting data from the business domain sub-database; the differentiated transmission schemes include: an economic mode that transmits only a subset of hot data, a standard mode that transmits both hot and ordinary data, or a complete mode that transmits all data; and constructing an intelligent agent based on the prompt statement and the data source.

11. An electronic device, comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

13. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method of any one of claims 1-9.

Images