Traffic service recommendation method, electronic equipment and medium

Abstract

The embodiment of the invention provides a transportation service recommendation method, electronic equipment and a medium, and belongs to the technical field of artificial intelligence and transportation. The method comprises the steps of performing service knowledge retrieval through a business agent according to travel service consultation information, and instructing the business agent to perform service content generation according to a first prompt word constructed by the travel service consultation information and retrieved target travel service knowledge to obtain target service text information; instructing a travel service agent to perform target service link extraction according to a second prompt word constructed by the service function knowledge base and the travel service consultation information; and generating service consultation feedback information according to the target service text information and the target service link. According to the embodiment of the invention, the target service text information is generated through the business agent and the target service link is extracted through the travel service agent, so that the user can obtain and operate the required service in real time, and the recommendation accuracy of the traffic travel service and the service providing efficiency are remarkably improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and transportation technology, and in particular to a transportation service recommendation method, electronic device, and medium. Background Art

[0002] Traditional transportation service recommendation methods typically rely on rules engines to match service features with user needs. For example, in the transportation sector, if a user enters the keyword "recharge" on the app's homepage, the rules engine will recommend recharge-related function portals such as "Shenzhen Tong Card Recharge" and "Mobile Interconnect Card Recharge" to the user, allowing the user to independently select service functions based on their needs.

[0003] However, due to the client's extensive service capabilities, multiple services may be associated solely through keywords, and similar service names can lead to user confusion, increasing user operation time and resulting in low service matching efficiency. Therefore, improving the accuracy of transportation service recommendations and optimizing the efficiency of transportation service provision have become urgent issues to be addressed. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a transportation service recommendation method, electronic device and medium, aiming 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 an embodiment of the present application provides a method for recommending transportation services, which is applied to a server. The method includes: Receiving travel service consultation information sent by a client; wherein the travel service consultation information is obtained by the client; Based on the travel service consultation information, a pre-trained business agent searches for service knowledge from a pre-built travel service knowledge base to obtain target travel service knowledge, and the business agent constructs a first prompt based on the travel service consultation information and the target travel service knowledge; Instructing the business agent to generate service content according to the first prompt to obtain target service text information; constructing a second prompt based on a pre-built service function knowledge base and the travel service consultation information; Instructing the pre-trained travel service agent to extract a service link according to the second prompt to obtain a target service link; Generate service consultation feedback information according to the target service text information and the target service link; 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.

[0006] In some embodiments, instructing a pre-trained travel service agent to extract a service link according to the second prompt to obtain a target service link includes: Instructing the travel service agent to perform consultation intention recognition according to the second prompt to obtain a target consultation intention; Determine the target service name corresponding to the target consulting intention according to the target consulting intention; Filtering a target service function from among the reserve service functions in the service function knowledge base according to the target service name; wherein the service function knowledge base includes a plurality of reserve service entries corresponding to the reserve service functions; Extract a target service link from the reserve service entries corresponding to the target service function.

[0007] In some embodiments, the target service link includes an address information collection link and a device binding operation link, and extracting the target service link from the reserve service entry corresponding to the target service function further includes: If the target service function is a card type distribution type, determining a reserve service code corresponding to a physical card distribution type and a reserve service code corresponding to a virtual card distribution type from the reserve service entry; wherein the card type distribution type includes the physical card distribution type and the virtual card distribution type; extracting the address information collection link from the reserve service entry based on the reserve service code corresponding to the physical card distribution type; extracting the device binding operation link from the reserve service entry based on the reserve service code corresponding to the virtual card distribution type; Generating service consultation feedback information according to the target service text information and the target service link includes: Extracting physical card service text information and virtual card service text information from the target service text information; Generate physical card consultation feedback information based on the physical card service text information and the address information collection link; Generate virtual card consultation feedback information according to the virtual card service text information and the device binding operation link; The physical card consultation feedback information and the virtual card consultation feedback information are integrated to generate the service consultation feedback information.

[0008] In some embodiments, the target service link includes a common ride code link and a premium ride link, and extracting the target service link from the reserve service entry corresponding to the target service function further includes: If the target service function is a ride function type, determining a reserve service code corresponding to an ordinary car ride type and a reserve service code corresponding to a premium car ride type from the reserve service entries; wherein the ride function type includes the ordinary car ride type and the premium car ride type; Extracting the ordinary carriage code link from the reserve service entry based on the reserve service code corresponding to the ordinary carriage ride type; Extracting the preferred ride link from the reserved service entry based on the reserved service code corresponding to the preferred carriage ride type; Generating service consultation feedback information according to the target service text information and the target service link includes: extracting ordinary carriage service text information and premium carriage service text information from the target service text information; Generate ordinary carriage service consultation feedback information according to the ordinary carriage service text information and the ordinary carriage code link; Generate preferential ride consultation feedback information based on the preferential carriage service text information and the preferential ride link; The ordinary ride consultation feedback information and the premium ride consultation feedback information are integrated to generate the service consultation feedback information.

[0009] In some embodiments, the target service link includes a travel data collection link and an invoice issuance link, and extracting the target service link from the reserve service entry corresponding to the target service function further includes: If the target service function is a ride voucher service type, determining a reserve service code corresponding to a trip query type and a reserve service code corresponding to a ride invoice generation type from the reserve service entry; wherein the ride voucher service type includes the trip query type and the ride invoice generation type; extracting the travel data collection link from the reserve service entry based on the reserve service code corresponding to the travel query type; Extracting the invoice issuance link from the reserve service entry based on the reserve service code corresponding to the ride invoice generation type; Generating service consultation feedback information according to the target service text information and the target service link includes: extracting itinerary service text information and invoice service text information from the target service text information; Generate itinerary consultation feedback information based on the itinerary service text information and the itinerary data collection link; Generate invoice consultation feedback information based on the invoice service text information and the invoice issuance link; The itinerary consultation feedback information and the invoice consultation feedback information are integrated to generate the service consultation feedback information.

[0010] In some embodiments, constructing the first prompt by the business agent based on the travel service consultation information and the target travel service knowledge includes: Obtaining at least one response constraint requirement matching the travel service consultation information; The business agent generates a service content text based on the travel service consultation information and the target travel service knowledge to obtain first service content information; The business agent generates a constraint text based on at least one response constraint requirement to obtain agent response constraint information; The first service content information and the agent response constraint information are integrated to construct the first prompt.

[0011] In some embodiments, constructing the second prompt based on the pre-built service function knowledge base and the travel service consultation information includes: Obtain basic information of the travel service of the travel service consultation information; Performing intent analysis and constraint on the travel service consultation information to obtain intent constraint indication information; performing service quantity analysis and constraint on the travel service consultation information according to the service function knowledge base to obtain service quantity constraint information; A prompt is constructed for the travel service consultation information and the service function knowledge base according to the basic information of the travel service, the intention constraint indication information and the service quantity constraint information to obtain the second prompt.

[0012] To achieve the above-mentioned purpose, a second aspect of the embodiments of the present application proposes a method for recommending transportation services, which is applied to a client. The method includes: Obtain travel service consultation information from target users; The travel service consultation information is sent to a server, so that the server searches for service knowledge from a preset travel service knowledge base through a pre-trained business agent based on the travel service consultation information to obtain target travel service knowledge, and constructs a first prompt based on the travel service consultation information and the target travel service knowledge through the business agent; instructs the business agent to generate service content based on the first prompt to obtain target service text information; constructs a second prompt based on the pre-constructed service function knowledge base and the travel service consultation information, and instructs the pre-trained travel service agent to extract a service link based on the second prompt to obtain a target service link; and generates service consultation feedback information based on the target service text information and the target service link; receiving service consultation feedback information from the server in response to the travel service consultation information; A service feedback interface is generated based on the service consultation feedback information.

[0013] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0014] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method of the above-mentioned first aspect.

[0015] The present application proposes a method, electronic device, and medium for recommending transportation services. The method first receives transportation service consultation information sent by a client, and then uses a business agent to retrieve service knowledge from a transportation service knowledge base, thereby obtaining service knowledge related to the user's needs. This effectively resolves the confusion that users may encounter when faced with multiple similar services, thereby improving the accuracy of service matching. Secondly, the business agent constructs a first prompt based on the transportation service consultation information and the retrieved target service knowledge, thereby further refining the user's needs. The first prompt instructs the business agent to generate service content, thereby obtaining target service text information. This optimizes service provision efficiency and reduces the time cost of user operations. Furthermore, a second prompt is constructed based on the service function knowledge base and the transportation service consultation information, and the second prompt instructs a pre-trained transportation service agent to extract service links, thereby obtaining target service links. This ensures that users can quickly access the required service functions, further improving the efficiency of service recommendations. Finally, the server sends service consultation feedback information containing the target service text information and links to the client, which then generates an intuitive service feedback interface, enabling users to instantly access and operate the required services. This significantly improves the accuracy of transportation service recommendations and optimizes the efficiency of transportation service provision. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the transportation service recommendation method provided in an embodiment of the present application; Figure 2 yes Figure 1 Flowchart of step S102 in FIG. Figure 3 yes Figure 1 Flowchart of step S104 in FIG. Figure 4 yes Figure 1 Flowchart of step S105 in FIG. Figure 5 yes Figure 4 Flowchart of step S404 in FIG. Figure 6 yes Figure 4 Another flowchart of step S404 in FIG. Figure 7 yes Figure 4 Another flowchart of step S404 in FIG. Figure 8 is another flow chart of the method for recommending transportation services provided in an embodiment of the present application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0018] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0020] First, let’s analyze some of the terms used in this application: Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner 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 thinking. It also encompasses the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0021] The embodiments of the present application provide a transportation service recommendation method, electronic device, and medium, which aim to improve the accuracy of transportation service recommendations and optimize the efficiency of transportation service provision.

[0022] The embodiments of the present application provide a method for recommending transportation services, an electronic device, and a medium, which are specifically described through the following embodiments. First, the method for recommending transportation services in the embodiments of the present application is described.

[0023] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, 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 achieve optimal results.

[0024] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0025] The method for recommending transportation services provided in the embodiment of the present application relates to the field of artificial intelligence and transportation technology. The method for recommending transportation services provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the method for recommending transportation services, etc., but is not limited to the above forms.

[0026] The present application can be used in many general or special computer system environments or configurations. For example: 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, distributed computing environments including any of the above systems or devices, and the like. The present 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, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0027] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on user information, user operation behavior data or characteristic-related data, the user's permission or consent will be obtained first, and the collection, use and processing of such data will comply with relevant laws, regulations and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0028] Figure 1 This is an optional flow chart of the method for recommending transportation services provided in the embodiment of the present application, which is applied to the server. Figure 1 The method may include but is not limited to steps S101 to S107.

[0029] Step S101: receiving travel service consultation information sent by a client; wherein the travel service consultation information is obtained by the client.

[0030] In step S102, based on the travel service consultation information, the pre-trained business intelligence agent searches for service knowledge from a pre-built travel service knowledge base to obtain target travel service knowledge, and the business intelligence agent constructs a first prompt based on the travel service consultation information and the target travel service knowledge.

[0031] Step S103: instructing the business agent to generate service content according to the first prompt to obtain target service text information.

[0032] Step S104: construct a second prompt based on the pre-built service function knowledge base and travel service consultation information.

[0033] Step S105: Instruct the pre-trained travel service agent to extract service links according to the second prompt to obtain target service links.

[0034] Step S106: Generate service consultation feedback information based on the target service text information and the target service link.

[0035] Step S107: sending the service consultation feedback information to the client, so that the client generates a service feedback interface based on the service consultation feedback information.

[0036] In steps S101 to S107 shown in the embodiment of the present application, first, travel service consultation information sent by the client is received, and the server retrieves service knowledge from the travel service knowledge base through the business agent, thereby obtaining service knowledge related to the user's needs, effectively solving the confusion problem when the user is faced with multiple similar services, and helping to improve the accuracy of service matching; secondly, the business agent constructs a first prompt based on the travel service consultation information and the retrieved target service knowledge, which can further refine the user's needs, and instructs the business agent to generate service content according to the first prompt to obtain target service text information, thereby optimizing service provision efficiency and reducing the time cost of user operation; further, a second prompt is constructed based on the service function knowledge base and the travel service consultation information, and instructs the pre-trained travel service agent to extract service links according to the second prompt to obtain target service links, thereby ensuring that the user can quickly access the required service functions and further improving the efficiency of service recommendation; finally, the server sends service consultation feedback information containing the target service text information and links to the client, and the client generates an intuitive service feedback interface based on this, enabling the user to instantly obtain and operate the required services, significantly improving the recommendation accuracy and service provision efficiency of transportation services.

[0037] In step S101 of some embodiments, specifically, the client refers to a software application or interface through which a user interacts with travel services, typically an application installed on the user's device (such as a mobile phone APP) or a small program on a web page.

[0038] Specifically, travel service consultation information refers to text or voice information about transportation services sent by users to the server through the client. The travel service consultation information is used to represent the user's travel service demand information.

[0039] For example, when a user enters keywords such as "subway card recharge" or "subway route query" in an APP related to transportation, these keywords and their contextual information together constitute travel service consultation information.

[0040] Specifically, the client accesses the user's travel service inquiry information through a user interface (such as a text input box or voice input box) and sends this information to the server. If the user inputs voice information, the server's voice-to-text agent invokes the SenseVoice-Small model for speech recognition, returning the recognized text of the travel service inquiry information to the client.

[0041] In this embodiment, by receiving the travel service consultation information sent by the client, it is possible to initially understand the user's travel service needs, and provide basic data support for subsequent transportation travel service recommendations.

[0042] In step S102 of some embodiments, specifically, the pre-trained business intelligence agent is a pre-trained neural network model (such as a Transformer model), which is used to retrieve relevant service knowledge from a 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.

[0043] Specifically, the travel service knowledge base is a pre-designed database that stores relevant knowledge in the field of transportation. The travel service knowledge base includes but is not limited to basic information of enterprises related to transportation, transportation business service information (such as information on transportation card recharge service functions, transportation card processing service functions and ride service functions), and detailed answers to questions such as the processing rules and processes of transportation-related services. The information in the travel service knowledge base is presented in Markdown format. The travel service knowledge base is used to preliminarily respond to users' travel service consultation information.

[0044] Specifically, the target travel service knowledge refers to the transportation service information most relevant to the user's problem retrieved from the travel service knowledge base.

[0045] 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 knowledge items such as the conditions, materials, and procedures for applying for a student card.

[0046] Specifically, the business intelligence body can be used to perform word embedding processing on the travel service consultation information to extract the travel service consultation feature vector, and perform cosine similarity matching calculation on the travel service consultation feature vector and the travel service knowledge in the travel service knowledge base to obtain the consultation knowledge matching similarity. The consultation knowledge matching similarity is compared with the preset similarity threshold, and the travel service knowledge corresponding to the consultation knowledge matching similarity greater than the similarity threshold is determined as the target travel service knowledge.

[0047] 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, which can preliminarily acquire service knowledge related to user needs, effectively and preliminarily solve the confusion problem of users when facing multiple similar services, and help improve the accuracy of service matching.

[0048] See also Figure 2 In some embodiments, step S102 further includes but is not limited to steps S201 to S204: Step S201: Obtain at least one response constraint requirement matching the travel service consultation information.

[0049] In step S202 , the business agent generates a service content text based on the travel service consultation information and the target travel service knowledge to obtain first service content information.

[0050] Step S203: The business agent generates a constraint text based on at least one response constraint requirement to obtain agent response constraint information.

[0051] Step S204: Integrate the first service content information and the agent response constraint information to construct a first prompt.

[0052] In step S201 of some embodiments, specifically, the response constraint requirement refers to a condition that needs to be met when generating service content.

[0053] Specifically, at least one response constraint requirement that matches the travel service consultation information is obtained, including: when the travel service consultation information is a travel discount query type, a discount qualification query constraint is performed on the target user to obtain a discount query constraint requirement; when the travel service consultation information is a complaint type, emotion recognition is performed on the target user to obtain the target user's emotion, and an emotion reply constraint is performed based on the target user's emotion to obtain an emotion reply constraint requirement; when the travel service consultation information is a device compatibility type, a device detection constraint is performed on the target device to obtain a device detection constraint requirement.

[0054] For example, for travel service consultation information of the discount inquiry type, the discount query constraint requirements may include identifying whether the user is eligible for travel discounts (such as not meeting the student identity but asking about student card discounts), and directly outputting "Please enjoy travel discounts according to your actual identity". If the user is eligible for the discount, the discount range of different types of transportation cards and different payment methods will be informed to the user, and the timeliness of the discount activities will be emphasized, and the start and end dates of the activities will be indicated. For conditional transportation travel discounts (such as recharge discounts, transfer discounts), the applicable travel scenarios and restrictions will be listed. For travel service consultation information of the complaint type, the emotional response constraint requirements may include directly outputting "I am sorry to have caused you an unpleasant experience" if the user uses extreme words to make a complaint. We will handle your problem seriously", record the specific content of the user's complaint and related travel service information, ensure subsequent traceability, and provide estimated processing time and feedback channels to let users know the progress of problem solving; for travel service consultation information of device compatibility type, the device detection constraint requirements can include if the user's device model is too old to support the service function, then directly output "Your device may not be able to use this function due to hardware limitations. It is recommended to upgrade the device or try other alternatives", and list the operating system versions and device models that support the service function; if the user's travel consultation service information contains illegal and unauthorized content, then directly output "Let's change the topic" and do not output any other content to ensure the compliance of the consultation.

[0055] In step S202 of some embodiments, specifically, the first service content information refers to a preliminary service description text generated based on the travel service consultation information and the target travel service knowledge.

[0056] 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], and the target travel service knowledge retrieved from the travel service knowledge base: [Applicable people for applying for student cards, required materials, application channels, and other student card application service knowledge].

[0057] In this embodiment, the business intelligence body generates service content text based on travel service consultation information and target travel service knowledge to obtain first service content information, provide preliminary service suggestions for user service needs, and provide service suggestion data support for the subsequent first prompt construction.

[0058] In step S203 of some embodiments, specifically, the intelligent agent response constraint information refers to supplementary text generated according to the constraint requirements, which is used to ensure that the final service content meets the constraint conditions. The intelligent agent response constraint information includes but is not limited to preferential query constraint requirements, emotional response constraint requirements, equipment detection constraint requirements and compliance constraint requirements, etc.

[0059] For example, when generating service content, if the constraint requirement is to respond emotionally to the user's impatience, the agent's response constraint information can be "I understand that you are not in a good mood now, let's change the topic to something lighter", and no other content will be output.

[0060] In this embodiment, the business intelligent agent generates constraint text based on at least one response constraint requirement to obtain intelligent agent response constraint information, further optimizing the expression of service content, ensuring that the generated service content meets the actual needs of users, and avoiding situations where violations or inappropriate content may occur.

[0061] In step S204 of some embodiments, specifically, the first prompt refers to prompt information generated by integrating the first service content information and the agent response constraint information.

[0062] For example, in the subway travel scenario, if the agent's response constraint information is a compliance constraint requirement and a friendly greeting emotion requirement, then for the consultation information on how to apply for a student card for transportation, the corresponding first prompt can be: "Target travel service knowledge: {travel service knowledge base search.data}; travel service consultation information: {start.question}; Agent response constraint information: If the user's question (i.e., travel service consultation information) contains illegal or irregular content, then directly output "Let's change the topic" without outputting any other content; If the user's question is a complaint type about travel services, and contains negative content such as impatience and anxiety, then the ... If the user's question is about transportation discounts, the query constraint is to identify whether the user is eligible for travel discounts. If the user is not eligible, the output is "Please enjoy travel discounts according to your actual identity." If the user is eligible, the user will be informed of the discount ranges for different transportation cards and payment methods, the timeliness of the discount activities, the applicable travel scenarios and restrictions; use "you" to refer to the user in the question reply; the answer style must be clear and friendly."

[0063] Through steps S201 to S204, the user's needs can be further refined, and the user input can be rewritten into prompts that the business intelligence agent can understand, thereby improving the accuracy of understanding the user's needs, so as to subsequently improve the efficiency of providing transportation services.

[0064] In step S103 of some embodiments, specifically, the target service text information refers to a service content description that meets user needs and is generated based on the first prompt.

[0065] For example, if the travel service consultation information is "How to apply for a student card", the business agent can generate the target service text information based on the user needs in the travel service consultation information and the first prompt: "Hello, the steps to apply for a student transportation card are as follows: 1. Applicable groups: All students currently enrolled in primary and secondary schools (including high schools) and secondary vocational schools can apply for the application.

[0066] II. Required materials: The student’s original identification document (ID card, household registration booklet or passport, etc.); for students under the age of 15, a guardian must apply on their behalf and provide the guardian’s original identification document.

[0067] 3. Application channels: For special-shaped student transportation cards: they can be processed through transportation-related apps, transportation-self-operated customer service outlets, transportation-self-operated business halls and post offices; for standard transportation cards: they can be processed through transportation-related apps, transportation-self-operated customer service outlets, transportation micro-customer service terminals, transportation-self-operated business halls and post offices; for watch transportation student cards: they can be processed through transportation-self-operated customer service outlets, transportation apps, transportation-self-operated business halls and transportation card sales and recharge self-service terminals at subway stations.

[0068] 4. Warm reminder: When applying at the Transportation Travel Micro Customer Service Terminal, you must bring the original student ID card, student ID card or proof of attendance. Students under the age of 15 must apply through their guardian and must also bring the original guardian ID card. If you apply for a student card through Transportation Travel's own customer service outlets, Transportation Travel App, or Transportation Travel card vending and recharging machines, the student card will be delivered by China Unicom.

[0069] I hope this information is helpful to you! If you have any other questions, please feel free to ask."

[0070] See also Figure 3 In some embodiments, step S104 includes but is not limited to steps S301 to S304: Step S301: construct a second prompt based on a pre-built service function knowledge base and travel service consultation information.

[0071] Step S302: performing intent analysis and constraint on the travel service consultation information to obtain intent constraint indication information.

[0072] Step S303 : performing service quantity analysis and constraint on the travel service consultation information according to the service function knowledge base to obtain service quantity constraint information.

[0073] Step S304 : constructing a prompt for the travel service consultation information and the service function knowledge base according to the basic information of the travel service, the intention constraint indication information, and the service quantity constraint information to obtain a second prompt.

[0074] In step S301 of some embodiments, specifically, the basic information of travel services refers to the background information of the user when using travel services such as a transportation APP or a physical transportation card, including but not limited to the usage rules of the transportation APP account balance and the physical card balance (such as being able to swipe the boarding code to board the bus and deducting the fee from the transportation APP account, and the APP account balance and the user's physical card balance are not interoperable, and the user can only choose to recharge from the APP account balance to the physical card balance when recharging through NFC card sticking), recharge method, card type (such as ordinary physical card, student card, mobile phone interoperability card) and card function (such as card boarding, recharge, interconnection range, etc.).

[0075] In step S302 of some embodiments, the intent constraint indication information specifically refers to guidance information generated based on the user's intent and constraints when parsing the travel service inquiry information, which is 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 the constraints "the user intends to apply for a student card" and "the user must meet student status."

[0076] In step S303 of some embodiments, the service function knowledge base is a pre-designed repository that stores information related to all client travel services in the field of transportation. The service function knowledge base includes, but is not limited to, travel service names, travel service descriptions, travel service links, and travel service codes. The information in the service function knowledge base is organized in Markdown format to form a client service list.

[0077] For example, the service name in the client service list can be Student Card, and the service description can be "applying for, binding, reporting loss, reissuing, and extending student cards, viewing and obtaining the school 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.

[0078] Specifically, the service quantity constraint information refers to the constraint conditions obtained after analyzing the travel service consultation information input by the user according to the service function knowledge base, which is used to limit the number of recommended services.

[0079] For example, given a known client service list, we try to determine which functions in the instruction list are most likely to satisfy the user's intent based on this list, and use the user's intent to determine the corresponding "service name" and "service code". In the process of analyzing the number of services, we strictly follow the known client service list information and discuss them by category: if two possible service functions can be found, we determine them as these two; if only one possible service function can be found, we determine it as this one; if all functions in the list cannot directly satisfy the user's intent, we only output [], and the final output format is json:[{"text":"xxx","value":"yyy"}], where xxx is the determined "service name" and yyy is the determined "service code". The service name and service code correspond one to one. If two functions are both possible, they are represented as two objects, and the output can only contain two objects at most.

[0080] In step S304 of some embodiments, specifically, the second prompt refers to the prompt information generated by integrating the basic information of the travel service, the intention constraint indication information and the service quantity constraint information with the travel service consultation information and the service function knowledge base, and is used to indicate the extraction service link of the travel service intelligent body.

[0081] For example, in the subway travel scenario, for information on how to apply for a student card for transportation, the corresponding second prompt can be: "Basic information on travel services: {Usage rules for the balance of the transportation APP account and the balance of the physical card, recharge methods, card types (such as ordinary physical cards, student cards, mobile phone intercommunication cards) and card functions (such as card boarding, recharge, interconnection scope, etc.}; Intent constraint indication information: {Client service list retrieval.data}; Service quantity constraint information: If two possible service functions can be found, then these two will be determined; if only one possible service function can be found, then this one will be determined; if all functions in the list cannot directly meet the user's intention, only [] will be output, and the final output format will be json:[{"text":"xxx","value":"yyy"}]".

[0082] Through steps S301 to S304, the user's needs can be accurately identified and service recommendations that meet the user's intentions can be generated. By reasonably controlling the number of recommendations, the accuracy of transportation service recommendations is further improved, thereby improving the efficiency of providing transportation services.

[0083] See also Figure 4 In some embodiments, step S105 includes but is not limited to steps S401 to S404: Step S401: Instruct the travel service agent to identify the consultation intention according to the second prompt to obtain the target consultation intention.

[0084] Step S402: determining the target service name corresponding to the target consultation intention according to the target consultation intention.

[0085] Step S403 , screening 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 a plurality of reserve service entries corresponding to the reserve service functions.

[0086] Step S404: extract the target service link from the reserve service entries corresponding to the target service function.

[0087] In step S401 of some embodiments, specifically, the travel service agent is a pre-trained large model (such as deepseekV3-671B), which is used to match the client service list content to extract the service link corresponding to the consultation intent of the travel service consultation information.

[0088] Specifically, target consultation intention refers to the consultation demand or consultation purpose of travel service consultation information.

[0089] For example, in a transportation APP, if the travel service consultation information is "How to apply for a student card", the target consultation intention is "Apply for a student card".

[0090] In step S402 of some embodiments, specifically, the target service name refers to the name of the transportation service corresponding to the target consultation intention.

[0091] Furthermore, the service function knowledge base includes a plurality of reserve service entries corresponding to the reserve service functions, and each reserve service entry includes a reserve service code, a reserve service name, and a reserve service link.

[0092] For example, in a transportation APP, if the target consultation intention is to "apply for a student card", the target service name "student card application" can be extracted from the reserve service entry.

[0093] In step S403 of some embodiments, specifically, the target service function refers to a specific service function that matches the target service name.

[0094] For example, if the target service name is "student card application", the corresponding reserve service entries (such as "online student card application", "inquiry on application progress", "view required materials", etc.) are searched in the service function knowledge base, and the target service function that best meets the needs is selected as "online student card application" based on the user's consultation intention.

[0095] See also Figure 5In some embodiments, the target service link includes an address information collection link and a device binding operation link. Step S404 includes but is not limited to steps S501 to S507: Step S501: If the target service function is a card type distribution type, the reserve service code corresponding to the physical card distribution type and the reserve service code corresponding to the virtual card distribution type are determined from the reserve service entries; wherein the card type distribution type includes the physical card distribution type and the virtual card distribution type.

[0096] Step S502 : extracting an address information collection link from a reserve service entry based on the reserve service code corresponding to the physical card distribution type.

[0097] Step S503 : extracting a device binding operation link from the reserve service entry based on the reserve service code corresponding to the virtual card distribution type.

[0098] In step S106, service consultation feedback information is generated according to the target service text information and the target service link, including: Step S504, extracting physical card service text information and virtual card service text information from the target service text information; Step S505: Generate physical card consultation feedback information based on the physical card service text information and address information collection link; Step S506: Generate virtual card consultation feedback information based on the virtual card service text information and the device binding operation link; Step S507: Integrate the physical card consultation feedback information and the virtual card consultation feedback information to generate service consultation feedback information.

[0099] In step S501 of some embodiments, specifically, the card distribution type refers to the card distribution method consulted in the travel service consultation information, including a physical card distribution type and a virtual card distribution type.

[0100] For example, in a transportation app, users need to apply for a physical card or virtual card (such as a mobile phone intercommunication card) for transportation.

[0101] Specifically, the reserve service code is a unique identification code assigned to each service function in the service function knowledge base, which is used to quickly locate and extract specific service function information.

[0102] For example, if the user needs to apply for a physical card for transportation, the reserve service code assigned to the physical card is determined to be "101" from the reserve service item. If the user needs to apply for a virtual card for transportation, the reserve service code assigned to the virtual card can be "102".

[0103] In step S502 of some embodiments, specifically, the address information collection link is a web page or in-application link used to guide the user to complete filling in the address information during the physical card distribution process, and the link can be expressed as a pop-up control.

[0104] For example, when a user applies for a student card, he or she needs to provide a mailing address. The reserve service code 101 can be used to extract the address information collection pop-up control from the reserve service entry. The user can fill in the address information after clicking the pop-up control.

[0105] In step S503 of some embodiments, the device binding operation link refers to a link that the user needs to bind the device to when applying for a virtual card, and the link can be a pop-up window control.

[0106] For example, when a user applies for a mobile phone intercommunication card, he needs to bind a mobile phone device. Based on the reserve service code "102" corresponding to the virtual card issuance type, the device binding operation pop-up control can be extracted from the reserve service entry. The user can complete the device binding operation after clicking the pop-up control.

[0107] In step S504 of some embodiments, specifically, the physical card service text information refers to a detailed service description text related to the physical card service and link usage.

[0108] Specifically, the virtual card service text information refers to the detailed service description text related to the virtual card.

[0109] For example, the physical card service text information may include the steps for applying for a physical card, the required materials, and the use of the application location and address information collection pop-up control (such as please click the address collection button to fill in the address information based on the button pop-up window); the virtual card service text information may include the steps for applying for a virtual card, supported device types, binding operations, and device binding operation pop-up control (such as please click the device binding button to fill in device binding related information based on the button pop-up window).

[0110] 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, required materials, application location, address information collection link, and link usage description.

[0111] 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 issuance type inquired 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.

[0112] In step S507 of some embodiments, specifically, the service consultation feedback information refers to the card type distribution consultation feedback information generated by integrating the physical card consultation feedback information and the virtual card consultation feedback information.

[0113] Through steps S501 to S507, by identifying the card type and issuing type according to the user's inquiry content and extracting the service link and service text information corresponding to the card type and issuing type, it can not only provide users with detailed and accurate service operation guides, effectively solve the confusion problem of users when facing multiple similar services, help improve the accuracy of service matching, but also help improve the speed at which users find the required card type and issuing services, so as to reduce user operation time and ensure that users can quickly access the required service functions, thereby improving the efficiency of transportation service provision.

[0114] See also Figure 6 In some embodiments, the target service link includes a common ride code link and a premium ride code link. Step S404 further includes, but is not limited to, steps S601 to S607: Step S601: If the target service function is a ride function type, the reserve service code corresponding to the ordinary car ride type and the reserve service code corresponding to the premium car ride type are determined from the reserve service entries; wherein the ride function type includes the ordinary car ride type and the premium car ride type.

[0115] Step S602: extracting an ordinary carriage code link from the reserve service entry based on the reserve service code corresponding to the ordinary carriage carriage type.

[0116] Step S603: extracting a preferential ride link from the reserve service entry based on the reserve service code corresponding to the preferential carriage ride type.

[0117] In step S106, service consultation feedback information is generated according to the target service text information and the target service link, which also includes: Step S604: extracting ordinary carriage service text information and premium carriage service text information from the target service text information.

[0118] Step S605: Generate ordinary carriage consultation feedback information based on the ordinary carriage service text information and the ordinary carriage code link.

[0119] Step S606: Generate premium ride consultation feedback information based on the premium carriage service text information and the premium ride link.

[0120] Step S607: Integrate the ordinary ride consultation feedback information and the premium ride consultation feedback information to generate service consultation feedback information.

[0121] In step S601 of some embodiments, specifically, the ride function type refers to the ride mode inquired in the travel service consultation information, including ordinary car ride type and premium car ride type.

[0122] For example, in the subway travel scenario, if the user is riding in an ordinary car, he or she needs to use the ordinary car boarding code. If the user needs to ride in a premium car, he or she can purchase a premium car ticket on the transportation APP to generate a premium car boarding code and enjoy priority access and premium services (such as free Internet, etc.).

[0123] Specifically, the reserve service code is a unique identification code assigned to each service function in the service function knowledge base, which is used to quickly locate and extract specific service function information.

[0124] For example, if the user needs to use the ordinary car boarding code, the reserve service code corresponding to the ordinary car boarding type is determined from the reserve service item to be "201". If the user needs to use the premium car boarding rights, the reserve service code corresponding to the premium car boarding type can be "202".

[0125] In step S602 of some embodiments, specifically, the ordinary boarding code link is a link used to guide users to use the ordinary car boarding code, and the link can be expressed as a button control.

[0126] For example, when a user uses the ordinary carriage boarding code, after clicking the "Use ordinary boarding code" button, the system extracts the ordinary boarding code link from the reserve service entry through the reserve service code "201", and the user can directly use the boarding code after clicking the button.

[0127] In step S603 of some embodiments, specifically, the premium ride link refers to a link that the user needs to click when riding in a premium carriage, and the link can be a button control.

[0128] For example, when a user uses the boarding code for a premium car or uses the premium riding rights, after clicking the "Use Premium Ride" button, the premium ride link will be extracted from the reserve service entry based on the reserve service code "202" corresponding to the premium car ride type. After clicking the button, the user can view and use the premium ride code and premium ride rights.

[0129] In step S604 of some embodiments, specifically, the ordinary car service text information refers to a detailed service description text related to ordinary car riding service and link usage.

[0130] Specifically, the premium car service text information refers to the detailed service description text related to the premium car ride service and link usage.

[0131] For example, the text information of ordinary car services may include the usage description, scope of application, and usage of ordinary car code links for ordinary car codes; the text information of premium car services may include the usage description, supported car types, and usage of premium car code links for premium car codes or redemption of travel rights.

[0132] In step S605 of some embodiments, specifically, the ordinary ride consultation feedback information refers to the service content and service link usage information generated based on the ordinary car ride type inquired by the user. The ordinary ride consultation feedback information may include but is not limited to the specific steps of using the ordinary ride code, ride rules, ordinary ride code link and link usage description.

[0133] For example, the feedback information for ordinary ride consultation may be that the specific steps for using the ordinary ride code are to open the transportation APP, and click the ordinary ride code button to obtain the ordinary ride code, and then align the ride code with the gate scanning area to complete the ride.

[0134] In step S606 of some embodiments, specifically, the preferential ride consultation feedback information refers to the service content and service link usage information generated based on the preferential car ride type inquired by the user. The preferential ride consultation feedback information may include but is not limited to the specific steps for enjoying the preferential car ride rights and obtaining the preferential car ride code, supported payment methods, preferential ride links and link usage descriptions.

[0135] For example, the text information of the premium carriage service may be that the specific steps to enjoy the premium carriage ride rights are to open the transportation APP, click the premium ride code button on the homepage, select the payment method and complete the payment to obtain the premium ride code, and please click the premium ride code button to obtain the premium carriage ride code; if the user needs to know about the premium carriage rights, then click the premium rights button on the homepage to obtain priority access and other rights information.

[0136] In step S607 of some embodiments, specifically, the service consultation feedback information refers to the ride consultation feedback information generated by integrating the ordinary ride consultation feedback information and the premium ride consultation feedback information. The service consultation feedback information provides the user with a complete ride guide.

[0137] For example, the service consultation feedback information can be "Hello! According to your inquiry, the following is relevant information about riding in ordinary cars and premium cars: For riding in ordinary cars, please use the specific steps of the ordinary boarding code to open the transportation travel APP, and click the ordinary boarding code button to obtain the ordinary boarding code, and align the boarding code with the gate scanning area to complete the boarding. I hope the above information is helpful to you. If you have other questions, please feel free to consult."

[0138] Through steps S601 to S607, by identifying the type of ride function based on the user's inquiry content and extracting the service link and service text information corresponding to the ride function type, a detailed and accurate ride operation guide can be provided to the user, so that the user can directly obtain the ride code when using the ordinary car ride code, and can directly bind the relevant rights when enjoying the premium car ride rights, reducing the time the user spends on searching and operating in the client, thereby improving the efficiency of transportation service provision.

[0139] See also Figure 7 In some embodiments, the target service link includes a travel data collection link and an invoice issuance link. Step S404 further includes but is not limited to steps S701 to 707: Step S701: If the target service function is a ride voucher service type, the reserve service code corresponding to the itinerary query type and the reserve service code corresponding to the ride invoice generation type are determined from the reserve service entries; wherein the ride voucher service type includes the itinerary query type and the ride invoice generation type.

[0140] Step S702 : extracting a travel data collection link from a reserve service entry based on the reserve service code corresponding to the travel query type.

[0141] Step S703: extracting an invoice issuance link from the reserve service entry based on the reserve service code corresponding to the ride invoice generation type.

[0142] In step S106, service consultation feedback information is generated according to the target service text information and the target service link, which also includes: Step S704: extracting the itinerary service text information and the invoice service text information from the target service text information.

[0143] Step S705: Generate itinerary consultation feedback information based on the itinerary service text information and the itinerary data collection link.

[0144] Step S706: Generate invoice consultation feedback information based on the invoice service text information and the invoice issuance link.

[0145] Step S707: Integrate the itinerary consultation feedback information and the invoice consultation feedback information to generate service consultation feedback information.

[0146] In step S701 of some embodiments, specifically, the ride voucher service type refers to the ride voucher-related service consulted in the travel service consultation information, including the itinerary query type and the ride invoice generation type.

[0147] Specifically, the reserve service code is a unique identification code assigned to each service function in the service function knowledge base, which is used to quickly locate and extract specific service function information.

[0148] For example, if the user needs to query travel data, the reserve service code corresponding to the travel query type is determined from the reserve service entry to be "301". If the user needs to issue a fare invoice, the reserve service code corresponding to the fare invoice generation type can be "302".

[0149] In step S702 of some embodiments, specifically, the travel data collection link is a link for guiding the user to complete travel data collection, and the link may be expressed as a button control.

[0150] For example, when a user queries travel data, he or she can extract a travel query button from the reserve service entry through the reserve service code "301". After clicking the travel query button, the user can directly query the travel data of the transportation trip.

[0151] In step S703 of some embodiments, specifically, the invoice issuance link refers to a link that the user needs to click when issuing a ride invoice, and the link can be a button control.

[0152] For example, when a user issues a bus invoice, he or she can extract the invoice issuance button from the reserve service entry based on the reserve service code "302" corresponding to the bus invoice generation type. The user can complete the invoice issuance operation by clicking the invoice issuance button.

[0153] In step S704 of some embodiments, specifically, the itinerary service text information refers to a detailed service description text related to the itinerary query service and link usage. The itinerary service text information may include information such as the steps for querying itinerary data, the scope of application, and the use of the itinerary data collection link.

[0154] Specifically, the invoice service text information refers to the detailed service description text related to the invoice issuance service and link usage. The invoice service text information may include information such as the steps for issuing invoices, supported invoice types, binding operations, and the usage of invoice issuance links.

[0155] 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.

[0156] For example, the itinerary inquiry feedback information may be that the specific steps for querying itinerary data are to open the transportation APP, click the itinerary query button on the homepage, and enter the itinerary information (such as date, starting station and destination station) to query your itinerary records.

[0157] 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 ride invoice generation inquired by the user. The invoice consultation feedback information may include specific steps for issuing invoices, supported invoice types, binding operations, invoice issuance links, and link usage descriptions.

[0158] For example, the invoice consultation feedback information may be that the specific steps for issuing a ride invoice are to open the transportation APP and click the invoice issuance button on the homepage to 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.

[0159] In step S707 of some embodiments, the service consultation feedback information specifically refers to the ride voucher service consultation feedback information generated by integrating the itinerary consultation feedback information and the invoice consultation feedback information. The service consultation feedback information provides the user with a complete ride voucher service guide.

[0160] For example, a service inquiry feedback message might read: Hello! Based on your inquiry, here's information regarding itinerary inquiries and invoice issuance: To inquire about your itinerary, you can open the Transportation app, tap the Inquiry button on the homepage, and enter your itinerary information (such as date, starting and ending stations) to view your itinerary history. To issue an invoice, you can open the Transportation app, tap the Issue Invoice button on the homepage, select the invoice type (e-invoice or paper invoice), fill in the invoice information (such as the 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.

[0161] Through steps S701 to S707, the needs for itinerary inquiry and invoice issuance are identified according to the user's inquiry content, and the corresponding ride voucher service link and service text information are extracted. This not only provides the user with a detailed and accurate ride voucher service operation guide, thereby improving the accuracy of service matching, but also helps to increase the speed at which users find the required ride voucher services, thereby reducing user operation time and ensuring that users can quickly access the required ride voucher service functions, thereby improving the efficiency of transportation service provision.

[0162] Through steps S401 to S404, by identifying consultation intentions, determining target service names, filtering target service functions, and extracting target service links, it is possible to accurately identify user needs and provide service links that meet user needs, thereby improving the accuracy of transportation service recommendations. By directly providing service links, it reduces the number of user operation steps, thereby improving the efficiency of transportation service provision.

[0163] 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 a transportation mini-program), and after the client receives the service consultation feedback information, a service feedback interface is generated 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.

[0164] In this example, by sending service consultation feedback information to the client, so that the client generates a service feedback interface based on the service consultation feedback information, it not only ensures that the user can clearly understand how to complete the required operations, but also reduces the time cost of users jumping between different pages or applications by directly generating the feedback interface on the client, thereby further improving the efficiency of transportation service provision.

[0165] The embodiment of the present application first receives travel service consultation information sent by the client, and the server retrieves service knowledge from the travel service knowledge base through the business intelligence agent, which can obtain service knowledge related to the user's needs, effectively solve the confusion problem when the user is faced with multiple similar services, and help improve the accuracy of service matching; secondly, the business intelligence agent constructs a first prompt based on the travel service consultation information and the retrieved target service knowledge, which can further refine the user's needs, and instructs the business intelligence agent to generate service content according to the first prompt to obtain target service text information, which can optimize service provision efficiency and reduce the time cost of user operation; further, based on the service function knowledge base and travel service consultation information, a second prompt is constructed, and according to the second prompt, the pre-trained travel service intelligence agent is instructed to extract service links to obtain target service links, which can ensure that the user can quickly access the required service functions and further improve the efficiency of service recommendation; finally, the server sends the service consultation feedback information containing the target service text information and links to the client, and the client generates an intuitive service feedback interface based on this, so that the user can instantly obtain and operate the required services, significantly improving the recommendation accuracy and service provision efficiency of transportation services.

[0166] See also Figure 8 The embodiment of the present application further provides a method for recommending a transportation service, which is applied to a client and can implement the above-mentioned method for recommending a transportation service. The method may include steps S801 to S804: Step S801: Obtain travel service consultation information of the target user.

[0167] Step S802, the travel service consultation information is sent to the server, so that the server searches for service knowledge from a preset travel service knowledge base through a pre-trained business intelligent body according to the travel service consultation information, obtains the 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 intelligent body; instructs the business intelligent body to generate service content according to the first prompt, and obtains the target service text information; constructs a second prompt according to the pre-constructed service function knowledge base and the travel service consultation information, and instructs the pre-trained travel service intelligent body to extract the service link according to the second prompt, and obtains the target service link; generates service consultation feedback information according to the target service text information and the target service link.

[0168] Step S803: receiving service consultation feedback information from the server in response to the travel service consultation information.

[0169] Step S804: Generate a service feedback interface based on the service consultation feedback information.

[0170] The specific implementation of the transportation service recommendation method applied to the client is basically the same as the specific embodiment of the transportation service recommendation method applied to the server, and will not be repeated here.

[0171] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the aforementioned transportation service recommendation method. The electronic device can be any smart terminal, such as a tablet computer or an in-vehicle computer.

[0172] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes: The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an 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 the present application. The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the processing system and other applications. 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 is called by the processor 901 to execute the transportation service recommendation method of the embodiments of this application. Input / output interface 903, used to implement information input and output; Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.); Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 ); The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0173] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned transportation service recommendation method.

[0174] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0175] The embodiments described in the embodiments of this application are intended to more clearly illustrate 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. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0176] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

Claims

1. A method for recommending transportation services, characterized in that: Applied to a server, the method includes: Receiving travel service consultation information sent by a client; wherein the travel service consultation information is obtained by the client; Based on the travel service consultation information, a pre-trained business agent searches for service knowledge from a pre-built travel service knowledge base to obtain target travel service knowledge, and the business agent constructs a first prompt based on the travel service consultation information and the target travel service knowledge; Instructing the business agent to generate service content according to the first prompt to obtain target service text information; constructing a second prompt based on a pre-built service function knowledge base and the travel service consultation information; Instructing the pre-trained travel service agent to extract a service link according to the second prompt to obtain a target service link; Generate service consultation feedback information according to the target service text information and the target service link; 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.

2. The method according to claim 1, characterized in that The step of instructing the pre-trained travel service agent to extract a service link according to the second prompt to obtain a target service link includes: Instructing the travel service agent to perform consultation intention recognition according to the second prompt to obtain a target consultation intention; Determine the target service name corresponding to the target consulting intention according to the target consulting intention; Filtering a target service function from among the reserve service functions in the service function knowledge base according to the target service name; wherein the service function knowledge base includes a plurality of reserve service entries corresponding to the reserve service functions; Extract a target service link from the reserve service entries corresponding to the target service function.

3. The method according to claim 2, characterized in that The target service link includes an address information collection link and a device binding operation link, and extracting the target service link from the reserve service entry corresponding to the target service function further includes: If the target service function is a card type distribution type, determining a reserve service code corresponding to a physical card distribution type and a reserve service code corresponding to a virtual card distribution type from the reserve service entry; wherein the card type distribution type includes the physical card distribution type and the virtual card distribution type; extracting the address information collection link from the reserve service entry based on the reserve service code corresponding to the physical card distribution type; extracting the device binding operation link from the reserve service entry based on the reserve service code corresponding to the virtual card distribution type; Generating service consultation feedback information according to the target service text information and the target service link includes: Extracting physical card service text information and virtual card service text information from the target service text information; Generate physical card consultation feedback information based on the physical card service text information and the address information collection link; Generate virtual card consultation feedback information according to the virtual card service text information and the device binding operation link; The physical card consultation feedback information and the virtual card consultation feedback information are integrated to generate the service consultation feedback information.

4. The method according to claim 2, characterized in that The target service link includes a common ride code link and a premium ride link, and extracting the target service link from the reserve service entry corresponding to the target service function further includes: If the target service function is a ride function type, determining a reserve service code corresponding to an ordinary car ride type and a reserve service code corresponding to a premium car ride type from the reserve service entries; wherein the ride function type includes the ordinary car ride type and the premium car ride type; Extracting the ordinary carriage code link from the reserve service entry based on the reserve service code corresponding to the ordinary carriage ride type; Extracting the preferred ride link from the reserved service entry based on the reserved service code corresponding to the preferred carriage ride type; Generating service consultation feedback information according to the target service text information and the target service link includes: extracting ordinary carriage service text information and premium carriage service text information from the target service text information; Generate ordinary carriage service consultation feedback information according to the ordinary carriage service text information and the ordinary carriage code link; Generate preferential ride consultation feedback information based on the preferential carriage service text information and the preferential ride link; The ordinary ride consultation feedback information and the premium ride consultation feedback information are integrated to generate the service consultation feedback information.

5. The method according to claim 2, characterized in that The target service link includes a travel data collection link and an invoice issuance link. The step of extracting the target service link from the reserve service items corresponding to the target service function further includes: If the target service function is a ride voucher service type, determining a reserve service code corresponding to a trip query type and a reserve service code corresponding to a ride invoice generation type from the reserve service entry; wherein the ride voucher service type includes the trip query type and the ride invoice generation type; extracting the travel data collection link from the reserve service entry based on the reserve service code corresponding to the travel query type; Extracting the invoice issuance link from the reserve service entry based on the reserve service code corresponding to the ride invoice generation type; Generating service consultation feedback information according to the target service text information and the target service link includes: extracting itinerary service text information and invoice service text information from the target service text information; Generate itinerary consultation feedback information based on the itinerary service text information and the itinerary data collection link; Generate invoice consultation feedback information based on the invoice service text information and the invoice issuance link; The itinerary consultation feedback information and the invoice consultation feedback information are integrated to generate the service consultation feedback information.

6. The method according to claim 1, wherein The constructing of a first prompt by the business agent according to the travel service consultation information and the target travel service knowledge includes: Obtaining at least one response constraint requirement matching the travel service consultation information; The business agent generates a service content text based on the travel service consultation information and the target travel service knowledge to obtain first service content information; The business agent generates a constraint text based on at least one response constraint requirement to obtain agent response constraint information; The first service content information and the agent response constraint information are integrated to construct the first prompt.

7. The method according to claim 1, characterized in that The constructing of the second prompt according to the pre-built service function knowledge base and the travel service consultation information includes: Obtain basic information of the travel service of the travel service consultation information; Performing intent analysis and constraint on the travel service consultation information to obtain intent constraint indication information; performing service quantity analysis and constraint on the travel service consultation information according to the service function knowledge base to obtain service quantity constraint information; A prompt is constructed for the travel service consultation information and the service function knowledge base according to the basic information of the travel service, the intention constraint indication information and the service quantity constraint information to obtain the second prompt.

8. A method for recommending transportation services, characterized in that: Applied to a client, the method includes: Obtain travel service consultation information from target users; The travel service consultation information is sent to a server, so that the server searches for service knowledge from a preset travel service knowledge base through a pre-trained business agent based on the travel service consultation information to obtain target travel service knowledge, and constructs a first prompt based on the travel service consultation information and the target travel service knowledge through the business agent; instructs the business agent to generate service content based on the first prompt to obtain target service text information; constructs a second prompt based on the pre-constructed service function knowledge base and the travel service consultation information, and instructs the pre-trained travel service agent to extract a service link based on the second prompt to obtain a target service link; and generates service consultation feedback information based on the target service text information and the target service link; receiving service consultation feedback information from the server in response to the travel service consultation information; A service feedback interface is generated based on the service consultation feedback information.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the transportation service recommendation method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for recommending transportation services according to any one of claims 1 to 7 is implemented.

Images