Information Interaction Method, Apparatus, Device, and Storage Medium

Abstract

The present application discloses an information interaction method, apparatus, device and storage medium, relating to the field of Internet technology. The method includes: when providing a target service for a terminal, obtaining an interaction statement of the terminal in the i-th round of conversation, where i is an integer greater than 1; determining a target service node corresponding to the interaction statement among a plurality of service nodes included in the service flow of the target service, each service node of the service flow is used to obtain elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation; determining a target interaction statement based on a plurality of interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node, and sending the target interaction statement to the terminal. In the above solution, by leveraging the orderliness of the service flow, the target service node is quickly located, and the historical conversation is combined to accurately determine the target interaction statement, thereby improving the information interaction efficiency.

Description

Technical Field

[0001] This application relates to the field of Internet technologies, and particularly to an information interaction method, apparatus, device, and storage medium. Background Art

[0002] With the development of Internet technologies, how to provide services for users (such as telecommunications services, legal services, or health services, etc.) in an online information interaction manner has become an urgent problem to be solved.

[0003] In related technologies, online services generally provide online customer service. Users input questions, and the online customer service searches for the corresponding answers to the questions and then returns the answers for the users to view. Among them, the online customer service determines the answers based on a large amount of information related to the service stored in the knowledge base.

[0004] In the above technologies, since there is a large amount of information involved in the service and the questions raised by different users in the information interaction process are quite different, the questions are relatively scattered. In this case, the online customer service needs to determine the answers related to the questions one by one from the large amount of information stored in the knowledge base, so the information interaction efficiency is relatively low. Summary of the Invention

[0005] Embodiments of this application provide an information interaction method, apparatus, device, and storage medium, which can improve the efficiency of information interaction. The technical solutions are as follows:

[0006] On the one hand, an information interaction method is provided. The method includes:

[0007] When providing a target service for a terminal, obtain the interaction statement of the terminal in the i-th round of conversation, where i is an integer greater than 1;

[0008] Among multiple service nodes included in the service flow of the target service, determine the target service node corresponding to the interaction statement. Each of the service nodes of the service flow is used to obtain elements required to implement the target service, and each of the service nodes has a guiding statement for triggering the next round of conversation;

[0009] Based on multiple interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node, determine a target interaction statement, and send the target interaction statement to the terminal.

[0010] In a possible implementation manner, the target service is a health service, and the health service is used to provide users with consultations on health information; among multiple service nodes included in the service flow of the target service, determining the target service node corresponding to the interaction statement includes:

[0011] Obtain the target element of the health service from the interaction statement;

[0012] Among the multiple service nodes included in the service flow of the health service, determine the target service node corresponding to the target element.

[0013] In a possible implementation manner, determining the target interaction statement based on the multiple interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node includes:

[0014] Based on the target element, the obtained historical elements, and the multiple elements required to implement the health service, determine the target interaction statement from the guiding statement corresponding to the target service node;

[0015] Wherein, the historical elements are the elements obtained from the multiple interaction statements included in the historical conversation, and the target interaction statement is used to obtain the elements other than the target element and the historical elements among the multiple elements.

[0016] In a possible implementation manner, the method further includes:

[0017] Perform intention recognition on the interaction statement to obtain an intention recognition result;

[0018] In the case where the intention recognition result does not match the target service, based on the intention recognition result, re-determine the type of the target service, and perform information interaction based on the re-determined type of the target service.

[0019] In a possible implementation manner, after obtaining the interaction statement of the terminal in the i-th round of conversation, the method further includes:

[0020] In the case where the statement type of the interaction statement is a question type, obtain the answer corresponding to the interaction statement, and send the answer to the terminal;

[0021] In the case where the statement type of the interaction statement is not a question type, execute the step of determining the target service node corresponding to the interaction statement among the multiple service nodes included in the service flow of the target service.

[0022] In a possible implementation manner, the method further includes:

[0023] In the case where the answer corresponding to the interaction statement is not obtained, execute the step of determining the target service node corresponding to the interaction statement among the multiple service nodes included in the service flow of the target service.

[0024] In a possible implementation manner, the method further includes:

[0025] Obtain historical interaction data, where the historical interaction data includes multiple interaction statements obtained during the historical information interaction process;

[0026] Extract questions and answers from the historical interaction data to obtain multiple questions and the answers corresponding to each of the questions;

[0027] Store the correspondence between each question and the answer corresponding to the question in a knowledge base.

[0028] In a possible implementation, the storing the correspondence between each question and the answer corresponding to the question in a knowledge base includes:

[0029] Based on a relevance determination model, determine the target question corresponding to each question, where the target question is a question already stored in the knowledge base and has the largest relevance parameter with the question, and the relevance determination model is trained based on the relevance parameters between multiple sample questions;

[0030] In the knowledge base, update the answer corresponding to the target question based on the answer corresponding to the question.

[0031] In a possible implementation, the method further includes:

[0032] When the answer passes the review, execute the step of updating the answer corresponding to the target question based on the answer corresponding to the question in the knowledge base.

[0033] In a possible implementation, the method further includes:

[0034] Obtain the portrait information corresponding to the terminal, where the portrait information is used to describe the user to which the terminal belongs;

[0035] The determining the target interaction statement based on the multiple interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target business node includes:

[0036] Based on the multiple interaction statements included in the historical conversation before the i-th round of conversation, determine the first guiding statement from at least one guiding statement corresponding to the target business node;

[0037] Based on the portrait information, determine the second guiding statement from at least one guiding statement corresponding to the next-level business node associated with the first guiding statement;

[0038] Adjust the second guiding statement based on the portrait information to obtain the target interaction statement.

[0039] In a possible implementation, the method further includes:

[0040] Extract portrait information from historical interaction data to obtain the portrait information of the user to whom the terminal belongs. The historical interaction data includes a plurality of interaction statements obtained during the historical information interaction with the terminal.

[0041] On the other hand, an information interaction device is provided. The device includes:

[0042] A statement acquisition module, configured to acquire the interaction statement of the terminal in the i-th round of conversation when providing a target service for the terminal, where i is an integer greater than 1;

[0043] A node determination module, configured to determine the target service node corresponding to the interaction statement among a plurality of service nodes included in the service flow of the target service. Each service node of the service flow is used to acquire elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation;

[0044] A statement determination module, configured to determine a target interaction statement based on a plurality of interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node, and send the target interaction statement to the terminal.

[0045] In a possible implementation, the target service is a health service, and the health service is used to provide health information consultation for users; the node determination module is configured to acquire the target element of the health service from the interaction statement; and determine the target service node corresponding to the target element among a plurality of service nodes included in the service flow of the health service.

[0046] In a possible implementation, the statement determination module is configured to determine the target interaction statement from the guiding statement corresponding to the target service node based on the target element, the acquired historical elements, and a plurality of elements required to implement the health service;

[0047] wherein, the historical element is an element acquired from a plurality of interaction statements included in the historical conversation, and the target interaction statement is used to acquire elements other than the target element and the historical element among the plurality of elements.

[0048] In a possible implementation, the device further includes:

[0049] An intention recognition module, configured to perform intention recognition on the interaction statement to obtain an intention recognition result;

[0050] A type determination module, configured to, when the intent recognition result does not match the target service, re-determine the type of the target service based on the intent recognition result, and perform information interaction based on the re-determined type of the target service.

[0051] In a possible implementation manner, the apparatus further includes:

[0052] An answer acquisition module, configured to, when the statement type of the interaction statement is a question type, acquire the answer corresponding to the interaction statement and send the answer to the terminal;

[0053] The node determination module is further configured to, when the statement type of the interaction statement is not a question type, determine the target business node corresponding to the interaction statement among the multiple business nodes included in the business process of the target service.

[0054] In a possible implementation manner, the apparatus further includes:

[0055] The node determination module is further configured to, when the answer corresponding to the interaction statement is not acquired, determine the target business node corresponding to the interaction statement among the multiple business nodes included in the business process of the target service.

[0056] In a possible implementation manner, the apparatus further includes:

[0057] A data acquisition module, configured to acquire historical interaction data, where the historical interaction data includes multiple interaction statements obtained during the historical information interaction process;

[0058] A data extraction module, configured to extract questions and answers from the historical interaction data to obtain multiple questions and the answers corresponding to each question;

[0059] A data storage module, configured to store the corresponding relationship between each question and the answer corresponding to the question in a knowledge base.

[0060] In a possible implementation manner, the data storage module is configured to determine, based on a relevance determination model, a target question corresponding to each question, where the target question is a question already stored in the knowledge base and has the largest relevance parameter with the question, and the relevance determination model is trained based on the relevance parameters between multiple sample questions; in the knowledge base, update the answer corresponding to the target question based on the answer corresponding to the question.

[0061] In a possible implementation manner, the data storage module is configured to, when the answer passes the review, update the answer corresponding to the target question in the knowledge base based on the answer corresponding to the question.

[0062] In a possible implementation, the apparatus further includes:

[0063] An image acquisition module, configured to acquire image information corresponding to the terminal, where the image information is used to describe the user to which the terminal belongs;

[0064] The statement determination module is further configured to determine a first guiding statement from at least one guiding statement corresponding to the target service node based on a plurality of interaction statements included in the historical conversation before the i-th round of conversation; determine a second guiding statement from at least one guiding statement corresponding to the next-level service node associated with the first guiding statement based on the image information; and adjust the second guiding statement based on the image information to obtain the target interaction statement.

[0065] In a possible implementation, the apparatus further includes:

[0066] An image extraction module, configured to extract image information of the user to which the terminal belongs from historical interaction data, where the historical interaction data includes a plurality of interaction statements obtained during the historical information interaction process with the terminal.

[0067] On the other hand, an electronic device is provided, where the electronic device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the information interaction method described in the above aspect.

[0068] On the other hand, a computer-readable storage medium is provided, where at least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by a processor to implement the information interaction method described in the above aspect.

[0069] On the other hand, a computer program product is provided, where the computer program product includes at least one program code, and the at least one program code is loaded and executed by a processor to implement the information interaction method described in the above aspect.

[0070] The beneficial effects brought by the technical solution provided in the embodiments of this application at least include:

[0071] In the embodiments of this application, when providing a target service for a terminal, by leveraging the orderliness of the service flow of the target service, the target service node corresponding to the interaction statement in the i-th round of conversation is quickly located. Further, in combination with the historical conversation and the guiding statements corresponding to the target service node, the target interaction statement returned to the terminal is accurately determined, thereby improving the information interaction efficiency. Description of the Drawings

[0072] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0073] Figure 1 It is a schematic diagram of an implementation environment provided by an embodiment of the present application;

[0074] Figure 2 It is a flowchart of an information interaction method provided by an embodiment of the present application;

[0075] Figure 3 It is a flowchart of an information interaction method provided by an embodiment of the present application;

[0076] Figure 4 It is a flowchart of an information interaction method provided by an embodiment of the present application;

[0077] Figure 5 It is a flowchart of a knowledge base construction method provided by an embodiment of the present application;

[0078] Figure 6 It is a flowchart of an information interaction method provided by an embodiment of the present application;

[0079] Figure 7 It is a block diagram of an information interaction device provided by an embodiment of the present application;

[0080] Figure 8 It is a block diagram of a server provided by an embodiment of the present application. Detailed implementation manners

[0081] To make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0082] The terms "first", "second", "third", and "fourth" in the specification, claims, and accompanying drawings of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0083] It should be noted that the user data involved in this application (including but not limited to user device information, user personal information, etc.) are all information authorized by the user or fully authorized by all parties.

[0084] Figure 1 FIG. 4 is a schematic diagram of an implementation environment provided by an embodiment of the present application. As Figure 1 shown, the implementation environment includes: a terminal 101 and a server 102, and the terminal 101 and the server 102 are connected through a wired or wireless network.

[0085] In some embodiments, the terminal 101 is at least one of devices such as a mobile phone, a tablet computer, a desktop computer, or a laptop computer. The server 102 can be at least one of a single server, a server cluster composed of multiple servers, a cloud server, a cloud computing platform, and a virtualization center. The embodiments of the present application do not limit this.

[0086] In some embodiments, the terminal 101 provides a target application with background services provided by the server 102, and the target application can provide an operating environment for an online customer service. The terminal 101 can implement functions such as information interaction and information display through the target application, and the terminal 101 can implement information interaction between the online customer service and the user of the operating terminal through the target application. In the embodiments of the present application, the terminal 101 is used to obtain an interaction statement input by the user and send the interaction statement to the server 102. The server 102 is used to receive the interaction statement of the terminal 101, determine a target interaction statement based on the interaction statement, and send the target interaction statement to the terminal 101. Correspondingly, the terminal 101 is further used to receive the target interaction statement and display the target interaction statement.

[0087] In the embodiments of the present application, the technical solutions provided by the embodiments of the present application can be implemented with the server or the terminal as the execution subject, or the technical methods provided by the present application can be implemented through the interaction between the terminal and the server. The embodiments of the present application do not limit this.

[0088] The information interaction method provided by the embodiments of the present application can be applied to the information interaction scenario of any target service, such as online services such as telecommunications services, legal services, or health services. The embodiments of the present application will be described by taking the target service as a health service as an example.

[0089] For example, taking the health service as a nucleic acid testing service as an example, the user inputs an interaction statement "I want to make an appointment for nucleic acid testing" in the terminal 101, and the terminal 101 sends the interaction statement to the server 102. The server 102 realizes information interaction with the terminal by executing the information interaction method provided by the embodiments of the present application, so as to provide the user with a nucleic acid testing service.

[0090] It should be noted that the embodiments of the present application only take the target service as a health service as an example, and take the nucleic acid detection service as an example of the health service for illustration, and do not limit the scenarios of the information interaction method of the present application. For example, the health service can also be a nucleic acid result query service or a vaccine reservation service, etc.

[0091] Figure 2 It is a flowchart of an information interaction method provided by an embodiment of the present application. The embodiments of the present application are executed by a server, and the method includes the following steps:

[0092] Step 201: When the server provides a target service for a terminal, obtain the interaction statement of the terminal in the i-th round of conversation, where i is an integer greater than 1.

[0093] In the embodiments of the present application, when a user operating a terminal wants to obtain a target service, an interaction statement is input in the terminal, thereby triggering the information interaction between the terminal and the server. This information interaction process exists in the form of a conversation, such as a single-round or multi-round conversation.

[0094] Step 202: Among the multiple service nodes included in the service flow of the target service, determine the target service node corresponding to the interaction statement. Each service node of this service flow is used to obtain the elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation.

[0095] In the embodiments of the present application, the server pre-sets a corresponding service flow for each type of target service. Therefore, when providing a certain type of target service for a terminal, the corresponding service nodes are triggered in sequence according to the execution order of the service flow corresponding to this type, so as to realize the information interaction with the terminal. Among them, by dividing the service flow according to the type of the target service, the field of the target service is subdivided.

[0096] Among them, the service flow has a corresponding service flow description language. The server, as a dialogue engine, that is, a service flow engine, loads the service flow description language of the provided target service to trigger the service nodes. Optionally, the server manages the service flow by managing the service flow configuration file. For example, the management methods of the service flow include adding a service flow or modifying a service flow, etc. The service flow configuration file includes the configuration information of the service flow, and the configuration information includes the type of the corresponding target service, the number of service nodes, the elements corresponding to each service node, etc.

[0097] It should be noted that the present application does not make specific limitations on the setting methods of the service flow and service nodes. For example, the server sets service flows for nucleic acid reservation services and vaccine inoculation services respectively. It should be noted that the guiding statements corresponding to the service nodes are obtained by means of natural language generation.

[0098] Step 203: The server determines a target interaction statement based on multiple interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node, and sends the target interaction statement to the terminal.

[0099] In the embodiment of the present application, when providing a target service for the terminal, by virtue of the orderliness of the service flow of the target service, the target service node corresponding to the interaction statement in the i-th round of conversation is quickly located. Further, in combination with the historical conversation and the guiding statement corresponding to the target service node, the target interaction statement returned to the terminal is accurately determined, thereby improving the information interaction efficiency.

[0100] In the embodiment of the present application, when a user wants to obtain a target service by means of a terminal, the user inputs an interaction statement in the first round of conversation in the terminal. The terminal obtains the interaction statement and sends the interaction statement to the server; the server receives the interaction statement. In some embodiments, after receiving the interaction statement, the server performs intent recognition on the interaction statement to obtain an intent recognition result, determines the type of the target service that matches the intent recognition result, determines the service flow corresponding to the type, and thus realizes information interaction with the terminal according to the service flow.

[0101] For example, the interaction statement input by the user in the first round of conversation is "I want to make an appointment for a vaccine", the intent recognition result of the interaction statement is "vaccine appointment", and the type of the target service corresponding to the intent recognition result is "vaccine appointment". Then the server determines the service flow corresponding to the "vaccine appointment" type, that is, the vaccine appointment service flow.

[0102] In the embodiment of the present application, since providing a target service often requires multiple elements to be realized, and after the first round of conversation is started, it is difficult for the user to provide all the complete multiple elements in one round of conversation. Then the server obtains multiple elements through multiple rounds of conversation with the terminal, so as to provide the target service for the terminal. For example, for the vaccine appointment service, the server needs to obtain multiple elements such as the user's age, gender, address, and previous medical history. Then the server uses the information interaction method provided in the embodiment of the present application to obtain the multiple elements to provide high-quality target services for the terminal.

[0103] In some embodiments, the target service is a health service, and the health service is used to provide users with consultations on health information. The types of health services include nucleic acid testing, vaccination, nucleic acid result query, or other health service types. Accordingly, Figure 3 is a flowchart of an information interaction method provided by an embodiment of the present application. The embodiment of the present application takes the target service as a health service and takes the i-th round of conversation between the terminal and the server as an example for description. The method includes the following steps:

[0104] Step 301: The terminal obtains the interaction statement in the i-th round of conversation and sends the interaction statement to the server, where i is an integer greater than 1.

[0105] In the embodiments of the present application, the terminal provides health services for users with the help of the server. During the multi-round conversation between the terminal and the server, every time the terminal obtains an interaction statement, it sends the interaction statement to the server so that the server can timely determine the conversation strategy according to the interaction statement.

[0106] Step 302: The server receives the interaction statement.

[0107] In some embodiments, after receiving the interaction statement sent by the terminal, the server stores the interaction statement for subsequent processing.

[0108] Step 303: The server obtains the target element of the health service from the interaction statement.

[0109] Since the interaction statement sent by the terminal may contain the elements required to implement the health service, the server obtains the target element from the interaction statement after obtaining the interaction statement. Optionally, the implementation manner of step 303 includes: the server performs natural language processing on the interaction statement to obtain semantic information, and extracts the target element from the semantic information. For example, if the interaction statement is "I don't have a fever", the semantic information is "The user doesn't have a fever", and the target element is "don't have a fever".

[0110] Step 304: The server determines the target service node corresponding to the target element among the multiple service nodes included in the service flow of the health service.

[0111] Among them, the server has determined the service node corresponding to the (i - 1)-th round of conversation before the i-th round of conversation. Correspondingly, the server determines the target service node corresponding to the target element from the next-level service nodes of the service node. For example, the service node corresponding to the (i - 1)-th round of conversation is used to determine whether the user has a fever, that is, to obtain the element of "whether having a fever". The two next-level service nodes of this service node are the "yes" node and the "no" node respectively. If the target element is "don't have a fever", then the target service node is the "no" node.

[0112] In the embodiments of the present application, for the i-th round of conversation, the target element is obtained from the interaction statement by means of natural language understanding, and the target service node is triggered by the target element, so as to realize the element acquisition process in the process of providing health services in the form of a service flow, improving the orderliness of information interaction.

[0113] Step 305: Based on the target element, the obtained historical elements, and multiple elements required to implement the health service, the server determines a target interaction statement from the guiding statements corresponding to the target service node.

[0114] Among them, the historical elements are elements obtained from multiple interaction statements included in the historical conversation before the i-th round of conversation. The target interaction statement is used to obtain elements other than the target element and the historical elements among the multiple elements. In some embodiments, the implementation manner of step 305 includes: the server determines, from the multiple elements, elements other than the target element and the historical elements; and determines, from the guiding statements corresponding to the target service node, a target interaction statement for obtaining the elements.

[0115] For example, if the multiple elements are "gender, age, residential address", the target element is "female", and the historical element is "26 years old", then the remaining element to be obtained is "residential address". Correspondingly, the target interaction statement is "May I ask where you live now".

[0116] In some embodiments, when the number of remaining elements to be obtained is multiple, the server selects, from the multiple guiding statements corresponding to the target service node, the guiding statement with the earliest execution order as the target interaction statement; or the server randomly selects a guiding statement as the target interaction statement. Optionally, the server pre-sets the execution order of each guiding statement corresponding to the service node, so that elements can be obtained according to the execution order subsequently. The execution order can be set as needed, and the embodiments of the present application do not make specific limitations thereto.

[0117] In the embodiments of the present application, the server makes a decision on the current round of conversation strategy based on the current conversation and the historical conversation, that is, the context information of the conversation. Among them, the determination of the conversation strategy includes sending a target interaction statement to ask the user for more detailed intentions, or clarifying and confirming some or multiple elements of the user's current intention, so as to provide a health service for the user based on the latest intention.

[0118] In some embodiments, during the process of providing a health service to the terminal, the user operating the terminal may change the intention during the conversation, and the server needs to provide a health service for the terminal according to the user's intention. Correspondingly, before step 304, the information interaction method provided by the embodiments of the present application further includes the following steps: the server performs intention recognition on the interaction statement to obtain an intention recognition result; in the case where the intention recognition result does not match the health service, based on the intention recognition result, re-determine the type of the health service, and perform information interaction based on the re-determined type of the health service.

[0119] Among them, after each interaction statement sent by the terminal is obtained, the server performs intent recognition on the interaction statement to timely maintain the user's complete intent. If the intent recognition result does not match the health service, indicating that the user's intent has changed, then the implementation method for the server to re-determine the type of health service based on the intent recognition result includes: the server determines the type of health service that matches the intent recognition result. Accordingly, the implementation method for the server to perform information interaction based on the re-determined type of health service includes: the server determines the service flow that matches the type according to the re-determined type of health service, and performs information interaction according to the service flow, that is, performs the operations of steps 304 - 305 according to the re-determined service flow.

[0120] For example, the intent recognition result corresponding to the interaction statement in the (i - 1)-th round of conversation is "nucleic acid test appointment", and the intent recognition result corresponding to the interaction statement in the i-th round of conversation is "vaccine appointment". It can be seen that the intent recognition result has changed, and the re-determined type of health service is "vaccine appointment", then the server determines that the service flow corresponding to the "vaccine appointment" type is the vaccine appointment service flow.

[0121] In a possible implementation manner, when the intent recognition result matches the health service, the server performs the operations of steps 304 - 305 based on the service flow of the health service.

[0122] In the embodiments of the present application, by re-determining the intent recognition result for each interaction statement, the status of multiple rounds of conversations is tracked, so as to maintain the user's intent according to the latest status of multiple rounds of conversations, determine the target interaction statement according to the latest user intent, and thus improve the accuracy of the target interaction statement.

[0123] Step 306: The server sends the target interaction statement to the terminal.

[0124] In the embodiments of the present application, after obtaining the target interaction statement, the server sends the target interaction statement to the terminal.

[0125] Step 307: The terminal receives the target interaction statement and displays the target interaction statement.

[0126] In some embodiments, after receiving the target interaction statement sent by the server, the terminal displays the target interaction statement on the display interface so that the user operating the terminal can view it in a timely manner.

[0127] In the embodiments of the present application, the conversation state tracking and conversation strategy determination are carried out in the way of service flow to realize multiple rounds of conversations, so that the conversation task can be completed with higher efficiency on the premise of maximizing the satisfaction of the user's intent.

[0128] In the embodiments of the present application, when providing health services to a terminal, on the one hand, by selecting the target service node corresponding to the interaction statement of the i-th round of conversation from the service flow of the health service, the task can be quickly located by virtue of the orderliness of the service flow. On the other hand, by combining the historical conversation and the guiding statement corresponding to the target service node, the target interaction statement is determined, thereby improving the information interaction efficiency.

[0129] In some embodiments, the statement type of the interaction statement input by the user in the terminal is not a question type. For example, the interaction statement is "I want to make an appointment for nucleic acid testing", "Query the results of nucleic acid testing", or "The latest epidemic information". Then, there is no fixed answer for this interaction statement. Therefore, the server can determine the target interaction statement used to reply to this interaction statement in the form of a service flow, that is, when the statement type of the interaction statement is not a question type, the server performs the operations of steps 303-306.

[0130] In other embodiments, the statement type of the interaction statement input by the user in the terminal is a question type. For example, the interaction statement is "What is a vaccine", "What are the precautions for getting vaccinated", or "What are the symptoms of pneumonia". Then, for the interaction statement of the question type, the server can obtain the answer corresponding to this interaction statement and return the answer to the terminal accordingly. Figure 4 It is a flowchart of an information interaction method provided by the embodiments of the present application. The embodiments of the present application take the statement type of the interaction statement sent by the terminal as a question statement as an example for illustration. The method includes the following steps:

[0131] Step 401: The terminal obtains the interaction statement in the i-th round of conversation and sends the interaction statement to the server, where i is an integer greater than 1.

[0132] Step 402: The server receives the interaction statement.

[0133] In some embodiments, the implementation manners of steps 401-step 402 are the same as those of steps 301-step 302, and will not be elaborated here.

[0134] Step 403: When the statement type of the interaction statement is a question type, the server obtains the answer corresponding to the interaction statement.

[0135] In some embodiments, the server pre-constructs a knowledge base, which is used to store the corresponding relationship between questions and answers. Among them, the questions in the knowledge base are used as indexes (queries), and the answers are used as the values corresponding to the indexes. When the server obtains an interaction statement of the question type, it retrieves the answer corresponding to this interaction statement from the knowledge base. Accordingly, the implementation manner for the server to obtain the answer corresponding to the interaction statement includes: the server uses the interaction statement as an index to find the answer corresponding to this interaction statement from the knowledge base.

[0136] In a possible implementation, when the server obtains the answer corresponding to the interaction statement, it performs the operation of step 404. In another possible implementation, the answer corresponding to the interaction statement may not be stored in the knowledge base. Then, the information interaction method provided by the embodiments of the present application further includes the following steps: when the answer corresponding to the interaction statement is not obtained, the server performs the operations of step 303 to step 306.

[0137] In the embodiments of the present application, since there is a large amount of information involved in the target service, and the obtained interaction statement may not have a corresponding answer, the information interaction with the terminal is realized by means of the service flow corresponding to the target service. Thus, even if no answer is obtained, the normal provision of the target service can be realized, thereby improving the stability of the dialogue function and also improving the user experience.

[0138] Step 404: The server sends the answer to the terminal.

[0139] Step 405: The terminal receives the answer and displays the answer.

[0140] In some embodiments, the implementation manners of step 404 to step 405 are the same as those of step 306 to step 307, and will not be elaborated here.

[0141] In the embodiments of the present application, for the interaction statement of the question type, by directly obtaining the answer corresponding to the interaction statement, the rapid provision of the target service is realized, and the efficiency of information interaction is improved.

[0142] In the embodiments of the present application, before providing the target service for the terminal, the server first constructs an initial knowledge base, and then maintains the knowledge base according to the interaction statements obtained in the information interaction process based on the target service. Optionally, the construction manner of the initial knowledge base includes: the technician obtains questions and corresponding answers from a large amount of information related to the target service, and the server stores the questions and corresponding answers in the knowledge base to obtain the initial knowledge base. Among them, the large amount of information related to the target service can be obtained through books, websites, questionnaires, etc.

[0143] Correspondingly, Figure 5 It is a flowchart of a knowledge base construction method provided by the embodiments of the present application. The embodiments of the present application are executed by the server, and the method includes the following steps:

[0144] Step 501: The server obtains historical interaction data, and the historical interaction data includes a plurality of interaction statements obtained in the historical information interaction process.

[0145] Among them, the historical interaction data includes the historical interaction data generated during the historical information interaction between the server and multiple terminals. In some embodiments, the implementation manner of the server storing the historical interaction data includes: during each information interaction process, the server stores the interaction statements sent by the terminal and generated by the server, so as to obtain the historical interaction data. Alternatively, the server periodically collects the logs generated during the information interaction process and extracts the historical interaction data from the logs.

[0146] For example, taking the target service as the epidemic prevention and control consultation service as an example, the server obtains the online logs of the intelligent customer service (such as the anti-epidemic consultation robot) for the epidemic prevention and control consultation service, and obtains the historical interaction data related to the epidemic prevention and control consultation service from the online logs.

[0147] Step 502: The server extracts questions and answers from the historical interaction data to obtain a plurality of questions and the answers corresponding to each of the questions.

[0148] Among them, during the historical information interaction based on the target service, the user may ask questions to the server through the terminal, so the terminal sends the questions to the server, and the server answers the questions to obtain the answers. Therefore, the server can extract questions and answers from the historical interaction data.

[0149] Step 503: The server stores the corresponding relationship between each question and the answer corresponding to the question in the knowledge base.

[0150] In some embodiments, the server stores the corresponding relationship between the obtained questions and answers in the knowledge base. In this way, since the extracted questions are the original questions input by the user through the terminal, by storing the original questions and the corresponding answers in the knowledge base, the questions stored in the knowledge base are more in line with the questions that users may ask in the real target service scenario, and further, the search speed of the answers can also be improved during the subsequent provision of the target service.

[0151] In some other embodiments, the questions sent by the terminal during the information interaction process may be related to the questions already stored in the knowledge base. Then the server can first determine the correlation parameters of the questions extracted from the historical interaction data, and then store the questions and the corresponding answers according to the magnitude of the correlation parameters. Correspondingly, the implementation manner of step 503 includes: the server determines the target question corresponding to each question based on the correlation determination model, the target question is the question already stored in the knowledge base and has the largest correlation parameter with the question, and the correlation determination model is trained based on the correlation parameters between multiple sample questions; in the knowledge base, based on the answer corresponding to the question, update the answer corresponding to the target question.

[0152] Among them, the correlation parameter is used to measure the semantic correlation degree between two questions. The representation method of the correlation parameter can be set as needed, and the present application does not make specific limitations on this. For example, the correlation parameter is represented in the form of a score. In the embodiments of the present application, the server pre-trains a correlation determination model. Optionally, the server pre-obtains multiple sample questions, labels the correlation parameters of the sample questions, and trains the correlation determination model based on the multiple sample questions with the correlation parameter as the supervision. It should be noted that the correlation determination model can be a machine learning model, and the present application does not make specific limitations on this.

[0153] Among them, the implementation manner in which the server determines the target question corresponding to each of these questions based on the correlation determination model includes: The server inputs the extracted question and the questions already stored in the knowledge base as model input data into the correlation determination model, and the correlation determination model outputs the target question and the correlation parameter between the target question and the extracted question.

[0154] The server can update the questions in the knowledge base in combination with the numerical value of the correlation parameter. Optionally, in the knowledge base, the implementation manner in which the server updates the answer corresponding to the target question based on the answer corresponding to the question includes: When the correlation parameter is greater than the correlation threshold, the server supplements the answer corresponding to the question into the answer corresponding to the target question in the knowledge base. When the correlation parameter is not greater than the correlation threshold, the server supplements the corresponding relationship between the question and the corresponding answer into the knowledge base.

[0155] Among them, the size of the correlation threshold can be set as needed, and the present application does not make specific limitations on this. It should be noted that the server can periodically update and train the correlation determination model to improve the accuracy of the model.

[0156] In the embodiments of the present application, by means of the correlation determination model, it is determined whether the question to be supplemented into the knowledge base is repeated with the questions already stored in the knowledge base, so as to be able to realize the clustering of similar questions, and further optimize the questions and corresponding answers in the knowledge base.

[0157] In some embodiments, during the process of updating the questions and answers already stored in the knowledge base, the extracted questions and answers are first audited to ensure the accuracy of the questions and answers. Correspondingly, the information interaction method provided by the embodiments of the present application further includes the following steps: When the answer is audited and passed, the server executes the step of updating the answer corresponding to the target question based on the answer corresponding to the question in the knowledge base.

[0158] In a possible implementation, when the review fails, the server discards the questions and answers that fail the review, or the technical staff modifies the questions and answers that fail the review until the questions and answers pass the review.

[0159] It should be noted that before the review passes, since the original questions and original answers are still stored in the knowledge base, when the server conducts information interaction based on the knowledge base, it still interacts with the terminal with the original answers. In the embodiments of the present application, by reviewing the questions and answers updated to the knowledge base, the accuracy of the questions and answers in the knowledge base can be ensured.

[0160] In addition to historical interaction data, the server can also obtain other data to build the knowledge base. Optionally, the server obtains historical call record information of the customer service phone based on the target service, extracts questions and answers from the historical call record information, and builds the knowledge base according to the questions and answers. Of course, the server can also maintain the knowledge base in other ways, and the present application does not make specific limitations on this.

[0161] In the embodiments of the present application, the server can regularly perform the operations of step 501-step 503 to maintain the knowledge base, so as to enrich and expand the knowledge base, and thus provide a better target service by means of the knowledge base. For example, regularly classify the questions in the knowledge base and merge the same questions, so as to achieve the cleaning of the knowledge base. In the process of providing the target service based on the business flow, the business flow includes multiple business nodes, and each business node may correspond to one or more questions. Then the server can update and maintain a large number of questions stored in the knowledge base according to the business nodes, so as to build a knowledge base in the sub-field of the target service, and further improve the coverage rate of the user's long-tail questions. For example, the server focuses on maintaining the business nodes with high usage frequency.

[0162] In the embodiments of the present application, since the historical interaction data can represent the target service required by the user in the real information interaction process, by building the knowledge base based on the historical interaction data, the questions and answers stored in the knowledge base can be closer to the user's needs, thus improving the accuracy of the knowledge base.

[0163] In the embodiments of the present application, in the process of providing the target service for the terminal, the server may obtain the portrait information of the user. Then the server can store the portrait information, so as to use the stored portrait information to determine the target interaction statement in the subsequent information interaction process, thereby improving the efficiency of information interaction and improving the user experience. Correspondingly, Figure 6 is a flowchart of an information interaction method provided by the embodiments of the present application. The embodiments of the present application are executed by the server, and the method includes the following steps:

[0164] Step 601: The terminal obtains the interaction statement in the i-th round of conversation and sends the interaction statement to the server, where i is an integer greater than 1.

[0165] Step 602: The server receives the interaction statement.

[0166] Step 603: The server determines the target service node corresponding to the interaction statement among the multiple service nodes included in the service flow of the target service. Each service node in the service flow is used to obtain the elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation.

[0167] In some embodiments, the implementation manners of steps 601 - 603 are the same as those of steps 301 - 304, and thus will not be elaborated herein.

[0168] Step 604: The server obtains the portrait information corresponding to the terminal, and the portrait information is used to describe the user to which the terminal belongs.

[0169] Among them, the server stores the user identifier and the portrait information in association with each other, so as to facilitate the subsequent acquisition of the portrait information. The user identifier is an identifier such as a user account. Optionally, the information interaction method provided in the embodiments of the present application further includes the following steps: The server extracts the portrait information from the historical interaction data to obtain the portrait information of the user to which the terminal belongs, and the historical interaction data includes multiple interaction statements obtained during the historical information interaction process with the terminal.

[0170] Among them, the historical interaction data is the historical interaction data corresponding to the same user identifier. The portrait information includes at least one of gender, age, residential address, or preference information, etc. In the embodiments of the present application, by extracting the portrait information of the user from the historical interaction data with the terminal, data support is provided for the subsequent target service, the time for information acquisition is saved, and the information interaction efficiency is improved.

[0171] Step 605: The server determines the first guiding statement from at least one guiding statement corresponding to the target service node based on the multiple interaction statements included in the historical conversation before the i-th round of conversation.

[0172] In some embodiments, the implementation manner for the server to determine the first guiding statement is the same as that of step 305, and thus will not be elaborated herein.

[0173] Step 606: The server determines the second guiding statement from at least one guiding statement corresponding to the next-level service node associated with the first guiding statement based on the portrait information.

[0174] Among them, for each guiding statement corresponding to the target service node, the guiding statement may be associated with a next-level service node. Then, the next-level service node obtains other elements from the user according to the elements included in the portrait information. Since the server has obtained the portrait information, there is no need to send the first guiding statement to the terminal to guide the user to input the corresponding elements.

[0175] Step 607: The server adjusts the second guiding statement based on the portrait information to obtain a target interaction statement.

[0176] Among them, the server can use the second guiding statement as a template statement. Correspondingly, the implementation manner of step 607 includes: the server fills the corresponding elements in the portrait information into the second guiding statement to obtain a target interaction statement. For example, the interaction statement sent by the terminal is "I want to make an appointment for a nucleic acid test", the first guiding statement is "May I ask where you live now", if the portrait information already includes the user's residential address, and the determined second guiding statement is "Do you want to make an appointment at XX Hospital", the adjusted target interaction statement is "Do you want to make an appointment at XX Hospital in XX City, XX", where XX Hospital in XX City, XX is determined according to the portrait information, for example, select a hospital near the residential address.

[0177] In the embodiment of the present application, the above steps 605 - 607 are an implementation manner for the server to determine the target interaction statement based on multiple interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node.

[0178] Step 608: The server sends the target interaction statement to the terminal.

[0179] Step 609: The terminal receives the target interaction statement and displays the target interaction statement.

[0180] In some embodiments, the implementation manners of steps 608 - 609 are the same as those of steps 306 - 307, and will not be elaborated here.

[0181] In the embodiment of the present application, information interaction with the terminal is realized by combining the user's portrait information, thereby saving the acquisition process of some elements in the information interaction process, and further greatly improving the information interaction efficiency and improving the user experience.

[0182] Figure 7 is a block diagram of an information interaction device provided by an embodiment of the present application. Refer to Figure 7 The device includes:

[0183] A statement acquisition module 701, configured to obtain the interaction statement of the terminal in the i-th round of conversation when providing a target service for the terminal, where i is an integer greater than 1;

[0184] A node determination module 702, configured to determine a target service node corresponding to the interaction statement from multiple service nodes included in the service flow of the target service, where each service node in the service flow is used to obtain elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation.

[0185] A statement determination module 703, configured to determine a target interaction statement based on multiple interaction statements included in the historical conversation before the i-th round of conversation and the guiding statement corresponding to the target service node, and send the target interaction statement to the terminal.

[0186] In a possible implementation, the target service is a health service, which is used to provide users with consultations on health information; the node determination module 702 is configured to obtain the target element of the health service from the interaction statement, and determine the target service node corresponding to the target element from multiple service nodes included in the service flow of the health service.

[0187] In a possible implementation, the statement determination module 703 is configured to determine the target interaction statement from the guiding statement corresponding to the target service node based on the target element, the obtained historical elements, and multiple elements required to implement the health service.

[0188] Wherein, the historical element is an element obtained from multiple interaction statements included in the historical conversation, and the target interaction statement is used to obtain elements other than the target element and the historical element among the multiple elements.

[0189] In a possible implementation, the device further includes:

[0190] An intent recognition module, configured to perform intent recognition on the interaction statement to obtain an intent recognition result;

[0191] A type determination module, configured to, when the intent recognition result does not match the target service, re-determine the type of the target service based on the intent recognition result, and perform information interaction based on the re-determined type of the target service.

[0192] In a possible implementation, the device further includes:

[0193] An answer acquisition module, configured to, when the statement type of the interaction statement is a question type, obtain an answer corresponding to the interaction statement, and send the answer to the terminal;

[0194] The node determination module 702 is further configured to, when the statement type of the interaction statement is not a question type, determine the target service node corresponding to the interaction statement from multiple service nodes included in the service flow of the target service.

[0195] In a possible implementation, the apparatus further includes:

[0196] The node determination module 702 is further configured to determine a target service node corresponding to the interaction statement among multiple service nodes included in the service flow of the target service when an answer corresponding to the interaction statement is not obtained.

[0197] In a possible implementation, the apparatus further includes:

[0198] A data acquisition module, configured to acquire historical interaction data, where the historical interaction data includes multiple interaction statements obtained during a historical information interaction process;

[0199] A data extraction module, configured to extract questions and answers from the historical interaction data to obtain multiple questions and answers corresponding to each question;

[0200] A data storage module, configured to store the corresponding relationship between each question and the answer corresponding to the question in a knowledge base.

[0201] In a possible implementation, the data storage module is configured to determine a target question corresponding to each question based on a relevance determination model, where the target question is a question already stored in the knowledge base and has the largest relevance parameter with the question, and the relevance determination model is trained based on relevance parameters between multiple sample questions; in the knowledge base, update the answer corresponding to the target question based on the answer corresponding to the question.

[0202] In a possible implementation, the data storage module is configured to, when the answer passes the review, update the answer corresponding to the target question in the knowledge base based on the answer corresponding to the question.

[0203] In a possible implementation, the apparatus further includes:

[0204] A portrait acquisition module, configured to acquire portrait information corresponding to the terminal, where the portrait information is used to describe the user to which the terminal belongs;

[0205] The statement determination module 703 is further configured to determine a first guiding statement from at least one guiding statement corresponding to the target service node based on multiple interaction statements included in the historical conversation before the i-th round of conversation; determine a second guiding statement from at least one guiding statement corresponding to the next-level service node associated with the first guiding statement based on the portrait information; and adjust the second guiding statement based on the portrait information to obtain the target interaction statement.

[0206] In a possible implementation, the apparatus further includes:

[0207] An image extraction module, configured to extract image information from historical interaction data to obtain the image information of the user to which the terminal belongs. The historical interaction data includes a plurality of interaction statements obtained during the historical information interaction process with the terminal.

[0208] In the embodiment of the present application, when providing a target service for a terminal, by virtue of the orderliness of the service flow of the target service, the target service node corresponding to the interaction statement in the i-th round of conversation is quickly located. Further, in combination with the historical conversation and the guiding statement corresponding to the target service node, the target interaction statement returned to the terminal is accurately determined, thereby improving the information interaction efficiency.

[0209] In the embodiment of the present application, an example is given with an electronic device serving as a server. Figure 8 A block diagram of a server 800 provided by an embodiment of the present application. The server 800 may vary greatly due to configuration or performance differences, and may include one or more processors (Central Processing Units, CPUs) 801 and one or more memories 802. Among them, one or more memories 802 are used to store at least one program code, and at least one program code is loaded and executed by one or more processors 801 to implement the information interaction method in the above embodiment. Of course, the server 800 may also have components such as wired or wireless network interfaces, keyboards, and input / output interfaces for input / output. The server 800 may also include other components for implementing device functions, which will not be elaborated here.

[0210] Those skilled in the art can understand that Figure 8 the structure shown in does not constitute a limitation on the server 800, and may include more or fewer components than shown in the figure, or combine certain components, or adopt different component arrangements.

[0211] The embodiment of the present application also provides a computer-readable storage medium, in which at least one program code is stored, and at least one program code is loaded and executed by a processor to implement the information interaction method in the above embodiment.

[0212] The embodiment of the present application also provides a computer program product, which includes at least one program code, and the at least one program code is stored in a computer-readable storage medium. The processor of the electronic device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the electronic device executes the information interaction method in the above embodiment.

[0213] In some embodiments, the computer program involved in the embodiments of the present application may be deployed to execute on an electronic device, or on multiple electronic devices located at one location. Alternatively, it may be executed on multiple electronic devices distributed at multiple locations and interconnected through a communication network. The multiple electronic devices distributed at multiple locations and interconnected through a communication network may form a blockchain system.

[0214] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An information interaction method, characterized in that, The method includes: When providing a target service for a terminal, obtaining the interaction statement of the terminal in the i-th round of conversation, where i is an integer greater than 1, the target service is a health service, and the health service is used to provide consultation on health information for users; Obtaining the target element of the health service from the interaction statement; Among the multiple service nodes included in the service flow of the health service, determining the target service node corresponding to the target element, where each service node of the service flow is used to obtain the elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation; Determining the elements other than the target element and the obtained historical elements from the multiple elements required to implement the health service, determining the target interaction statement for obtaining the remaining elements to be obtained from the guiding statements corresponding to the target service node in the execution order of each guiding statement, and sending the target interaction statement to the terminal, where the historical elements are the elements obtained from the multiple interaction statements included in the historical conversation before the i-th round of conversation, and the target interaction statement is used to obtain the elements other than the target element and the historical elements among the multiple elements; 2. The method according to claim 1, wherein The method further includes: Performing intention recognition on the interaction statement to obtain an intention recognition result; In the case where the intention recognition result does not match the target service, based on the intention recognition result, re-determining the type of the target service, and performing information interaction based on the re-determined type of the target service; 3. The method according to claim 1, wherein After obtaining the interaction statement of the terminal in the i-th round of conversation, the method further includes: In the case where the statement type of the interaction statement is a question type, obtaining the answer corresponding to the interaction statement and sending the answer to the terminal; In the case where the statement type of the interaction statement is not a question type, performing the step of determining the target service node corresponding to the target element obtained from the interaction statement among the multiple service nodes included in the service flow of the target service; 4. The method according to claim 3, characterized in that The method further includes: In the case where the answer corresponding to the interaction statement is not obtained, performing the step of determining the target service node corresponding to the target element obtained from the interaction statement among the multiple service nodes included in the service flow of the target service; 5. The method according to claim 3 or 4, characterized in that, The method further includes: Obtaining historical interaction data, where the historical interaction data includes multiple interaction statements obtained in the historical information interaction process; Extracting questions and answers from the historical interaction data to obtain multiple questions and the answers corresponding to each question; Storing the correspondence between each question and the answer corresponding to the question in a knowledge base; 6. The method according to claim 5, wherein The storing the correspondence between each question and the answer corresponding to the question in the knowledge base includes: Based on a relevance determination model, determining the target question corresponding to each question, where the target question is a question already stored in the knowledge base and has the largest relevance parameter with the question, and the relevance determination model is trained based on the relevance parameters between multiple sample questions; In the knowledge base, update the answer corresponding to the target question based on the answer corresponding to the question.

7. The method according to claim 6, wherein The method further includes: When the answer passes the review, execute the step of updating the answer corresponding to the target question based on the answer corresponding to the question in the knowledge base.

8. The method according to claim 1, wherein The method further includes: Obtain the portrait information corresponding to the terminal, where the portrait information is used to describe the user to whom the terminal belongs. After determining the target service node corresponding to the target element, it further includes: Determine, from multiple elements for implementing the health service, elements other than the target element and the acquired historical elements, where the historical elements are elements obtained from multiple interaction statements included in the historical conversation before the i-th round of conversation. Determine, from at least one guiding statement corresponding to the target service node, a first guiding statement for obtaining the remaining elements to be obtained according to the execution order of each guiding statement. Based on the portrait information, determine a second guiding statement from at least one guiding statement corresponding to the next-level service node associated with the first guiding statement. Adjust the second guiding statement based on the portrait information to obtain the target interaction statement.

9. The method according to claim 8, wherein The method further includes: Extract portrait information from historical interaction data to obtain the portrait information of the user to whom the terminal belongs, where the historical interaction data includes multiple interaction statements obtained during the historical information interaction process with the terminal.

10. An information interaction device, characterized in that, The device includes: A statement acquisition module, configured to, when providing a target service for a terminal, acquire the interaction statement of the terminal in the i-th round of conversation, where i is an integer greater than 1, the target service is a health service, and the health service is used to provide consultation on health information for a user. A node determination module, configured to obtain the target element of the health service from the interaction statement, and determine the target service node corresponding to the target element among multiple service nodes included in the service flow of the health service. Each service node in the service flow is used to obtain elements required to implement the target service, and each service node has a guiding statement for triggering the next round of conversation. A statement determination module, configured to determine, from multiple elements required to implement the health service, elements other than the target element and the acquired historical elements, and determine, from the guiding statements corresponding to the target service node, a target interaction statement for obtaining the remaining elements to be obtained according to the execution order of each guiding statement, and send the target interaction statement to the terminal. The historical elements are elements obtained from multiple interaction statements included in the historical conversation before the i-th round of conversation, and the target interaction statement is used to obtain elements other than the target element and the historical elements among the multiple elements.

11. An electronic device, characterized in that, The electronic device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The at least one program code is loaded and executed by the one or more processors to implement the information interaction method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, At least one program code is stored in the storage medium, and the at least one program code is loaded and executed by a processor to implement the information interaction method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product includes at least one program code, and the at least one program code is loaded and executed by a processor to implement the information interaction method according to any one of claims 1 to 9.

Images