A traffic travel service recommendation method, electronic device and medium

Abstract

The embodiment of the application provides a traffic travel service recommendation method, an electronic device and a medium, and belongs to the technical field of artificial intelligence and traffic travel. The method comprises the following steps: according to travel service consultation information, service knowledge retrieval is performed through a business intelligent agent, and a first prompt instruction constructed according to the travel service consultation information and target travel service knowledge obtained through retrieval is used to instruct the business intelligent agent to generate service content, so as to obtain target service text information; a second prompt instruction constructed according to a service function knowledge base and the travel service consultation information is used to instruct a travel service intelligent agent to extract a target service link; and service consultation feedback information is generated according to the target service text information and the target service link. According to the embodiment of the application, the target service text information is generated through the business intelligent agent, and the target service link is extracted through the travel service intelligent agent, so that the user can instantly obtain and operate the required service, and the recommendation accuracy of the traffic travel service and the service providing efficiency are significantly improved.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and transportation technology, and in particular to a method, electronic device and medium for recommending transportation services. Background Technology

[0002] Traditional methods for recommending transportation services typically rely on rule engines to match service functions related to user needs. For example, in the transportation sector, if a user enters the keyword "recharge" on the app's homepage, the rule engine can recommend recharge-related function entries such as "Shenzhen Tong Card Recharge" and "Mobile Interoperable Card Recharge" to the user, who can then choose the service function based on their needs.

[0003] However, due to the numerous service functions available on the client-side, multiple services may still be associated using only keywords, and these services often have similar names. This can lead to confusion for users, increasing their time commitment and resulting in low service matching efficiency. Therefore, improving the accuracy of transportation service recommendations and optimizing the efficiency of transportation service delivery have become urgent issues to be addressed. Summary of the Invention

[0004] The main objective of this application is to propose a transportation service recommendation method, electronic device, and medium, which aims to improve the accuracy of transportation service recommendations and optimize the efficiency of transportation service provision.

[0005] To achieve the above objectives, a first aspect of this application proposes a transportation service recommendation method, applied to a server, the method comprising:

[0006] Receive travel service consultation information sent by the client; wherein the travel service consultation information is obtained by the client.

[0007] Based on the travel service consultation information, a pre-trained business agent retrieves service knowledge from a pre-built travel service knowledge base to obtain target travel service knowledge, and then the business agent constructs a first prompt based on the travel service consultation information and the target travel service knowledge.

[0008] The business intelligence agent generates service content according to the first prompt, and obtains the target service text information.

[0009] A second prompt message is constructed based on a pre-built service function knowledge base and the travel service consultation information.

[0010] Based on the second prompt, the pre-trained travel service agent extracts service links to obtain the target service links.

[0011] Generate service consultation feedback information based on the target service text information and the target service link;

[0012] The service inquiry feedback information is sent to the client so that the client can generate a service feedback interface based on the service inquiry feedback information.

[0013] In some embodiments, the step of extracting service links from the pre-trained travel service agent based on the second prompt to obtain the target service link includes:

[0014] The travel service agent performs consultation intent recognition according to the second prompt, and obtains the target consultation intent;

[0015] Determine the target service name corresponding to the target consultation intent based on the target consultation intent;

[0016] The target service function is selected from the reserve service functions in the service function knowledge base according to the target service name; wherein, the service function knowledge base includes multiple reserve service entries corresponding to the reserve service functions;

[0017] Extract the target service link from the reserve service entries corresponding to the target service function.

[0018] In some embodiments, the target service link includes an address information collection link and a device binding operation link. Extracting the target service link from the reserve service entries corresponding to the target service function further includes:

[0019] If the target service function is a card type allocation type, then the reserve service code corresponding to the physical card allocation type and the reserve service code corresponding to the virtual card allocation type are determined from the reserve service entries; wherein, the card type allocation type includes the physical card allocation type and the virtual card allocation type;

[0020] Based on the reserve service code corresponding to the physical card distribution type, the address information collection link is extracted from the reserve service entry;

[0021] Based on the reserve service code corresponding to the virtual card allocation type, extract the device binding operation link from the reserve service entry;

[0022] The step of generating service consultation feedback information based on the target service text information and the target service link includes:

[0023] Extract physical card service text information and virtual card service text information from the target service text information;

[0024] Based on the physical card service text information and the address information collection link, generate physical card consultation feedback information;

[0025] Based on the virtual card service text information and the device binding operation link, generate virtual card consultation feedback information;

[0026] The service inquiry feedback information is generated by integrating the physical card inquiry feedback information and the virtual card inquiry feedback information.

[0027] In some embodiments, the target service link includes a regular ride code link and a premium ride link. Extracting the target service link from the reserve service entries corresponding to the target service function further includes:

[0028] If the target service function is a travel function type, then the reserve service code corresponding to the ordinary carriage travel type and the reserve service code corresponding to the premium carriage travel type are determined from the reserve service entries; wherein, the travel function type includes the ordinary carriage travel type and the premium carriage travel type;

[0029] Based on the reserve service code corresponding to the ordinary carriage travel type, the ordinary travel code link is extracted from the reserve service entry;

[0030] Based on the reserve service code corresponding to the premium carriage travel type, the premium travel link is extracted from the reserve service entry;

[0031] The step of generating service consultation feedback information based on the target service text information and the target service link includes:

[0032] Extract the text information of regular carriage services and the text information of premium carriage services from the target service text information;

[0033] Based on the regular carriage service text information and the regular boarding code link, generate regular boarding inquiry feedback information;

[0034] Based on the premium carriage service text information and the premium ride link, generate premium ride inquiry feedback information;

[0035] The service inquiry feedback information is generated by integrating the general passenger inquiry feedback information and the premium passenger inquiry feedback information.

[0036] In some embodiments, the target service link includes a trip data collection link and an invoice issuance link. Extracting the target service link from the reserve service entries corresponding to the target service function further includes:

[0037] If the target service function is a travel voucher service type, then the reserve service code corresponding to the trip query type and the reserve service code corresponding to the travel invoice generation type are determined from the reserve service entries; wherein, the travel voucher service type includes the trip query type and the travel invoice generation type;

[0038] Based on the reserve service code corresponding to the trip query type, extract the trip data collection link from the reserve service item;

[0039] Based on the reserve service code corresponding to the travel invoice generation type, the invoice issuance link is extracted from the reserve service item;

[0040] The step of generating service consultation feedback information based on the target service text information and the target service link includes:

[0041] Extract the trip service text information and invoice service text information from the target service text information;

[0042] Based on the trip service text information and the trip data collection link, generate trip inquiry feedback information;

[0043] Based on the invoice service text information and the invoice issuance link, generate invoice inquiry feedback information;

[0044] The service inquiry feedback information is generated by integrating the trip inquiry feedback information and the invoice inquiry feedback information.

[0045] In some embodiments, the step of constructing a first prompt by the business intelligence agent based on the travel service consultation information and the target travel service knowledge includes:

[0046] Obtain at least one response constraint requirement that matches the travel service consultation information;

[0047] The business intelligence agent generates service content text based on the travel service consultation information and the target travel service knowledge to obtain the first service content information.

[0048] The business intelligence agent generates constraint text based on at least one of the response constraint requirements to obtain the intelligence agent response constraint information.

[0049] The first prompt message is constructed by integrating the first service content information and the intelligent agent response constraint information.

[0050] In some embodiments, constructing the second prompt based on a pre-built service function knowledge base and the travel service consultation information includes:

[0051] The travel service information obtained from the travel service consultation information includes basic travel service information.

[0052] The intent constraint information of the travel service consultation information is parsed and constrained to obtain intent constraint indication information;

[0053] Based on the service function knowledge base, service quantity analysis and constraints are performed on the travel service consultation information to obtain service quantity constraint information;

[0054] Based on the basic travel service information, the intent constraint indication information, and the service quantity constraint information, a prompt message is constructed from the travel service consultation information and the service function knowledge base to obtain the second prompt message.

[0055] To achieve the above objectives, a second aspect of this application proposes a transportation service recommendation method, applied to a client, the method comprising:

[0056] Obtain travel service consultation information from target users;

[0057] The travel service consultation information is sent to the server, so that the server, based on the travel service consultation information, uses a pre-trained business agent to retrieve service knowledge from a preset travel service knowledge base to obtain target travel service knowledge. The business agent then constructs a first prompt based on the travel service consultation information and the target travel service knowledge. Based on the first prompt, the business agent is instructed to generate service content to obtain target service text information. A second prompt is constructed based on a pre-built service function knowledge base and the travel service consultation information, and the pre-trained travel service agent is instructed to extract service links to obtain target service links. Finally, service consultation feedback information is generated based on the target service text information and the target service link.

[0058] Receive service consultation feedback information from the server in response to the travel service consultation information;

[0059] A service feedback interface is generated based on the service inquiry feedback information.

[0060] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0061] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of the first aspect described above.

[0062] This application proposes a transportation service recommendation method, electronic device, and medium. First, it receives transportation service inquiry information from a client. The server, through a business intelligence agent, retrieves service knowledge from a transportation service knowledge base, obtaining service knowledge relevant to the user's needs. This effectively solves the confusion problem when users face multiple similar services, improving the accuracy of service matching. Second, the business intelligence agent constructs a first prompt based on the transportation service inquiry information and the retrieved target service knowledge. This further refines the user's needs. The first prompt instructs the business intelligence agent to generate service content, obtaining the target service text information, thus optimizing service delivery efficiency and reducing user operation time costs. Furthermore, a second prompt is constructed based on the service function knowledge base and the transportation service inquiry information. The second prompt instructs a pre-trained transportation service intelligence agent to extract service links, obtaining the target service link. This ensures users can quickly access the required service functions, further improving service recommendation efficiency. Finally, the server sends service inquiry feedback information containing the target service text information and the link to the client. The client then generates an intuitive service feedback interface, enabling users to instantly obtain and operate the required service, significantly improving the accuracy of transportation service recommendations and optimizing transportation service delivery efficiency. Attached Figure Description

[0063] Figure 1 This is a flowchart of the transportation service recommendation method provided in the embodiments of this application;

[0064] Figure 2 yes Figure 1 The flowchart of step S102 in the document;

[0065] Figure 3 yes Figure 1 The flowchart of step S104 in the process;

[0066] Figure 4 yes Figure 1 The flowchart of step S105 in the process;

[0067] Figure 5 yes Figure 4 The flowchart of step S404 in the document;

[0068] Figure 6 yes Figure 4 Another flowchart of step S404 in the process;

[0069] Figure 7 yes Figure 4 Another flowchart of step S404 in the process;

[0070] Figure 8This is another flowchart of the transportation service recommendation method provided in the embodiments of this application;

[0071] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0073] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0075] First, let's analyze some of the terms used in this application:

[0076] Artificial intelligence (AI) is a new branch of computer science that studies, develops, and applies theories, methods, technologies, and systems to simulate, extend, and expand human intelligence. It aims to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thought. Furthermore, AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results.

[0077] This application provides a method, electronic device, and medium for recommending transportation services, aiming to improve the accuracy of transportation service recommendations and optimize the efficiency of transportation service provision.

[0078] This application provides a method, electronic device, and medium for recommending transportation services, which will be described in detail through the following embodiments. First, the method for recommending transportation services in this application is described.

[0079] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0080] Foundational artificial intelligence technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0081] The transportation service recommendation method provided in this application relates to the fields of artificial intelligence and transportation technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the transportation service recommendation method, but is not limited to the above forms.

[0082] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0083] It should be noted that in all specific embodiments of this application, when processing is required based on user information, user operation behavior data, or characteristic-related data, the user's permission or consent will be obtained first. Furthermore, the collection, use, and processing of this data will comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user will be obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent will the necessary user-related data for the normal operation of the embodiments of this application be obtained.

[0084] Figure 1 This is an optional flowchart of the transportation service recommendation method provided in the embodiments of this application, applied to a server. Figure 1 The method may include, but is not limited to, steps S101 to S107.

[0085] Step S101: Receive travel service consultation information sent by the client; wherein the travel service consultation information is obtained by the client.

[0086] Step S102: Based on the travel service consultation information, the pre-trained business agent retrieves service knowledge from the pre-built travel service knowledge base to obtain the target travel service knowledge, and then constructs the first prompt based on the travel service consultation information and the target travel service knowledge.

[0087] Step S103: The business intelligence agent is instructed to generate service content according to the first prompt to obtain the target service text information.

[0088] Step S104: Construct a second prompt based on the pre-built service function knowledge base and travel service consultation information.

[0089] Step S105: According to the second prompt, the pre-trained travel service agent extracts service links to obtain the target service links.

[0090] Step S106: Generate service consultation feedback information based on the target service text information and the target service link.

[0091] Step S107: Send the service inquiry feedback information to the client so that the client can generate a service feedback interface based on the service inquiry feedback information.

[0092] Steps S101 to S107 of this embodiment first receive travel service consultation information sent by the client. The server then uses a business intelligence agent to retrieve service knowledge from the travel service knowledge base, obtaining service knowledge related to the user's needs. This effectively solves the problem of user confusion when faced with multiple similar services and helps improve the accuracy of service matching. Second, the business intelligence agent constructs a first prompt based on the travel service consultation information and the retrieved target service knowledge. This further refines the user's needs. The first prompt instructs the business intelligence agent to generate service content, obtaining target service text information, which optimizes service delivery efficiency and reduces the time cost of user operations. Furthermore, a second prompt is constructed based on the service function knowledge base and the travel service consultation information. The second prompt instructs the pre-trained travel service intelligence agent to extract service links, obtaining target service links. This ensures that users can quickly access the required service functions, further improving the efficiency of service recommendation. Finally, the server sends service consultation feedback information containing the target service text information and the link to the client. The client then generates an intuitive service feedback interface, enabling users to instantly obtain and operate the required services, significantly improving the accuracy of transportation service recommendations and the efficiency of service delivery.

[0093] In step S101 of some embodiments, specifically, the client refers to the software application or interface through which the user interacts with travel services, which is usually an application (such as a mobile APP) installed on the user's device or a mini-program on a web page.

[0094] Specifically, travel service inquiry information refers to text or voice messages from users sending questions about transportation services to the server through the client. This travel service inquiry information is used to represent the user's travel service needs.

[0095] For example, when users enter keywords such as "metro card recharge" or "metro line query" into a transportation-related app, these keywords and their contextual information together constitute travel service information.

[0096] Specifically, the client obtains the user's travel service information through a user interface (such as a text input box or a voice input box) and sends the information to the server. If the user inputs voice information, the server's voice-to-text agent calls the SenseVoice-Small model to perform speech recognition, and returns the speech-recognized travel service information text to the client.

[0097] In this embodiment, by receiving travel service inquiry information sent by the client, it is possible to gain a preliminary understanding of the user's travel service needs, providing basic data support for subsequent transportation service recommendations.

[0098] In step S102 of some embodiments, specifically, the pre-trained business agent is a pre-trained neural network model (such as a Transformer model) used to retrieve relevant service knowledge from the travel service knowledge base based on the user's travel service consultation information, and generate a first prompt for further refining the user's needs.

[0099] Specifically, the travel service knowledge base is a pre-designed database that stores knowledge related to the transportation field. This knowledge base includes, but is not limited to, basic information about transportation-related enterprises, information on transportation business services (such as transportation card recharge services, transportation card application services, and information on ride services), detailed answers to questions regarding the rules and procedures for handling transportation-related services, and the information in the travel service knowledge base is presented in Markdown format. This travel service knowledge base is used to initially respond to users' travel service inquiries.

[0100] Specifically, target travel service knowledge refers to the transportation and travel service information most relevant to the user's question, retrieved from the travel service knowledge base.

[0101] For example, in a subway travel app, if a user asks "how to apply for a student card", the target travel service knowledge can be a knowledge entry containing information such as the conditions, materials, and procedures for applying for a student card.

[0102] Specifically, the business intelligence agent can perform word embedding processing on travel service consultation information to extract travel service consultation feature vectors. The travel service consultation feature vectors are then matched with travel service knowledge in the travel service knowledge base using cosine similarity to obtain consultation knowledge matching similarity. The consultation knowledge matching similarity is compared with a preset similarity threshold, and the travel service knowledge corresponding to consultation knowledge matching similarity greater than the similarity threshold is determined as the target travel service knowledge.

[0103] In this embodiment, based on travel service consultation information, a pre-trained business intelligence agent retrieves service knowledge from a pre-built travel service knowledge base to obtain target travel service knowledge. This enables the initial acquisition of service knowledge related to user needs, effectively solving the problem of user confusion when faced with multiple similar services and helping to improve the accuracy of service matching.

[0104] Please see Figure 2 In some embodiments, step S102 may include, but is not limited to, steps S201 to S204:

[0105] Step S201: Obtain at least one response constraint requirement that matches the travel service consultation information.

[0106] Step S202: The business intelligence agent generates service content text based on travel service consultation information and target travel service knowledge to obtain the first service content information.

[0107] Step S203: The business agent generates constraint text based on at least one response constraint requirement to obtain the agent's response constraint information.

[0108] Step S204: Integrate the first service content information and the agent response constraint information to construct the first prompt.

[0109] In step S201 of some embodiments, specifically, response constraint requirements refer to the conditions that need to be met when generating service content.

[0110] Specifically, obtaining at least one response constraint requirement matching the travel service consultation information includes: when the travel service consultation information is a travel discount query type, performing a discount eligibility query constraint on the target user to obtain a discount query constraint requirement; when the travel service consultation information is a complaint type, performing emotion recognition on the target user to obtain the target user's emotion, and performing an emotion response constraint based on the target user's emotion to obtain an emotion response constraint requirement; when the travel service consultation information is a device compatibility type, performing a device detection constraint on the target device to obtain a device detection constraint requirement.

[0111] For example, for travel service inquiries about discounts, the discount inquiry constraint requirements could include identifying whether the user is eligible for travel discounts (e.g., inquiring about student card discounts when the user is not a student). If so, the system would directly output "Please enjoy travel discounts according to your actual status." If the user is eligible, the system would inform the user of the discount range for different transportation card types and payment methods, emphasizing the time-limited nature of the discount activities and specifying the start and end dates. For conditional transportation discounts (e.g., top-up discounts, transfer discounts), the system would supplement the information by listing the applicable travel scenarios and restrictions. For travel service inquiries about complaints, the emotional response constraint requirements could include directly outputting "We apologize for the unpleasant experience caused" if the user uses overly harsh language in their complaint. "We will carefully handle your issue," and record the specific details of the user complaint and related travel service information to ensure traceability. We will also provide the estimated processing time and feedback channels so users are informed of the progress. For travel service inquiries related to device compatibility, device testing constraints may include: if the user's device model is too old to support the service function, directly output "Your device may not be able to use this function due to hardware limitations. We recommend upgrading your device or trying other alternatives," and list the operating system versions and device models compatible with the supported service function. If the user's travel service inquiry contains illegal or non-compliant content, directly output "Let's change the subject," without outputting any other content to ensure the compliance of the inquiry.

[0112] In step S202 of some embodiments, specifically, the first service content information refers to the preliminary service description text generated based on travel service consultation information and target travel service knowledge.

[0113] For example, in a subway travel app, the first service content information may include user questions (i.e. travel service consultation information): [How to apply for a student card], as well as target travel service knowledge retrieved from the travel service knowledge base: [Student card application service knowledge such as the applicable groups, required materials, and application channels].

[0114] In this embodiment, the business intelligence agent generates service content text based on travel service consultation information and target travel service knowledge to obtain the first service content information, providing preliminary service suggestions for user service needs, and providing service suggestion data support for the construction of the subsequent first prompt.

[0115] In step S203 of some embodiments, specifically, the agent response constraint information refers to supplementary text generated according to constraint requirements to ensure that the final service content meets the constraint conditions. The agent response constraint information includes, but is not limited to, discount query constraint requirements, emotion response constraint requirements, device detection constraint requirements, and compliance constraint requirements.

[0116] For example, when generating service content, if the constraint requirement is to respond to the user's impatient emotions, the agent's response constraint information can be "I understand you're not in a good mood right now, let's change to a lighter topic," without outputting any other content.

[0117] In this embodiment, the business intelligence agent generates constraint text based on at least one response constraint requirement to obtain the intelligence agent response constraint information, which further optimizes the expression of service content, ensures that the generated service content meets the actual needs of users, and avoids situations where illegal or inappropriate content may be generated.

[0118] In step S204 of some embodiments, specifically, the first prompt refers to the prompt information generated after integrating the first service content information and the agent response constraint information.

[0119] For example, in a subway travel scenario, if the agent's response constraints are compliance requirements and friendly greetings, then the first prompt for inquiries about how to obtain a student card for transportation could be: "Target travel service knowledge: {travel service knowledge base search.data}; travel service inquiry information: {start.question}"; Agent response constraints: If the user's question (i.e., the travel service inquiry information) contains illegal or non-compliant content, then directly output "Let's change the subject" without outputting any other content; if the user's question is a complaint about travel services and contains negative emotions such as impatience and anxiety... If the user is expressing an emotion, the response should simply say, "I understand you're not in a good mood right now, let's change to a lighter topic," without providing any other information. If the user's question is about transportation discounts, the constraint should be to identify whether the user is eligible for discounts. If the user is not eligible, the response should simply say, "Please enjoy the discounts according to your actual identity." If the user is eligible, the response should inform the user of the discount range for different transportation cards and payment methods, the validity period of the discount activities, applicable travel scenarios, and restrictions. The response should use "you" to refer to the user. The response style should be clear and friendly.

[0120] Steps S201 to S204 allow for further refinement of user needs and rewriting user input into prompts that the business intelligence agent can understand, thereby improving the accuracy of understanding user needs and facilitating the subsequent improvement of the efficiency of transportation service provision.

[0121] In step S103 of some embodiments, specifically, the target service text information refers to a service content description that meets the user's needs, generated based on the first prompt.

[0122] For example, if the travel service inquiry is "How to apply for a student card", the business intelligence agent can generate the target service text information based on the user's needs and the first prompt in the travel service inquiry: "Hello, the steps to apply for a transportation student card are as follows:"

[0123] I. Applicable Groups: Students enrolled in primary and secondary schools (including high schools) and secondary vocational schools with student status are eligible to apply.

[0124] II. Required materials: The student's original identification document (ID card, household registration book, or passport, etc.); for students under the age of 15, the application must be made by their guardian, who must also provide the original identification document of the guardian.

[0125] III. Application Channels: For the Transportation Student Card (with non-standard shape): applications can be made through the Transportation App, Transportation's self-operated customer service outlets, Transportation's self-operated business halls, and post offices; For the Transportation Standard Card: applications can be made through the Transportation App, Transportation's self-operated customer service outlets, Transportation's micro-customer service terminals, Transportation's self-operated business halls, and post offices; For the Watch-type Transportation Student Card: applications can be made through Transportation's self-operated customer service outlets, the Transportation App, Transportation's self-operated business halls, and Transportation card sales and recharge self-service terminals in subway stations.

[0126] IV. Warm Reminder: When applying at the Transportation Travel Micro Customer Service Terminal, you need to bring the original student ID card, student ID card or proof of enrollment. Students under the age of 15 should have their guardians apply on their behalf and should also bring the original ID card of the guardians. If the watch Transportation Travel Student Card is applied for through the Transportation Travel self-operated customer service outlets, Transportation Travel App, or Transportation Travel card sales and recharge machines, it will be delivered by China Unicom.

[0127] We hope this information is helpful! Please feel free to contact us if you have any further questions.

[0128] Please see Figure 3 In some embodiments, step S104 includes, but is not limited to, steps S301 to S304:

[0129] Step S301: Construct a second prompt based on the pre-built service function knowledge base and travel service consultation information.

[0130] Step S302: Perform intent parsing constraints on the travel service consultation information to obtain intent constraint indication information.

[0131] Step S303: Based on the service function knowledge base, perform service quantity analysis and constraints on travel service consultation information to obtain service quantity constraint information.

[0132] Step S304: Based on the basic information of travel services, the intent constraint instruction information and the service quantity constraint information, construct the prompt message for the travel service consultation information and service function knowledge base to obtain the second prompt message.

[0133] In step S301 of some embodiments, specifically, the basic travel service information refers to the background information of the user when using travel services such as a travel APP or a physical travel card, including but not limited to the usage rules of the travel APP account balance and the physical card balance (such as being able to take the bus by swiping the ride code and deducting the fare from the travel APP account, and the APP account balance and the user's physical card balance not being interconnected, and only when the user recharges via NFC card tapping can the user choose to recharge from the APP account balance to the physical card balance), recharge method, card type (such as ordinary physical card, student card, mobile phone interoperable card) and card function (such as card ride, recharge, interconnection range, etc.).

[0134] In step S302 of some embodiments, specifically, the intent constraint indication information refers to guidance information generated based on the user's intent and constraints when parsing travel service consultation information, used to ensure that subsequent service content generation meets the user's needs. The constraints are used to limit the scope of subsequent service recommendations. For example, in a transportation app, if a user inquires about "how to apply for a student card," the intent constraint indication information may include constraints such as "the user's intent is to apply for a student card" and "the user needs to meet student status."

[0135] In step S303 of some embodiments, specifically, the service function knowledge base is a pre-designed and stored database containing relevant information about all travel services for clients in the transportation field. This service function knowledge base includes, but is not limited to, travel service names, travel service descriptions, travel service links, and travel service codes, and the information in the service function knowledge base is organized in Markdown format to form a client service list.

[0136] For example, in the client service list, the service name can be "student card", the service description can be "applying for, binding, reporting loss, renewing, or extending student cards, viewing and obtaining the on-campus certificate template required for student cards, and querying the documents required for student cards"; the service link can be "StudentCardActivity", and the service code can be 5.

[0137] Specifically, service quantity constraint information refers to the constraints obtained after analyzing the travel service consultation information input by the user based on the service function knowledge base, which are used to limit the number of recommended services.

[0138] For example, given a list of client services, the task is to determine which functions in the instruction list are most likely to satisfy the user's intent. The user intent is then assigned a corresponding "service name" and "service code." During the service quantity analysis, the process strictly adheres to the known client service list information, classifying and discussing cases as follows: if two possible service functions can be found, then those two are selected; if only one possible service function can be found, then that one is selected; if none of the functions in the list can directly satisfy the user's intent, then only [] is output, and the final output format is json:[{"text":"xxx","value":"yyy"}]. Here, xxx is the determined "service name," and yyy is the determined "service code." Service names and service codes are one-to-one. If two functions are possible, they are represented as two objects, and the output can contain at most two objects.

[0139] In step S304 of some embodiments, specifically, the second prompt refers to the prompt information generated after integrating the basic information of travel services, the intention constraint indication information, and the service quantity constraint information with the travel service consultation information and service function knowledge base, which is used to instruct the travel service agent to extract the service link.

[0140] For example, in the subway travel scenario, for inquiries about how to apply for a student card for transportation, the corresponding second prompt could be: "Basic information on travel services: {rules for using the balance in the transportation APP account and the balance in the physical card, recharge methods, card types (such as ordinary physical cards, student cards, mobile interoperable cards) and card functions (such as card rides, recharge, interoperability scope, etc.}; Intent constraint information: {client service list search.data}; Service quantity constraint information: if two possible service functions can be found, then these two are selected; if only one possible service function can be found, then this one is selected; if none of the functions in the list can directly satisfy the user's intent, then only [] is output, and the final output format is json:[{"text":"xxx","value":"yyy"}]."

[0141] Through steps S301 to S304, user needs can be accurately identified and service recommendations that match user intent can be generated. Furthermore, by reasonably controlling the number of recommendations, the accuracy of transportation service recommendations can be further improved, thereby increasing the efficiency of transportation service provision.

[0142] Please see Figure 4 In some embodiments, step S105 includes, but is not limited to, steps S401 to S404:

[0143] Step S401: Based on the second prompt, the travel service agent performs consultation intent recognition to obtain the target consultation intent.

[0144] Step S402: Determine the target service name corresponding to the target consultation intent based on the target consultation intent.

[0145] Step S403: Select the target service function from the reserve service functions in the service function knowledge base according to the target service name; wherein, the service function knowledge base includes reserve service entries corresponding to multiple reserve service functions.

[0146] Step S404: Extract the target service link from the reserve service entries corresponding to the target service function.

[0147] In step S401 of some embodiments, specifically, the travel service agent is a pre-trained large model (such as deepseekV3-671B) used to match the content of the client's service list to extract the service link corresponding to the consultation intent of the travel service consultation information.

[0148] Specifically, the target consultation intent refers to the consultation need or purpose of travel service consultation information.

[0149] For example, in a transportation app, if the travel service information is "How to apply for a student card", the target inquiry intent is "to apply for a student card".

[0150] In step S402 of some embodiments, specifically, the target service name refers to the name of the transportation service corresponding to the target consultation intent.

[0151] Furthermore, the service function knowledge base includes multiple reserve service entries corresponding to reserve service functions. Each reserve service entry includes a reserve service code, a reserve service name, and a reserve service link.

[0152] For example, in a transportation app, if the intended inquiry is "to apply for a student card", then the target service name "student card application" can be extracted from the reserve service items.

[0153] In step S403 of some embodiments, specifically, the target service function refers to a specific service function that matches the target service name.

[0154] For example, if the target service name is "student card application", then the corresponding reserve service items (such as "apply for student card online", "check application progress", "view required materials", etc.) will be searched in the service function knowledge base, and the target service function that best meets the user's needs will be selected as "apply for student card online" based on the user's inquiry intent.

[0155] Please see Figure 5In some embodiments, the target service link includes an address information collection link and a device binding operation link, and step S404 includes, but is not limited to, steps S501 to S507:

[0156] Step S501: If the target service function is card type allocation type, then determine the reserve service code corresponding to the physical card allocation type and the reserve service code corresponding to the virtual card allocation type from the reserve service entries; wherein, card type allocation type includes physical card allocation type and virtual card allocation type.

[0157] Step S502: Based on the reserve service code corresponding to the physical card distribution type, extract the address information collection link from the reserve service entry.

[0158] Step S503: Extract the device binding operation link from the reserve service entry based on the reserve service code corresponding to the virtual card allocation type.

[0159] In step S106, service inquiry feedback information is generated based on the target service text information and the target service link, including:

[0160] Step S504: Extract physical card service text information and virtual card service text information from the target service text information;

[0161] Step S505: Collect links based on physical card service text information and address information, and generate physical card inquiry feedback information;

[0162] Step S506: Generate virtual card consultation feedback information based on the virtual card service text information and the device binding operation link;

[0163] Step S507: Integrate physical card consultation feedback information and virtual card consultation feedback information to generate service consultation feedback information.

[0164] In step S501 of some embodiments, specifically, the card type allocation refers to the card issuance method inquired in the travel service consultation information, including physical card allocation type and virtual card allocation type.

[0165] For example, in transportation apps, users need to apply for a physical or virtual transportation card (such as a mobile phone interoperable card).

[0166] Specifically, the reserve service code is a unique identifier assigned to each service function in the service function knowledge base, used to quickly locate and extract specific service function information.

[0167] For example, if a user needs to apply for a physical card for transportation, the reserve service code for the physical card will be "101" from the reserve service list. If a user needs to apply for a virtual card for transportation, the reserve service code for the virtual card can be "102".

[0168] In step S502 of some embodiments, specifically, the address information collection link is a webpage or application link used to guide the user to fill in the address information during the physical card issuance process. The link can be in the form of a pop-up control.

[0169] For example, when a user applies for a student card, they need to provide a mailing address. The address information collection pop-up control can be extracted from the reserve service entry through reserve service code 101. After the user clicks the pop-up control, they can fill in the address information.

[0170] In step S503 of some embodiments, the device binding operation link refers to the link that the user needs to bind the device when applying for a virtual card, and the link can be a pop-up control.

[0171] For example, when a user applies for a mobile interoperability card, they need to bind a mobile device. Based on the reserve service code "102" corresponding to the virtual card allocation type, the device binding operation pop-up control can be extracted from the reserve service entry. The user can complete the device binding operation by clicking the pop-up control.

[0172] In step S504 of some embodiments, specifically, the physical card service text information refers to detailed service description text related to the physical card service and link usage.

[0173] Specifically, virtual card service text information refers to the detailed service description text related to virtual cards.

[0174] For example, the text information for physical card services may include the steps for applying for a physical card, the required materials, and the use of pop-up controls for collecting application location and address information (such as "Please click the address collection button to fill in address information based on the button pop-up"); the text information for virtual card services may include the steps for applying for a virtual card, the supported device types, the binding operation, and the use of pop-up controls for device binding operation (such as "Please click the device binding button to fill in device binding related information based on the button pop-up").

[0175] In step S505 of some embodiments, specifically, the physical card consultation feedback information refers to the service content and service link usage information generated based on the physical card issuance type consulted by the user. The physical card consultation feedback information may include, but is not limited to, the specific steps for applying for a physical card, the required materials, the application location, the address information collection link, and the link usage description.

[0176] In step S506 of some embodiments, specifically, the virtual card consultation feedback information refers to the service content and service link usage information generated based on the virtual card allocation type consulted by the user. The virtual card consultation feedback information may include the specific steps for applying for a virtual card, supported device types, binding operations, device binding operation links, and link usage descriptions.

[0177] In step S507 of some embodiments, specifically, the service consultation feedback information refers to the card type allocation consultation feedback information generated by integrating physical card consultation feedback information and virtual card consultation feedback information.

[0178] Through steps S501 to S507, by identifying the card type and allocation type based on the user's inquiry content and extracting the corresponding service links and service text information, not only can detailed and accurate service operation guides be provided to users, effectively solving the problem of user confusion when faced with multiple similar services, thus improving the accuracy of service matching, but also can help improve the speed at which users find the card type and allocation services they need, thereby reducing user operation time and ensuring that users can quickly access the service functions they need, thereby improving the efficiency of transportation service provision.

[0179] Please see Figure 6 In some embodiments, the target service link includes a regular ride code link and a premium ride link, and step S404 also includes, but is not limited to, steps S601 to S607:

[0180] Step S601: If the target service function is a travel function type, then determine the reserve service code corresponding to the ordinary carriage travel type and the reserve service code corresponding to the premium carriage travel type from the reserve service entries; wherein, the travel function type includes the ordinary carriage travel type and the premium carriage travel type.

[0181] Step S602: Based on the reserve service code corresponding to the ordinary carriage travel type, extract the ordinary travel code link from the reserve service entry.

[0182] Step S603: Based on the reserve service code corresponding to the premium carriage ride type, extract the premium ride link from the reserve service entries.

[0183] In step S106, service inquiry feedback information is generated based on the target service text information and the target service link, which also includes:

[0184] Step S604: Extract the regular carriage service text information and the premium carriage service text information from the target service text information.

[0185] Step S605: Generate ordinary passenger service inquiry feedback information based on the ordinary carriage service text information and the ordinary passenger code link.

[0186] Step S606: Generate preferential ride consultation feedback information based on the preferential carriage service text information and the preferential ride link.

[0187] Step S607: Integrate general passenger inquiry feedback information and premium passenger inquiry feedback information to generate service inquiry feedback information.

[0188] In step S601 of some embodiments, specifically, the ride function type refers to the ride mode consulted in the travel service consultation information, including the ordinary carriage ride mode and the premium carriage ride mode.

[0189] For example, in the subway travel scenario, if a user is traveling in a regular carriage, they need to use a regular carriage boarding code. If a user needs to travel in a premium carriage, they can purchase a premium carriage ticket on the transportation app to generate a premium carriage boarding code and enjoy priority passage and premium services (such as free Wi-Fi).

[0190] Specifically, the reserve service code is a unique identifier assigned to each service function in the service function knowledge base, used to quickly locate and extract specific service function information.

[0191] For example, if a user needs to use the regular carriage ride code, the reserve service code corresponding to the regular carriage ride type is determined from the reserve service entry as "201". If a user needs to use the premium carriage ride benefits, the reserve service code corresponding to the premium carriage ride type can be "202".

[0192] In step S602 of some embodiments, specifically, the ordinary boarding code link is a link used to guide the user to use the ordinary carriage boarding code, and the link can be represented as a button control.

[0193] For example, when a user uses a regular carriage ride code, after clicking the "Use Regular Ride Code" button, the system extracts the regular ride code link from the reserve service entry using the reserve service code "201". The user can then directly use the ride code after clicking the button.

[0194] In step S603 of some embodiments, specifically, the "Premium Ride Link" refers to the link that the user needs to click when using the Premium Ride Car, and the link can be a button control.

[0195] For example, when a user uses the premium ride code or premium ride benefits, after clicking the "Use Premium Ride" button, the premium ride link is extracted from the reserve service entries based on the reserve service code "202" corresponding to the premium ride type. After clicking the button, the user can view and use the premium ride code and premium ride benefits.

[0196] In step S604 of some embodiments, specifically, the general carriage service text information refers to the detailed service description text related to general carriage travel services and link usage.

[0197] Specifically, the Premium Carriage service text information refers to the detailed service description text related to Premium Carriage travel service and link usage.

[0198] For example, the text information for regular carriage services may include a description of the use of the regular fare code, its applicable scope, and information on how to use the regular fare code; the text information for premium carriage services may include a description of the use of the premium fare code or fare benefits redemption, the supported carriage types, and information on how to use the premium fare benefits.

[0199] In step S605 of some embodiments, specifically, the ordinary travel consultation feedback information refers to the service content and service link usage information generated based on the ordinary carriage travel type consulted by the user. The ordinary travel consultation feedback information may include, but is not limited to, the specific steps for using the ordinary travel code, travel rules, ordinary travel code link, and link usage description.

[0200] For example, the feedback information for general public transportation inquiries can be as follows: the specific steps for using the general public transportation code are to open the transportation app, click the general public transportation code button to obtain the general public transportation code, and then align the code with the gate's scanning area to complete the ride.

[0201] In step S606 of some embodiments, specifically, the premium ride consultation feedback information refers to the service content and service link usage information generated based on the premium carriage ride type consulted by the user. The premium ride consultation feedback information may include, but is not limited to, the specific steps for enjoying premium carriage ride benefits and obtaining the premium carriage ride code, supported payment methods, premium ride links, and link usage descriptions.

[0202] For example, the text information for the Premium Carriage service could be: to open the transportation app, click the Premium Ride Code button on the homepage, select a payment method and complete the payment to obtain the Premium Ride Code, and click the Premium Ride Code button to obtain the Premium Carriage Ride Code; if users need to know about Premium Carriage benefits, they can click the Premium Benefits button on the homepage to obtain information on benefits such as priority passage.

[0203] In step S607 of some embodiments, specifically, the service consultation feedback information refers to the service consultation feedback information generated by integrating ordinary ride consultation feedback information and premium ride consultation feedback information, which provides users with a complete ride guide.

[0204] For example, a service inquiry feedback message could be: "Hello! Based on your inquiry, the following information is regarding travel in regular and premium carriages: For travel in regular carriages, please follow these steps: Open the transportation app and click the 'Regular Ride Code' button to obtain your regular ride code. Then, scan the code at the gate to complete your journey. We hope this information is helpful. If you have any further questions, please feel free to contact us."

[0205] Through steps S601 to S607, by identifying the type of travel function based on the user's inquiry content and extracting the corresponding service links and service text information, detailed and accurate travel operation guides can be provided to users. This allows users to directly obtain the travel code when using the regular carriage travel code and directly bind the relevant benefits when enjoying the premium carriage travel benefits, reducing the time users spend searching and operating in the client and thus improving the efficiency of transportation service provision.

[0206] Please see Figure 7 In some embodiments, the target service link includes a trip data collection link and an invoice issuance link, and step S404 also includes, but is not limited to, steps S701 to S707:

[0207] Step S701: If the target service function is a travel voucher service type, then determine the reserve service code corresponding to the trip query type and the reserve service code corresponding to the travel invoice generation type from the reserve service entries; wherein, the travel voucher service type includes the trip query type and the travel invoice generation type.

[0208] Step S702: Based on the reserve service code corresponding to the trip query type, extract the trip data collection link from the reserve service item.

[0209] Step S703: Based on the reserve service code corresponding to the travel invoice generation type, extract the invoice issuance link from the reserve service item.

[0210] In step S106, service inquiry feedback information is generated based on the target service text information and the target service link, which also includes:

[0211] Step S704: Extract trip service text information and invoice service text information from the target service text information.

[0212] Step S705: Generate itinerary inquiry feedback information based on the itinerary service text information and itinerary data collection link.

[0213] Step S706: Generate invoice inquiry feedback information based on the invoice service text information and the invoice issuance link.

[0214] Step S707: Integrate itinerary inquiry feedback information and invoice inquiry feedback information to generate service inquiry feedback information.

[0215] In step S701 of some embodiments, specifically, the ride pass service type refers to the ride pass-related services consulted in the travel service consultation information, including the trip query type and the ride invoice generation type.

[0216] Specifically, the reserve service code is a unique identifier assigned to each service function in the service function knowledge base, used to quickly locate and extract specific service function information.

[0217] For example, if a user needs to query travel data, the reserve service code corresponding to the travel query type is determined from the reserve service entry as "301". If the user needs to issue a travel invoice, the reserve service code corresponding to the travel invoice generation type can be "302".

[0218] In step S702 of some embodiments, specifically, the trip data collection link is a link used to guide the user to complete the trip data collection, and the link can be represented as a button control.

[0219] For example, when users query travel data, they can extract the "Query Travel" button from the reserve service entry using the reserve service code "301". After clicking the "Query Travel" button, users can directly query their travel data.

[0220] In step S703 of some embodiments, specifically, the invoice issuance link refers to the link that the user needs to click when issuing a travel invoice, and the link can be a button control.

[0221] For example, when a user issues a travel invoice, the invoice issuance button can be extracted from the reserve service item based on the reserve service code "302" corresponding to the travel invoice generation type. After clicking the invoice issuance button, the user can complete the invoice issuance operation.

[0222] In step S704 of some embodiments, specifically, the trip service text information refers to detailed service description text related to the trip query service and link usage. The trip service text information may include information such as the steps for querying trip data, the scope of application, and the use of the trip data collection link.

[0223] Specifically, the invoice service text information refers to the detailed service description text related to the invoice issuance service and link usage. This invoice service text information may include the steps for issuing an invoice, supported invoice types, binding operations, and the use of the invoice issuance link.

[0224] In step S705 of some embodiments, specifically, the itinerary consultation feedback information refers to the service content and service link usage information generated based on the itinerary query type consulted by the user. The itinerary consultation feedback information may include, but is not limited to, the specific steps for querying itinerary data, the scope of application, the itinerary data collection link, and the link usage description.

[0225] For example, the specific steps to query your travel data can be: open the travel app, click the travel query button on the homepage, and enter your travel information (such as date, origin and destination) to query your travel records.

[0226] In step S706 of some embodiments, specifically, the invoice consultation feedback information refers to the service content and service link usage information generated based on the type of travel invoice generated by the user's consultation. The invoice consultation feedback information may include the specific steps for issuing an invoice, supported invoice types, binding operations, invoice issuance link, and link usage description.

[0227] For example, the feedback information for invoice inquiries can be that the specific steps for issuing a travel invoice are to open the transportation app, click the invoice issuance button on the homepage, select the invoice type (such as electronic invoice or paper invoice), fill in the invoice information (such as header, tax number, etc.), and complete the invoice issuance.

[0228] In step S707 of some embodiments, specifically, the service consultation feedback information refers to the travel voucher service consultation feedback information generated by integrating trip consultation feedback information and invoice consultation feedback information. This service consultation feedback information provides users with a complete travel voucher service guide.

[0229] For example, a service inquiry feedback message could be: Hello! Based on your inquiry, the following information pertains to trip tracking and invoice issuance: For trip tracking, you can open the Transportation App and click the Trip Tracking button on the homepage, enter your trip information (such as date, origin, and destination) to view your trip records; for invoice issuance, you can open the Transportation App and click the Invoice Issuance button on the homepage, select the invoice type (such as e-invoice or paper invoice), fill in the invoice information (such as header, tax number, etc.), and complete the invoice issuance. We hope this information is helpful. If you have any further questions, please feel free to contact us.

[0230] Through steps S701 to S707, the user's inquiry content is used to identify the needs for itinerary inquiry and invoice issuance, and the corresponding travel voucher service links and service text information are extracted. This not only provides users with detailed and accurate travel voucher service operation guides and improves the accuracy of service matching, but also helps to improve the speed at which users find the travel voucher services they need, thereby reducing user operation time and ensuring that users can quickly access the travel voucher service functions they need, thus improving the efficiency of transportation service provision.

[0231] Through steps S401 to S404, which involve identifying the consultation intent, determining the target service name, filtering the target service function, and extracting the target service link, the user's needs can be accurately identified, and service links that meet the user's needs can be provided. This improves the accuracy of transportation service recommendations and reduces the number of steps required for user operations by directly providing service links, thereby improving the efficiency of transportation service provision.

[0232] In step S107 of some embodiments, specifically, the service consultation feedback information is sent to the client device used by the user (such as a transportation APP or transportation mini-program), and after the client receives the service consultation feedback information, it generates a service feedback interface based on the service consultation feedback information. The interface displays the service consultation feedback information, including but not limited to the specific operation steps of the transportation service, related service links and service descriptions.

[0233] In this example, by sending service inquiry feedback information to the client, the client can generate a service feedback interface based on the service inquiry feedback information. This not only ensures that users can clearly understand how to complete the required operations, but also reduces the time cost for users to jump between different pages or applications by generating the feedback interface directly on the client, thereby further improving the efficiency of transportation service provision.

[0234] This embodiment first receives travel service inquiry information sent by the client. The server then uses a business intelligence agent to retrieve service knowledge from the travel service knowledge base, obtaining service knowledge related to the user's needs. This effectively solves the problem of user confusion when faced with multiple similar services, improving the accuracy of service matching. Second, the business intelligence agent constructs a first prompt based on the travel service inquiry information and the retrieved target service knowledge. This further refines the user's needs. The first prompt instructs the business intelligence agent to generate service content, obtaining the target service text information, which optimizes service delivery efficiency and reduces the user's time cost. Furthermore, a second prompt is constructed based on the service function knowledge base and the travel service inquiry information. The second prompt instructs the pre-trained travel service intelligence agent to extract service links, obtaining the target service link. This ensures that the user can quickly access the required service function, further improving the efficiency of service recommendation. Finally, the server sends service inquiry feedback information containing the target service text information and the link to the client. The client then generates an intuitive service feedback interface, enabling the user to instantly obtain and operate the required service, significantly improving the accuracy of transportation service recommendations and the efficiency of service delivery.

[0235] Please see Figure 8 This application also provides a transportation service recommendation method, applied to a client, which can implement the above-mentioned transportation service recommendation method. The method may include steps S801 to S804:

[0236] Step S801: Obtain travel service consultation information from the target user.

[0237] Step S802: The travel service consultation information is sent to the server, so that the server, based on the travel service consultation information, uses a pre-trained business agent to retrieve service knowledge from a preset travel service knowledge base to obtain the target travel service knowledge. The business agent then constructs a first prompt based on the travel service consultation information and the target travel service knowledge. Based on the first prompt, the business agent is instructed to generate service content to obtain the target service text information. Based on the pre-built service function knowledge base and the travel service consultation information, a second prompt is constructed, and based on the second prompt, the pre-trained travel service agent is instructed to extract the service link to obtain the target service link. Finally, service consultation feedback information is generated based on the target service text information and the target service link.

[0238] Step S803: Receive service consultation feedback information from the server in response to travel service consultation information.

[0239] Step S804: Generate a service feedback interface based on the service inquiry feedback information.

[0240] The specific implementation method of this transportation service recommendation method applied to the client is basically the same as the specific implementation method of the transportation service recommendation method applied to the server, and will not be described again here.

[0241] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned transportation service recommendation method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0242] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0243] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0244] The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the processing system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and called by the processor 901 to execute the transportation service recommendation method of the embodiments of this application.

[0245] The input / output interface 903 is used to implement information input and output;

[0246] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0247] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0248] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0249] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described transportation service recommendation method.

[0250] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0251] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0252] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

Claims

1. A method for recommending transportation services, characterized in that, Applied to a server, the method comprises: Receiving travel service consultation information sent by a client; wherein the travel service consultation information is obtained by the client; According to the travel service consultation information, the target travel service knowledge is obtained by service agent from pre-built travel service knowledge base, and the first prompt is constructed by the service agent according to the travel service consultation information and the target travel service knowledge; According to the first prompt, the target service text information is obtained by indicating the service agent to generate service content; According to the pre-built service function knowledge base and the travel service consultation information, the second prompt is constructed; According to the second prompt, the target service link is obtained by indicating the pre-trained travel service agent to extract service link; According to the target service text information and the target service link, the service consultation feedback information is generated; The service consultation feedback information is sent to the client, so that the client generates a service feedback interface based on the service consultation feedback information; According to the pre-built service function knowledge base and the travel service consultation information, the second prompt is constructed, comprising: Obtaining travel service basic information of the travel service consultation information; The intention analysis constraint of the travel service consultation information is obtained, and the intention constraint indication information is obtained; According to the service function knowledge base, the service quantity analysis constraint of the travel service consultation information is obtained, and the service quantity constraint information is obtained; According to the travel service basic information, the intention constraint indication information and the service quantity constraint information, the travel service consultation information and the service function knowledge base are constructed, and the second prompt is obtained.

2. The method of claim 1, wherein, According to the second prompt, the target service link is obtained by indicating the pre-trained travel service agent to extract service link, comprising: According to the second prompt, the target consultation intention is obtained by indicating the travel service agent to identify the consultation intention; According to the target consultation intention, the target service name corresponding to the target consultation intention is determined; According to the target service name, the target service function is filtered in each reserve service function in the service function knowledge base; wherein the service function knowledge base comprises a reserve service item corresponding to a plurality of reserve service functions; From the reserve service item corresponding to the target service function, the target service link is extracted.

3. The method of claim 2, wherein, The target service link comprises address information collection link and device binding operation link, and the target service link is extracted from the reserve service item corresponding to the target service function, further comprising: If the target service function is card type distribution type, the reserve service code corresponding to entity card distribution type and the reserve service code corresponding to virtual card distribution type are determined from the reserve service item; wherein the card type distribution type comprises the entity card distribution type and the virtual card distribution type; Based on the reserve service code corresponding to the entity card distribution type, the address information collection link is extracted from the reserve service item; extract the device binding operation link from the reserved service item based on the reserved service code corresponding to the virtual card distribution type; the service consultation feedback information is generated according to the target service text information and the target service link, including: extracting entity card service text information and virtual card service text information from the target service text information; generating entity card consultation feedback information according to the entity card service text information and the address information collection link; generating virtual card consultation feedback information according to the virtual card service text information and the device binding operation link; integrating the entity card consultation feedback information and the virtual card consultation feedback information to generate the service consultation feedback information.

4. The method of claim 2, wherein, the target service link includes ordinary ride code link and preferential ride link, and the target service link is extracted from the reserved service item corresponding to the target service function, further including: if the target service function is a ride function type, determining the reserved service code corresponding to the ordinary car ride type and the reserved service code corresponding to the preferential car ride type from the reserved service item; wherein the ride function type includes the ordinary car ride type and the preferential car ride type; extracting the ordinary ride code link from the reserved service item based on the reserved service code corresponding to the ordinary car ride type; extracting the preferential ride link from the reserved service item based on the reserved service code corresponding to the preferential car ride type; the service consultation feedback information is generated according to the target service text information and the target service link, including: extracting ordinary car service text information and preferential car service text information from the target service text information; generating ordinary ride consultation feedback information according to the ordinary car service text information and the ordinary ride code link; generating preferential ride consultation feedback information according to the preferential car service text information and the preferential ride link; integrating the ordinary ride consultation feedback information and the preferential ride consultation feedback information to generate the service consultation feedback information.

5. The method of claim 2, wherein, the target service link includes journey data collection link and invoice issuing link, and the target service link is extracted from the reserved service item corresponding to the target service function, further including: if the target service function is a ride voucher service type, determining the reserved service code corresponding to the journey query type and the reserved service code corresponding to the ride invoice generation type from the reserved service item; wherein the ride voucher service type includes the journey query type and the ride invoice generation type; extracting the journey data collection link from the reserved service item based on the reserved service code corresponding to the journey query type; extracting the invoice issuing link from the reserved service item based on the reserved service code corresponding to the ride invoice generation type; the service consultation feedback information is generated according to the target service text information and the target service link, including: extracting journey service text information and invoice service text information from the target service text information; According to the travel service text information and the travel data collection link, travel consultation feedback information is generated; According to the invoice service text information and the invoice issuing link, invoice consultation feedback information is generated; The travel consultation feedback information and the invoice consultation feedback information are integrated to generate the service consultation feedback information.

6. The method of claim 1, wherein, The first prompt is constructed by the business agent according to the travel service consultation information and the target travel service knowledge, including: At least one response constraint requirement matched with the travel service consultation information is obtained; The first service content information is obtained by generating service content text based on the travel service consultation information and the target travel service knowledge through the business agent; The agent response constraint information is obtained by generating constraint text based on at least one response constraint requirement through the business agent; The first service content information and the agent response constraint information are integrated to construct the first prompt.

7. A traffic trip service recommendation method characterized by, Applied to a client, the method includes: Obtaining travel service consultation information of a target user; Sending the travel service consultation information to a server, so that the server retrieves service knowledge from a preset travel service knowledge base through a pre-trained business agent according to the travel service consultation information, obtains target travel service knowledge, and constructs a first prompt according to the travel service consultation information and the target travel service knowledge through the business agent; service content generation is instructed according to the first prompt, target service text information is obtained; a second prompt is constructed according to a pre-constructed service function knowledge base and the travel service consultation information, and service link extraction is instructed according to the second prompt through a pre-trained travel service agent, target service links are obtained; service consultation feedback information is generated according to the target service text information and the target service links; Receiving service consultation feedback information from the server in response to the travel service consultation information; Generating a service feedback interface based on the service consultation feedback information; The second prompt is constructed according to the pre-constructed service function knowledge base and the travel service consultation information, including: Obtaining travel service basic information of the travel service consultation information; Intention analysis constraint is performed on the travel service consultation information to obtain intention constraint indication information; Service quantity analysis constraint is performed on the travel service consultation information according to the service function knowledge base to obtain service quantity constraint information; The travel service consultation information and the service function knowledge base are prompted according to the travel service basic information, the intention constraint indication information, and the service quantity constraint information to construct the second prompt.

8. An electronic device, comprising: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the traffic travel service recommendation method of any one of claims 1-6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the traffic travel service recommendation method of any one of claims 1-6.

Images