Dialogue setting method and device, server, and computer-readable storage medium

Abstract

The present application relates to a method and device for setting a dialogue, a server, and a computer-readable storage medium, including: obtaining a user's tag from a user tag library, setting a dialogue robot's dialogue information according to the user's tag and business scenario, and conducting a dialogue with the user according to the dialogue robot's dialogue information. Because each user has a variety of tags, setting a dialogue robot's dialogue information according to the user's tag and business scenario can provide personalized dialogue services for each different user, thereby improving the success rate of communication.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a dialogue setting method and device, a server, and a computer-readable storage medium. Background Art

[0002] With the continuous development of artificial intelligence and natural language processing technologies, conversational robots have gradually been widely used in multiple business scenarios such as financial services, home life, personal assistants, etc., improving the quality and efficiency of services.

[0003] However, traditional conversational robots use a set of set conversation templates for all users to communicate. Obviously, using a set of set conversation templates for communication cannot achieve a good communication effect, and it will make users feel disgusted or resistant, so the communication success rate is low. Summary of the invention

[0004] The embodiments of the present application provide a conversation setting method, device, server, and computer-readable storage medium, which can improve the communication success rate.

[0005] A dialogue setting method, applied to a dialogue robot, comprising:

[0006] Get the user's tags from the user tag library;

[0007] Setting the conversation information of the conversation robot according to the user's tag and business scenario;

[0008] Conduct a dialogue with the user according to the dialogue information of the dialogue robot.

[0009] In one of the embodiments, the method further includes: establishing the user tag library.

[0010] In one embodiment, the establishing of the user tag library includes:

[0011] Obtain relevant information of the user in the business scenario and historical call information between the conversation robot and the user;

[0012] Generate a tag for the user according to the relevant information of the user in the business scenario and the historical call information;

[0013] The user tag library is established based on tags of a plurality of the users.

[0014] In one embodiment, the dialogue information includes dialogue content and dialogue flow; the dialogue information of the dialogue robot is set according to the user's tag and business scenario, including:

[0015] The conversation content and conversation flow of the conversation robot are set accordingly according to the user's tag and business scenario.

[0016] In one embodiment, the setting of the conversation content and conversation flow of the conversation robot according to the user's tag and business scenario includes:

[0017] Setting the conversation process of the conversation robot according to the user's tag and business scenario;

[0018] In the dialogue process, the dialogue content of the dialogue robot is set accordingly in combination with the user's tag and the user's dialogue content.

[0019] In one embodiment, the setting of the conversation content and conversation flow of the conversation robot according to the user's tag and business scenario also includes:

[0020] The conversation flow is adjusted in combination with the user's tag and the user's conversation content.

[0021] In one embodiment, the setting of the dialogue process of the dialogue robot according to the user's tag and the business scenario includes:

[0022] In a preset business scenario, recommend corresponding services to the user according to the user's tags;

[0023] A dialogue process is formed based on the recommended business.

[0024] In one embodiment, the dialog content of the dialog robot is set correspondingly in combination with the user's tag and the user's dialog content in the dialog process, including:

[0025] In the dialogue process, combining the user's tag and the user's question content, and setting the answer content of the dialogue robot accordingly; or

[0026] In the dialogue process, the question content of the dialogue robot is set accordingly in combination with the user's label and the user's answer content.

[0027] A dialogue setting device, applied to a dialogue robot, comprising:

[0028] The tag acquisition module is used to obtain the user's tags from the user tag library;

[0029] A dialogue information setting module, used to set the dialogue information of the dialogue robot according to the user's tag and business scenario;

[0030] A dialogue control module is used to conduct a dialogue with the user according to the dialogue information of the dialogue robot.

[0031] In one of the embodiments, the analysis module, the conversation information includes the conversation content and the conversation flow;

[0032] The dialogue information setting module is also used to set the dialogue content and dialogue flow of the dialogue robot according to the user's label and business scenario.

[0033] A server includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0034] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0035] The above-mentioned dialogue setting method, device, server, and computer-readable storage medium obtain the user's tag from the user tag library, set the dialogue information of the dialogue robot according to the user's tag and business scenario, and conduct a dialogue with the user according to the dialogue information of the dialogue robot. Because each user has a variety of tags, the dialogue information of the dialogue robot is set according to the user's tag and business scenario, so as to provide personalized dialogue services for each different user, thereby improving the communication success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 An application environment diagram of a dialog setting method in one embodiment;

[0038] Figure 2 A flowchart of a method for setting a dialogue in one embodiment;

[0039] Figure 3 A flowchart of a method for setting a dialogue in another embodiment;

[0040] Figure 4 for Figure 3 A flowchart of a method for establishing a user tag library;

[0041] Figure 5It is a flowchart of a method for setting the conversation content and conversation flow of the conversation robot according to the user's tag and business scenario in an embodiment;

[0042] Figure 6 It is a structural block diagram of a dialogue setting device in one embodiment;

[0043] Figure 7 It is a structural block diagram of a dialogue setting device in another embodiment;

[0044] Figure 8 FIG. 1 is a schematic diagram of the internal structure of a server in an embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] It can be understood that the terms "first", "second", etc. used in the present application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0047] Figure 1 FIG. 1 is an application scenario diagram of a method for setting a dialogue in an embodiment. Figure 1 As shown, the application environment includes a conversation robot 120 and a user 140. The conversation robot 120 obtains the user's tag from the user tag library; sets the conversation robot's conversation information according to the user's tag and business scenario; and conducts a conversation with the user according to the conversation robot's conversation information. The conversation robot may be a server or terminal having the above functions, which is not limited in this application.

[0048] Figure 2 FIG. 1 is a flow chart of a method for setting a dialog in one embodiment. Figure 2 As shown, a dialogue setting method is provided, which is applied to a dialogue robot, and the dialogue robot can be a server or a terminal (such as a robot). The dialogue setting method includes steps 220 to 260.

[0049] Step 220: Obtain the user's tag from the user tag library.

[0050] Among them, the user tag library stores a large number of user tags. These user tags can be basic tags obtained through big data analysis, such as gender, personality, interests, permanent residence, occupation, education, age, etc. Of course, user tags also include user tags in specific business scenarios. For example, in the business scenario of bank collection, the user tags in this business scenario include the user's credit information, the user's income, the user's arrears, etc. This application does not limit this. These user tags such as the user's credit information, the user's income, the user's arrears, etc. can be obtained from bank flow, of course, on the premise that they are obtained reasonably and legally.

[0051] Before or during a conversation with a user, the conversation robot obtains the user's tag from the user tag library corresponding to the user. Here, it can be selected from the user's multiple tags according to the business scenario of the call. For example, for the bank collection business scenario mentioned above, you can obtain tags such as the user's occupation, the user's credit information, the user's income, and the user's outstanding balance. Of course, this application does not limit this.

[0052] Step 240, setting the conversation information of the conversation robot according to the user's tag and business scenario.

[0053] After obtaining the user's label, the dialogue information of the dialogue robot is set in accordance with the business scenario. Different users have different labels, and the business scenarios are also diverse. Therefore, by setting the dialogue information of the dialogue robot according to the user's label and the business scenario, the effect of customizing the dialogue information of the dialogue robot for different users in accordance with the business scenario can be achieved. And the business scenario will be further subdivided into sub-business scenarios and different stages in the business scenario. For example, the different stages in the business scenario can be the number of collections in the business scenario of bank collection mentioned above. Obviously, for the first collection and multiple collections without results, the dialogue information of the dialogue robot set accordingly is different. Among them, the dialogue information includes text information, sound information, logic information, etc. in the communication process between the dialogue robot and the user in a specific business scenario. For example, the language used by the dialogue robot during the communication process, the emotions, timbre, speech speed, intonation, etc., of course, this application does not limit this.

[0054] Step 260: Have a conversation with the user based on the conversation information of the conversation robot.

[0055] After obtaining the user's tag and setting the conversation robot's conversation information according to the business scenario, the conversation robot can have a conversation with the user in real time according to the conversation robot's conversation information. Specifically, the conversation robot communicates with the user using customized text information, sound information, logical information, etc. For example, by adjusting the conversation robot's timbre, speech speed, and intonation, the user's churn rate during the call can be controlled.

[0056] In the embodiment of the present application, the user's tag is obtained from the user tag library, the dialogue information of the dialogue robot is set according to the user's tag and business scenario, and the dialogue is conducted with the user according to the dialogue information of the dialogue robot. Because each user has a variety of tags, the dialogue information of the dialogue robot is set according to the user's tag and business scenario, so that personalized dialogue services can be provided for each different user, thereby improving the communication success rate. This solves the problem that traditional dialogue robots use a set of set dialogue templates to communicate with all users, which obviously has a low communication success rate.

[0057] In one embodiment, Figure 3 As shown, a dialog setting method is improved, and also includes: step 280, establishing a user tag library.

[0058] Among them, the user tag library is a database. A large number of user tags are stored in the database. These user tags can be basic tags obtained through big data analysis, such as gender, personality, interests, permanent residence, occupation, education, age, etc. Of course, user tags also include user tags in specific business scenarios. For example, in the business scenario of bank collection, the user tags in this business scenario include not only basic tags, but also the user's credit information, the user's income, the user's arrears, etc. This application does not limit this.

[0059] Collect user information in advance, which can be done through big data analysis or from the historical call records between the conversation robot and the user. Then, based on the collected user information, analyze the user information to extract the user's tags, and store the user's tags in the database to obtain the user tag library. For example, the tags corresponding to a user A stored in the user tag library are: Gender: Male; Education: Doctor; Occupation: Doctor; Credibility: Excellent. Of course, the above is not exhaustive.

[0060] In the embodiment of the present application, the user's information is collected in advance, and based on the collected user information, the user information is analyzed to extract the user's tag, and the user's tag is stored in the database to obtain the user tag library. Accurately establish the user tag library to facilitate the subsequent accurate acquisition of the user's tag from the user tag library, set the conversation information of the conversation robot according to the user's tag and business scenario, and communicate with the user according to the conversation information of the conversation robot. Provide personalized conversation services for each different user, thereby improving the success rate of communication.

[0061] In one embodiment, Figure 4 As shown, step 280, establishing a user tag library, includes:

[0062] Step 282, obtain relevant information of the user in the business scenario and historical call information between the dialogue robot and the user.

[0063] Because the subsequent dialogue information of the dialogue robot is set according to the user's tags and business scenarios, when establishing the user tag library, the tags of the user in the business scenario can be generated in a targeted manner in combination with the business scenario. Specifically, the relevant information of the user in the business scenario and the historical call information between the dialogue robot and the user in the business scenario are obtained. Among them, the relevant information of the user in the business scenario can be the basic information obtained through big data analysis, such as gender, personality, interests, permanent residence, occupation, education, age, etc. For example, in the business scenario of bank collection, the user's "amount of debt" and "last repayment date" and other information can be directly traced back based on the credit card consumption information.

[0064] Step 284, generating a user tag based on the user's relevant information and historical call information in the business scenario.

[0065] After obtaining the relevant information of the user in the business scenario and the historical call information between the conversation robot and the user in the business scenario, a user tag is generated based on the two types of information. Specifically, keywords can be extracted from the relevant information of the user in the business scenario and the historical call information between the conversation robot and the user in the business scenario, and the user tag is filtered out from the keywords.

[0066] Because for different business scenarios, users have specific labels in different business scenarios. For example, in the business scenario of bank collection, the user labels in this business scenario include the user's credit information, the user's income, the user's debt situation, etc., and this application does not limit this. In the business scenario of insurance recommendation, the user labels in this business scenario may not be exactly the same as the user labels in the bank collection business scenario. For example, in the business scenario of insurance recommendation, the user labels in this business scenario include basic labels, as well as whether insurance has been purchased, whether insurance claims have been made, etc., and this application does not limit this.

[0067] Step 286, establishing a user tag library based on tags of multiple users.

[0068] For each user in the user group that needs to use a conversational robot for conversations, the relevant information of the user in the business scenario and the historical conversation information between the conversational robot and the user are obtained, and the label of each user is further generated based on these two types of information. In this way, the labels of multiple users are obtained, and then a user label library can be established based on the labels of multiple users.

[0069] In the embodiment of the present application, since the subsequent dialogue information of the dialogue robot is set according to the user's tag and the business scenario, when establishing the user tag library, the relevant information of the user in the business scenario and the historical call information between the dialogue robot and the user in the business scenario can be obtained, so that the tags of the user in the business scenario are generated in a targeted manner in combination with the business scenario. In this way, the obtained user tags are highly targeted and have a high degree of matching with the business scenario, which improves the accuracy of providing personalized dialogue services, thereby further improving the communication success rate.

[0070] In one embodiment, the dialogue information includes the dialogue content and the dialogue process; the dialogue information of the dialogue robot is set according to the user's tag and the business scenario, including:

[0071] Set the conversation content and conversation process of the conversation robot according to the user's tags and business scenarios.

[0072] Specifically, the conversation information includes the conversation content and the conversation process. The conversation content includes the speech used by the conversation robot to talk to the user. As the name suggests, speech is the art of speaking, so speech not only includes the text language of the call, but also includes the emotions and tone of voice revealed by the conversation robot during the call. The conversation content of the conversation robot is set according to the user's tags and business scenarios. The conversation robot can be configured with multiple sets of speech libraries, and different speech is used for communication according to different application scenarios and different user tags. For example, according to "whether the user is strongly willing to repay the loan", a gentler speech or a stronger speech can be used to guide.

[0073] For example, in the bank collection scenario, for users whose debt amount is labeled as "debt amount is less than 10,000", when the dialogue robot recognizes that the user is expressing the intention of "no money to pay", the answer can be designed as "your debt amount is not much, it is recommended that you pay it off in one go, so as not to deduct your credit score for overdue payment" and other similar words to urge the user to repay as soon as possible. For users whose debt amount is labeled as "debt amount is greater than 10,000", the words "you can consider dividing XXX yuan (total debt amount) into 12 installments, so that repayment is easy and stress-free" can be designed to guide users to repay in installments, thereby reducing the user's one-time repayment pressure and improving the collection success rate. When recognizing the user's language, the dialogue robot can use NLP (Natural Language Processing) to recognize the user's language. Of course, this application does not limit this. For example, when a user expresses the intention of "I haven't received my salary recently and have no money to pay back", the information of "low willingness to repay-no money" is recognized through NLP semantic analysis. Then, based on the information of "low willingness to repay - no money", jump to the installment business process.

[0074] The conversation process refers to the process of a conversation robot talking to a user, that is, the logic of a conversation robot talking to a user. For example, if the conversation robot has multiple conversation nodes built in, and the conversation content in each conversation node is different, then the conversation process is to select the preset conversation nodes from the above multiple conversation nodes to form the set conversation process.

[0075] Set the conversation process of the conversation robot according to the user's label and business scenario. For example, in the above example, for users whose debt amount label is "debt amount less than 10,000", when jumping to the node where the user refuses to repay, it will jump to the node for continued collection. If the user still refuses to repay, it will enter the node for installment payment. If the user accepts installment payment, it will jump to the node for 3 installments. For users whose debt amount label is "debt amount greater than 10,000", when jumping to the node where the user refuses to repay, it will directly jump to the node for installment payment. If the user accepts installment payment, it will jump to the node for 12 installments.

[0076] In the embodiment of the present application, the conversation content and conversation flow of the conversation robot are set according to the user's label and business scenario. That is, in a specific business scenario, the conversation content and conversation flow of the conversation robot are set according to the user's label. The labels of each user are different, so the conversation content and conversation flow of the customized conversation robot are also different. In this way, not only the conversation content is customized for users with different labels in business scenarios, but also the conversation flow is customized. Unlike traditional conversation robots, all users use a set of set conversation templates for communication. Thus, personalized conversation services are provided for each different user, thereby improving the success rate of communication. Based on the above-mentioned conversation setting method, the conversation robot can configure the outbound call conversation flow based on different scenarios such as marketing and collection, subdivide the scenarios, depict accurate customer portraits, and adopt different speech techniques accordingly, and effectively improve the marketing and collection efficiency through the "thousands of faces" outbound call strategy.

[0077] In one embodiment, Figure 5 As shown, the conversation content and conversation process of the conversation robot are set according to the user's tags and business scenarios, including:

[0078] Step 520, setting the conversation process of the conversation robot according to the user's tag and business scenario;

[0079] Step 540, in the dialogue process, the dialogue content of the dialogue robot is set accordingly in combination with the user's tag and the user's dialogue content.

[0080] First, obtain the user's tag from the user tag library. After obtaining the user's tag in the business scenario, set the conversation process of the conversation robot according to the user's tag and business scenario. Because the conversation process is the overall framework of the conversation between the conversation robot and the user, the conversation process is formulated first to correctly grasp the direction of the call.

[0081] Secondly, in the conversation process, the conversation content of the conversation robot is set in accordance with the user's tag and the user's conversation content. Because in the process of conversation between the conversation robot and the user, the user may encounter various predictable and unpredictable situations during the call, that is, the user's conversation content varies greatly. Therefore, in the conversation process, the conversation content of the conversation robot is set in accordance with the user's tag and the user's conversation content in real time.

[0082] In the embodiment of the present application, the conversation process of the conversation robot is first set according to the user's label and the business scenario. Then, in the conversation process, the conversation content of the conversation robot is set accordingly in combination with the user's label and the user's conversation content. In this way, the conversation process is first formulated to correctly grasp the direction of the call, and then the conversation content of the conversation robot is set in real time in combination with the user's label and the user's conversation content in the conversation process. From the two aspects of the conversation process and the conversation content, personalized conversation services are provided for each different user, thereby improving the success rate of communication.

[0083] In one embodiment, the conversation content and conversation process of the conversation robot are set according to the user's tag and business scenario, and further includes:

[0084] In the conversation process, the user's label and the user's conversation content are combined to adjust the conversation process.

[0085] First, obtain the user's tag from the user tag library. After obtaining the user's tag in the business scenario, set the conversation process of the conversation robot according to the user's tag and business scenario. Because the conversation process is the overall framework of the conversation between the conversation robot and the user, the conversation process is formulated first to correctly grasp the direction of the call.

[0086] However, because the user may encounter various predictable and unpredictable situations during the conversation between the conversation robot and the user, that is, the content of the user's conversation varies greatly. Therefore, if the user's conversation content deviates from the preset conversation process, the conversation process needs to be adjusted to adapt to the user's conversation content.

[0087] In the embodiment of the present application, although the conversation process of the conversation robot is set in advance according to the user's tag and business scenario, if the user's conversation content deviates from the preset conversation process, the conversation process needs to be adjusted to adapt to the user's conversation content. Thus, it is discovered in real time that the user's conversation content deviates from the preset conversation process, and the conversation process is adjusted in time to adapt to the user's conversation content. This avoids the situation where the conversation is still conducted according to the preset conversation process and the user's needs cannot be captured keenly, thereby improving communication efficiency.

[0088] In one embodiment, the conversation process of the conversation robot is set according to the user's tag and business scenario, including:

[0089] In the preset business scenario, recommend corresponding services to users based on their tags;

[0090] Form a conversation flow based on recommended business.

[0091] Specifically, the dialogue process of the dialogue robot is set according to the user's tags and business scenarios, including: in a preset business scenario, recommending corresponding services to the user according to the user's tags, and forming a dialogue process based on the recommended services.

[0092] For example, in the business scenario of insurance recommendation, the corresponding insurance business is recommended to the user according to the user's tag. For example, the corresponding insurance business is recommended to the user according to the user's age; the corresponding insurance business is recommended to the user according to the user's occupation; the corresponding insurance business is recommended to the user according to the user's insurance purpose, etc.

[0093] After recommending the corresponding insurance business to the user based on the user's tag, the system jumps to the corresponding node based on the user's conversation content, thus forming a conversation process.

[0094] In the embodiment of the present application, the dialogue process of the dialogue robot is set according to the user's tag and the business scenario, including: in the preset business scenario, the corresponding business is recommended to the user according to the user's tag, and the dialogue process is formed based on the recommended business. Different recommended businesses are provided for each different user, thereby improving the success rate of business recommendations.

[0095] In one embodiment, in the conversation process, the conversation content of the conversation robot is set accordingly in combination with the user's tag and the user's conversation content, including:

[0096] In the conversation process, combine the user's tags and the user's questions to set the conversation robot's answers accordingly; or

[0097] In the conversation process, the question content of the conversation robot is set accordingly based on the user's label and the user's answer content.

[0098] In the embodiment of the present application, because in the call process, when the user is talking to the dialogue robot, he will not only answer the questions of the dialogue robot, but also ask questions on his own. Therefore, in the dialogue process, in combination with the user's label and the user's dialogue content, when setting the dialogue content of the dialogue robot accordingly, it not only includes: in the dialogue process, in combination with the user's label and the user's question content, the dialogue robot's answer content is set accordingly. It also includes in the dialogue process, in combination with the user's label and the user's answer content, the dialogue robot's question content is set accordingly. Thus, in the call between the dialogue robot and the user, a mutual supervision mechanism is established to improve communication efficiency.

[0099] In one embodiment, a dialogue setting device 600 is provided, such as Figure 6 As shown, it is applied to conversational robots, including:

[0100] The tag acquisition module 620 is used to acquire the user's tag from the user tag library;

[0101] The dialogue information setting module 640 is used to set the dialogue information of the dialogue robot according to the user's tags and business scenarios;

[0102] The dialogue control module 660 is used to conduct a dialogue with the user according to the dialogue information of the dialogue robot.

[0103] In one embodiment, a dialogue setting device 600 is provided, such as Figure 7 As shown, it also includes:

[0104] The user tag library establishment module 680 is used to establish a user tag library.

[0105] In one embodiment, the user tag library building module 680 includes:

[0106] An information acquisition unit, used to acquire relevant information of the user in the business scenario and historical call information between the conversation robot and the user;

[0107] A user tag generation unit, used to generate a user tag based on the user's relevant information and historical call information in the business scenario;

[0108] The user tag library establishing unit is used to establish a user tag library based on tags of multiple users.

[0109] In one embodiment, the dialogue information includes dialogue content and dialogue flow; the dialogue information setting module 640 is also used to set the dialogue content and dialogue flow of the dialogue robot according to the user's tags and business scenarios.

[0110] In one embodiment, the dialog information setting module 640 further includes:

[0111] A dialogue process setting unit, used to set the dialogue process of the dialogue robot according to the user's tags and business scenarios;

[0112] The conversation content setting unit is used to set the conversation content of the conversation robot accordingly according to the user's label and the user's conversation content in the conversation process.

[0113] In one embodiment, the conversation information setting module 640 is further used to adjust the conversation process in combination with the user's tag and the user's conversation content.

[0114] In one embodiment, the dialogue process setting unit is used to recommend corresponding services to the user according to the user's tags in a preset service scenario; and form a dialogue process based on the recommended services.

[0115] The division of the various modules in the above-mentioned conversation setting device is only for illustration. In other embodiments, the conversation setting device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned conversation setting device.

[0116] Figure 8 FIG. 1 is a schematic diagram of the internal structure of a server in an embodiment. Figure 8 As shown, the server includes a processor and a memory connected via a system bus. The processor is used to provide computing and control capabilities to support the operation of the entire server. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by the processor to implement a method for setting up a conversation provided in each of the following embodiments. The internal memory provides a high-speed cache operating environment for the operating system computer program in the non-volatile storage medium. The server may be a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc.

[0117] The implementation of each module in the dialogue setting device provided in the embodiment of the present application can be in the form of a computer program. The computer program can be run on a terminal or a server. The program modules constituted by the computer program can be stored in the memory of the terminal or the server. When the computer program is executed by the processor, the steps of the method described in the embodiment of the present application are implemented.

[0118] The embodiment of the present application also provides a computer-readable storage medium, one or more non-volatile computer-readable storage media containing computer-executable instructions, which, when executed by one or more processors, cause the processors to execute the steps of the dialog setting method.

[0119] A computer program product comprising instructions, when executed on a computer, causes the computer to perform a session setting method.

[0120] Any reference to memory, storage, database or other media used in the embodiments of the present application may include non-volatile and / or volatile memory. Suitable non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM), which is used as an external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0121] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A dialogue setting method, applied to a dialogue robot, characterized in that: include: Obtain relevant information about the user in the business scenario and historical call information between the conversational robot and the user; Generate a tag for the user according to the relevant information of the user in the business scenario and the historical call information, wherein the tag for the user is selected from the relevant information of the user in the business scenario and the keywords extracted from the historical call information; Establishing a user tag library based on tags of the plurality of users; Acquire the user's tag from the user tag library; The conversation information of the conversation robot is set according to the user's tag and the business scenario, the conversation information includes the conversation content and the conversation process, the conversation process includes the logic of the conversation robot talking to the user, the conversation process is adjusted in real time according to the user's tag and the user's conversation content, the conversation process is formed based on the recommended business, the recommended business is determined according to the user's tag and the business scenario, the conversation content includes the speech of the conversation robot talking to the user, the speech includes text language, emotion and tone, and the conversation content is set in real time in the conversation process in combination with the user's tag and the user's conversation content; The conversation robot conducts a conversation with the user according to the conversation information of the conversation robot, wherein the conversation information is used by the conversation robot to adjust the timbre, speech speed and intonation of the conversation robot according to the text information, sound information and logic information included in the conversation information during the conversation.

2. The method according to claim 1, characterized in that In the conversation process, the conversation content of the conversation robot is set accordingly in combination with the user's tag and the user's conversation content, including: In the dialogue process, combining the user's tag and the user's question content, and setting the answer content of the dialogue robot accordingly; or In the dialogue process, the question content of the dialogue robot is set accordingly in combination with the user's label and the user's answer content.

3. A dialogue setting device, applied to a dialogue robot, characterized in that: include: A user tag library establishment module is used to establish a user tag library. The user tag library establishment module includes: An information acquisition unit, used to acquire relevant information of the user in the business scenario and historical call information between the conversation robot and the user; A user tag generating unit, configured to generate a tag for the user according to the relevant information of the user in the business scenario and the historical call information, wherein the tag for the user is selected from the relevant information of the user in the business scenario and the keywords extracted from the historical call information; A user tag library establishing unit, used to establish a user tag library based on tags of a plurality of said users; A tag acquisition module, used to acquire the user's tag from the user tag library; A dialogue information setting module, used to set the dialogue information of the dialogue robot according to the user's tag and business scenario, the dialogue information includes dialogue content and dialogue flow, the dialogue flow includes the logic of the dialogue robot talking to the user, the dialogue flow is adjusted in real time according to the user's tag and the user's dialogue content, the dialogue flow is formed based on recommended services, the recommended services are determined according to the user's tag and the business scenario, the dialogue content includes the speech of the dialogue robot talking to the user, the speech includes text language, emotion and tone, and the dialogue content is set in real time in the dialogue flow in combination with the user's tag and the user's dialogue content; A dialogue control module is used to conduct a dialogue with the user based on the dialogue information of the dialogue robot, and the dialogue information is used by the dialogue robot to adjust the timbre, speaking speed and intonation of the dialogue robot according to the text information, sound information and logic information included in the dialogue information during the dialogue process.

4. A server comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the computer program is executed by the processor, the processor is caused to perform the steps of the dialog setting method according to any one of claims 1 and 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the dialog setting method according to any one of claims 1 and 2 are implemented.

Images