Customer service function navigation method and device, electronic equipment and storage medium

Abstract

The invention discloses a customer service function navigation method and device, electronic equipment and a storage medium, and relates to the technical field of natural language processing, and the method comprises the following steps: obtaining natural language information input by a user; determining the intention of the user according to the natural language information; searching a function module related to the intention in a local knowledge base to obtain a plurality of candidate function modules; calculating relevancy between the intention and each candidate function module according to the vector database; selecting one or more candidate function modules as recommended function modules according to the relevancy; and outputting operation guidance information of the recommended function module to the user. Access and query to an online platform can be reduced through a local knowledge base, and the response speed and stability of a customer service system are improved; the information of the candidate function module can be converted into the vector through the vector database, the relevancy between the vector and the intention is calculated, the recommended function module can be accurately selected according to the relevancy, and then appropriate operation guidance information is provided for the user.

Description

Technical Field

[0001] The present application relates to the field of natural language processing technology, and in particular to a customer service function navigation method, device, electronic device and storage medium. Background Art

[0002] In order to improve user experience and satisfaction, most online platforms provide customer service systems to answer users' questions and needs. Customer service systems usually interact with users in the form of natural language dialogue, that is, users can enter natural language to express questions or needs, and the customer service system outputs answers to guide users or provide solutions.

[0003] However, the existing customer service system has some problems and shortcomings. On the one hand, due to the numerous and complex functional modules of the online platform, users may not know which functional module to use or how to use a certain functional module. On the other hand, users may not be able to express their questions or needs in concise or accurate language, and the natural language understanding ability of the customer service system is limited, resulting in the inability to solve the problems raised by users. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a customer service function navigation method, device, electronic device and storage medium to provide effective solutions to user problems or needs.

[0005] To achieve the above purpose, one aspect of an embodiment of the present application provides a customer service function navigation method, the method comprising the following steps:

[0006] Obtain natural language information input by the user;

[0007] determining the user's intention according to the natural language information;

[0008] Searching for a functional module related to the intent in a local knowledge base to obtain multiple candidate functional modules;

[0009] Calculate the relevance between the intention and each of the candidate functional modules according to the vector database;

[0010] Selecting one or more of the candidate function modules as recommended function modules according to the relevance;

[0011] Outputting operation guidance information of the recommended function module to the user.

[0012] In some embodiments, determining the user's intention according to the natural language information comprises the following steps:

[0013] Extracting information keywords and entities from the natural language information;

[0014] The intention of the user is determined based on the information keywords and the entity.

[0015] In some embodiments, searching the local knowledge base for a functional module related to the intent to obtain a plurality of candidate functional modules comprises the following steps:

[0016] Searching for functional keywords related to the intent in the local knowledge base;

[0017] The function module containing the function keyword in the local knowledge base is determined as the candidate function module.

[0018] In some embodiments, the step of calculating the relevance between the intention and each of the candidate functional modules according to the vector database comprises the following steps:

[0019] Converting the intent into a vector as an intent vector;

[0020] Determining a module vector of each of the candidate function modules in the vector database; wherein the module vector includes a name vector and a function keyword vector of the candidate function module;

[0021] The correlation between the intention vector and each of the module vectors is calculated respectively.

[0022] In some embodiments, selecting one or more of the candidate function modules as recommended function modules according to the relevance comprises the following steps:

[0023] Sorting the candidate function modules from high to low according to the relevance;

[0024] One or more of the candidate function modules with the highest ranking are used as the recommended function modules.

[0025] In some embodiments, the outputting the operation guidance information of the recommended function module to the user includes the following steps:

[0026] At least one of an operation guidance text, an operation guidance image, an operation guidance audio, or an operation guidance link of the recommended function module is output to the user as the operation guidance information.

[0027] In some embodiments, the method further comprises the following steps:

[0028] receiving feedback information from the user on the recommended function module;

[0029] Determining whether the recommended function module meets the intention according to the feedback information;

[0030] If not, the process returns to the step of determining the user's intention based on the natural language information until it is determined based on the feedback information that the recommended function module satisfies the intention.

[0031] To achieve the above purpose, another aspect of the embodiment of the present application provides a customer service function navigation device, the device comprising:

[0032] An information acquisition unit, used to acquire natural language information input by a user;

[0033] an intention determination unit, configured to determine the user's intention according to the natural language information;

[0034] A function module search unit, used to search for function modules related to the intent in a local knowledge base to obtain multiple candidate function modules;

[0035] A relevance calculation unit, used for calculating the relevance between the intention and each of the candidate functional modules according to the vector database;

[0036] A function module selection unit, configured to select one or more of the candidate function modules as recommended function modules according to the relevance;

[0037] An operation guidance unit is used to output operation guidance information of the recommended function module to the user.

[0038] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned customer service function navigation method when executing the computer program.

[0039] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned customer service function navigation method is implemented.

[0040] The embodiments of the present application include at least the following beneficial effects:

[0041] This application can obtain natural language information input by the user; determine the user's intention based on the natural language information; search for functional modules related to the intention in the local knowledge base to obtain multiple candidate functional modules; calculate the relevance between the intention and each candidate functional module based on the vector database; select one or more candidate functional modules as recommended functional modules based on the relevance; and output the operation guidance information of the recommended functional modules to the user. The local knowledge base can reduce the access and query to the online platform, and improve the response speed and stability of the customer service system; the information of the candidate functional modules can be converted into vectors through the vector database, and the vector can be correlated with the intention. According to the relevance, the recommended functional module can be accurately selected, and then the user is provided with appropriate operation guidance information to solve the user's questions or meet the user's needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments 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 creative work.

[0043] Figure 1 A flowchart of a customer service function navigation method provided in an embodiment of the present application;

[0044] Figure 2 An example flow chart of a customer service function navigation method provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of the structure of a customer service function navigation device provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0048] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0049] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0051] Before describing the embodiments of the present application in detail, the related technologies involved in the embodiments of the present application are first described as follows:

[0052] Online platforms refer to platforms that provide various services and transactions through the Internet, such as e-commerce platforms, social platforms, education platforms, etc. Online platforms usually include multiple functional modules, such as product search, order management, returns and exchanges, evaluation feedback, etc. In order to improve user experience and satisfaction, most online platforms provide customer service systems to answer users' questions and needs.

[0053] Customer service systems usually interact with users through natural language dialogue, that is, users can express questions or needs by inputting natural language, and the customer service system can answer questions or guide users by outputting natural language.

[0054] However, the existing customer service system has some problems and shortcomings. On the one hand, due to the numerous and complex functional modules of the online platform, users may not know which functional module to use or how to use a certain functional module; for example, users need to check the order status, but do not know which page or column to find the order management function. On the other hand, users may not be able to express their questions or needs in concise or accurate language, and the natural language understanding ability of the customer service system is limited, resulting in the inability to solve the problems raised by users; for example, users need to return or exchange products, but do not know what vocabulary or grammar should be used to describe the problem or reason of the product.

[0055] Therefore, the embodiments of the present application provide a customer service function navigation method, device, electronic device and storage medium. The technical solution of the present application includes: obtaining natural language information input by the user; determining the user's intention based on the natural language information; searching for function modules related to the intention in the local knowledge base to obtain multiple candidate function modules; calculating the relevance between the intention and each candidate function module based on the vector database; selecting one or more candidate function modules as recommended function modules based on the relevance; and outputting the operation guidance information of the recommended function module to the user. The local knowledge base can reduce the access and query to the online platform, and improve the response speed and stability of the customer service system; the information of the candidate function module can be converted into a vector through the vector database, and the vector can be correlated with the intention. According to the relevance, the recommended function module can be accurately selected, thereby providing the user with appropriate operation guidance information to solve the user's questions or meet the user's needs.

[0056] The embodiment of the present application provides a customer service function navigation method, which relates to the field of natural language processing technology. The customer service function navigation method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server, the server can also be a node server in the blockchain network; the software can be an application that implements the customer service function navigation method, etc., but is not limited to the above forms.

[0057] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0058] Reference Figure 1 The embodiment of the present application provides a customer service function navigation method, which may include but is not limited to S100 to S150, as follows:

[0059] S100: Acquire natural language information input by a user.

[0060] Exemplarily, the natural language information may be information in text form. If the user inputs an image or audio, the embodiment of the present application may also extract the natural language information in text form from the image or audio.

[0061] S110: Determine the user's intention according to the natural language information.

[0062] It can be understood that the present embodiment can determine the user's intention from the natural language information, and the user's intention may be to solve a certain problem or to meet a certain demand.

[0063] Furthermore, S110 may include S111-S112:

[0064] S111: extracting information keywords and entities from the natural language information.

[0065] Exemplarily, information keywords may include texts expressing user demands such as "I want XXX", "I think XXX" or "Why XXX"; entities may include names of people, places, organizations or institutions, dates, times, etc.

[0066] S112: Determine the intention of the user according to the information keywords and the entity.

[0067] It can be understood that this embodiment can convert information keywords and entities into corresponding questions or needs, and the questions or needs serve as the user's intention.

[0068] S120: Searching for a function module related to the intent in a local knowledge base to obtain a plurality of candidate function modules.

[0069] Specifically, the local knowledge base refers to the knowledge base stored in the customer service system. The local knowledge base may include information such as the function module name, function description, function keywords, etc. of the online platform. For example, the local knowledge base may include the following information:

[0070] Functional module name: Order management;

[0071] Function description: Used to view, modify, cancel, evaluate and other operations on user orders;

[0072] Function keywords: order, status, modification, cancellation, evaluation, etc.

[0073] Further, S120 may include S121-S122:

[0074] S121: Searching for functional keywords related to the intent in the local knowledge base.

[0075] S122: Determine the function module containing the function keyword in the local knowledge base as the candidate function module.

[0076] Exemplarily, if the user's intention is "I want to cancel the order", this embodiment can determine that the functional keyword in the intention is "cancel", and then search for functional modules whose functional keywords include "cancel" in the local knowledge base, such as finding the above-mentioned order management module, and then use the order management module as a candidate functional module.

[0077] The local knowledge base can reduce visits and queries to online platforms and improve the response speed and stability of the customer service system.

[0078] S130: Calculate the relevance between the intention and each of the candidate functional modules according to the vector database.

[0079] Specifically, the vector database refers to a database that converts the names and function keywords of the function modules in the local knowledge base into vectors and stores them in the customer service system. In this embodiment, the relevance between the intent and each candidate function module can be calculated through the vector database. For example, the vector database may contain the following information:

[0080] Name of the functional module: Order Management;

[0081] Function module name vector: [0.2, 0.5, 0.3, 0.1, 0.4];

[0082] Function keywords: order, status, modification, cancellation, evaluation, etc.

[0083] Function keyword vectors: [0.3, 0.6, 0.2, 0.1, 0.5], [0.4, 0.7, 0.1, 0.2, 0.6], [0.2, 0.4, 0.3, 0.1, 0.3], [0.1, 0.3, 0.2, 0.4, 0.2], [0.3, 0.5, 0.4, 0.2, 0.7], etc.

[0084] Further, S130 may include:

[0085] S131: Convert the intention into a vector as an intention vector.

[0086] It is understandable that users Figure 1 Generally, it is text. In this embodiment, the text can be converted into a vector as an intention vector.

[0087] S132: Determine a module vector of each of the candidate function modules in the vector database; wherein the module vector includes a name vector and a function keyword vector of the candidate function module.

[0088] Specifically, this embodiment can search for the module vector of each candidate functional module from the vector database.

[0089] S133: Calculate the correlation between the intention vector and each of the module vectors respectively.

[0090] Specifically, this embodiment can calculate the correlation between the intention vector and each module vector, that is, obtain the correlation between the user's intention and each candidate functional module.

[0091] The vector database can be used to convert the names of functional modules and functional keywords into vector representations, and similarity calculations can be used to match user intentions and functional modules, thereby improving the functional search and recommendation effects of the customer service system.

[0092] S140: Select one or more of the candidate function modules as recommended function modules according to the relevance.

[0093] It can be understood that, in this embodiment, several suitable candidate function modules can be selected as recommended function modules according to the relevance between each candidate function module and the intention.

[0094] Further, S140 may include S141-S142:

[0095] S141: Sort the candidate function modules from high to low according to the relevance.

[0096] S142: Use one or more of the candidate function modules with the highest ranking as the recommended function modules.

[0097] It is understandable that the higher the relevance, the more the candidate function module matches the user's intention. Therefore, in this embodiment, several candidate function modules with the highest relevance rankings may be selected as recommended function modules.

[0098] S150: Outputting operation guidance information of the recommended function module to the user.

[0099] Specifically, the operation guidance information may include the location of the recommended function module, operation steps, solvable problems or operation effective time, etc.

[0100] Furthermore, S150 may include:

[0101] At least one of an operation guidance text, an operation guidance image, an operation guidance audio, or an operation guidance link of the recommended function module is output to the user as the operation guidance information.

[0102] Exemplarily, the user clicks on the operation guide link to jump to the interface of the recommended function module, and the interface can also display the above-mentioned operation guide information.

[0103] To further improve the user experience, the embodiment of the present application may further include the following steps:

[0104] S160: Receive feedback information from the user on the recommended function module.

[0105] Exemplarily, the feedback information may include whether the user's intention is met, or other intentions.

[0106] S170: Determine whether the recommended function module meets the intention according to the feedback information.

[0107] In this embodiment, feedback options may be pre-set, and the feedback options may include whether the user is satisfied with the recommended function module, whether the intention is met, etc. If the user selects an unsatisfactory or unsatisfactory option, it can be determined that the recommended function module fails to meet the user's intention.

[0108] S180: If not satisfied, return to the step of determining the user's intention according to the natural language information until it is determined according to the feedback information that the recommended function module satisfies the intention.

[0109] It is understandable that if the recommended function module does not meet the user's intention, the process may return to step S110 to redefine the user's intention, that is, obtain an intention different from the previous round of intentions, and then execute S120 to S170 until it is determined based on the feedback information that the recommended function module meets the user's intentions.

[0110] Next, the solution of the embodiment of the present application will be described in detail and explained in conjunction with specific application examples:

[0111] In this embodiment, a customer service function navigation method for multi-round natural dialogue based on a local knowledge base, a vector database, and an LLM (Large Language Model) (wherein, in this embodiment, the LLM can be pre-trained and fine-tuned, and then the customer service function navigation method provided by this embodiment is executed using the LLM, that is, the LLM can generate and output corresponding operation guidance information according to the natural language information input by the user, guide the user to conduct multi-round dialogue, and realize customer service function navigation), this embodiment may include the following steps:

[0112] S101: receiving natural language information input by a user;

[0113] S102: Analyze the natural language information input by the user, and extract information such as keywords, intent, entities, etc. in the natural language information;

[0114] S103: According to the analysis and extraction results of S102, search the local knowledge base for functional modules related to the user's intention, and generate a list of candidate functional modules;

[0115] S104: Calculate the relevance between the user's intention and each candidate function module according to the vector database; sort the candidate function module list according to the relevance between the function modules in the candidate function module list and the intention, and select one or more candidate function modules with the highest ranking as recommended function modules;

[0116] S105: Outputting the recommended function module to the user and providing corresponding operation guidance information; wherein the operation guidance information may include an operation guidance link;

[0117] S106: receiving user feedback information on the recommended function module;

[0118] S107: judging whether the recommended function module meets the user's intention according to the feedback information;

[0119] S108: If the recommended function module meets the user's intention, the conversation ends; if the recommended function module does not meet the user's intention, return to S102 to continue analyzing the natural language information input by the user until the recommended function module meets the user's intention, and then end the conversation.

[0120] Figure 2 This is an example flow chart of a customer service function navigation method provided in this embodiment. Figure 2 The present embodiment will be described in detail with reference to more specific examples.

[0121] Assume that the online platform is an e-commerce platform, which provides functional modules such as product search, order management, return and exchange, and evaluation feedback. The local knowledge base stores the above functional modules and their related information. The names, functional descriptions, and functional keywords of the functional modules are as follows:

[0122] Product search: used to search for products on the platform, and can be filtered by category, price, sales volume and other conditions; product, search, filter, category, price, sales volume, etc.

[0123] Order management: used to view, modify, cancel, evaluate and other operations on user orders; order, status, modification, cancellation, evaluation, etc.

[0124] Return and Exchange: Used to apply for return and exchange of goods purchased on the platform. You need to fill in the reason for return and exchange and contact information; return and exchange, after-sales service, application, reason, contact information, etc.

[0125] Evaluation and feedback: used to evaluate or provide feedback on the goods or services purchased on the platform. Images or texts can be uploaded; evaluation and feedback, product evaluation, service evaluation, image upload, text input, etc.

[0126] The vector database stores the vector representation of the above functional modules and their related information. The names, name vectors, functional keywords, and functional keyword vectors of the functional modules are respectively exemplified as follows:

[0127] Product search; [0.2, 0.5, 0.3, 0.1, 0.4]; product, search, filter, category, price, sales volume, etc.; [0.3, 0.6, 0.2, 0.1, 0.5], [0.4, 0.7, 0.1, 0.2, 0.6], [0.2, 0.4, 0.3, 0.1, 0.3], [0.1, 0.3, 0.2, 0.4, 0.2], [0.3, 0.5, 0.4, 0.2, 0.7].

[0128] Example 1: LLM can generate the following operation guidance information for "I want to return a product" based on the natural language information entered by the user:

[0129] Hello, you can return or exchange products in the following ways:

[0130] Click here to enter the after-sales service page, select the product you want to return, fill in the reason for return and contact information, and submit your application.

[0131] Do you have any other questions?

[0132] Example 2: If the user inputs the natural language information "I want to check my order", LLM may not be able to judge, and LLM will continue to ask the customer: Do you want to call the API or HTTP? If the user answers "API", LLM can generate the following operation guidance information:

[0133]

Call API

[0134] Hello, you can check your order in the following ways:

[0135] Click here to enter the order management page to check your order status and logistics information;

[0136] Do you have any other questions?

[0137] LLM is an intelligent model similar to ChatGPT. It is understandable that LLM can generate different operation guidance information based on different natural language information, and guide users to conduct multiple rounds of dialogue to achieve function navigation. Optionally, LLM can improve the quality and adaptability of generating operation guidance information through pre-training and fine-tuning.

[0138] More specifically, assuming that the natural language information input by the user is "I want to buy a book", the LLM can perform the following steps:

[0139] S201: receiving natural language information input by a user, that is, “I want to buy a book”;

[0140] S202: Analyze the natural language information input by the user, and extract information such as keywords, intents, entities, etc. in the natural language information, such as the keywords are "buy" and "book", the intent is "buy goods", and the entity is "book";

[0141] S203: According to the analysis and extraction results of S202, search for function modules related to the intent in the local knowledge base, and generate a list of candidate function modules, such as [product search, order management, return and exchange, evaluation feedback];

[0142] S204: Calculate the relevance between the user's intention and each candidate function module according to the vector database; sort the candidate function module list according to the relevance between the function modules in the candidate function module list and the intention, and select one or more candidate function modules with the highest ranking as recommended function modules, such as the recommended function module is [product search];

[0143] S205: Outputting a recommendation function module to the user and providing corresponding operation guidance information, such as outputting “Hello, you can find the books you want through the product search function. Click the following link to enter the product search page. You can filter your favorite books according to categories, prices, sales volume and other conditions”;

[0144] S206: receiving user feedback information on the recommendation function module, such as the user clicking a link on a product search page;

[0145] S207: judging whether the user's intention is met according to the feedback information, such as judging that the user has entered the product search page, and continuing to use the recommendation function module to operate;

[0146] S208: If the recommended function module meets the user's intention, the conversation ends; if the recommended function module does not meet the user's intention, the process returns to S202 to continue analyzing the natural language information input by the user.

[0147] It can be understood that the LLM of this embodiment uses the local knowledge base and vector database to quickly and accurately find and recommend relevant functional modules based on the natural language information input by the user, and provides corresponding operation guidance information to guide the user to conduct multiple rounds of dialogue to achieve functional navigation.

[0148] Reference Figure 3 The embodiment of the present application also provides a customer service function navigation device, which can implement the above-mentioned customer service function navigation method, and the device includes:

[0149] An information acquisition unit, used to acquire natural language information input by a user;

[0150] an intention determination unit, configured to determine the user's intention according to the natural language information;

[0151] A function module search unit, used to search for function modules related to the intent in a local knowledge base to obtain multiple candidate function modules;

[0152] A relevance calculation unit, used for calculating the relevance between the intention and each of the candidate functional modules according to the vector database;

[0153] A function module selection unit, configured to select one or more of the candidate function modules as recommended function modules according to the relevance;

[0154] An operation guidance unit is used to output operation guidance information of the recommended function module to the user.

[0155] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0156] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above customer service function navigation method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0157] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0158] See also Figure 4 , Figure 4 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0159] The processor 401 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0160] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the customer service function navigation method of the embodiment of this application;

[0161] Input / output interface 403, used to implement information input and output;

[0162] Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0163] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0164] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0165] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned customer service function navigation method is implemented.

[0166] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0167] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0169] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0170] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0172] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0173] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0175] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0178] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A customer service function navigation method, characterized in that: The method comprises the following steps: Obtain natural language information input by the user; determining the user's intention according to the natural language information; Searching for a functional module related to the intent in a local knowledge base to obtain multiple candidate functional modules; Calculate the relevance between the intention and each of the candidate functional modules according to the vector database; Selecting one or more of the candidate function modules as recommended function modules according to the relevance; Outputting operation guidance information of the recommended function module to the user.

2. A customer service function navigation method according to claim 1, characterized in that: Determining the user's intention according to the natural language information comprises the following steps: Extracting information keywords and entities from the natural language information; The intention of the user is determined based on the information keywords and the entity.

3. A customer service function navigation method according to claim 1, characterized in that: The step of searching the local knowledge base for a functional module related to the intent to obtain a plurality of candidate functional modules includes the following steps: Searching for functional keywords related to the intent in the local knowledge base; The function module containing the function keyword in the local knowledge base is determined as the candidate function module.

4. A customer service function navigation method according to claim 1, characterized in that: The step of calculating the relevance between the intention and each of the candidate functional modules according to the vector database comprises the following steps: Converting the intent into a vector as an intent vector; Determining a module vector of each of the candidate function modules in the vector database; wherein the module vector includes a name vector and a function keyword vector of the candidate function module; The correlation between the intention vector and each of the module vectors is calculated respectively.

5. A customer service function navigation method according to claim 1, characterized in that: The step of selecting one or more candidate function modules as recommended function modules according to the relevance comprises the following steps: Sorting the candidate function modules from high to low according to the relevance; One or more of the candidate function modules with the highest ranking are used as the recommended function modules.

6. A customer service function navigation method according to claim 1, characterized in that: The step of outputting the operation guidance information of the recommended function module to the user comprises the following steps: At least one of an operation guidance text, an operation guidance image, an operation guidance audio, or an operation guidance link of the recommended function module is output to the user as the operation guidance information.

7. A customer service function navigation method according to any one of claims 1 to 6, characterized in that: The method further comprises the following steps: receiving feedback information from the user on the recommended function module; Determining whether the recommended function module meets the intention according to the feedback information; If not, the process returns to the step of determining the user's intention based on the natural language information until it is determined based on the feedback information that the recommended function module satisfies the intention.

8. A customer service function navigation device, characterized in that: The device comprises: An information acquisition unit, used to acquire natural language information input by a user; an intention determination unit, configured to determine the user's intention according to the natural language information; A function module search unit, used to search for function modules related to the intent in a local knowledge base to obtain multiple candidate function modules; A relevance calculation unit, used for calculating the relevance between the intention and each of the candidate functional modules according to the vector database; A function module selection unit, configured to select one or more of the candidate function modules as recommended function modules according to the relevance; An operation guidance unit is used to output operation guidance information of the recommended function module to the user.

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

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

Images