Artificial intelligence-based order creation methods, devices, equipment, and storage media
By using intelligent agent clusters for voice interaction and order creation, the problem of users being unfamiliar with the operation was solved, the efficiency and accuracy of order generation were improved, and the user experience was enhanced.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PING AN HEALTH CLOUD CO LTD
- Filing Date
- 2026-02-03
- Publication Date
- 2026-06-02
AI Technical Summary
Users who are unfamiliar with operating smart terminals or have poor eyesight may encounter difficulties in order generation and service booking, thus affecting their user experience.
By acquiring the user's voice data, the system calls upon a cluster of intelligent agents to perform intent recognition, selects the target interactive agent and the order generation agent, and then performs voice interaction and order creation.
It improved the efficiency and accuracy of order creation, and enhanced user convenience.
Smart Images
Figure CN122134422A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence technology, and in particular to an order creation method, apparatus, device and storage medium based on artificial intelligence. Background Technology
[0002] As an excellent human-computer interaction medium, smart terminals can provide users with various services. For example, in the financial industry, users can use smart terminals to generate orders for various financial products; in the medical industry, users can use smart terminals to fill in personal information and symptoms before medical consultations to facilitate the generation of appointment orders; and elderly people can use smart terminals to generate orders for consumer services. However, users may not be familiar with the operation of smart terminals, or elderly people may have poor eyesight, leading to difficulties in order generation and service appointment completion, causing inconvenience to users and seriously affecting their user experience.
[0003] Therefore, how to accurately and conveniently generate demand orders based on user needs is an urgent problem to be solved. Summary of the Invention
[0004] The main purpose of this application is to provide an order creation method, apparatus, device, and storage medium based on artificial intelligence, which aims to improve the efficiency and accuracy of generating user-demand orders.
[0005] In a first aspect, this application provides an order creation method based on artificial intelligence, the order creation method based on artificial intelligence including the following steps: The system acquires the user's voice data and invokes a cluster of intelligent agents, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent. The intent recognition agent performs intent recognition on the voice data to obtain the user's target intent. Based on the target intent, a target interactive agent and a target order generating agent are selected from the agent cluster; The target interactive intelligent agent interacts with the user via voice to request orders, thereby obtaining order voice interaction information. The target order generating agent creates an order based on the order voice interaction information, generating the order information for the services required by the user.
[0006] Secondly, this application also provides an order creation device, which includes an acquisition module, a generation module, a selection module, and an order creation module, wherein: The acquisition module is used to acquire the user's voice data and call the intelligent agent cluster, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent. The generation module is used to perform intent recognition on the voice data through the intent recognition agent to obtain the user's target intent; The selection module is used to select a target interactive agent and a target order generating agent from the agent cluster according to the target intent; The generation module is also used to conduct order request voice interaction with the user through the target interactive intelligent agent to obtain order voice interaction information; The order creation module is used to create an order based on the order voice interaction information through the target order generation agent, and generate the order information for the services required by the user.
[0007] Thirdly, this application also provides a smart terminal, which includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the steps of the artificial intelligence-based order creation method described above.
[0008] Fourthly, this application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the artificial intelligence-based order creation method described above.
[0009] This application provides an artificial intelligence-based order creation method, apparatus, device, and storage medium. The method involves acquiring a user's voice data and invoking an intelligent agent cluster, which comprises multiple agents, including at least one intent-recognition agent. The intent-recognition agent performs intent recognition on the voice data to obtain the user's target intent. Based on the target intent, a target interaction agent and a target order generation agent are selected from the intelligent agent cluster. The target interaction agent engages with the user through voice interaction regarding the order request, obtaining order voice interaction information. The target order generation agent then creates the order based on the order voice interaction information, generating the order information for the services required by the user. This application utilizes matching agents within the intelligent agent cluster to interact with the user via voice, thereby generating the order information for the services required by the user. This significantly improves the efficiency and accuracy of order creation, thus enhancing the convenience of users' lives. Attached Figure Description
[0010] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 A flowchart illustrating an artificial intelligence-based order creation method provided in this application embodiment; Figure 2 A flowchart illustrating another artificial intelligence-based order creation method provided in this application embodiment; Figure 3 A schematic block diagram of an order creation device provided in an embodiment of this application; Figure 4 This is a schematic block diagram of the structure of a smart terminal provided in an embodiment of this application.
[0012] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0014] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.
[0015] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.
[0016] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.
[0017] As an excellent human-computer interaction medium, smart terminals can provide users with various services. For example, in the financial industry, users can use smart terminals to generate orders for various financial products; in the medical industry, users can use smart terminals to fill in personal information and symptoms before medical consultations to facilitate the generation of appointment orders; and elderly people can use smart terminals to generate orders for consumer services. However, users may not be familiar with the operation of smart terminals, or elderly people may have poor eyesight, leading to difficulties in order generation and service appointment completion, causing inconvenience to users and seriously affecting their user experience.
[0018] To address the aforementioned problems, this application provides an artificial intelligence-based order creation method, apparatus, device, and storage medium. The AI-based order creation method includes acquiring a user's voice data and invoking an intelligent agent cluster, which comprises multiple intelligent agents, including at least one intent-recognition intelligent agent; using the intent-recognition intelligent agent to identify the user's target intent from the voice data; selecting a target interaction intelligent agent and a target order generation intelligent agent from the intelligent agent cluster based on the target intent; engaging in order request voice interaction with the user through the target interaction intelligent agent to obtain order voice interaction information; and using the target order generation intelligent agent to create an order based on the order voice interaction information, generating order information for the services required by the user. This method generates order information for the services required by the user, significantly improving the efficiency and accuracy of order creation, thereby enhancing the convenience of users' lives.
[0019] This AI-based order creation method can be applied to smart terminals, such as mobile phones, tablets, laptops, desktop computers, smart speakers, personal digital assistants, and wearable devices.
[0020] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0021] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an artificial intelligence-based order creation method provided for an embodiment of this application.
[0022] like Figure 1 As shown, the AI-based order creation method includes steps S101 to S104.
[0023] Step S101: Obtain the user's voice data and invoke the intelligent agent cluster, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent.
[0024] The voice data refers to the voice data of a user who needs to place an order, such as the voice requesting cleaning. The intelligent agent cluster is a pre-trained cluster of multiple intelligent agents, such as an intent recognition agent, an interaction agent, and an order generation agent.
[0025] In some embodiments, such as Figure 2 As shown, the AI-based order creation method also includes steps S201 to S205.
[0026] Step S201: Obtain a sample dataset, which includes multiple sample data, including sample voice data, sample order voice interaction information, and sample order information.
[0027] The sample dataset includes multiple sample data, including sample voice data, sample order voice interaction information, and sample order information. The sample voice data consists of the user's request voice, the sample order voice interaction information consists of the user's voice interaction with the intelligent agent, and the sample order information consists of the orders requested by the user.
[0028] In some embodiments, user-input voice data is acquired, an intent recognition agent, an interaction agent, and an order generation agent are manually selected, and order interaction information and order information are set according to the voice data. The voice data is recorded as sample voice data, the order interaction information is recorded as sample order interaction information, and the order information is recorded as sample order information. The sample voice data, sample order interaction information, and sample order information are used as a single sample data set. The aforementioned steps are repeated to obtain a sample dataset.
[0029] Step S202: Obtain a preset intelligent agent cluster, which includes multiple untrained intelligent agents.
[0030] Obtain a pre-defined cluster of agents, which includes multiple untrained agents—those in their initial state, not yet undergoing autonomous learning and evolution. By obtaining this pre-defined cluster, diverse agents can be effectively trained.
[0031] Step S203: Select a sample data from the sample dataset as the target sample data.
[0032] In some embodiments, a sample data is randomly selected from the sample dataset as the target sample data.
[0033] Step S204: Create orders for the target sample data through a preset intelligent agent cluster to obtain predicted order information.
[0034] In some embodiments, the intent recognition agent of a preset agent cluster performs intent recognition on the sample voice data of the target sample data to obtain the user's predicted intent; based on the predicted intent, a target interaction agent and a target order generation agent are selected from the predicted agent cluster; the predicted order voice interaction information is generated by the target interaction agent interacting with the order question voice in the sample order voice interaction information; and the target order generation agent creates an order based on the predicted order voice interaction information to generate the predicted order information for the services required by the user.
[0035] It should be noted that the predicted order information obtained by creating orders from the target sample data through a preset intelligent agent cluster can be found in another embodiment of order creation based on artificial intelligence in this application, which will not be elaborated on in this embodiment.
[0036] Step S205: Based on the predicted order information and the sample order information, determine whether each agent in the preset agent cluster has completed training.
[0037] Based on the predicted order information and sample order information, a preset loss value for the intelligent agent cluster is determined. If the loss value is greater than or equal to the preset loss value, it is determined that each intelligent agent in the preset intelligent agent cluster has not completed training; if the loss value is less than the preset loss value, it is determined that each intelligent agent in the preset intelligent agent cluster has completed training. The preset loss value can be set according to actual conditions, and this embodiment does not impose specific limitations on it. For example, the preset loss value can be set to 0.02.
[0038] In some embodiments, the method for determining the loss value of the preset intelligent agent cluster based on the predicted order information and sample order information can be as follows: calculate the similarity between the predicted order information and the sample order information to obtain the current similarity; obtain the historical similarity, which is the mean of the current similarities of each sample data that has been trained; calculate the mean of the current similarity and the historical similarity to obtain the target similarity; subtract the target similarity from the unit value to determine the loss value of the preset intelligent agent cluster. The method for calculating the similarity can be selected according to the actual situation, and this embodiment does not specifically limit it. For example, the cosine similarity between the predicted order information and the sample order information can be calculated.
[0039] Step S206: If each agent in the preset agent cluster has not completed training, the parameters of at least one agent in the preset agent cluster are adjusted, and the step of selecting a sample data from the sample dataset as the target sample data continues to be executed until a converged agent cluster is obtained.
[0040] If the loss value is less than the preset loss value, it is determined that each agent in the preset agent cluster has completed training; if the loss value is greater than the preset loss value, it is determined that there are agents in the agent cluster that have not completed training. In this case, the parameters of at least one agent in the preset agent cluster are adjusted, and the process continues to select a sample data from the sample dataset as the target sample data; an order is created on the target sample data through the preset agent cluster to obtain the predicted order information; based on the predicted order information and the sample order information, it is determined whether each agent in the preset agent cluster has completed training; until a converged agent cluster is obtained.
[0041] It should be noted that the specific training process of this intelligent agent cluster is an existing technical solution, and this application will not elaborate on it further.
[0042] In some embodiments, acquiring a user's voice data involves invoking a cluster of intelligent agents, including a consciousness recognition agent. Invoking this cluster after acquiring the user's voice data effectively improves the efficiency and accuracy of order creation.
[0043] For example, the smart terminal is a smart speaker, which collects the user's voice data and calls up a cluster of smart agents.
[0044] Step S102: The intent recognition agent performs intent recognition on the voice data to obtain the user's target intent.
[0045] The target intent is the intent of the user to receive the service.
[0046] In some embodiments, an intent-recognition agent performs semantic recognition on the voice data to obtain the user's semantic information; the user's intent is then extracted from the semantic information to obtain the user's target intent. By performing semantic recognition and intent extraction on the voice data, the user's target intent can be accurately obtained.
[0047] In some embodiments, the way to obtain the user's semantic information by performing semantic recognition on voice data through an intent recognition agent can be: performing voice recognition on the voice data to obtain voice text data; and performing user semantic recognition on the voice text data to obtain the user's semantic information, which greatly improves the efficiency and accuracy of order generation.
[0048] Step S103: Select the target interactive agent and the target order generating agent from the agent cluster according to the target intent.
[0049] The target interactive agent is used for voice interaction with the user, and the target order generation agent is used for order creation. The target interactive agent and / or target order generation agent differs depending on the intent. For example, in cleaning services, the target interactive agent is a daily interaction agent, and the order generation agent is a daily order generation agent; similarly, in the financial technology field, the target interactive agent is a financial interaction agent, and the order generation agent is a financial order generation agent. By setting different agents, the accuracy of order generation can be effectively improved.
[0050] In some embodiments, user needs are determined based on the target intent, and a preset mapping table between user needs and interactive agents and order-generating agents is obtained. The target interactive agent and target order-generating agent matching the user needs are then queried from the mapping table. This mapping table is pre-established based on user needs, interactive agents, and order-generating agents, and can be established according to actual circumstances; this embodiment does not impose specific limitations on this. The target interactive agent and target order-generating agent can be accurately queried through this mapping table.
[0051] In some embodiments, the user's needs can be determined based on the target intent by: obtaining a preset needs library, which includes different types of needs; matching the target intent with each need in the preset needs library; and taking the need with the highest matching degree as the user's needs.
[0052] For example, in the field of financial technology, a user's need is to purchase financial products. Based on the purchase of financial products, the target interactive intelligent agent is found from the mapping relationship table as a financial interactive intelligent agent, and the order generating intelligent agent is a financial order generating intelligent agent.
[0053] For example, in the field of medical technology, if a user's need is to purchase medical drugs, the target interactive agent is found to be a medical interactive agent by querying the mapping relationship table based on the user's need to purchase medical drugs, and the order generating agent is a medical order generating agent.
[0054] Step S104: The target interactive intelligent agent interacts with the user via voice to request order information, thereby obtaining order voice interaction information.
[0055] In some embodiments, a target interactive agent outputs multiple order question voice messages to the user based on a target intent; multiple order question-and-answer voice messages are acquired based on the user's input of each of the order question messages; and order voice interaction information is generated based on the multiple order question voice messages and the multiple order question-and-answer voice messages. By outputting order question voice messages to the user and acquiring the user's order answer voice messages, order voice interaction information can be accurately obtained.
[0056] In some embodiments, the method of outputting multiple order question voices to the user based on the target intent by the target interactive intelligent agent can be as follows: the target interactive intelligent agent determines multiple question texts according to the target intent, converts the multiple question texts into multiple order question voices, and plays the multiple order question voices through the speaker of the intelligent terminal so that the user can hear the multiple order question voices.
[0057] In some embodiments, the method of obtaining multiple order question and answer voices based on the user's input of each order question information can be as follows: after the user hears the order question voice, he / she answers the corresponding question based on the order question voice to obtain the order question and answer voice, and then obtains multiple order answer voices through the smart terminal to obtain multiple order answer voices.
[0058] For example, in the field of financial technology, a user's need is to purchase financial products. The target interactive intelligent agent generates order-related voice prompts based on this intention, including the product name, product code, purchase time, purchase amount, and user information. The intelligent terminal plays these order-related voice prompts. After hearing them, the user answers each question, verbally stating the product name, product code, purchase time, purchase amount, and user information. The intelligent terminal then receives the order-related voice prompts containing the product name, product code, purchase time, purchase amount, and user information.
[0059] In some embodiments, after acquiring multiple order question-and-answer voice messages, the target interactive agent generates multiple new order question voice messages based on the user's input of these messages; acquires multiple new order question-and-answer voice messages input by the user based on these new messages; and generates order voice interaction information according to the question-and-answer logic relationships between the multiple order question voice messages, the multiple order question-and-answer voice messages, the multiple new order question voice messages, and the multiple new order question-and-answer voice messages. By supplementing with multiple new order question voice messages and acquiring multiple new order question-and-answer voice messages, the created orders become more accurate.
[0060] For example, after the target interactive agent obtains the order response voice containing the product name, product code, purchase time, purchase amount, and user information, it generates a new order question voice containing the financial product's unit price, purchase amount, and whether the purchase has been made due to a change in the unit price of the financial product. It then obtains multiple new order question and answer voices based on the user's input of multiple financial product unit prices, purchase amounts, and whether the purchase has been made. Based on the question-and-answer logic relationship between the multiple order question voices, multiple order question and answer voices, multiple new order question voices, and multiple new order question and answer voices, it generates order voice interaction information.
[0061] Step S105: The target order generating agent creates an order based on the order voice interaction information, generating the order information for the services required by the user.
[0062] In some embodiments, an order list item is generated based on the order voice interaction information. This order list item includes multiple order service items. User information and service information are input into the order list item based on the order voice interaction information to obtain the order information for the services required by the user. By creating an order list item and populating it with information, order information can be accurately obtained.
[0063] For example, in the field of financial management, an order list item is generated based on the order voice interaction information. This order list item includes product name, product code, purchase time, purchase amount, and user information. The order information is then obtained by filling in the product name, product code, purchase time, purchase amount, and user information based on the order voice interaction information.
[0064] For example, in a scenario where a user purchases medicine, an order list item is generated based on the order voice interaction information. This order list item includes the medicine name, medicine quantity, user information, and medication precautions. The order information is then filled in based on the order voice interaction information to obtain the order information.
[0065] For example, in a cleaning service scenario, an order list item is generated based on the order voice interaction information. This order list item includes service type, service duration, service address, and service time. The order information is then populated by filling in the service type, service duration, service address, and service time items based on the order voice interaction information to obtain the order information.
[0066] In some embodiments, an order request, including the order information, is sent to the corresponding target server. By sending an order request to the target server, orders can be completed for users in a timely manner, greatly improving the convenience of users' lives.
[0067] By setting up different intelligent agents to achieve different stages of order generation, the accuracy and efficiency of order generation can be effectively improved. By helping users complete their orders through voice interaction, the problem of users being unfamiliar with operating smart terminals can be greatly solved, and the convenience of users' lives can be greatly improved.
[0068] The AI-based order creation method provided in the above embodiments acquires user voice data and invokes an intelligent agent cluster, which consists of multiple intelligent agents, including at least one intent recognition intelligent agent. The intent recognition intelligent agent performs intent recognition on the voice data to obtain the user's target intent. Based on the target intent, a target interaction intelligent agent and a target order generation intelligent agent are selected from the intelligent agent cluster. The target interaction intelligent agent interacts with the user to request the order via voice, obtaining order voice interaction information. The target order generation intelligent agent then creates the order based on the order voice interaction information, generating the order information for the services required by the user. This application utilizes the voice interaction between matched intelligent agents in the intelligent agent cluster and the user to generate the order information for the services required by the user, greatly improving the efficiency and accuracy of order creation, thereby enhancing the convenience of users' lives.
[0069] Please see Figure 3 , Figure 3 This is a schematic block diagram of an order creation device provided in an embodiment of this application.
[0070] like Figure 3 As shown, the order creation device 300 includes an acquisition module 310, a generation module 320, a selection module 330, and an order creation module 340, wherein: The acquisition module 310 is used to acquire the user's voice data and call the intelligent agent cluster, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent. The generation module 320 is used to perform intent recognition on the voice data through the intent recognition agent to obtain the user's target intent; The selection module 330 is used to select a target interactive agent and a target order generating agent from the agent cluster according to the target intent; The generation module 320 is also used to conduct order request voice interaction with the user through the target interactive intelligent agent to obtain order voice interaction information; The order creation module 340 is used to create an order based on the order voice interaction information through the target order generation agent, and generate the order information for the services required by the user.
[0071] In some embodiments, the generation module 320 is further configured to: The intent recognition agent performs semantic recognition on the voice data to obtain the user's semantic information; Extract the user intent from the semantic information to obtain the user's target intent.
[0072] In some embodiments, the selection module 330 is further configured to: Based on the target intent, determine the user's user needs and obtain a preset mapping table between user needs and interactive intelligent agents and order generation intelligent agents; Query the target interactive agent and target order generating agent that match the user's needs from the mapping table.
[0073] In some embodiments, the generation module 320 is further configured to: The target interactive intelligent agent outputs multiple order-related voice questions to the user based on the target intent; Acquire multiple order question and answer voice recordings input by the user based on the order question information; Based on the multiple order question voice messages and multiple order question and answer voice messages, generate order voice interaction information.
[0074] In some embodiments, the generation module 320 is further configured to: The target interactive intelligent agent generates multiple new order question voices based on the multiple order question and answer voices input by the user; Acquire multiple new order question and answer voices based on the user's input of multiple new order question voices; The step of generating order voice interaction information based on the multiple order question voices and multiple order question-and-answer voices includes: Based on the question-and-answer logic relationship between the multiple order question voices, multiple order question and answer voices, multiple new order question voices, and multiple new order question and answer voices, the order voice interaction information is generated.
[0075] In some embodiments, the generation module 320 is further configured to: Based on the order voice interaction information, an order list item is generated, which includes multiple order service items; Based on the order voice interaction information, user information and service information are input into the order list items to obtain the order information for the services required by the user.
[0076] In some embodiments, the order creation device 300 is further configured to: The order request, which includes the order information, is sent to the corresponding target server.
[0077] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the above-mentioned order creation device can be referred to the corresponding process in the aforementioned embodiment of the artificial intelligence-based order creation method, and will not be repeated here.
[0078] Please see Figure 4 , Figure 4 This is a schematic block diagram of the structure of a smart terminal provided in an embodiment of this application.
[0079] like Figure 4 As shown, the smart terminal 400 includes a processor 402 and a memory 403 connected via a system bus 401, wherein the memory 403 may include a storage medium and internal memory.
[0080] The storage medium may store a computer program. This computer program includes program instructions that, when executed, cause the processor to perform any artificial intelligence-based order creation method.
[0081] The processor 402 provides computing and control capabilities to support the operation of the entire smart terminal.
[0082] Internal memory provides an environment for the execution of computer programs stored in the storage medium. When these computer programs are executed by the processor, the processor can execute any artificial intelligence-based order creation method.
[0083] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the smart terminal to which the solution of this application is applied. A specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0084] It should be understood that processor 402 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.
[0085] In one embodiment, the processor 402 is configured to run a computer program stored in a memory to perform the following steps: The system acquires the user's voice data and invokes a cluster of intelligent agents, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent. The intent recognition agent performs intent recognition on the voice data to obtain the user's target intent. Based on the target intent, a target interactive agent and a target order generating agent are selected from the agent cluster; The target interactive intelligent agent interacts with the user via voice to request orders, thereby obtaining order voice interaction information. The target order generating agent creates an order based on the order voice interaction information, generating the order information for the services required by the user.
[0086] In one embodiment, when the processor 402 performs intent recognition on the voice data through the intent recognition agent to obtain the user's target intent, it is configured to: The intent recognition agent performs semantic recognition on the voice data to obtain the user's semantic information; Extract the user intent from the semantic information to obtain the user's target intent.
[0087] In one embodiment, when the processor 402 selects the target interactive agent and the target order generating agent from the agent cluster according to the target intent, it is configured to: Based on the target intent, determine the user's user needs and obtain a preset mapping table between user needs and interactive intelligent agents and order generation intelligent agents; Query the target interactive agent and target order generating agent that match the user's needs from the mapping table.
[0088] In one embodiment, when the processor 402 performs the order request voice interaction with the user through the target interactive intelligent agent to obtain order voice interaction information, it is configured to: The target interactive intelligent agent outputs multiple order-related voice questions to the user based on the target intent; Acquire multiple order question and answer voice recordings input by the user based on the order question information; Based on the multiple order question voice messages and multiple order question and answer voice messages, generate order voice interaction information.
[0089] In one embodiment, before generating order voice interaction information based on the plurality of order question voices and the plurality of order question-and-answer voices, the processor 402 is further configured to implement: The target interactive intelligent agent generates multiple new order question voices based on the multiple order question and answer voices input by the user; Acquire multiple new order question and answer voices based on the user's input of multiple new order question voices; The step of generating order voice interaction information based on the multiple order question voices and multiple order question-and-answer voices includes: Based on the question-and-answer logic relationship between the multiple order question voices, multiple order question and answer voices, multiple new order question voices, and multiple new order question and answer voices, the order voice interaction information is generated.
[0090] In one embodiment, when the processor 402 implements the process of creating an order based on the order voice interaction information through the target order generating agent and generating order information for the services required by the user, it is configured to: Based on the order voice interaction information, an order list item is generated, which includes multiple order service items; Based on the order voice interaction information, user information and service information are input into the order list items to obtain the order information for the services required by the user.
[0091] In one embodiment, when the processor 402 implements the process of creating an order based on the order voice interaction information through the target order generating agent and generating order information for the services required by the user, it is configured to: The order request, which includes the order information, is sent to the corresponding target server.
[0092] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the smart terminal described above can be referred to the corresponding process in the aforementioned embodiment of the order creation method based on artificial intelligence, and will not be repeated here.
[0093] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to various embodiments of the artificial intelligence-based order creation method of this application.
[0094] The computer-readable storage medium can be an internal storage unit of the smart terminal described in the foregoing embodiments, such as the hard drive or memory of the smart terminal. The computer-readable storage medium can be non-volatile or volatile. Alternatively, the computer-readable storage medium can be an external storage device of the smart terminal, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the smart terminal.
[0095] Furthermore, the computer-readable storage medium may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system, at least one application required for a function, etc.; and the data storage area may store data created based on the use of blockchain nodes, etc.
[0096] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.
[0097] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms.
[0098] It should also be understood that the term "and / or" as used in this specification refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0099] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.
Claims
1. An order creation method based on artificial intelligence, characterized in that, include: The system acquires the user's voice data and invokes a cluster of intelligent agents, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent. The intent recognition agent performs intent recognition on the voice data to obtain the user's target intent. Based on the target intent, a target interactive agent and a target order generating agent are selected from the agent cluster; The target interactive intelligent agent interacts with the user via voice to request orders, thereby obtaining order voice interaction information. The target order generating agent creates an order based on the order voice interaction information, generating the order information for the services required by the user.
2. The order creation method based on artificial intelligence as described in claim 1, characterized in that, The step of performing intent recognition on the voice data through the intent recognition agent to obtain the user's target intent includes: The intent recognition agent performs semantic recognition on the voice data to obtain the user's semantic information; Extract the user intent from the semantic information to obtain the user's target intent.
3. The order creation method based on artificial intelligence as described in claim 1, characterized in that, The step of selecting the target interactive agent and the target order generating agent from the agent cluster according to the target intent includes: Based on the target intent, determine the user's user needs and obtain a preset mapping table between user needs and interactive intelligent agents and order generation intelligent agents; Query the target interactive agent and target order generating agent that match the user's needs from the mapping table.
4. The order creation method based on artificial intelligence as described in claim 1, characterized in that, The step of obtaining order voice interaction information by engaging in order request voice interaction with the user through the target interactive intelligent agent includes: The target interactive intelligent agent outputs multiple order-related voice questions to the user based on the target intent; Acquire multiple order question and answer voice recordings input by the user based on the order question information; Based on the multiple order question voice messages and multiple order question and answer voice messages, generate order voice interaction information.
5. The order creation method based on artificial intelligence as described in claim 4, characterized in that, Before generating order voice interaction information based on the multiple order question voices and multiple order question-and-answer voices, the method further includes: The target interactive intelligent agent generates multiple new order question voices based on the multiple order question and answer voices input by the user; Acquire multiple new order question and answer voices based on the user's input of multiple new order question voices; The step of generating order voice interaction information based on the multiple order question voices and multiple order question-and-answer voices includes: Based on the question-and-answer logic relationship between the multiple order question voices, multiple order question and answer voices, multiple new order question voices, and multiple new order question and answer voices, the order voice interaction information is generated.
6. The order creation method based on artificial intelligence as described in claim 1, characterized in that, The step of creating an order through the target order generating agent based on the order voice interaction information, and generating order information for the services required by the user, includes: Based on the order voice interaction information, an order list item is generated, which includes multiple order service items; Based on the order voice interaction information, user information and service information are input into the order list items to obtain the order information for the services required by the user.
7. The order creation method based on artificial intelligence as described in claim 1, characterized in that, The step of creating an order through the target order generating agent based on the order voice interaction information, and generating order information for the services required by the user, includes: The order request, which includes the order information, is sent to the corresponding target server.
8. An order creation device, characterized in that, The order creation device includes an acquisition module, a generation module, a selection module, and an order creation module, wherein: The acquisition module is used to acquire the user's voice data and call the intelligent agent cluster, which consists of multiple intelligent agents and includes at least one intent recognition intelligent agent. The generation module is used to perform intent recognition on the voice data through the intent recognition agent to obtain the user's target intent; The selection module is used to select a target interactive agent and a target order generating agent from the agent cluster according to the target intent; The generation module is also used to conduct order request voice interaction with the user through the target interactive intelligent agent to obtain order voice interaction information; The order creation module is used to create an order based on the order voice interaction information through the target order generation agent, and generate the order information for the services required by the user.
9. A smart terminal, characterized in that, The smart terminal includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the steps of the artificial intelligence-based order creation method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the artificial intelligence-based order creation method as described in any one of claims 1 to 7.