Service configuration method and related device

Abstract

This application provides a service configuration method and related equipment. According to the method provided, an electronic device can parse multiple service parameters from user input using a large language model guided by multiple prompts, thus automating service configuration. The electronic device can also verify the parsed service parameters and their values ​​to ensure accuracy. If an error is found during verification, the user can be prompted to modify the service parameters until the verification passes. To improve the convenience and interactivity of service configuration, the electronic device provides a visual interface and interacts with the user through dialogue, displaying the parsed service parameters and their values ​​in a graphical format. Implementing the method provided in this application automates the service configuration process, improves service configuration efficiency, reduces configuration errors caused by manual configuration, and alleviates the operational burden.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a service configuration method and related equipment. Background Technology

[0002] In the telecommunications industry, operators frequently launch new tariff packages to meet market demands and customer preferences. Traditional package configuration methods require technicians to manually input relevant parameters and rules—such as package price, data allowance, call duration, and discounts—into multiple systems, including business support systems and operations support systems, based on package design documents provided by product managers. Telecommunications system architectures are complex, involving multi-module collaboration, and configuration needs to be performed simultaneously across multiple systems. This process is not only cumbersome but also prone to human error leading to misconfigurations. This package configuration method heavily relies on the skill level of technicians, resulting in low efficiency, poor accuracy, and high maintenance costs. Summary of the Invention

[0003] The purpose of this application is to provide a service configuration method and related equipment, which completes service configuration by automatically parsing the package description information in the product document, thereby automating the configuration process, shortening service configuration time, reducing manual configuration errors, and alleviating the maintenance burden.

[0004] The aforementioned and other objectives will be achieved through the features described in the independent claims. Further implementations are illustrated in the dependent claims, the specification, and the drawings.

[0005] Firstly, this application provides a service configuration method, which may include: an electronic device receiving first user input, which is used to request the creation of a first service. In response to the first user input, the electronic device sending a first prompt to a cloud server, guiding a large language model to parse the service type of the first service from the first user input. The first prompt contains the first user input. After receiving the parsing result returned by the cloud server, the electronic device, based on the service type of the first service, sends multiple second prompts to the cloud server, guiding the large language model to parse multiple first parameters and their values ​​required for configuring the first service from the first user input. After receiving the first parameters and their values ​​returned by the cloud server, the electronic device creates the first service based on the received first parameters and their values.

[0006] In this application, the first user input can be in various forms, including but not limited to voice input, document input, text input, and image input.

[0007] In this application, the first parameter is the parameter required to create the first service, and the first parameter required to create the first service of different service types is different.

[0008] Implementing the first approach, the electronic device uses multiple prompts to guide a large language model to parse the service type of the first service and the multiple parameters and their values ​​required to configure the first service from the first user input. By automatically parsing the configuration information using the large language model, the service configuration process is automated, saving users from the tedious manual configuration process, improving the efficiency of service configuration, reducing configuration errors caused by manual configuration, and alleviating the burden of operation and maintenance.

[0009] In conjunction with the first aspect, in some embodiments, the first prompt can be generated by assembling a first prompt template and first user input, and the second prompt can be generated by assembling a second prompt template and first user input. The first and second prompt templates can be pre-stored on the electronic device. Specifically, the electronic device stores a prompt template library containing multiple pre-designed prompt templates for parsing service parameters.

[0010] In conjunction with the first aspect, in some embodiments, there can be multiple first parameters and multiple second prompts. When the electronic device sends a second prompt to the cloud server according to the service type of the first service, the electronic device can first determine multiple second prompt templates required to identify multiple first parameters and their values ​​based on the service type of the first service. Then, it fills the first user input into the corresponding positions in these multiple second prompt templates to generate multiple second prompts. Finally, the electronic device sends the assembled multiple second prompts to the cloud server.

[0011] In conjunction with the first aspect, in some embodiments, multiple second prompts can also be sent to the cloud server in a specific order, the order of which is related to the dependency relationship between the first parameters. Specifically, the multiple second prompts are used to identify different types of first parameters from the first user, with the second prompt corresponding to the first parameter with a higher degree of dependency being sent earlier.

[0012] In conjunction with the first aspect, in some embodiments, before the electronic device creates a first service based on the first parameter and its value, the electronic device can verify the first parameter and its value to determine that the value of the first parameter has passed verification. Then, the electronic device can detect user confirmation of the first parameter and its value. By verifying the first parameter and its value, the error rate of the first parameter and its value is reduced.

[0013] In conjunction with the first aspect, in some embodiments, the electronic device can display a first user interface. The first user interface includes a first part and a second part. The first part can be used to graphically display a first parameter and its value, and the graphical form can be a tree diagram, network diagram, or other forms. The second part can be used to display a dialogue. The dialogue includes first user input and a first response to the first user input. The first response can include response text. The response text is used to describe a first service based on the first parameter and its value. The first user interface enhances the interactivity and convenience for users in configuring services.

[0014] In conjunction with the first aspect, in some embodiments, the first response may include a response image for graphically displaying the first parameter and its value. Users can zoom in on the response image in a first part of the first user interface by clicking on it.

[0015] In conjunction with the first aspect, in some embodiments, the electronic device receives the first parameter and its value returned by the cloud server in JSON format. The first parameter and its value using a structured data format enhances data readability and facilitates conversion into diagrams for display.

[0016] In conjunction with the first aspect, in some embodiments, before the electronic device creates a first service based on the first parameter and its value, the electronic device may receive second user input and update the first parameter and its value according to the second user input. Then, the electronic device creates the first service based on the updated first parameter and its value. The second user input, like the first user input, includes one or more of the following inputs: voice input, document input, text input, and image input. Updating the first parameter and its value includes modifying the value of the first parameter, adding parameters for creating the first service, and deleting parameters for creating the first service. By receiving second user input, the electronic device allows the user to supplement and modify the first parameter and its value, ensuring the accuracy and completeness of the first parameter and its value.

[0017] In conjunction with the first aspect, in some embodiments, the electronic device can receive second user input by continuing the dialogue in the first user interface, thereby enhancing interactivity and convenience, improving service configuration efficiency, and enhancing the user experience. Specifically, continuing the dialogue includes the electronic device first outputting a first prompt, indicating to the user that a first parameter and its value are incorrect, and then receiving second user input.

[0018] In conjunction with the first aspect, in some embodiments, when an electronic device creates a first service based on the first parameter and its value, it can first send the first parameter and its value to the product center, and then complete the configuration, publication and management of the first service through the product center.

[0019] In conjunction with the first aspect, in some embodiments, the first service may be a telecommunications service, such as configuring a telecommunications package. In this case, the first parameters required to configure the first service include basic package information, package rental parameters, package tariff parameters, etc.

[0020] Secondly, this application provides a configuration method applied to a cloud server. The cloud server receives a first prompt sent by an electronic device, which includes first user input. The cloud server uses the first prompt to guide a large language model to identify the service type of a first service from the first user input, and then sends the identified service type to the electronic device. Next, the cloud server receives a second prompt sent by the electronic device. The cloud server uses the second prompt to guide the large language model to identify the first parameters and their values ​​required to create the first service from the first user input, and sends the first parameters and their values ​​to the electronic device so that the electronic device can create the first service based on the first parameters and their values. The first user input is the user input received by the electronic device, expressing the user's intention to create the first service. The first user input includes one or more of the following inputs: voice input, document input, text input, and image input. The first parameters are the parameters required to create the first service; the first parameters required to create different types of first services are different.

[0021] The second approach utilizes a large language model to automatically parse configuration information, thus automating the service configuration process. This saves users from tedious manual configuration, improves service configuration efficiency, reduces configuration errors caused by manual configuration, and alleviates the burden on operations and maintenance.

[0022] In conjunction with the second aspect, in some embodiments, the first prompt can be generated by assembling a first prompt template and first user input, and the second prompt can be generated by assembling a second prompt template and first user input. The first and second prompt templates can be pre-stored on the electronic device. Specifically, the electronic device stores a prompt template library containing multiple pre-designed prompt templates for parsing service parameters.

[0023] In conjunction with the second aspect, in some embodiments, there can be multiple first parameters and multiple second prompts. When the electronic device sends a second prompt to the cloud server according to the service type of the first service, the electronic device can first determine multiple second prompt templates required to identify multiple first parameters and their values ​​based on the service type of the first service. Then, it fills the first user input into the corresponding positions in these multiple second prompt templates to generate multiple second prompts. Finally, the electronic device sends the assembled multiple second prompts to the cloud server.

[0024] In conjunction with the second aspect, in some embodiments, the first parameter and its value received by the electronic device from the cloud server are in JSON format. The first parameter and its value use a structured data format, enhancing data readability and facilitating its conversion into diagrams for display.

[0025] Thirdly, embodiments of this application provide an electronic device that may include a memory, a processor, and a computer program stored in the memory, enabling the electronic device to perform operations corresponding to the methods provided in the first and second aspects.

[0026] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, the computer program including executable instructions, which, when executed by a processor, cause the processor to perform operations corresponding to the methods provided in the first and second aspects.

[0027] Fifthly, embodiments of this application provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the operations corresponding to the methods provided in the first and second aspects. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0029] Figure 1 This illustrates a traditional telecommunications service configuration process;

[0030] Figure 2 The overall flow of the service configuration method provided in the embodiments of this application is illustrated;

[0031] Figure 3 An exemplary first user interface 20 provided in an embodiment of this application is shown;

[0032] Figure 4 The specific implementation flow of the telecommunications service configuration method provided in Embodiment 1 is shown;

[0033] Figure 5 The specific implementation flow of the telecommunications service configuration method provided in Embodiment 2 is shown;

[0034] Figure 6 The specific implementation flow of the telecommunications service configuration method provided in Embodiment 3 is shown;

[0035] Figures 7A-7B A method is shown for an electronic device to receive second user input and present an updated first parameter and its value.

[0036] Figure 8 An electronic device 100 provided in an embodiment of this application is shown;

[0037] Figure 9 This illustrates a software architecture for an electronic device 100;

[0038] Figure 10 The server 300 provided in an embodiment of this application is shown. Detailed Implementation

[0039] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be a limitation of this application.

[0040] To meet diverse user needs, major telecom operators frequently offer various data traffic tariff packages, allowing users to choose the appropriate package based on their usage. Currently, traditional package configuration relies on manual setup. Technical personnel first need to extract a series of parameter values ​​and complex rules required for configuring the tariff package from the product design documents. Then, they must fill in and configure all parameters item by item in a web form. After configuration, technical personnel need to further verify that all information is configured correctly and build test cases to check whether the configured package can provide services and charge fees according to the preset package rules. If the test passes, the package product can be released.

[0041] Figure 1 This illustrates a traditional telecommunications service configuration process. For example... Figure 1 As shown, the traditional method of configuring data traffic tariff packages relies on manual operation, and its process steps are as follows:

[0042] S1. Technical staff receive descriptions of the service packages from product managers and other marketing and operations personnel. These descriptions can be presented in various formats. For example, operations personnel can verbally explain the package design rules to the technical staff. Alternatively, operations personnel can submit product design documents to the technical staff.

[0043] S2. Technicians extract all information related to the package pricing configuration from the package description information, including the package name, pricing structure, discount policy, billing cycle, and included services or resources (such as data traffic, call minutes, SMS, etc.). Based on the extracted package pricing configuration information, technicians manually fill out the parameter configuration form on the configuration website, setting each parameter and rule one by one.

[0044] S3. After configuration, technical personnel conduct configuration verification. On one hand, they compare the configured parameters one by one with the parameters designed in the product documentation to ensure there are no omissions or errors. On the other hand, technical personnel construct test cases in batches to test and verify the accuracy of the package tariff configuration. During testing, the test number is set to the above-configured package, and then it is checked whether the number enjoys the services provided by the package and whether the charges are deducted according to the preset package rules. For example, checking whether the number enjoys the preset call minutes, mobile data, broadband, etc., and verifying whether the overage charge rate is accurate by adjusting the remaining call minutes and mobile data in the package. If the verification confirms that the configuration is correct, the product can be released.

[0045] However, the aforementioned traditional telecommunications service configuration methods heavily rely on the operational proficiency of technicians, resulting in inefficient and inaccurate package configuration. On one hand, the manual configuration process, where technicians painstakingly input each package configuration item, is time-consuming. During configuration, technicians may also need to repeatedly communicate and confirm with marketing and operations personnel. This lengthy configuration process significantly extends the product launch cycle, making it difficult for operators to quickly respond to market changes and user needs. On the other hand, especially for complex product configurations, technicians need to perform numerous complex configuration operations within intricate web forms. Such manual operations are highly susceptible to errors such as omissions, misconfigurations, or logical conflicts. Once configuration errors occur, they will severely impact customer experience and may even lead to business complaints and losses. Furthermore, due to the complex architecture of telecommunications systems (involving business support systems, operational support systems, customer relationship management modules, etc.), configuration needs to be performed simultaneously across multiple systems. This system characteristic also increases the risk of errors and operational costs in package configuration.

[0046] To address the above issues, this application provides a telecommunications service configuration method that automatically parses package description information from product documents to complete service configuration, thereby automating the configuration process, shortening service configuration time, reducing manual configuration errors, and alleviating the operational burden.

[0047] This application's embodiments leverage the natural language understanding capabilities of a large language model to automatically parse complex telecommunications service product design documents, extract key information, and transform this information into a structured data format, such as JSON. This structured data format is required by the configuration platform and can be directly used for package configuration. Operator package information is complex and diverse, but can generally be categorized into several basic types: basic package information, package rental fees, and package tariffs. To extract the aforementioned key information more efficiently, the method provided in this application constructs multiple large language model prompt templates. Each template focuses on identifying a specific type of parameter information. For example, "Please extract the package rental information from the user-input package description, including fixed fees and billing cycles.", "Please extract the following basic package information from the user-input package description, including package name, type, applicable user group, and validity period.", "Please extract the package tariff information, including call duration, number of SMS messages, data traffic quota and its fees, and billing rules after exceeding the quota.", etc.

[0048] Compared with existing technologies, the embodiments of this application, by introducing a large language model and multiple customized prompt templates, can not only quickly process large amounts of package information but also ensure the accuracy and completeness of the information, greatly improving the efficiency and accuracy of telecommunications service configuration and providing strong support for operators' package configuration and management. Furthermore, this method also has good scalability and flexibility. As telecommunications services are constantly updated and changed, operators can adapt to these changes by simply adjusting or adding new prompt templates without making major modifications to the overall method.

[0049] Figure 2 The overall flow of the service configuration method provided in the embodiments of this application is shown, such as... Figure 2 As shown, the method may include the following steps:

[0050] S101. The electronic device receives input from a first user, and the user intent expressed by the first user request is to create a first service.

[0051] Taking the first service as a telecommunications service (or telecommunications service package) as an example, the first user input can refer to a user's request to configure a telecommunications service. A telecommunications service is the first service created by the user's intent expressed by the first user input.

[0052] The first user input may include descriptions of various parameters and rules required to configure telecommunications services, typically including: basic package information, package rental fee, and package tariff. The basic package information may include the package name, applicable user group (individual users, enterprise users, etc.), and package validity period. The package rental fee may include the fixed cost of the package and the billing cycle. The package tariff may include the quota and cost of communication resources such as call duration (domestic and international call duration), number of SMS messages, and data traffic (general data traffic, targeted data traffic), as well as the billing rules for exceeding the quota. It should be noted that the above is an exemplary description of the content included in the first user input. In some embodiments, the first user input may contain more or less descriptive information.

[0053] The first user input can take various forms, including but not limited to document input, text input, voice input, image input, or a combination of these. Electronic devices need to convert non-text content in the first user input into text format to ensure readability.

[0054] Taking a scanned product design document included in the first user input as an example, the electronic device can use optical character recognition (OCR) technology to recognize the text information within it. OCR technology scans the document image, identifies characters such as text, numbers, and symbols, and converts them into computer-readable text format. Similarly, for package description information in image form input by the user, the electronic device can also use OCR technology to extract the text from the image and convert it into text format. For voice input, the electronic device can employ speech recognition technology, analyzing the acoustic characteristics of the speech signal to convert the user's voice information into plain text.

[0055] During the format conversion of the initial user input, the electronic device can also preprocess the resulting text information, including standardizing data format, removing special characters and unnecessary information (such as headers, footers, and comments). Some special characters, such as control characters and non-printing characters, may not be correctly recognized or converted, causing confusion or errors during document format conversion and interfering with text parsing and subsequent processing. Therefore, removing these interfering elements during the conversion process ensures the accuracy and relevance of the information, making the text clearer and easier to read, and improving processing speed.

[0056] The first service can also contain multiple services. For example, the first user input may contain configuration requests for two telecommunications services simultaneously.

[0057] S102. The electronic device sends a first prompt to the cloud server. The first prompt contains first user input and is used to identify the service type of the first service from the first user input.

[0058] The first prompt is assembled from a first prompt template and first user input. The first prompt template is a prompt template pre-stored in a prompt template library on the electronic device, used to identify the service type of the first service from the first user input.

[0059] The prompt template library contains multiple prompt templates. These prompt templates are pre-designed by technical personnel and include action instructions, rule requirements, input prompts, etc. These prompt templates have different functions, each used to guide the large language model to parse different types of information from the first user input. In this embodiment, the multiple prompt templates are used to parse different parameters and their values ​​required to configure the first service from the first user input. For example, the first prompt template is used to parse the service type of the first service from the first user input.

[0060] For example, the first prompt template may include the following:

[0061] "Next, the user will provide a package description. Please determine the type of package based on this description, with the following requirements:"

[0062] Package types include: prepaid and postpaid.

[0063] Returns the package type (tariff_type) in JSON format;

[0064] Example return: {"tariff_type":"prepaid"}

[0065] The first service description entered by the user: ${user_input}”

[0066] Here, "${user_input}" indicates that the first user input needs to be entered here. After the electronic device enters the first user input into the "${user_input}" field in the first prompt template, it obtains the first prompt as shown below:

[0067] "Next, the user will provide a package description. Please determine the type of package based on this description, with the following requirements:"

[0068] Package types include: prepaid and postpaid.

[0069] Returns the package type (tariff_type) in JSON format;

[0070] Example return: {"tariff_type":"prepaid"}

[0071] The user's first service description: Configure a personal prepaid 5G live streaming package, monthly fee 100 yuan, including 100GB of data traffic.

[0072] The first prompt template shown above is only an example. In order to enable the configuration of more different types of services, in some embodiments, the first prompt may include other rule designs.

[0073] In some embodiments, before the user inputs the first user input, multiple prompt templates in the prompt template library can be adaptively modified according to the characteristics of the first service created by the user's intent, so as to better implement the configuration of the first service. For example, adding prompt templates or modifying the rule design of some prompt templates.

[0074] Correspondingly, the cloud server can receive the first prompt sent by the electronic device and use the first prompt to guide the large language model to identify the service type of the first service from the first user input.

[0075] After receiving the first prompt, the cloud server inputs it into the large language model deployed on the cloud server. Guided by the first prompt, the large language model uses its natural language understanding capabilities to parse the service type of the first service from the first user input.

[0076] S103. After identifying the service type of the first service, the cloud server can return the service type of the first service to the electronic device. Accordingly, the electronic device can receive the service type of the first service returned by the cloud server.

[0077] S104. The electronic device sends a second prompt to the cloud server, the second prompt being used to guide the large language model to identify the first parameters and their values ​​required to create the first service from the first user input.

[0078] There are multiple first parameters required to create a first service, and the number of first parameters varies depending on the service type. First parameters are the service parameters required to configure the first service. For example, configuring a telecommunications service requires parameters such as package fee, call duration, and data allowance when configuring an individual plan, while configuring a family plan requires even more parameters, including package fee, call duration, data allowance, and broadband speed.

[0079] The second prompt is used to identify the first parameter and its value required to create the first service from the first user input, and there are multiple second prompts. The second prompt is generated by assembling multiple prompt templates (excluding the first prompt template) from a pre-stored prompt template library in the electronic device with the first user input. The electronic device can determine the multiple second prompt templates required to identify the first parameter and its value based on the service type of the first service, and then fill the first user input into the corresponding positions in the multiple second prompt templates to generate multiple second prompts. The electronic device sequentially sends the assembled multiple second prompts to the cloud server. The assembly method of the second prompt template and the first user input is the same as the assembly method of the first prompt template and the first user input, and will not be repeated here.

[0080] The electronic device can have a mapping table to store the correspondence between the service type of the first service and the second prompt template. For example, in the aforementioned steps, the electronic device identifies the service type of the first service as "family package" from the first user input. By querying the mapping table, the electronic device confirms that the second prompts required to configure the "family package" service include: a basic information prompt, a package rental fee prompt, and a package tariff prompt. The electronic device retrieves the prompt templates corresponding to the above three prompts from the prompt template library and assembles them with the first user input to generate three complete second prompts, which are used to identify the basic information, package rental fee, and package tariff required to configure the first service from the first user input, respectively.

[0081] In other embodiments, the electronic device may also confirm multiple prompts in the second prompt using other methods. For example, a summary prompt may be set. This summary prompt is used to identify multiple parameter types contained in the first user input, and then retrieve multiple corresponding second prompt templates from a prompt template library based on these multiple parameter types.

[0082] Correspondingly, the cloud server can receive the second prompt sent by the electronic device and use the second prompt to guide the large language model to identify the first parameter and its value from the first user input.

[0083] After receiving the second prompt, the cloud server inputs it into the large language model deployed on the cloud server. Guided by the second prompt, the large language model uses its natural language understanding capabilities to parse the first parameters and their values ​​required to create the first service from the first user input.

[0084] S105. After identifying the first parameter and its value, the cloud server can return the first parameter and its value to the electronic device. Accordingly, the electronic device can receive the first parameter and its value returned by the cloud server.

[0085] There can be multiple first parameters, including various parameters used to create the first service. For example, when configuring a data plan, the first parameters may include: plan name, plan fee, data allowance, call duration, number of SMS messages, etc. If the configuration of the first service also requires a service type, then the first parameter may also include the service type parameter.

[0086] The first parameter and its value can be in JSON format. The second prompt sent by the electronic device to the cloud service can include requirements for the output format of the parsed result. For example, if the second prompt contains "output the package name in JSON format", then the large language model will output the parsed result of "package name" in JSON format: {"package name": Dongxiang 5G Live Streaming Package}.

[0087] The first parameter and its value are output in a formatted structure, which enhances data readability and facilitates subsequent synchronization with multiple systems or databases such as business support systems and operational support systems, thereby improving the efficiency and accuracy of service configuration. In some embodiments, the first parameter and its value may also be output in other structured formats besides JSON, and this application does not impose any restrictions on this.

[0088] S106. The electronic device creates a first service based on the first parameter and its value.

[0089] In embodiments where the first service is a telecommunications service, the electronic device can transmit the first parameter and its value parsed from the first user input to the Unified Product Catalog (UPC) to encapsulate and publish the first service. Not limited to the UPC, other network elements in the telecommunications operator's business architecture can also perform the telecommunications service publishing function, and the electronic device can transmit the first parameter and its value to the corresponding network element to create the first service. This application does not limit how the first service is created based on the first parameter and its value.

[0090] This embodiment also provides a first user interface for implementing the human-computer interaction process between the electronic device provided by this method and the user, including but not limited to: receiving user input, displaying user input and the electronic device's return results for user input, and graphically presenting the first parameter and its value.

[0091] The first user interface may include a first part and a second part. The first part is used to graphically display a first parameter and its value. The second part is used to display a dialogue, including first user input and a first response to the first user input. The first response may include response text for describing a first service based on the first parameter and its value.

[0092] Figure 3 An exemplary first user interface 20 provided in an embodiment of this application is illustrated. An electronic device can receive first user input at the first user interface and present a return result to the user based on the first user input, including a first parameter and its value.

[0093] like Figure 3 As shown, the first user interface 20 may include: a visualization window 201 and a dialog window 202.

[0094] The visualization window 201 can be used to graphically display the first parameter and its value. Users can use the zoom control 201A to control the display size of the preview image, or use the control 201B to switch the display mode, such as switching from a network diagram to parameter detail configuration.

[0095] The dialog window 202 may include: a dialog display area 202A, a text input box 202B, a send control 202C, and a control 202D for opening more tools. Users can directly enter package description information in text format through the text input box 202B, or select other input methods, such as voice input or document input, through the control 202D. After the user interacts with the send control 202C, the electronic device will receive the first user input.

[0096] The electronic device displays a dialogue between itself and the user in the dialogue display area 202A, including a first user input 202E and a first response 202F to the first user input. The first response 202F contains response text describing a first service based on a first parameter and its value, and may also include a response image for graphically displaying the first parameter and its value. After detecting a user action on the graphical display in the first response 202F, the electronic device can zoom in and present the graphical display of the first parameter and its value in the visualization window 201.

[0097] In this embodiment, the visual window 201 and the dialog window 202 can be referred to as the first part and the second part of the first user interface, respectively.

[0098] Figure 3 The illustration only provides a first user interface as an example and should not be construed as limiting the embodiments of this application.

[0099] The above is a general overview of the method provided in this application. The following three specific embodiments further illustrate the service configuration method provided in this application.

[0100] Example 1

[0101] In this embodiment, a user configures a telecommunications service using the service configuration method provided in this application. The electronic device receives a description of configuring a telecommunications service (i.e., the first user input) entered by the user in a first user interface. Guided by multiple prompts, the large language model parses the service parameters and their values ​​(i.e., the first parameters and their values) required to configure this telecommunications service from the first user input. The electronic device graphically presents the first parameters and their values ​​to the user in the first user interface. Finally, the telecommunications service is encapsulated and published through a unified product management center.

[0102] Figure 4 The specific implementation flow of the telecommunications service configuration method provided in Embodiment 1 is shown. Figure 4 In this context, the first user input is in text format, and the specific implementation process may include:

[0103] S301. The electronic device receives first user input in a dialog window of the first user interface. The first user input describes configuration information for a telecommunications service.

[0104] For example, electronic devices detect when a user passes through Figure 3In the text input box 202B shown in the first user interface, enter the following description of configuring a telecommunications service: Configure a personal prepaid 5G package with a monthly fee of 30 yuan, including 5GB of data traffic and 200 minutes of talk time. Talk time exceeding the limit will be charged at 0.3 yuan / minute, and data traffic exceeding the limit will be charged at 3 yuan / MB.

[0105] In this embodiment, the first user input does not contain non-text format input, so no format conversion is required.

[0106] S302. The electronic device sends a first prompt to the cloud server. The first prompt is used to parse the user's intended telecommunications service package type from the first user input.

[0107] For example, an electronic device pre-stores a "summary prompt template" (i.e., the first prompt template). After receiving a user's input request to configure a description of a telecommunications service (i.e., the first user input), the electronic device fills this description into the area corresponding to "user-input package description" in this "summary prompt template," generating the following complete summary prompt (also called a parameter extraction instruction):

[0108] "Next, the user will provide a package description. Please determine the type of package based on this description, with the following requirements:"

[0109] Package types include: prepaid and postpaid.

[0110] Returns the package type (tariff_type) in JSON format;

[0111] Returning to the example:

[0112] {“tariff_type”:prepaid}

[0113] The user-entered package description: Configure a personal prepaid 5G package with a monthly fee of 30 yuan, calls charged at 0.3 yuan / minute, and data charged at 3 yuan / MB.

[0114] The electronic device sends the assembled summary prompt (i.e., the first prompt) to the cloud server. This summary prompt is used to parse the user's intended telecommunications service package type from the first user input.

[0115] Correspondingly, the cloud server can receive the first prompt sent by the electronic device and use the first prompt to guide the large language model to identify the service type of the first service from the first user input.

[0116] After receiving the first prompt, the cloud server inputs it into the large language model deployed on the cloud server. Guided by the first prompt, the large language model uses its natural language understanding capabilities to parse the service type of the first service from the first user input.

[0117] The cloud server returns the service type of the first service to the electronic device in the format required in the first prompt.

[0118] S303. After identifying the service type of the first service, the cloud server can return the telecommunications service package type to the electronic device. Accordingly, the electronic device can receive the parsing result returned by the cloud server and confirm that the telecommunications service package type that the user intends to configure is "personal prepaid".

[0119] The large language model parses the type of telecommunications service the user wants to configure from the user's input package description based on the above summary prompt, and outputs the following parsing results:

[0120] {“tariff_type”: prepaid}

[0121] Based on the analysis results of the above large language model, the electronic device determines the package type as: personal prepaid.

[0122] In this embodiment, the package type can be referred to as the service type of the first service, and the first service is a telecommunications service.

[0123] S304. Based on the identified package type, the electronic device determines the required second prompt template.

[0124] The electronic device retrieves three second prompt templates from the prompt template library required to configure the "personal prepaid" type of telecommunications service, including the basic information prompt template, the rental fee prompt template, and the tariff prompt template.

[0125] S305. The electronic device assembles the first user input with the second prompt template to generate a complete second prompt.

[0126] The electronic device assembles the first user input with the three second prompt templates obtained above to generate three second prompts. The second prompts are used to parse the first parameters and their values ​​required for configuring the telecommunications service from the telecommunications service configuration information input by the user.

[0127] For example, by combining the text input by the user to describe the package parameter configuration with the basic information prompt template, the rental fee prompt template, and the tariff prompt template, the following three complete prompts (i.e., the second prompt) are obtained:

[0128] [Basic Information Prompt]

[0129] Next, the user will provide a package description. Please extract the basic information of the package based on this description, with the following requirements:

[0130] 1. The basic information extracted includes: package name (tariff_name) and package description (tariff_desc);

[0131] 2. Return the package name and package description in JSON format;

[0132] Example:

[0133] User input: Configure a Dynamic Enjoyment package, 5 yuan per month.

[0134] {"tariff_name": Enjoy the mobile package, "tariff_desc": Enjoy the mobile package, 5 yuan per month}

[0135] User-entered description: Configure a personal prepaid 5G package with a monthly fee of 30 yuan, calls are charged at 0.3 yuan / minute, and data is charged at 3 yuan / MB.

[0136] [Rental Fee Prompt]

[0137] Next, the user will provide a package description. Please extract the package rental information based on this description, with the following requirements:

[0138] 1. The rental fee information retrieved for the package includes: rental fee amount (rental_fee_value) and rental fee unit (rental_fee_unit);

[0139] 2. Return the rental amount and unit in JSON format;

[0140] Example:

[0141] User input: Configure a Dynamic Enjoyment package, 5 yuan per month.

[0142] {"rental_fee_value": 5, "rental_fee_unit": yuan}

[0143] User input: Configure a personal prepaid 5G plan with a monthly fee of 30 yuan, calls charged at 0.3 yuan / minute, and data charged at 3 yuan / MB.

[0144] [Pricing Prompt]

[0145] Next, the user will provide a package description. Please extract the package's pricing information based on this description, with the following requirements:

[0146] 1. The tariff information retrieved for the package includes: tariff type (tariff_type), tariff amount (tariff_value), tariff unit (tariff_fee_unit), and tariff unit of measurement (tariff_resource_unit);

[0147] 2. The package details are returned in JSON format;

[0148] Example:

[0149] User input: Configure a Dynamic Enjoyment package, 5 yuan per month, voice call fee 3 yuan / minute.

[0150] {"tariff_type": voice, "tariff_value": 3, "tariff_fee_unit": yuan, "tariff_resource_unit": minutes}

[0151] User input: Configure a personal prepaid 5G plan with a monthly fee of 30 yuan, calls charged at 0.3 yuan / minute, and data charged at 3 yuan / MB.

[0152] S306. The electronic device sends the assembled second prompts to the cloud server.

[0153] Correspondingly, the cloud server can receive the second prompt sent by the electronic device and use the second prompt to guide the large language model to identify the first parameter and its value required to configure the telecommunications service from the first user input.

[0154] After receiving the second prompt, the cloud server inputs it into the large language model deployed on the cloud server. Guided by the second prompt, the large language model uses its natural language understanding capabilities to parse the first parameters and their values ​​required to create the first service from the first user input.

[0155] S307. After identifying the first parameter and its value, the cloud server can return the first parameter and its value to the electronic device. Accordingly, the electronic device can receive the first parameter and its value returned by the cloud server.

[0156] The electronic device sends multiple prompts to the cloud server to guide the large language model to parse specific parameters and their values ​​from the user-input package description information.

[0157] For example, after the electronic device sends the three assembled prompts to the cloud server, it receives the following basic information, rental information, and tariff information parsed from the user's input package description information by the large language model:

[0158] {“tariff_name”: prepaid 5G plan, “tariff_desc”: prepaid 5G plan};

[0159] {"rental_fee_value": 30, "rental_fee_unit": yuan};

[0160] {

[0161] {"tariff_type": voice, "tariff_value": 0.3, "tariff_fee_unit": yuan, "tariff_resource_unit": minutes},

[0162] {"tariff_type": data, "tariff_value": 3, "tariff_fee_unit": yuan, "tariff_resource_unit": MB}

[0163] };

[0164] In this embodiment, the first parameter includes: basic package information, rental fee information, and tariff information. The basic package information includes the rental fee amount (rental_fee_value) and rental fee unit (rental_fee_unit); the rental fee information includes the rental fee amount (rental_fee_value) and rental fee unit (rental_fee_unit); and the tariff information includes the tariff type (tariff_type), tariff amount (tariff_value), tariff unit (tariff_fee_unit), and tariff unit of measurement (tariff_resource_unit).

[0165] The three second prompts mentioned above specify that the parameters and their values ​​parsed from the package description information should be output in JSON data format. The method provided in this application does not limit the data format of the large language model output results. In some embodiments, the prompt design can be modified to specify that the large model parsing results should be input in other formats.

[0166] S308. The electronic device presents the user with the first parameters and their values ​​required to configure telecommunications services.

[0167] Electronic devices can present a first parameter and its value to the user in a graphical form on a first user interface. For example... Figure 3 As shown, the electronic device displays the first user's input and the electronic device's response to the first user's input in a dialog window on the right side of the first user interface. Figure 3 The first user input received in S301 is displayed in the form of a dialog card.

[0168] The response from an electronic device to a first user's input may include response text and a response image. The response text is a description of the first service determined by the aforementioned first parameter and its value. If the first user's input is text, then the response text can be the text entered by the first user. The response image presents the first parameter and its value to the user in a graphical form, based on the first parameter and its value. The graphical form can be various, including but not limited to: tree diagrams, network diagrams, tables, etc. Figure 3 As shown, the electronic device displays the first parameters and their values ​​required to configure the first service in the form of a tree diagram in the reply text. Each node in the tree diagram can include a first parameter and its value obtained from a second prompt guiding a large speech model. The electronic device can also utilize the depth relationship of the tree diagram nodes to represent the hierarchical relationship of the prompt or the dependencies between the first parameters.

[0169] After the electronic device detects that a user clicks on the reply image in the response results, it can also display the reply image in a visualization window of the first user interface. In this visualization window, the electronic device can present a magnified reply image to the user, providing a more intuitive view of the large language model's parsing results for the service parameters. Within this dialog window, users can click or drag nodes in the tree diagram to selectively hide or view more detailed information about those nodes and the hierarchical relationships between the first parameters. The visualization window of the first user interface can also include multiple controls for zooming in, zooming out, moving the icons in the visualization window, or switching the display format of the first parameters and their values. Through these functions provided by the electronic device, users can view the first parameters and their values ​​more clearly, intuitively, conveniently, and quickly.

[0170] The method described above for presenting the first parameter and its value to the user in the form of a tree diagram in the first user interface is merely an exemplary description, and this application does not limit it.

[0171] In this embodiment, the visual window of the first user interface can be called the first part of the first user interface, and the dialog window of the first user interface can be called the second part of the first user interface.

[0172] S309. The electronic device sends the first parameter and its value to the product center to create the first service.

[0173] In the service configuration method provided in Example 1, the user inputs a simple description of configuring telecommunications services (i.e., the first user input) into the electronic device. The electronic device, guided by multiple prompts, uses a large language model to parse the service package type (the service type of the first service) and the multiple package parameters and their values ​​required to configure the telecommunications service (i.e., the first service) from the first user input (i.e., the first parameters and their values). The method provided in Example 1 utilizes a large language model to automatically parse configuration information, saving users from the tedious manual configuration process, improving the efficiency of package configuration, and reducing configuration errors caused by manual configuration.

[0174] Example 2

[0175] In this embodiment, the user needs to configure a more complex telecommunications service, which includes more parameter information and package rules compared to Embodiment 1. To better complete the configuration of the complex telecommunications service, in this embodiment, the electronic device uses a hierarchical design for multiple second prompts based on the relationship between the first parameters and sets a specific sending order. The electronic device can first send the upper-layer second prompt to the server, and then send the lower-layer second prompt to the cloud server.

[0176] Figure 5 The following is a detailed implementation flow of the telecommunications service configuration method provided in Embodiment 2. This detailed implementation flow may include:

[0177] S401. The electronic device detects that a user has entered first user input in a dialog window of the first user interface. The first user input is used to describe configuration information for a telecommunications service.

[0178] For example, a user enters the following configuration information for telecommunications services: Configure a 5G live streaming package with a monthly fee of 299 yuan and a broadband speed of 1000Mb / s; the package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for any data traffic exceeding the limit; the package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for any calls exceeding the limit.

[0179] In this embodiment, the description of the configured telecommunications service entered by the user can be referred to as the first user input.

[0180] S402. The electronic device sends a first prompt to the cloud server. The first prompt is used to parse the user's intended telecommunications service package type from the first user input. Accordingly, the cloud server can receive the first prompt and input it into the large language model.

[0181] S403. After identifying the telecommunications service package type, the cloud server can return the telecommunications service package type to the electronic device. Accordingly, the electronic device receives the parsing result of the first prompt returned by the cloud server, confirming that the telecommunications service package type intended to be configured by the user is "5G live streaming".

[0182] In this embodiment, the package type can be referred to as the service type of the first service, and the first service is a telecommunications service.

[0183] For the method of generating the first prompt, please refer to S202 in Example 1, which will not be repeated here.

[0184] S404. The electronic device determines the required second prompt template based on the identified package type.

[0185] Specifically, the electronic device retrieves four second prompt templates from the prompt template library required to configure the "5G Live Broadcast" telecommunications service, including the basic information prompt, rental fee prompt, tariff prompt, and broadband prompt.

[0186] S405. The electronic device assembles the first user input with the second prompt template to generate a complete second prompt.

[0187] Specifically, the electronic device assembles the first user input with the four second prompt templates obtained above to generate four second prompts. The second prompts are used to parse the first parameters and their values ​​required for configuring the telecommunications service from the telecommunications service configuration information input by the user.

[0188] For example, by combining the first user input with the basic information prompt template, rental fee prompt template, tariff prompt template, and broadband prompt template respectively, the following four complete second prompts are obtained:

[0189] [Rental Fee Prompt]

[0190] Next, the user will provide a package description. Please extract the package's pricing information based on this description, with the following requirements:

[0191] 1. The tariff information extracted for the package includes: tariff type (tariff_type) and tariff description text (tariff_text);

[0192] 2. Return the tariff type and tariff description text in JSON format;

[0193] Example:

[0194] User input: Configure a data plan with a monthly fee of 10 yuan, including 10GB of data traffic and 100 minutes of call time.

[0195] {

[0196] {"tariff_type": "data", "tariff_text": "The package includes 10GB of data traffic"}

[0197] {"tariff_type": "voice", "tariff_text": "The package includes 100 minutes of talk time"}

[0198] }

[0199] User-entered package description: Configure a 5G live streaming package with a monthly fee of 299 yuan and a broadband speed of 1000Mb / s; the package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for data traffic exceeding the limit; the package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for calls exceeding the limit.

[0200] Broadband prompt

[0201] Next, the user will provide a package description. Please extract the description of the broadband information based on this package, with the following requirements:

[0202] 1. The package pricing information includes: broadband speed (Broadband_speed) and broadband unit (Broadband_unit);

[0203] 2. Return broadband speed and broadband unit in JSON format;

[0204] Example:

[0205] User input: Configure a dynamic package with a monthly fee of 10 yuan and a broadband speed of 100Mb / s.

[0206] {"Broadband_speed": 100, "Broadband_unit": Mb / s}

[0207] User-entered package description: Configure a 5G live streaming package with a monthly fee of 299 yuan and a broadband speed of 1000Mb / s; the package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for data traffic exceeding the limit; the package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for calls exceeding the limit.

[0208] For basic information prompts and rental fee prompts, please refer to the assembly results shown in Example 1, which will not be listed here again.

[0209] The pricing prompt in this embodiment differs from the pricing prompt rule shown in Embodiment 1. In this embodiment, the pricing prompt is used to extract information from the first user input that may describe voice or data traffic pricing.

[0210] S406. The electronic device sends a second prompt to the cloud server. The second prompt includes a basic information prompt, a rental fee prompt, a tariff prompt, and a broadband prompt. Accordingly, the cloud server can receive the above multiple prompts.

[0211] S407. After parsing is complete, the cloud server can return the first parameter and its value to the electronic device. Correspondingly, the electronic device can receive the first parameter and its value returned by the cloud server, including the parsing results returned for the basic information prompt, rental fee prompt, tariff prompt, and broadband prompt.

[0212] For example, after the electronic device sends the four assembled prompts to the cloud server, it receives the following basic information, rental information, tariff information, and broadband information, which are parsed from the user's input package description information using a large language model:

[0213]

[0214] S408. Voice tariff prompt and data traffic tariff prompt for electronic equipment assembly.

[0215] The sending order of multiple second prompts is related to the dependency relationship between multiple first parameters. The higher the degree of dependency of the first parameter, the earlier the second prompt is sent.

[0216] In this embodiment, the electronic device needs to parse more complex pricing information from the first user input, i.e., the description of the configuration package entered by the user, including voice pricing and data traffic pricing. Voice pricing and data traffic pricing each contain multiple parameters. To achieve better parsing results, when parsing the pricing information, a pricing prompt is first used to extract text fragments describing the voice pricing and data traffic pricing from the first user input. As shown above, the parsing result of the large language model for the pricing prompt is as follows: the content describing the voice pricing in the first user input is "The package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for exceeding the limit," and the content describing the data traffic pricing is "The package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for exceeding the limit."

[0217] Based on the parsing results obtained above, the electronic device assembles the extracted text fragments with the lower-level voice tariff prompt template and data traffic tariff prompt template to generate two complete prompts. That is, the phrase "The package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for any excess" is filled into the corresponding area of ​​the voice tariff prompt template, and the phrase "The package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for any excess data traffic" is filled into the corresponding area of ​​the data traffic tariff prompt template.

[0218] [Voice call rate prompt]

[0219] Next, the user will provide a package description. Please extract the description of the voice call charges based on this package, with the following requirements:

[0220] 1. The tariff information retrieved for the package includes: call duration (voice_time), call duration unit (voice_time_unit), overcharge amount (voice_overcharge_value), overcharge unit (voice_overcharge_unit), and overcharge metering unit (voice_overcharge_resource_unit);

[0221] 2. Return the call duration, call duration unit, overcharge amount, overcharge unit, and overcharge metering unit in JSON format;

[0222] Example:

[0223] User input: Configure a mobile plan with a monthly fee of 10 yuan, which includes 50 minutes of free talk time. Any talk time exceeding this will be charged at an additional 1 yuan per minute.

[0224] {"voice_time": 50, "voice_time_unit": minutes, "voice_overcharge_value": 1, "voice_overcharge_unit": yuan, "voice_overcharge_resource_unit": minutes}

[0225] User-entered package description: The package includes 200 minutes of fixed call time, with additional charges of 0.5 yuan / minute for any time exceeding this limit.

[0226] [Data Traffic Pricing Prompt]

[0227] Next, the user will provide a package description. Please extract a description of the data traffic pricing information based on this package description, with the following requirements:

[0228] 1. Extract the data traffic tariff information of the package, including: data type (data_type), data limit (data_type_value), data limit unit (data_type_unit), overcharge amount (data_overcharge_value), overcharge unit (data_overcharge_unit), and overcharge metering unit (data_overcharge_resource_unit);

[0229] 2. Return the traffic type, traffic limit, traffic limit unit, overage charge amount, overage charge unit, and overage charge metering unit in JSON format;

[0230] Example:

[0231] User input: Configure a data plan with a monthly fee of 10 yuan. The plan includes 10GB of domestic data traffic and 5GB of targeted data traffic. Any data traffic exceeding the limit will be charged at an additional 3 yuan / MB.

[0232]

[0233] User-input package description: The package includes 100GB of domestic data traffic and 50GB of targeted data traffic. Any data exceeding the limit will be charged at an additional 5 yuan / MB.

[0234] In this embodiment, the second prompt also includes a voice tariff prompt and a data traffic tariff prompt.

[0235] S409. The electronic device sends the assembled voice tariff prompt and data traffic tariff prompt to the cloud server. Correspondingly, the cloud server can receive the two prompts and process them using a large language model.

[0236] S410. After parsing, the cloud server returns voice tariff parameters and data traffic tariff parameters to the electronic device. Correspondingly, the electronic device can receive the parsing results returned by the cloud server, including voice tariff information and data traffic tariff information.

[0237] In this embodiment, the first parameter includes voice tariff information and data traffic tariff information.

[0238] For example, the electronic device sends the two prompts mentioned above to the cloud server and then receives the parsing results returned by the large language model, as shown below:

[0239]

[0240] S411. The electronic device presents the first parameter and its value as described above.

[0241] In this embodiment, the first parameter includes the basic package information, rental information, and broadband information returned by the above-mentioned basic information big model for the prompt, rental fee prompt, and broadband prompt, as well as the voice tariff information and data traffic tariff information returned by the big model for the voice tariff prompt and data traffic tariff prompt.

[0242] The method for presenting the first parameter and its value in this embodiment is the same as the method for presenting the first parameter and its value in the embodiment, and will not be repeated here.

[0243] S412. The electronic device sends the first parameter and its value to the product management center to create the first service.

[0244] Example 2 presents a method for configuring complex telecommunications services. The electronic device employs a hierarchical design for multiple prompts in a prompt template library. For complex parameter information, the upper-level prompt first extracts multiple relevant text description fragments from the first user input, and then the lower-level prompts parse different parameter information from these text fragments. This hierarchical design better guides the large language model to parse the multiple parameter information required for configuring the service package from the first user input, improving parsing accuracy.

[0245] In this embodiment, the prompt template is only an example. In some embodiments, multiple other different prompt templates can be used to parse the first parameter.

[0246] Example 3

[0247] Building upon Embodiment 2, to better configure complex telecommunications services, in this embodiment, the electronic device can also verify the first parameter and its value to determine if there are any errors. The electronic device also allows the user to modify or supplement the package description multiple times until the service configuration is finally confirmed.

[0248] Figure 6 The specific implementation flow of the telecommunications service configuration method provided in Embodiment 3 is shown. Figure 6 In this context, the package description information is input in text format, and the specific implementation process may include:

[0249] S501. The electronic device detects that a user has entered first user input in a dialog window of the first user interface. The first user input is used to describe configuration information for a telecommunications service.

[0250] In this embodiment, the first user input is the same as the first user input in Embodiment 2.

[0251] S502. The electronic device sends a first prompt to the cloud server. The first prompt is used to parse the user's intended telecommunications service package type from the first user input. Accordingly, the cloud server can receive the first prompt.

[0252] S503. The cloud server returns the telecommunications service package type to the electronic device. Accordingly, the electronic device can receive the parsing result of the first prompt returned by the cloud server, confirming that the telecommunications service package type intended to be configured by the user is "5G live streaming".

[0253] S504. The electronic device determines the required second prompt template based on the package type.

[0254] Specifically, the electronic device retrieves four second prompt templates from the prompt template library required to configure the "5G Live Broadcast" telecommunications service, including the basic information prompt, rental fee prompt, tariff prompt, and broadband prompt.

[0255] S505. The electronic device assembles the first user input with the second prompt template to generate a complete second prompt.

[0256] S506. The electronic device sends a second prompt to the cloud server. The second prompt includes a basic information prompt, a rental fee prompt, a tariff prompt, and a broadband prompt. Accordingly, the cloud server can receive the above multiple prompts.

[0257] S507. After parsing is complete, the cloud server can return the first parameter and its value to the electronic device.

[0258] S508. Voice tariff prompt and data traffic tariff prompt for electronic equipment assembly.

[0259] S509. The electronic device sends the assembled voice tariff prompt and data traffic tariff prompt to the cloud server.

[0260] S510. The electronic device receives the voice tariff parameters and data traffic tariff parameters returned by the cloud server.

[0261] S511. The electronic device presents the first parameter and its value as parsed above.

[0262] The implementation methods of S501-S511 are the same as those of S401-S411 in Embodiment 2, and will not be repeated here.

[0263] Figure 7A This demonstrates how an electronic device presents a first parameter and its value to a user. As shown in the diagram, in the dialog window on the right, the electronic device first displays the first user input, followed by the response to that input. In the visualization window on the left, the first parameter and its value are displayed in a tree diagram.

[0264] S512. Verification of the first parameter and its value for electronic devices.

[0265] The electronic device can also verify the parsed first parameter and its value to ensure that they conform to the set rules. Simultaneously, the electronic device can provide controls to the user on the first user interface so that the user can confirm the first parameter and its value. Only after the electronic device detects user confirmation of the first parameter and its value can it save the first parameter and its value and send it to the unified product management center to realize the encapsulation and release of the first service.

[0266] Validation can include format validation and content validation.

[0267] Format validation checks whether the first parameter and its value are returned according to the structured format specified in the prompt. For example, the broadband prompt in the above steps requires the parsed broadband speed and unit to be returned in JSON format; that is, the first parameter should be: {"Broadband_speed": 1000, "Broadband_unit": Mb / s}. If the broadband speed and unit in the first parameter are not in the JSON format shown above, then the format of the first parameter and its value is determined to be incorrect.

[0268] Content verification involves validating the value of the first parameter to determine if it falls within a reasonable range or conforms to the parameter setting rules. To perform content verification on the first parameter and its value, electronic devices can store one or more verification files. These verification files contain the rule requirements for each parameter.

[0269] Corresponding to the design of the aforementioned multiple different prompt templates, multiple different verification files can be set within the electronic device. Each verification file contains different verification content, specifying the setting requirements for different parameter types and verifying the compliance of the parameters obtained through large language model parsing. The content of the verification file can correspond to the parameter information extracted from the multiple prompts. For example, different prompt templates such as voice tariff, data traffic tariff, and rental fee have corresponding verification files with different contents, such as voice tariff verification files, data traffic tariff verification files, and rental fee verification files. For instance, the voice tariff verification file includes the unit and range of call duration, the reasonable range of call rates, etc., specifying that call duration must be a number in minutes / hour and call rate must be a number within a certain range. By comparing the voice tariff-related parameters in the first parameter with the content of the voice tariff verification file, it is determined whether the voice tariff parameters in the first parameter conform to the parameter rules in the verification file.

[0270] Similarly, other verification files contain their own relevant parameter setting rules.

[0271] The above-described method for setting multiple verification files is an example. In some embodiments, various different methods can be used to set the verification files. For example, a verification file can be designed that contains the setting rules for all parameters required for configuring the service.

[0272] If an error is detected in the first parameter or its value during the verification process, the electronic device can display an alarm message to the user, prompting them to modify the parameter information. For example, the rental fee verification file limits the monthly rental fee to no more than 200 yuan. During the verification process, the electronic device detects that the rental fee amount in the first parameter is 299. Figure 7A As shown, the electronic device can send an alarm message to the user: "Please set the package rental fee between 0 and 200 yuan", prompting the user to modify the package rental fee setting.

[0273] Alarm information can also be presented in many other different ways, and this application embodiment does not impose any restrictions.

[0274] S513. The electronic device receives a second user input.

[0275] To improve the accuracy of package configuration, the electronic device can also receive input from a second user. This second user input is used to update the first parameter and its value, including but not limited to modifying the first parameter and its value, adding parameters used to create the first service, and deleting parameters used to create the first service.

[0276] The electronic device can receive input from a second user by continuing the dialogue within a dialog window of the first user interface. That is, the electronic device first... Figure 7A The first user interface shown displays a first prompt to the user, reminding them that the first parameter and its value are incorrect. Then, as... Figure 7B As shown, the user continues to enter the following second user input into the electronic device through the text box in the dialog window of the first user interface: "Monthly package fee of 199 yuan, unused data can be rolled over to the next month up to 20GB".

[0277] Users can input second-user information in various ways, including but not limited to: voice input, text input, image input, and document input.

[0278] S514. Electronic devices send a third prompt to the cloud server.

[0279] S515. The electronic device receives the updated first parameter and its value returned by the cloud service.

[0280] In response to the received second user input, the electronic device can first modify the first user input based on the content of the second user input. For example, based on the second user input "monthly package fee of 199 yuan", the first user input can be modified to "configure a 5G live streaming package, monthly fee of 199 yuan, broadband speed of 1000Mb / s; the package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for data traffic exceeding the limit; the package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for exceeding the limit". Then, based on the modified first user input, the electronic device repeats steps S502-S509, resending multiple third prompts to the cloud server to guide the large language model to obtain the updated first parameter and its value from the modified first user input. The third prompt includes the following prompts: a prompt for identifying the service type of the first service from the modified first user input, and multiple prompts determined by the service type of the first service for identifying the first parameter and its value. The electronic device sequentially assembles the first user input with the corresponding prompt templates of these multiple prompts, and then sends them to the cloud server to parse out the updated first parameter and its value.

[0281] The electronic device can also process only the second user input. The electronic device can set a prompt template, and by assembling the second user input with this template, guide the large language model to parse the parameter types contained in the second user input. Based on the obtained parameter types, a prompt template for parsing the parameters of the above parameter types is retrieved from the prompt template library, such as a package rental template. The prompt generated by assembling the second user input with the package rental template is resent to the cloud server. The large language model in the cloud server parses the updated "package price" and "package price unit" from the second user input: {"rental_fee_value": 199, "rental_fee_unit": yuan}. The electronic device updates the first parameter and its value based on the above parameter information.

[0282] In addition to the methods described above for modifying the first parameter and its value, the electronic device can also supplement or delete the first parameter of the configuration package. For example, the electronic device receives a second user input: "Unused data can be rolled over to the next month up to 20GB." The electronic device can process the second user input used to supplement or modify the first parameter in the same way as the method described above for processing the second user input used to modify the first parameter and its value.

[0283] The aforementioned electronic device can also process second user input and update the first parameter and its value through other methods.

[0284] S516. The electronic device presents the updated first parameter and its value.

[0285] Figure 7B In the process, the electronic device displays the updated first parameter and its value on the first user interface.

[0286] The response text displayed to the user by the electronic device has been changed to the following: Configure a 5G live streaming package with a monthly fee of 199 yuan and a broadband speed of 1000Mb / s; the package includes 100GB of domestic data traffic and 50GB of targeted data traffic, with an additional charge of 5 yuan / MB for data usage exceeding the limit, and unused data can be rolled over to the next month up to 20GB; the package includes 200 minutes of fixed call time, with an additional charge of 0.5 yuan / minute for exceeding the limit. The package price in the first parameter has been changed from "299" to "199", and the data traffic tariff parameter has been added: the rollover limit is 20GB.

[0287] S517. The electronic device sends the updated first parameter and its value to the product center to create the first service.

[0288] In Embodiment 3, the electronic device can verify the parsed first parameter and its value to determine whether they conform to the parameter rules set in the verification file. If the verification fails, the electronic device can present an alarm to the user, indicating that there is an error in the first parameter and its value. Based on the alarm information, the user can re-enter a second user input in the user interface to modify the first user input. In response to the received second user input, the electronic device re-parses and updates the first parameter and its value. By verifying the first parameter and its value and supporting multiple modifications and additions by the user, the accuracy of the service configuration is improved.

[0289] Next, an exemplary electronic device 100 provided in the embodiments of this application will be introduced.

[0290] Figure 8 An electronic device 100 provided in an embodiment of this application is shown.

[0291] Electronic device 100 may include processor 110, external memory interface 120, internal memory 121, universal serial bus (USB) interface 130, charging management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, display screen 194, and subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0292] The processor 110 can be one or more, and they can be integrated into an integrated circuit of a system-on-a-chip (SOC). An SOC is a system-on-a-chip. The processor 110 may include a central processing unit (CPU), a graphics processing unit (GPU), and a neural network processing unit (NPU). The CPU may include an application processor (AP) and a baseband processor (BP). The AP is responsible for running the operating system, user interface, and applications on the terminal device; the BP is responsible for transmitting and receiving wireless signals and managing radio frequency services. The GPU is responsible for graphics rendering, performing tasks such as shading, material filling, rendering, and output based on rendering instructions and data from the CPU. The NPU, by referencing biological neural network structures, such as the transmission patterns between neurons in the human brain, can quickly process input information and continuously learn. The NPU can be used to run artificial intelligence algorithms, such as instruction recommendation algorithms, image processing algorithms, and image understanding algorithms. The CPU and GPU can be used to render and synthesize the image to be displayed on the screen 194.

[0293] The processor 110 may include one or more interfaces, such as an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface.

[0294] The processor 110 may include a cache memory, which can be used to store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can directly retrieve it from the cache memory, which can reduce the waiting time of the processor 110 and improve the program running efficiency.

[0295] The charging management module 140 is used to receive charging input from the charger. The charger can be a wireless charger or a wired charger.

[0296] The power management module 141 is used to connect the battery 142, the charging management module 140, and the processor 110.

[0297] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0298] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0299] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0300] The modem processor may include a modulator and a demodulator. The modulator modulates the low-frequency baseband signal to be transmitted into a mid-to-high frequency signal. The demodulator demodulates the received electromagnetic wave signal into a low-frequency baseband signal. After processing by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs sound signals through audio devices (not limited to speaker 170A, receiver 170B, etc.) or displays images or videos through the display screen 194. In some embodiments, the modem processor may be a separate device. In other embodiments, the modem processor may be independent of the processor 110 and housed within the same device as the mobile communication module 150 or other functional modules.

[0301] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc.

[0302] In some embodiments, antenna 1 of electronic device 100 is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, enabling electronic device 100 to communicate with networks and other devices via wireless communication technology. The wireless communication technology may include Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technologies, etc. The GNSS may include the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the BeiDou Navigation Satellite System (BDS), the Quasi-Zenith Satellite System (QZSS), and / or satellite-based augmentation systems (SBAS).

[0303] Electronic device 100 can realize display functions through GPU, display screen 194, and application processor. GPU is a microprocessor for image processing, connected to display screen 194 and application processor. GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs, which execute instructions to generate or modify display information.

[0304] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a miniature LED, a microLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, electronic device 100 may include one or N displays 194, where N is a positive integer greater than 1.

[0305] In some embodiments, after generating drawing commands for the application's UI thread to create interface elements, the CPU can transmit (or share) these drawing commands to the GPU and instruct the GPU to render according to the commands. Here, the drawing commands can be used to instruct how to use drawing elements, such as graphics, text, and images, to draw specific interface elements in the user interface.

[0306] Electronic device 100 can perform shooting functions through ISP, camera 193, video codec, GPU, display 194 and application processor.

[0307] Camera 193 is used to capture still images or video. The ISP (Internet Service Provider) is used to process the data fed back from camera 193. The digital signal processor (DSP) is used to process digital signals; in addition to digital image signals, it can process other digital signals. The video codec is used to compress or decompress digital video.

[0308] Electronic device 100 can implement audio functions, such as music playback and recording, through audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and application processor.

[0309] An NPU (Neural Processing Unit) is a computational processor for neural networks (NNs). By borrowing the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously learn on its own. NPUs enable intelligent cognitive applications in electronic devices, such as image recognition, facial recognition, speech recognition, and text understanding.

[0310] The external storage interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external storage interface 120 to perform data storage functions. For example, music, photos, videos, and other data can be stored on the external memory card.

[0311] The internal memory 121 can be used to store one or more computer programs, which include instructions. The processor 110 can execute the instructions stored in the internal memory 121, thereby causing the electronic device 100 to perform the photographic preview method, various functional applications, and data processing provided in some embodiments of this application. The internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system; it may also store one or more application programs (such as a gallery, contacts, etc.). The data storage area may store data created during the use of the electronic device 100 (such as photos, contacts, etc.). Furthermore, the internal memory 121 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0312] Buttons 190 include a power button, volume buttons, etc. Buttons 190 can be mechanical buttons or touch-sensitive buttons. Electronic device 100 can receive button input and generate key signal inputs related to user settings and function control of electronic device 100.

[0313] Motor 191 can generate vibration alerts. Motor 191 can be used for incoming call vibration alerts or for touch vibration feedback. For example, different vibration feedback effects can correspond to touch operations performed on different applications (such as taking photos, playing audio, etc.). Motor 191 can also correspond to different vibration feedback effects for touch operations performed on different areas of the display screen 194. Different application scenarios (such as time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

[0314] The components in the electronic device 100 can be implemented as hardware modules, software modules, or a combination of software and hardware modules. Figure 8 The illustrated device structure does not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements.

[0315] Figure 9 A software architecture for an electronic device 100 is shown.

[0316] like Figure 9 As shown, the electronic device may include: a document parsing module, a central process control module, a multi-prompt assembly module, a large model module, and a user interface module. The large model module is deployed on a cloud server, while the remaining modules can be deployed on local electronic devices. By constructing multiple functional modules, these modules work collaboratively to ensure data accuracy and integrity, achieving full automation from document parsing to system configuration. This edge-cloud collaborative deployment further improves system efficiency and user experience.

[0317] The document parsing module supports parsing various document formats, such as Word, PDF, and Excel. It converts user-uploaded descriptions of the first package into plain text, performing initial cleanup of irrelevant content like advertisements, headers, and footers to ensure the extraction of key information is not interfered with. The parsed plain text data serves as the basis for subsequent processing.

[0318] The central control module of the process is the command center of the software architecture, responsible for managing the interaction and data flow between various modules. The central control module includes a result verification and warning module and a request management module. The request management module receives text data output from the document parsing module and passes it to the multi-prompt assembly module; it receives the output (multiple parameter extraction instructions) from the multi-prompt assembly module and then passes the output of the prompt assembly module to the large model module; it coordinates the processing results of the large model to generate the final output or alarm information.

[0319] The result verification and alarm module is integrated into the central control module of the process. It is responsible for verifying the parsing results returned by the large model and checking the completeness and consistency of the information. If any missing or conflicting parsing results are detected in the large model module, an alarm message can be generated to remind the user to supplement or correct the information through the alarm mechanism.

[0320] The user interface module provides interactive functionality and displays the analysis results and alarm information in a visual format. The user interface module allows users to supplement or correct information as needed, and the system restarts the analysis process based on the new input until a complete and accurate result is obtained.

[0321] The multi-prompt assembly module is a key module in the software architecture. It is responsible for combining the text data output by the document parsing module to generate parameter extraction instructions, guiding the large model module to perform deep parsing and information extraction from the text data. The multi-prompt assembly module contains multiple different prompt modules, each containing one or more prompt templates, each focusing on parsing different information categories (such as basic package information, rental information, and pricing rules). The multi-prompt assembly module can also implement a hierarchical design for multiple prompt templates and set the template order to handle complex package configurations, making the entire parsing process clear and less prone to errors.

[0322] After receiving the parameter extraction instructions from the multiple prompt assembly modules, the large model module uses natural language understanding capabilities to perform semantic parsing on the text data and extract parameters, thereby obtaining the structured data required for the package configuration.

[0323] In some embodiments, the above modules can also be deployed in other edge-cloud configurations. For example, all modules can be deployed locally on the electronic device, or the multi-prompt assembly module and the large model module can be deployed in the cloud, while the remaining modules can be deployed on the local electronic device.

[0324] For details on the specific functions of each software module in this software architecture, please refer to the aforementioned method implementation examples, which will not be repeated here.

[0325] Figure 9 This application only exemplifies one software architecture for the package configuration method provided in the embodiments of this application. The electronic device 100 may also employ other software architectures to implement the search method described in the foregoing method embodiments.

[0326] Figure 10 A server 300 provided in an embodiment of this application is shown. For example... Figure 10 As shown, server 300 may include: processor 310, memory 320, input / output device 330, communication module 340, etc., and these components can be coupled via a bus.

[0327] Server 300 may have powerful computing resources, and its processor 310 may include one or more powerful processors, such as central processing unit (CPU), neural network processing unit (NPU), graphics processing unit (GPU), etc.

[0328] The processor 310 may include one or more interfaces, such as an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface.

[0329] The processor 310 may have a cache memory, which can be used to store instructions or data that the processor 310 has just used or that are used repeatedly. If the processor 310 needs to use the instruction or data again, it can directly retrieve it from the cache memory, which can reduce the waiting time of the processor 310 and improve the program running efficiency.

[0330] The processor 310 can also connect to external memory. This memory can be high-speed random access memory or non-volatile memory, such as a hard disk, flash memory, universal flash memory (UFS), etc. The memory can also be an external memory card, such as a Micro SD card.

[0331] The processor 310 is the computing core of the server 300, possessing powerful computing capabilities. Coupled with the memory 320, it can read and execute computer-readable instructions stored in the memory 320, running the operating system and various programs. Specifically, the CPU 310 can call programs stored in the memory 320, such as the implementation program of the edge-cloud collaborative computing power scheduling method provided in this application embodiment, and execute the instructions contained in that program.

[0332] The memory 320 may include high-speed random access memory and non-volatile memory, such as disk, flash memory, or other non-volatile solid-state storage devices. The memory 320 can be used to store various software programs and multiple sets of instructions. The memory 320 can store an operating system, such as Linux. The memory 320 can also store one or more programs, such as programs involved in patch creation, such as compilers and linkers. The memory 320 can also store the implementation program of the edge-cloud collaborative computing power scheduling method provided in the embodiments of this application.

[0333] Input / output device 330 may include devices such as a display screen, keyboard, and mouse, and can be used to receive user input and output program execution results to the user.

[0334] The communication module 340 may include a wired communication module and a wireless communication module. The wired communication module supports wired communication protocols such as Universal Serial Bus (USB), serial port, and Ethernet, communicating with other devices via a physical communication cable. The wireless communication module may include 2G / 3G / 4G / 5G wireless communication modules, Wi-Fi communication modules, etc. The wireless communication module receives electromagnetic waves via an antenna, modulates and filters the electromagnetic wave signals, and sends the processed signal to the CPU 310. The wireless communication module can also receive signals to be transmitted from the CPU 310, modulate and amplify them, and then convert them into electromagnetic waves for radiation via the antenna.

[0335] Figure 10 The illustrated structure does not constitute a limitation on server 300. Server 300 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The components illustrated may be implemented in hardware, software, or a combination of software and hardware.

[0336] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps performed by the human-computer interaction module in the above-described method embodiments, or the steps performed by the human-computer interaction module and the computing module.

[0337] This application also provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps executed by the human-computer interaction module in the above-described method embodiments, or the steps executed by the human-computer interaction module and the computing module.

[0338] This application also provides a chip system, which includes a processor coupled to a memory. The processor executes a computer program stored in the memory to implement the steps performed by the human-computer interaction module in any of the method embodiments of this application, or the steps performed by the human-computer interaction module and the computing module. The chip system can be a single chip or a chip module composed of multiple chips.

[0339] The term "user interface (UI)" used in the specification, claims, and drawings of this application refers to the medium through which an application or operating system interacts and exchanges information with the user. It converts information between its internal form and a form acceptable to the user. The user interface of an application is source code written in a specific computer language such as Java or Extensible Markup Language (XML). This source code is parsed and rendered on an electronic device, ultimately presenting user-recognizable content such as images, text, and buttons. Controls, also known as widgets, are the basic elements of the user interface. Typical controls include toolbars, menu bars, text boxes, buttons, scroll bars, images, and text. The attributes and content of controls in the interface are defined using tags or nodes, such as XML tags. <textview> 、 <imgview> 、 <videoview>Nodes define the controls contained in the interface. A node corresponds to a control or property in the interface, and after parsing and rendering, the node is presented as the content visible to the user. In addition, many applications, such as hybrid applications, often contain web pages within their interfaces. A web page, also known as a webpage, can be understood as a special control embedded in the application interface. Web pages are source code written in a specific computer language, such as Hypertext Markup Language (GTML), Cascading Style Sheets (CSS), JavaScript (JS), etc. Web page source code can be loaded and displayed as user-readable content by a browser or a web page display component with browser-like functionality. The specific content contained in a webpage is also defined through tags or nodes in the webpage source code; for example, GTML uses tags or nodes to define the content. 、 、 <video> 、 <canvas>To define the elements and attributes of a webpage.

[0340] The most common form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed graphically. A user interface can include interface elements such as windows and controls displayed on the screen of an electronic device. Controls can include visual interface elements such as icons, buttons, menus, lists, tabs, text boxes, dialog boxes, status bars, navigation bars, and widgets. The UI attributes such as size, style, and color designed by GUI designers for interface elements can be defined in the application's interface source code and resource files, with layout resources used to define the interface architecture.

[0341] Those skilled in the art will recognize that the functions described in the embodiments of this application in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0342] The above detailed embodiments further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.< / canvas> < / video> < / videoview> < / imgview> < / textview>

Claims

1. A service configuration method, characterized by, The method includes: The electronic device receives a first user input, the user's intention expressed by the first user input is to create a first service, and the first user input includes one or more of the following inputs: voice input, document input, text input, and image input; The electronic device sends a first prompt to the cloud server. The first prompt contains the first user input. The first prompt is used to guide the large language model to identify the service type of the first service from the first user input. The electronic device receives the service type of the first service returned by the cloud server; The electronic device sends a second prompt to the cloud server according to the service type of the first service. The second prompt contains the first user input. The second prompt is used to guide the large language model to identify the first parameter and its value from the first user input. The first parameter is the parameter required to create the first service. The first parameter required to create the first service of different service types is different. The electronic device receives the first parameter and its value returned by the cloud server; The electronic device creates the first service based on the first parameter and its value.

2. The method of claim 1, wherein, The first prompt is composed of a first prompt template and the first user input, and the second prompt is composed of a second prompt template and the first user input. The first prompt template and the second prompt template are pre-stored on the electronic device.

3. The method of claim 1 or 2, wherein, There are multiple first parameters and multiple second prompts. The electronic device sends the second prompt to the cloud server according to the service type of the first service, specifically including: The electronic device determines multiple second prompt templates required to identify the first parameter and its value based on the service type of the first service. The electronic device fills the first user input into the corresponding positions in the plurality of second prompt templates, thereby generating a plurality of second prompts; The electronic device sends multiple second prompts to the cloud server.

4. The method of claim 3, wherein, The sending order of the multiple second prompts is related to the dependency relationship between the multiple first parameters, wherein the second prompt corresponding to the first parameter with a higher degree of dependency is sent earlier.

5. The method according to any one of claims 1 to 4, wherein Before the electronic device creates the first service based on the first parameter and its value, it further includes: The electronic device verifies the value of the first parameter and determines that the value of the first parameter has passed the verification. The electronic device detects that the user has confirmed the first parameter and its value.

6. The method according to any one of claims 1 to 5, wherein, It also includes that the electronic device displays a first user interface, the first user interface comprising a first part and a second part, the first part being used to graphically display a first parameter and its value, the second part being used to display a dialogue, the dialogue including first user input and a first response to the first user input, the first response including response text, the response text being used to describe the first service based on the first parameter and its value.

7. The method as described in claim 6, characterized in that, The first reply also includes a reply image, which is used to graphically display the first parameter and its value.

8. The method according to any one of claims 1-7, characterized in that, The first parameter and its value returned by the cloud server are in JSON format.

9. The method according to any one of claims 1-8, characterized in that, Before the electronic device creates the first service based on the first parameter and its value, it further includes: The electronic device receives a second user input, which is used to update the first parameter and its value. The second user input includes one or more of the following inputs: voice input, document input, text input, and image input. The electronic device updates the first parameter and its value according to the second user input. Updating the first parameter and its value includes one or more of the following: modifying the value of the first parameter, adding a parameter for creating the first service, or deleting a parameter for creating the first service. The electronic device creates the first service based on the first parameter and its value, specifically including: the electronic device creates the first service based on the updated first parameter and its value.

10. The method as described in claim 9, characterized in that, The electronic device receives second user input, specifically by receiving the second user input through a continued dialogue.

11. The method as described in claim 10, characterized in that, The continued dialogue includes: the electronic device first outputs a first prompt, which is used to indicate that the first parameter and its value are incorrect, and then receives the second user input.

12. The method according to any one of claims 1-11, characterized in that, The electronic device creates the first service based on the first parameter and its value, including sending the first parameter and its value to the product center, and then configuring the first service through the product center. The product center is used to configure, publish and manage the first service.

13. The method according to any one of claims 1-12, characterized in that, The first service is a telecommunications service, and the first parameters required to configure the first service include one or more of the following: basic package information, package rental parameters, and package tariff parameters.

14. A service configuration method, characterized in that, The method includes: The cloud server receives a first prompt sent by an electronic device. The first prompt contains a first user input, which is the user input received by the electronic device. The user intent expressed by the first user input is to create a first service. The first user input includes one or more of the following inputs: voice input, document input, text input, and image input. The cloud server uses the first prompt to guide the large language model to identify the service type of the first service from the first user input; The cloud server returns the service type of the first service to the electronic device; The cloud server receives a second prompt sent by the electronic device, the second prompt containing the first user input; The cloud server uses the second prompt to guide the large language model to identify the first parameter and its value from the first user input. The first parameter is the parameter required to create the first service. The first parameter required to create the first service of different service types is different. The cloud server returns the first parameter and its value to the electronic device, and the first parameter and its value are used by the electronic device to create the first service.

15. The method as described in claim 14, characterized in that, The first prompt is composed of a first prompt template and the first user input, and the second prompt is composed of a second prompt template and the first user input. The first prompt template and the second prompt template are pre-stored on the electronic device.

16. The method as described in claim 14 or 15, characterized in that, There are multiple first parameters and multiple second prompts. The cloud server receives the second prompt sent by the electronic device, specifically including: The cloud server receives multiple second prompts sent by the electronic device, the multiple second prompts being determined by the electronic device based on the service type of the first service.

17. The method according to any one of claims 14-16, characterized in that, The first parameter and its value returned by the cloud server to the electronic device are in JSON format.

18. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-13.

19. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-13.

20. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-13.

Images