Movatterモバイル変換


[0]ホーム

URL:


CN116437011A - Method, device, equipment, storage medium and product for intelligently answering user demands - Google Patents

Method, device, equipment, storage medium and product for intelligently answering user demands
Download PDF

Info

Publication number
CN116437011A
CN116437011ACN202310251673.3ACN202310251673ACN116437011ACN 116437011 ACN116437011 ACN 116437011ACN 202310251673 ACN202310251673 ACN 202310251673ACN 116437011 ACN116437011 ACN 116437011A
Authority
CN
China
Prior art keywords
user
demand information
unit
call
user demand
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310251673.3A
Other languages
Chinese (zh)
Inventor
张姣姣
万莹
宋伟
邢宁哲
赵子兰
于蒙
于然
徐鑫
吴舜
张翼
张东辉
佟昆睿
赵烨
齐灿
段寒硕
毛一先
杜剑雯
张阳洋
那琼澜
吕海军
于林
汤伟
曹世杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Information and Telecommunication Branch of State Grid Jibei Electric Power Co Ltd
State Grid Corp of China SGCC
Original Assignee
Information and Telecommunication Branch of State Grid Jibei Electric Power Co Ltd
State Grid Corp of China SGCC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Information and Telecommunication Branch of State Grid Jibei Electric Power Co Ltd, State Grid Corp of China SGCCfiledCriticalInformation and Telecommunication Branch of State Grid Jibei Electric Power Co Ltd
Priority to CN202310251673.3ApriorityCriticalpatent/CN116437011A/en
Publication of CN116437011ApublicationCriticalpatent/CN116437011A/en
Pendinglegal-statusCriticalCurrent

Links

Images

Classifications

Landscapes

Abstract

The present disclosure relates to the field of communications, and more particularly, to a method, apparatus, device, storage medium, and article of manufacture for intelligently answering user needs. The method comprises the following steps: judging whether the demand information of the user call accords with the incoming call interception rule; if yes, intercepting the call of the user; if the information is not met, determining service response equipment according to the user demand information; according to the busy and idle state of the service processing unit in the service response equipment, determining a service processing target unit of user demand information; and sending the user demand information to a business processing target unit so that the business processing target unit can intelligently answer the user demand information by combining the question-answer database. According to the method and the device, the user call which does not accord with the incoming call interception rule is intercepted by identifying the requirement information of the user, the user requirement information which accords with the incoming call interception rule is provided for the service processing unit of the service response equipment for processing, unnecessary response can be reduced, and the processing pressure of a call center is reduced.

Description

Translated fromChinese
智能回答用户需求的方法、装置、设备、存储介质及产品Method, device, equipment, storage medium and product for intelligently answering user needs

技术领域technical field

本文涉及通信领域,尤其是智能回答用户需求的方法、装置、设备、存储介质及产品。This article relates to the field of communications, especially methods, devices, equipment, storage media and products for intelligently answering user needs.

背景技术Background technique

当前,各种业务系统对客服服务的要求逐渐提高,目前人工客服解答海量客户的大量问题,客服资源短缺、客服工作压力大,且很有可能出现错误,降低服务效率和质量。At present, the requirements of various business systems for customer service are gradually increasing. At present, manual customer service answers a large number of questions from a large number of customers. Customer service resources are short, customer service pressure is high, and errors are likely to occur, reducing service efficiency and quality.

另外,目前常见的系统通常对用户发起的呼叫请求无差别进行响应,而无法根据不同用户的情绪、用户所处的环境及用户咨询的业务作出相应不同的处理,或对部分用户请求进行拦截,容易造成系统较大的处理压力,造成响应系统的资源浪费。因此目前的业务服务响应系统不够智能、处理效率不够高。In addition, the current common systems usually respond to the call requests initiated by the users indiscriminately, but cannot make corresponding different processing according to the emotions of different users, the environment in which the users are located, and the business consulted by the users, or intercept some user requests. It is easy to cause a large processing pressure on the system and cause a waste of resources in the response system. Therefore, the current business service response system is not intelligent enough and the processing efficiency is not high enough.

发明内容Contents of the invention

为解决上述现有的客服服务呼叫系统服务效率低、不够便捷的问题,本文实施例提供了一种智能回答用户需求的方法、装置、设备、存储介质及产品。In order to solve the problems of low service efficiency and inconvenient service in the existing customer service calling system mentioned above, the embodiments of this paper provide a method, device, equipment, storage medium and product for intelligently answering user needs.

本文实施例公开了一种智能回答用户需求的方法,所述方法包括:判断用户呼叫的需求信息是否符合来电拦截规则;若符合,拦截所述用户的呼叫;若不符合,根据用户需求信息,确定业务响应设备;根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元;发送用户需求信息至业务处理目标单元,以由所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答。The embodiment of this document discloses a method for intelligently answering user needs. The method includes: judging whether the demand information of the user's call conforms to the call interception rules; determining the business response device; determining the business processing target unit of the user demand information according to the busy state of the business processing unit in the business response device; sending the user demand information to the business processing target unit, so that the business processing target unit combines the question-and-answer database, Provide intelligent answers to user demand information.

根据本文实施例的一个方面,所述判断用户呼叫的需求信息是否符合来电拦截规则包括:对用户需求信息进行情绪分析,确定所述用户的情绪;对用户需求信息进行环境分析,确定用户所处的环境;对用户需求信息进行语义分析,确定所述用户的呼叫意图;判断用户的情绪、所处环境及呼叫意图是否分别符合来电拦截规则中预设的情绪、环境及意图;若所述用户的情绪、所处环境及呼叫意图中的任意一项,不符合来电拦截规则,确定用户需求信息不符合来电拦截规则。According to an aspect of the embodiments herein, the judging whether the demand information of the user call conforms to the call interception rule includes: performing sentiment analysis on the user demand information to determine the user's emotion; performing environmental analysis on the user demand information to determine the user's location. environment; perform semantic analysis on user demand information to determine the call intention of the user; determine whether the user's emotion, environment, and call intention are in line with the preset emotion, environment, and intention in the call interception rules; if the user Any one of the emotion, environment, and call intention does not meet the call interception rules, and it is determined that the user demand information does not meet the call interception rules.

根据本文实施例的一个方面,确定出所述用户的情绪、所处环境及呼叫意图中的任意一项,不符合来电拦截规则后,还包括:确定用户需求信息不符合来电拦截规则中预设的情绪、环境、意图中的具体结果项;根据结果项,向用户发出改进提醒信息。According to an aspect of the embodiments herein, after determining that any one of the user's emotion, environment, and call intention does not comply with the incoming call interception rule, it also includes: determining that the user's demand information does not comply with the preset in the incoming call interception rule Specific result items in emotions, environments, and intentions; according to the result items, an improvement reminder message is sent to the user.

根据本文实施例的一个方面,所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答包括:将所述用户需求信息转换为文本;基于NLP算法对所述文本进行处理,得到用户需求信息中的关键词;将所述关键词与问答数据库中的问答数据对进行匹配,得到匹配结果;根据所述匹配结果,对用户需求信息提供智能回答。According to an aspect of the embodiments herein, the business processing target unit combined with the question-and-answer database to intelligently answer user demand information includes: converting the user demand information into text; processing the text based on NLP algorithms to obtain user demand information keywords in the information; match the keywords with the question-answer data pairs in the question-answer database to obtain matching results; and provide intelligent answers to user demand information according to the matching results.

根据本文实施例的一个方面,根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元包括:将业务响应设备中处于空闲状态的业务处理单元,确定为业务处理备选单元;从所述业务处理备选单元中,随机选取其中一个单元与用户通信;确定用户与随机选取的单元是否通信成功;若是,所述随机选取的单元为业务处理目标单元;若否,确定用户与所述随机选取的业务处理单元的备用单元是否通信成功;若是,确定所述随机选取的业务处理单元的备用单元为所述业务处理目标单元;若否,从业务处理备选单元中选择其他单元与用户通信,重复判断其他单元及其备用单元是否与用户是否通信成功。According to an aspect of the embodiments herein, according to the busy state of the service processing unit in the service response device, determining the service processing target unit of the user demand information includes: determining the service processing unit in the service response device in the idle state as the service processing standby select unit; from the business processing alternative units, randomly select one of the units to communicate with the user; determine whether the user communicates successfully with the randomly selected unit; if so, the randomly selected unit is the business processing target unit; if not, Determine whether the communication between the user and the standby unit of the randomly selected service processing unit is successful; if yes, determine that the standby unit of the randomly selected service processing unit is the service processing target unit; Select other units to communicate with the user, and repeatedly judge whether other units and their standby units communicate successfully with the user.

根据本文实施例的一个方面,所述对用户需求信息进行语义分析包括:将用户需求信息进行文字转换、文字提取及语义分析,确定用户需求信息中的关键字及所述关键字在用户需求信息中的词频;确定所述关键字是否属于预设数据库中记录的关键字;若是,根据所述关键字及词频,确定关键字对应的优先级;若所述优先级超出预设阈值,将所述用户与应急响应模块直接建立通信。According to an aspect of the embodiments herein, the semantic analysis of the user demand information includes: performing text conversion, text extraction and semantic analysis on the user demand information, determining the keywords in the user demand information and the keywords in the user demand information Word frequency in; Determine whether the keyword belongs to the keyword recorded in the preset database; If so, determine the corresponding priority of the keyword according to the keyword and word frequency; if the priority exceeds the preset threshold, the The above-mentioned user establishes communication directly with the emergency response module.

本文实施例还公开了一种智能回答用户需求的装置,所述装置包括:判断单元,用于判断用户需求信息是否符合来电拦截规则;若符合,拦截所述用户的呼叫;若不符合,根据所述用户需求信息中的业务需求信息,确定业务响应设备;业务处理目标单元确定单元,用于根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元;智能回答单元,用于由所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答。The embodiment of this paper also discloses a device for intelligently answering user needs. The device includes: a judging unit for judging whether the user demand information complies with the incoming call interception rules; if so, intercepting the user's call; The business demand information in the user demand information determines the business response equipment; the business processing target unit determination unit is used to determine the business processing target unit of the user demand information according to the busy state of the business processing unit in the business response equipment; intelligent answer A unit is used for intelligently answering user demand information by combining the business processing target unit with the question-and-answer database.

本文实施例还提供了一种计算机设备,所述计算机设备包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现所述方法。The embodiment of this document also provides a computer device, the computer device includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the method is implemented when the processor executes the computer program .

本文实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现所述方法。The embodiment of this document also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method is implemented.

本文实施例还提供了一种计算机程序产品,所述计算机程序产品包括计算机程序,所述计算机程序被处理器执行时实现所述方法。The embodiment of this document also provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the method is implemented.

本申请通过识别用户的需求信息,拦截不符合来电拦截规则的用户呼叫,将符合来电拦截规则的用户需求信息提供给业务响应设备的业务处理单元处理,能够减少不必要的应答,降低呼叫中心的处理压力。This application intercepts user calls that do not meet the call interception rules by identifying the user's demand information, and provides the user demand information that meets the call interception rules to the service processing unit of the service response device for processing, which can reduce unnecessary responses and reduce the call center's workload. Deal with stress.

附图说明Description of drawings

为了更清楚地说明本文实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本文的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments or prior art herein, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments or prior art. Obviously, the accompanying drawings in the following description are only For some embodiments herein, those skilled in the art can also obtain other drawings based on these drawings without creative effort.

图1所示为本文实施例一种智能回答用户需求的方法流程图;Fig. 1 shows a flow chart of a method for intelligently answering user needs according to an embodiment of this paper;

图2所示为本文实施例一种判断用户需求信息是否符合来电拦截规则的方法流程图;Fig. 2 shows a kind of flow chart of the method for judging whether the user demand information conforms to the incoming call interception rule according to the embodiment of this paper;

图3所示为本文实施例一种向用户发出改进提醒的方法流程图;FIG. 3 is a flow chart of a method for sending an improvement reminder to a user according to an embodiment of this paper;

图4所示为本文实施例一种确定业务处理目标单元的方法流程图;FIG. 4 is a flow chart of a method for determining a business processing target unit according to an embodiment of this paper;

图5所示为本文实施例一种对用户需求信息进行语义分析的方法流程图;FIG. 5 is a flow chart of a method for semantic analysis of user demand information according to an embodiment of this paper;

图6所示为本文实施例一种智能回答用户需求装置的结构示意图;Fig. 6 is a schematic structural diagram of an intelligent answering user demand device according to an embodiment of this paper;

图7所示为本实施例基于智能回答用户需求装置的具体结构示意图;Fig. 7 shows the specific structural diagram of the device based on intelligent answering user needs in this embodiment;

图8所示为本文实施例一种计算机设备的结构示意图。FIG. 8 is a schematic structural diagram of a computer device according to an embodiment of this document.

附图符号说明:Explanation of reference symbols:

601、判断单元;601. Judgment unit;

6011、情绪分析模块;6011. Sentiment analysis module;

6012、环境分析模块;6012. Environmental analysis module;

6013、意图分析模块;6013. Intent analysis module;

602、确定单元;602. Determine the unit;

6021、业务处理备选单元确定模块;6021. A business processing alternative unit determination module;

6022、通信确定模块;6022. Communication determination module;

603、智能回答单元;603. Intelligent answering unit;

802、计算机设备;802. Computer equipment;

804、处理器;804. Processor;

806、存储器;806. memory;

808、驱动机构;808. Driving mechanism;

810、输入/输出模块;810. Input/output module;

812、输入设备;812. Input device;

814、输出设备;814. Output device;

816、呈现设备;816. Presentation equipment;

818、图形用户接口;818. Graphical user interface;

820、网络接口;820. Network interface;

822、通信链路;822. Communication link;

824、通信总线。824. Communication bus.

具体实施方式Detailed ways

为了使本技术领域的人员更好地理解本说明书中的技术方案,下面将结合本文实施例中的附图,对本文实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本文一部分实施例,而不是全部的实施例。基于本文中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本文保护的范围。In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this paper will be clearly and completely described below in conjunction with the drawings in the embodiments of this paper. Obviously, the described implementation Examples are only some of the embodiments herein, not all of them. Based on the embodiments herein, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts fall within the scope of protection herein.

需要说明的是,本文的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本文的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、装置、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。It should be noted that the terms "first" and "second" in the description and claims herein and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments herein described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, means, product or equipment comprising a series of steps or elements need not be limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

本说明书提供了如实施例或流程图所述的方法操作步骤,但基于常规或者无创造性的劳动可以包括更多或者更少的操作步骤。实施例中列举的步骤顺序仅仅为众多步骤执行顺序中的一种方式,不代表唯一的执行顺序。在实际中的系统或装置产品执行时,可以按照实施例或者附图所示的方法顺序执行或者并行执行。This description provides the operation steps of the method described in the embodiment or flow chart, but more or less operation steps may be included based on routine or non-creative work. The sequence of steps enumerated in the embodiments is only one of the execution sequences of many steps, and does not represent the only execution sequence. When an actual system or device product is executed, it may be executed sequentially or in parallel according to the methods shown in the embodiments or drawings.

需要说明的是,本文的智能回答用户需求方法可用于通信领域,也可用于电力技术领域,本文对智能回答用户需求方法及装置的应用领域不做限定。It should be noted that the method for intelligently answering user needs in this paper can be used in the field of communication, and can also be used in the field of electric power technology. This article does not limit the application fields of the method and device for intelligently answering user needs.

图1所示为本文实施例一种智能回答用户需求的方法流程图,具体包括如下步骤:Figure 1 shows a flow chart of a method for intelligently answering user needs in an embodiment of this paper, which specifically includes the following steps:

步骤101,判断用户呼叫的需求信息是否符合来电拦截规则。在本步骤中,用户呼叫的形式包括:拨打电话、线上接入等方式。用户呼叫中包含的需求信息包括:用户想要办理的业务、用户咨询、用户投诉等。Step 101, judging whether the demand information of the user's call complies with the call interception rule. In this step, the form of the user's call includes: making a phone call, accessing online, and the like. The demand information contained in the user call includes: the service that the user wants to handle, user consultation, user complaint, and so on.

在本说明书的一些实施例中,来电拦截规则用于对用户呼叫进行预处理。其中,来电拦截规则预先规定了属于拦截来电的信息范围,包括但不限于:背景嘈杂无法准确识别需求信息的用户呼叫、用户情绪激动的用户呼叫、用户需求信息与业务不相关的用户呼叫。In some embodiments of the present specification, the incoming call interception rules are used to pre-process user calls. Among them, the call interception rules pre-determine the scope of information belonging to intercepted calls, including but not limited to: user calls with noisy backgrounds that cannot accurately identify demand information, user calls with emotional excitement, and user calls with user demand information that is not related to business.

步骤102,若符合,拦截所述用户的呼叫。在本步骤中,若用户呼叫的需求信息符合来电拦截规则,则拦截用户的呼叫,在本次过程中,不再处理该用户的呼叫请求。进一步的,可以根据用户呼叫的内容,对用户提出相应改进或提醒,直到用户下次呼叫的需求信息不符合来电拦截规则,以便使用户呼叫的需求信息能够得到处理。Step 102, if it matches, intercept the user's call. In this step, if the demand information of the user's call meets the incoming call interception rule, the user's call is intercepted, and in this process, the user's call request is no longer processed. Further, according to the content of the user's call, corresponding improvements or reminders can be proposed to the user until the demand information of the user's next call does not meet the call interception rules, so that the demand information of the user call can be processed.

步骤103,若不符合,根据用户需求信息,确定业务响应设备。在本步骤中,识别用户呼叫的需求信息,确定用户需求信息与业务相关内容的内容,进而确定能够对该用户需求进行准确响应的业务响应设备。例如,用户需求信息为:办理交费业务,则通过识别该用户呼叫内容中的交费关键词,从大量的业务响应设备中,选择交费业务响应设备作为该用户的服务设备。Step 103, if not, determine the service response device according to the user demand information. In this step, the demand information of the user call is identified, the content of the user demand information and service-related content is determined, and then the service response device capable of accurately responding to the user demand is determined. For example, if the user demand information is: to handle the payment service, then by identifying the payment keyword in the call content of the user, select the payment service response device from a large number of service response devices as the user's service device.

步骤104,根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元。Step 104, according to the busy state of the service processing unit in the service response device, determine the service processing target unit of the user demand information.

在本说明书的一些实施例中,同一类型的业务响应设备,可能包含多个业务处理单元。其中,业务处理单元可以理解为用于服务用户呼叫的最小处理单元。其中,每台业务处理单元具有对应的工作忙闲状态,包括:工作状态、待机状态、无应答状态等。选择处于待机状态的业务处理单元,作为用户需求信息的业务处理目标单元,处理用户业务需求。In some embodiments of this specification, a service response device of the same type may include multiple service processing units. Wherein, the service processing unit can be understood as the smallest processing unit for serving user calls. Wherein, each business processing unit has a corresponding busy or idle state, including: working state, standby state, no response state, etc. The service processing unit in the standby state is selected as the service processing target unit of the user demand information to process the user's business demand.

步骤105,发送用户需求信息至业务处理目标单元,以由所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答。本步骤中,当业务处理目标单元接收到用户呼叫的需求信息后,由业务处理目标单元根据问答数据库,匹配与用户呼叫的需求信息相关或相似的问题,并确定相应的回答。将所述回答反馈至用户,实现智能回答。Step 105, sending the user demand information to the business processing target unit, so that the business processing target unit can intelligently answer the user demand information in combination with the question-and-answer database. In this step, after the service processing target unit receives the demand information of the user call, the service processing target unit matches questions related to or similar to the demand information of the user call according to the question-and-answer database, and determines the corresponding answer. The answer is fed back to the user to realize intelligent answer.

图2所示为本文实施例一种判断用户需求信息是否符合来电拦截规则的方法流程图,具体包括如下步骤:Figure 2 shows a flow chart of a method for judging whether user demand information meets the incoming call interception rules according to the embodiment of this paper, which specifically includes the following steps:

步骤201,对用户需求信息进行情绪分析,确定所述用户的情绪。在本说明书的一些实施例中,用户呼叫的需求信息可以是语音形式的信息,通过对用户呼叫的语音信息进行特征识别,提取得到语音特征或音素特征。其中,语音特征包括语调、语速、音色特征、语音数据的波形特征等。将提取到的语音特征与声谱图进行比对,识别得到用户的情绪。进一步的,对用户情绪进行分类,例如,将用户情绪划分为:平和、正常、着急、激动、崩溃等不同类型。Step 201, performing sentiment analysis on user demand information to determine the user's mood. In some embodiments of this specification, the demand information called by the user may be information in the form of voice, and the voice feature or phoneme feature is extracted by performing feature recognition on the voice information called by the user. Among them, the voice features include intonation, speech rate, timbre features, waveform features of voice data, and the like. Compare the extracted speech features with the spectrogram to identify the user's emotion. Further, user emotions are classified, for example, user emotions are divided into different types such as peaceful, normal, anxious, excited, and collapsed.

步骤202,对用户需求信息进行环境分析,确定用户所处的环境。在本申请中,可以利用噪音识别模型对用户需求的语音信息进行特征提取,得到音频片段。进一步的,对音频片段进行识别,区分音频片段中的语音片段和非语音片段。提取非语音片段中,短时过零率和短时能量两类特征,通过统计非语音片段满足短时能量和短时过零率分布范围的最大帧数占非语音片段总帧数的比例,完成对用户需求信息的环境分析。进一步的,根据非语音片段中,满足短时能量和短时过零率分布范围的最大帧数占非语音片段总帧数的比例值的大小,对环境进行分类或打分,确定用户所处的环境嘈杂程度为一级、二级或三级,进一步的,可以根据比例值的大小,将用户所处的环境区分为:安静、嘈杂但能识别人声、操作无法识别人声等不同程度。Step 202, analyzing the environment of the user demand information to determine the environment in which the user is located. In this application, the noise recognition model can be used to extract features of the voice information required by the user to obtain audio clips. Further, the audio segments are identified, and speech segments and non-speech segments in the audio segments are distinguished. Extract the two types of features, short-term zero-crossing rate and short-term energy, from non-speech segments, and calculate the ratio of the maximum number of frames in the non-speech segments that meet the distribution range of short-term energy and short-term zero-crossing rate to the total number of non-speech segments. Complete the environmental analysis of user demand information. Further, according to the proportion of the maximum number of frames satisfying the distribution range of short-term energy and short-term zero-crossing rate in the non-speech segment to the total number of frames of the non-speech segment, the environment is classified or scored, and the user's location is determined. The environmental noise level is Level 1, Level 2, or Level 3. Further, according to the scale value, the user's environment can be divided into different levels: quiet, noisy but human voice can be recognized, and human voice cannot be recognized by operation.

步骤203,对用户需求信息进行语义分析,确定所述用户的呼叫意图。在本申请中,对用户需求信息进行分词、语音特征提取,对提取得到的语音特征进行语义分析,识别用户的需求信息中的关键词。其中,语义分析包括词汇级语义分析、句子级语义分析和章级语义分析。例如,根据用户的需求信息“我想办理交费业务”,识别到关键词“交费”,则可以判断用户的呼叫意图可能与交费业务相关;又例如,根据用户的需求信息“帮我查询去年12月的用电量”,语音分析识别到关键词为“用电量”,则可以判断用户的呼叫意图可能与用电查询相关。Step 203, perform semantic analysis on the user demand information, and determine the calling intention of the user. In this application, word segmentation and speech feature extraction are performed on the user demand information, semantic analysis is performed on the extracted speech features, and keywords in the user demand information are identified. Among them, semantic analysis includes vocabulary-level semantic analysis, sentence-level semantic analysis and chapter-level semantic analysis. For example, according to the user's demand information "I want to handle the bill payment service", if the keyword "payment bill" is identified, it can be judged that the user's call intention may be related to the bill payment service; another example, according to the user's demand information "help me Query the electricity consumption in December last year", and the voice analysis recognizes that the keyword is "electricity consumption", then it can be judged that the user's call intention may be related to the electricity consumption query.

步骤204,判断用户的情绪、所处环境及呼叫意图是否分别符合来电拦截规则中预设的情绪、环境及意图。在本说明书的一些实施例中,来电拦截规则中可以预先设定符合来电拦截规则的标准,包括用户的情绪达到什么程度符合来电拦截规则、用户所处的环境的嘈杂程度为嘈杂且无法识别人声时,符合来电拦截规则、当用户的意图与电力业务无关时,符合来电拦截规则。Instep 204, it is judged whether the user's emotion, environment and call intention conform to the preset emotion, environment and intention in the incoming call interception rule. In some embodiments of this specification, the criteria for meeting the call interception rules can be pre-set in the call interception rules, including the extent to which the user's emotions meet the call interception rules, the noise level of the user's environment is noisy, and people cannot be identified. When the sound is sound, it complies with the call interception rules, and when the user's intention has nothing to do with the power service, it complies with the call interception rules.

在本申请中,来电拦截规则预设的情绪、环境及意图的标准并不限定于前文描述,来电拦截规则可以有其他不同形式,本申请在此不作限定。In this application, the criteria of emotion, environment and intention preset by the call interception rules are not limited to the above description, and the call interception rules may have other different forms, which are not limited in this application.

步骤205,若所述用户的情绪、所处环境及呼叫意图中的任意一项,不符合来电拦截规则,确定用户需求信息不符合来电拦截规则。在本步骤中,若识别得到用户呼叫的需求信息中的情绪、用户所处环境、用户呼叫意图中,有其中一项识别结果不符合来电拦截规则,则确定用户需求信息不符合来电拦截规则。例如,识别确定用户的情绪为平和、用户所处环境为安静,但用户呼叫意图为办理话费充值业务,可以确定用户呼叫意图不符合来电拦截规则,则确定该用户的需求信息整体不符合来电拦截规则。Step 205, if any one of the user's emotion, environment, and call intention does not comply with the call interception rule, determine that the user demand information does not comply with the call interception rule. In this step, if one of the recognition results in the emotion in the demand information of the user call, the environment of the user, and the call intention of the user does not meet the call interception rules, then it is determined that the user demand information does not meet the call interception rules. For example, if it is determined that the user's mood is peaceful and the environment the user is in is quiet, but the user's call intention is to handle the recharge service, it can be determined that the user's call intention does not comply with the call interception rules, and then it is determined that the user's demand information does not meet call interception as a whole rule.

图3所示为本文实施例一种向用户发出改进提醒的方法流程图,具体包括如下步骤:Figure 3 is a flow chart of a method for sending an improvement reminder to a user according to an embodiment of this paper, which specifically includes the following steps:

步骤301,确定用户需求信息不符合来电拦截规则中预设的情绪、环境、意图中的具体结果项。在本步骤中,根据前述步骤205的判断结果,得到不符合来电拦截规则的具体项目,例如,用户A的呼叫信息不符合来电拦截规则中的预设意图,则判断该用户的需求信息不符合来电拦截规则。Step 301, determining that the user demand information does not meet the specific result items in the emotion, environment, and intention preset in the call interception rule. In this step, according to the judgment result of theaforementioned step 205, specific items that do not meet the call interception rules are obtained. Call blocking rules.

步骤302,根据结果项,向用户发出改进提醒信息。根据步骤301中确定的不符合来电拦截规则的具体结果项,对用户发出适应性的改进提醒。例如,通过向用户发送短信,或向用户拨打智能电话的方式,告知用户先前呼叫的需求信息不符合来电拦截规则的原因,并提供适应性的改进、提醒建议。例如,若用户不符合来电拦截规则的具体结果项为:用户所处环境嘈杂,则向用户发出建议用户移步安静区域重新呼叫;又例如,若用户不符合来电拦截规则的具体结果项为:用户情绪激动,则提示用户平复心情,待心情平复后重新呼叫。Step 302, send improvement reminder information to the user according to the result item. According to the specific result items determined instep 301 that do not meet the call interception rules, an adaptive improvement reminder is sent to the user. For example, by sending a text message to the user or dialing a smart phone to the user, the user is notified of the reason why the demand information of the previous call does not meet the call interception rules, and adaptive improvement and reminder suggestions are provided. For example, if the user does not meet the call interception rule, the specific result item is: the environment where the user is located is noisy, then send a suggestion to the user to move to a quiet area to call again; for another example, if the user does not meet the call interception rule, the specific result item is: If the user is emotionally excited, the user is prompted to calm down and call again after the mood calms down.

在本说明书的一些实施例中,业务处理目标单元结合问答数据库,对用户需求信息进行智能回答包括:将所述用户需求信息转换为文本;基于NLP算法对所述文本进行处理,得到用户需求信息中的关键词;将所述关键词与问答数据库中的问答数据对进行匹配,得到匹配结果;根据所述匹配结果,对用户需求信息提供智能回答。在本说明书中,首先将用户呼叫的需求信息转换为本文、对文本进行关键字识别并提取。其次,从问答数据库中查询关键字对应的问题及回答,对应的问题及回答即为匹配结果。将匹配结果作为用户需求信息的回答。其中,问答数据库相当于知识图谱,预先存储了不同场景下用户可能询问的问题及对应的回答。In some embodiments of this specification, the business processing target unit combined with the question-and-answer database to intelligently answer user demand information includes: converting the user demand information into text; processing the text based on NLP algorithms to obtain user demand information Key words in the question and answer database; match the key words with the question and answer data in the question and answer database to obtain matching results; provide intelligent answers to user demand information according to the matching results. In this specification, firstly, the demand information called by the user is converted into the text, and the text is identified and extracted by keywords. Secondly, the questions and answers corresponding to the keywords are queried from the question-and-answer database, and the corresponding questions and answers are the matching results. Use the matching result as the answer to the user's demand information. Among them, the question-and-answer database is equivalent to a knowledge map, which pre-stores the questions that users may ask in different scenarios and the corresponding answers.

图4所示为本文实施例一种确定业务处理目标单元的方法流程图,具体包括如下步骤:Figure 4 shows a flow chart of a method for determining a business processing target unit according to an embodiment of this paper, which specifically includes the following steps:

步骤401,将业务响应设备中处于空闲状态的业务处理单元,确定为业务处理备选单元。在本说明书的一些实施例中,同一类型的业务响应设备,可能包含多个业务处理单元。其中,业务处理单元可以理解为用于服务用户呼叫的最小处理单元。其中,每台业务处理单元具有对应的工作忙闲状态,包括:工作状态、待机状态、无应答状态等。在本说明书的一些实施例中,选择工作状态为待机状态的业务处理单元作为用户需求信息的业务处理备选单元。在后续步骤中,需要从业务处理备选单元中进一步选择,从而得到业务处理目标单元。Step 401: Determine a service processing unit in an idle state in the service response device as a service processing candidate unit. In some embodiments of this specification, a service response device of the same type may include multiple service processing units. Wherein, the service processing unit can be understood as the smallest processing unit for serving user calls. Wherein, each business processing unit has a corresponding busy or idle state, including: working state, standby state, no response state, etc. In some embodiments of this specification, a service processing unit whose working state is in a standby state is selected as a service processing candidate unit for user requirement information. In the subsequent steps, it is necessary to further select from the business processing candidate units, so as to obtain the business processing target unit.

步骤402,从所述业务处理备选单元中,随机选取其中一个单元与用户通信。在本说明书的一些实施例中,满足用户需求的一类业务响应设备中,处于待机状态的业务处理备选单元的个数可能不止一个,则本步骤中可以随机选择其中一个业务处理单元,作为业务处理目标单元。Step 402, randomly select one of the service processing candidate units to communicate with the user. In some embodiments of this specification, in a class of service response equipment that meets user needs, there may be more than one service processing candidate unit in the standby state, so one of the service processing units can be randomly selected in this step as Business processing object unit.

步骤403,确定用户与随机选取的单元是否通信成功。根据随机选取的单元与用户通信结果,确定用户与随机选取的单元是否通信成功。Step 403, determine whether the communication between the user and the randomly selected unit is successful. According to the result of the communication between the randomly selected unit and the user, it is determined whether the communication between the user and the randomly selected unit is successful.

步骤404,若是,所述随机选取的单元为业务处理目标单元。将与用户通信成功的单元,作为业务处理目标单元。Step 404, if yes, the randomly selected unit is the service processing target unit. The unit that successfully communicates with the user is taken as the target unit of business processing.

步骤405,若否,确定用户与所述随机选取的单元的备用单元是否通信成功。在本说明书的一些实施例中,每一业务处理单元具有一个对应备用单元,作为冗余单元承接当该业务处理单元发生故障或宕机时,业务处理单元上原本运行的服务。因此,当用户与随机选取的业务处理单元未取得成功通信之后,使用业务处理单元的备用单元,与用户进行通信,并确定通信成功与否。Step 405, if not, determine whether the communication between the user and the standby unit of the randomly selected unit is successful. In some embodiments of this specification, each business processing unit has a corresponding backup unit, which acts as a redundant unit to undertake the services originally running on the business processing unit when the business processing unit fails or goes down. Therefore, when the user fails to communicate successfully with the randomly selected service processing unit, the standby unit of the service processing unit is used to communicate with the user and determine whether the communication is successful or not.

步骤406,若是,确定所述随机选取的单元的备用单元为所述业务处理目标单元。Step 406, if yes, determine that the standby unit of the randomly selected unit is the service processing target unit.

步骤407,若否,从业务处理备选单元中选择其他单元与用户通信,重复判断其他单元及其备用单元是否与用户是否通信成功。若业务处理单元的备用单元与用户通信失败,则从业务响应设备中的其他业务处理单元中,选择任意一个业务处理单元与用户进行通信,并重复判断该选择的业务处理单元是否与用户通信成功,若否,判断该业务处理单元的备用单元是否与用户通信成功的过程。Step 407, if not, select other units from the service processing alternative units to communicate with the user, and repeatedly judge whether other units and their standby units communicate successfully with the user. If the backup unit of the service processing unit fails to communicate with the user, select any service processing unit from other service processing units in the service response device to communicate with the user, and repeatedly judge whether the selected service processing unit communicates with the user successfully , if not, the process of judging whether the standby unit of the service processing unit communicates with the user successfully.

图5所示为本文实施例一种对用户需求信息进行语义分析的方法流程图,具体包括如下步骤:FIG. 5 is a flowchart of a method for semantic analysis of user demand information according to an embodiment of this paper, which specifically includes the following steps:

步骤501,将用户需求信息进行文字转换、文字提取及语义分析,确定用户需求信息中的关键字及所述关键字在用户需求信息中的词频。在本步骤中,通过对用户需求信息的语音形式的信息进行转换,得到文字信息。并对文字进行分词、去停用词等处理,并利用语义分析技术,分析得到用户需求信息中的关键字。进一步的,统计关键字在用户需求信息中出现的频率。Step 501, perform text conversion, text extraction and semantic analysis on the user demand information, and determine the keywords in the user demand information and the word frequency of the keywords in the user demand information. In this step, the text information is obtained by converting the voice information of the user demand information. It also performs word segmentation and removal of stop words on the text, and uses semantic analysis technology to analyze and obtain keywords in user demand information. Further, the frequency of keywords appearing in the user demand information is counted.

步骤502,确定所述关键字是否属于预设数据库中记录的关键字。将步骤501中确定的关键字与预设数据库中记录的关键字进行匹配。确定从用户呼叫的需求信息中提取出的关键字属于预设数据库中记录的关键字。例如,从用户呼叫的需求信息中提取出的关键字为“交费”,而预设数据库中记录的关键字包括:交费、缴费、欠费、停电、故障、充值、交钱、维修、抢修等。用户的需求信息的关键字属于预设数据库中记录的关键字。Step 502, determine whether the keyword belongs to the keywords recorded in the preset database. The keywords determined instep 501 are matched with the keywords recorded in the preset database. It is determined that the keywords extracted from the demand information called by the user belong to the keywords recorded in the preset database. For example, the keyword extracted from the demand information called by the user is "payment", and the keywords recorded in the preset database include: payment, payment, arrears, power failure, failure, recharge, payment, maintenance, Emergency repairs, etc. The keywords of the user's demand information belong to the keywords recorded in the preset database.

步骤503,若是,根据所述关键字及词频,确定关键字对应的优先级。在本说明书的一些实施例中,预设数据库中不同的关键字具有不同的权重分值。具体的,根据关键字对应的业务类别,不同的关键字具有的权重分值不同。在本步骤中,可以根据关键字对应的权重与关键字在用户需求信息中出现的频率(即,词频),确定关键字对应的优先级。例如,关键字“交费”的权重分值为0.5,该词在用户需求中的词频为4,则“交费”的优先级为0.5与4的乘积,为2。Step 503, if yes, determine the priority corresponding to the keyword according to the keyword and word frequency. In some embodiments of this specification, different keywords in the preset database have different weight scores. Specifically, according to the business category corresponding to the keyword, different keywords have different weight scores. In this step, the priority corresponding to the keyword may be determined according to the weight corresponding to the keyword and the frequency (namely, word frequency) of the keyword appearing in the user demand information. For example, the weight score of the keyword "payment" is 0.5, and the word frequency of this word in the user demand is 4, then the priority of "payment" is the product of 0.5 and 4, which is 2.

步骤504,若所述优先级超出预设阈值,将所述用户与应急响应模块直接建立通信。在本说明书的一些实施例中,预设阈值用于判断用户需求的紧急程度。若根据关键字和词频计算得到的优先级超出预设阈值,说明用户需求紧急程度较高,直接将用户与应急响应模块建立通信,无需根据用户需求信息,确定业务响应设备及业务处理目标单元。提高对用户需求的应急处理效率,以提高用户体验。Step 504, if the priority exceeds the preset threshold, directly establish communication between the user and the emergency response module. In some embodiments of this specification, the preset threshold is used to judge the urgency of the user's needs. If the priority calculated based on keywords and word frequency exceeds the preset threshold, it means that the user's needs are urgent, and the user is directly connected to the emergency response module without determining the business response equipment and business processing target unit based on the user demand information. Improve the efficiency of emergency handling of user needs to improve user experience.

如图6所示为本文实施例一种智能回答用户需求装置的结构示意图,在本图中描述了智能回答用户需求装置的基本结构,其中的功能单元、模块可以采用软件方式实现,也可以采用通用芯片或者特定芯片实现智能回答用户需求,该装置具体包括:As shown in Figure 6, it is a schematic structural diagram of a device for intelligently answering user needs according to the embodiment of this paper. The basic structure of the device for intelligently answering user needs is described in this figure. General-purpose chips or specific chips can intelligently answer user needs. The device specifically includes:

判断单元601,用于判断用户呼叫的需求信息是否符合来电拦截规则;A judgingunit 601, configured to judge whether the demand information of the user's call complies with the incoming call interception rule;

确定单元602,用于根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元;A determiningunit 602, configured to determine the service processing target unit of the user demand information according to the busy state of the service processing unit in the service response device;

智能回答单元603,用于发送用户需求信息至业务处理目标单元,以由所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答。Theintelligent answering unit 603 is configured to send the user demand information to the business processing target unit, so that the business processing target unit can intelligently answer the user demand information in combination with the question-and-answer database.

本申请通过识别用户的需求信息,拦截不符合来电拦截规则的用户呼叫,将符合来电拦截规则的用户需求信息提供给业务响应设备的业务处理单元处理,能够减少不必要的应答,降低呼叫中心的处理压力。This application intercepts user calls that do not meet the call interception rules by identifying the user's demand information, and provides the user demand information that meets the call interception rules to the service processing unit of the service response device for processing, which can reduce unnecessary responses and reduce the call center's workload. Deal with stress.

作为本文的一个实施例,还可以参考如图7所示为本实施例基于智能回答用户需求装置的具体结构示意图。As an embodiment of this document, reference may also be made to FIG. 7 , which is a schematic structural diagram of a device for answering user needs based on intelligence in this embodiment.

作为本文的一个实施例,所述判断单元601进一步包括:As an embodiment of this document, the judgingunit 601 further includes:

情绪分析模块6011,用于对用户需求信息进行情绪分析,确定所述用户的情绪;Emotional analysis module 6011, used to perform emotional analysis on user demand information, and determine the user's emotion;

环境分析模块6012,用于对用户需求信息进行环境分析,确定用户所处的环境;Theenvironment analysis module 6012 is used to analyze the environment of the user demand information and determine the environment in which the user is located;

意图分析模块6013,用于对用户需求信息进行语义分析,确定所述用户的呼叫意图。Theintent analysis module 6013 is configured to perform semantic analysis on user demand information to determine the call intent of the user.

作为本文的一个实施例,所述确定单元602进一步包括:As an embodiment herein, the determiningunit 602 further includes:

业务处理备选单元确定模块6021,用于将业务响应设备中处于空闲状态的业务处理单元,确定为业务处理备选单元;A service processing candidateunit determining module 6021, configured to determine a service processing unit in an idle state in the service response device as a service processing candidate unit;

通信确定模块6022,用于确定用户与随机选取的单元是否通信成功、确定用户与所述随机选取的业务处理单元的备用单元是否通信成功。Thecommunication determination module 6022 is configured to determine whether the communication between the user and the randomly selected unit is successful, and whether the communication between the user and the standby unit of the randomly selected service processing unit is successful.

如图8所示,为本文实施例提供的一种计算机设备。本申请所述智能回答用户需求方法可以由所述计算机设备执行。所述计算机设备802可以包括一个或多个处理器804,诸如一个或多个中央处理单元(CPU),每个处理单元可以实现一个或多个硬件线程。计算机设备802还可以包括任何存储器806,其用于存储诸如代码、设置、数据等之类的任何种类的信息。非限制性的,比如,存储器806可以包括以下任一项或多种组合:任何类型的RAM,任何类型的ROM,闪存设备,硬盘,光盘等。更一般地,任何存储器都可以使用任何技术来存储信息。进一步地,任何存储器可以提供信息的易失性或非易失性保留。进一步地,任何存储器可以表示计算机设备802的固定或可移除部件。在一种情况下,当处理器804执行被存储在任何存储器或存储器的组合中的相关联的指令时,计算机设备802可以执行相关联指令的任一操作。计算机设备802还包括用于与任何存储器交互的一个或多个驱动机构808,诸如硬盘驱动机构、光盘驱动机构等。As shown in FIG. 8 , it is a computer device provided in the embodiment of this document. The method for intelligently answering user needs described in this application can be executed by the computer device. Thecomputer device 802 may include one ormore processors 804, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Thecomputer device 802 may also include anymemory 806 for storing any kind of information such as codes, settings, data, and the like. Non-limiting, for example, thememory 806 may include any one or combination of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, and so on. More generally, any memory can use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component ofcomputer device 802 . In one instance, whenprocessor 804 executes the associated instructions stored in any memory or combination of memories,computer device 802 may perform any operation of the associated instructions. Thecomputer device 802 also includes one ormore drive mechanisms 808 for interfacing with any memory, such as a hard disk drive, an optical disk drive, or the like.

计算机设备802还可以包括输入/输出模块810(I/O),其用于接收各种输入(经由输入设备812)和用于提供各种输出(经由输出设备814)。一个具体输出机构可以包括呈现设备816和相关联的图形用户接口(GUI)818。在其他实施例中,还可以不包括输入/输出模块810(I/O)、输入设备812以及输出设备814,仅作为网络中的一台计算机设备。计算机设备802还可以包括一个或多个网络接口820,其用于经由一个或多个通信链路822与其他设备交换数据。一个或多个通信总线824将上文所描述的部件耦合在一起。Computer device 802 may also include an input/output module 810 (I/O) for receiving various inputs (via input device 812) and for providing various outputs (via output device 814). One particular output mechanism may include apresentation device 816 and an associated graphical user interface (GUI) 818 . In other embodiments, the input/output module 810 (I/O), theinput device 812 and theoutput device 814 may not be included, and it is only used as a computer device in the network.Computer device 802 may also include one ormore network interfaces 820 for exchanging data with other devices via one or more communication links 822 . One ormore communication buses 824 couple together the components described above.

通信链路822可以以任何方式实现,例如,通过局域网、广域网(例如,因特网)、点对点连接等、或其任何组合。通信链路822可以包括由任何协议或协议组合支配的硬连线链路、无线链路、路由器、网关功能、名称服务器等的任何组合。Communication link 822 can be implemented in any manner, for example, through a local area network, wide area network (eg, the Internet), point-to-point connection, etc., or any combination thereof.Communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

对应于图1至图5中的方法,本文实施例还提供了一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述方法的步骤。Corresponding to the methods in Figures 1 to 5, the embodiments of this document also provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method are executed .

本文实施例还提供一种计算机可读指令,其中当处理器执行所述指令时,其中的程序使得处理器执行如图1至图5所示的方法。The embodiments herein also provide a computer-readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the methods shown in FIGS. 1 to 5 .

本文实施例还提供了一种计算机程序产品,计算机程序产品包括计算机程序,计算机程序被处理器执行时实现如图1至图5所示的方法。The embodiment of this document also provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the methods shown in FIGS. 1 to 5 are implemented.

应理解,在本文的各种实施例中,上述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本文实施例的实施过程构成任何限定。It should be understood that in the various embodiments herein, the sequence numbers of the above-mentioned processes do not mean the sequence of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not be used in the implementation of the embodiments herein. process constitutes any qualification.

还应理解,在本文实施例中,术语“和/或”仅仅是一种描述关联对象的关联关系,表示可以存在三种关系。例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。It should also be understood that in the embodiments herein, the term "and/or" is merely an association relationship describing associated objects, indicating that there may be three relationships. For example, A and/or B may mean that A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本文的范围。Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the relationship between hardware and software Interchangeability. In the above description, the composition and steps of each example have been generally described according to their functions. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. A skilled artisan may implement the described functionality using different methods for each particular application, but such implementation should not be considered beyond the scope of this document.

所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, and details are not repeated here.

在本文所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另外,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接,也可以是电的,机械的或其它的形式连接。In the several embodiments provided herein, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.

所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本文实施例方案的目的。The units described 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 may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solutions in the embodiments herein.

另外,在本文各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。In addition, each functional unit in each of the embodiments herein may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本文的技术方案本质上或者说对现有技术做出贡献的部分,或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本文各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。If the integrated unit is realized in the form of a software function 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 in this article is essentially or part of the contribution 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 several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments herein. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .

本文中应用了具体实施例对本文的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本文的方法及其核心思想;同时,对于本领域的一般技术人员,依据本文的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本文的限制。In this paper, specific examples have been used to illustrate the principles and implementation methods of this paper. The description of the above embodiments is only used to help understand the method and core ideas of this paper; meanwhile, for those of ordinary skill in the art, according to the ideas of this paper , there will be changes in specific implementation methods and application ranges. In summary, the contents of this specification should not be construed as limiting this text.

Claims (10)

Translated fromChinese
1.一种智能回答用户需求的方法,其特征在于,所述方法包括:1. A method for intelligently answering user needs, characterized in that the method comprises:判断用户呼叫的需求信息是否符合来电拦截规则;Determine whether the demand information of the user's call meets the call interception rules;若符合,拦截所述用户的呼叫;If so, intercept the call of said user;若不符合,根据用户需求信息,确定业务响应设备;If not, determine the service response equipment according to the user demand information;根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元;Determine the service processing target unit of the user demand information according to the busy state of the service processing unit in the service response device;发送用户需求信息至业务处理目标单元,以由所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答。The user demand information is sent to the service processing target unit, so that the service process target unit can intelligently answer the user demand information in combination with the question-and-answer database.2.根据权利要求1所述的智能回答用户需求的方法,其特征在于,所述判断用户呼叫的需求信息是否符合来电拦截规则包括:2. The method for intelligently answering user needs according to claim 1, wherein said judging whether the demand information called by the user meets the incoming call interception rule comprises:对用户需求信息进行情绪分析,确定所述用户的情绪;Perform sentiment analysis on user demand information to determine the user's sentiment;对用户需求信息进行环境分析,确定用户所处的环境;Carry out environmental analysis on user demand information to determine the environment in which users live;对用户需求信息进行语义分析,确定所述用户的呼叫意图;Performing semantic analysis on user demand information to determine the calling intention of the user;判断用户的情绪、所处环境及呼叫意图是否分别符合来电拦截规则中预设的情绪、环境及意图;Judging whether the user's emotion, environment and call intention conform to the preset emotion, environment and intention in the call interception rules;若所述用户的情绪、所处环境及呼叫意图中的任意一项,不符合来电拦截规则,确定用户需求信息不符合来电拦截规则。If any one of the user's emotion, environment, and call intention does not comply with the call interception rule, it is determined that the user demand information does not comply with the call interception rule.3.根据权利要求2所述的智能回答用户需求的方法,其特征在于,确定出所述用户的情绪、所处环境及呼叫意图中的任意一项,不符合来电拦截规则后,还包括:3. The method for intelligently answering user needs according to claim 2, characterized in that, after determining any one of the user's emotion, environment and call intention, after not meeting the incoming call interception rules, it also includes:确定用户需求信息不符合来电拦截规则中预设的情绪、环境、意图中的具体结果项;Determine that the user's demand information does not meet the specific result items in the emotion, environment, and intention preset in the call interception rules;根据结果项,向用户发出改进提醒信息。According to the result item, an improvement reminder message is issued to the user.4.根据权利要求3所述的智能回答用户需求的方法,其特征在于,所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答包括:4. The method for intelligently answering user needs according to claim 3, wherein the business processing target unit combines the question-and-answer database to intelligently answer user demand information comprising:将所述用户需求信息转换为文本;converting the user requirement information into text;基于NLP算法对所述文本进行处理,得到用户需求信息中的关键词;Processing the text based on an NLP algorithm to obtain keywords in the user demand information;将所述关键词与问答数据库中的问答数据对进行匹配,得到匹配结果;Matching the keyword with the question-answer data in the question-answer database to obtain a matching result;根据所述匹配结果,对用户需求信息提供智能回答。According to the matching result, an intelligent answer is provided to the user demand information.5.根据权利要求4所述的智能回答用户需求的方法,其特征在于,根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元包括:5. The method for intelligently answering user needs according to claim 4, characterized in that, according to the busy state of the business processing unit in the business response device, determining the business processing target unit of the user demand information includes:将业务响应设备中处于空闲状态的业务处理单元,确定为业务处理备选单元;Determining a service processing unit in an idle state in the service response device as a service processing candidate unit;从所述业务处理备选单元中,随机选取其中一个单元与用户通信;Randomly select one of the business processing candidate units to communicate with the user;确定用户与随机选取的单元是否通信成功;Determine whether the communication between the user and the randomly selected unit is successful;若是,所述随机选取的单元为业务处理目标单元;If so, the randomly selected unit is the business processing target unit;若否,确定用户与所述随机选取的业务处理单元的备用单元是否通信成功;If not, determine whether the communication between the user and the standby unit of the randomly selected service processing unit is successful;若是,确定所述随机选取的业务处理单元的备用单元为所述业务处理目标单元;If yes, determine that the standby unit of the randomly selected service processing unit is the service processing target unit;若否,从业务处理备选单元中选择其他单元与用户通信,重复判断其他单元及其备用单元是否与用户是否通信成功。If not, select other units from the service processing alternative units to communicate with the user, and repeatedly judge whether other units and their standby units communicate successfully with the user.6.根据权利要求2所述的智能回答用户需求的方法,其特征在于,所述对用户需求信息进行语义分析包括:6. The method for intelligently answering user needs according to claim 2, wherein said performing semantic analysis on user demand information comprises:将用户需求信息进行文字转换、文字提取及语义分析,确定用户需求信息中的关键字及所述关键字在用户需求信息中的词频;Perform text conversion, text extraction and semantic analysis on the user demand information, and determine the keywords in the user demand information and the word frequency of the keywords in the user demand information;确定所述关键字是否属于预设数据库中记录的关键字;determining whether the keyword belongs to the keywords recorded in the preset database;若是,根据所述关键字及词频,确定关键字对应的优先级;If so, determine the priority corresponding to the keyword according to the keyword and word frequency;若所述优先级超出预设阈值,将所述用户与应急响应模块直接建立通信。If the priority exceeds the preset threshold, the user will directly establish communication with the emergency response module.7.一种智能回答用户需求装置,其特征在于,所述装置包括:7. A device for intelligently answering user needs, characterized in that the device comprises:判断单元,用于判断用户呼叫的需求信息是否符合来电拦截规则;A judging unit, configured to judge whether the demand information of the user's call complies with the incoming call interception rule;若符合,拦截所述用户的呼叫;If so, intercept the call of said user;若不符合,根据所述用户需求信息,确定业务响应设备;If not, determine the service response device according to the user demand information;确定单元,用于根据业务响应设备中业务处理单元的忙闲状态,确定用户需求信息的业务处理目标单元;A determination unit, configured to determine the service processing target unit of the user demand information according to the busy state of the service processing unit in the service response device;智能回答单元,用于发送用户需求信息至业务处理目标单元,以由所述业务处理目标单元结合问答数据库,对用户需求信息进行智能回答。The intelligent answering unit is used to send the user demand information to the business processing target unit, so that the business processing target unit can intelligently answer the user demand information in combination with the question-and-answer database.8.一种计算机设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,其特征在于,所述处理器执行所述计算机程序时实现权利要求1至6任意一项所述的方法。8. A computer device, comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, characterized in that, when the processor executes the computer program, any one of claims 1 to 6 is realized method described in the item.9.一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现权利要求1至6任意一项所述的方法。9. 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 method according to any one of claims 1 to 6 is implemented.10.一种计算机程序产品,其特征在于,所述计算机程序产品包括计算机程序,所述计算机程序被处理器执行时实现权利要求1至6任意一项所述的方法。10. A computer program product, characterized in that the computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
CN202310251673.3A2023-03-102023-03-10Method, device, equipment, storage medium and product for intelligently answering user demandsPendingCN116437011A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202310251673.3ACN116437011A (en)2023-03-102023-03-10Method, device, equipment, storage medium and product for intelligently answering user demands

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202310251673.3ACN116437011A (en)2023-03-102023-03-10Method, device, equipment, storage medium and product for intelligently answering user demands

Publications (1)

Publication NumberPublication Date
CN116437011Atrue CN116437011A (en)2023-07-14

Family

ID=87091705

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202310251673.3APendingCN116437011A (en)2023-03-102023-03-10Method, device, equipment, storage medium and product for intelligently answering user demands

Country Status (1)

CountryLink
CN (1)CN116437011A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110070298A (en)*2019-04-292019-07-30携程旅游信息技术(上海)有限公司Call center's method for allocating tasks, system, equipment and storage medium
CN110096191A (en)*2019-04-242019-08-06北京百度网讯科技有限公司 Method, device and electronic equipment for man-machine dialogue
US20190253558A1 (en)*2018-02-132019-08-15Risto HaukiojaSystem and method to automatically monitor service level agreement compliance in call centers
CN111028827A (en)*2019-12-102020-04-17深圳追一科技有限公司Interaction processing method, device, equipment and storage medium based on emotion recognition
CN112035642A (en)*2020-08-312020-12-04康键信息技术(深圳)有限公司Customer service matching method, device, equipment and storage medium
CN112232665A (en)*2020-04-292021-01-15广元量知汇科技有限公司Service distribution method for smart city
CN112671983A (en)*2020-12-082021-04-16合肥金人科技有限公司Unattended management system of call center
CN113055523A (en)*2021-03-082021-06-29北京百度网讯科技有限公司Crank call interception method and device, electronic equipment and storage medium
CN115098659A (en)*2022-06-292022-09-23浙江理工大学科技与艺术学院Intelligent customer service method and system
CN115484350A (en)*2022-08-312022-12-16海尔优家智能科技(北京)有限公司Method and device for processing consultation voice, storage medium and electronic device

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20190253558A1 (en)*2018-02-132019-08-15Risto HaukiojaSystem and method to automatically monitor service level agreement compliance in call centers
CN110096191A (en)*2019-04-242019-08-06北京百度网讯科技有限公司 Method, device and electronic equipment for man-machine dialogue
CN110070298A (en)*2019-04-292019-07-30携程旅游信息技术(上海)有限公司Call center's method for allocating tasks, system, equipment and storage medium
CN111028827A (en)*2019-12-102020-04-17深圳追一科技有限公司Interaction processing method, device, equipment and storage medium based on emotion recognition
CN112232665A (en)*2020-04-292021-01-15广元量知汇科技有限公司Service distribution method for smart city
CN112035642A (en)*2020-08-312020-12-04康键信息技术(深圳)有限公司Customer service matching method, device, equipment and storage medium
CN112671983A (en)*2020-12-082021-04-16合肥金人科技有限公司Unattended management system of call center
CN113055523A (en)*2021-03-082021-06-29北京百度网讯科技有限公司Crank call interception method and device, electronic equipment and storage medium
CN115098659A (en)*2022-06-292022-09-23浙江理工大学科技与艺术学院Intelligent customer service method and system
CN115484350A (en)*2022-08-312022-12-16海尔优家智能科技(北京)有限公司Method and device for processing consultation voice, storage medium and electronic device

Similar Documents

PublicationPublication DateTitle
KR102289917B1 (en)Method for processing dialogue using dialogue act information and Apparatus thereof
CN106133825B (en) Generalized Phrases in Automatic Speech Recognition Systems
US10354677B2 (en)System and method for identification of intent segment(s) in caller-agent conversations
WO2020024389A1 (en)Method for collecting overdue payment, device, computer apparatus, and storage medium
CN111259132A (en) Method, apparatus, computer equipment and storage medium for speech recommendation
US20140314227A1 (en)System and method for speech-enabled call routing
CN111666380A (en)Intelligent calling method, device, equipment and medium
US12002454B2 (en)Method and apparatus for intent recognition and intent prediction based upon user interaction and behavior
JP2008512789A (en) Machine learning
CN114818649A (en) Business consultation processing method and device based on intelligent voice interaction technology
CN114925159B (en)User emotion analysis model training method and device, electronic equipment and storage medium
WO2019210556A1 (en)Call reservation method, agent leaving processing method and apparatus, device, and medium
CN113239164A (en)Multi-round conversation process construction method and device, computer equipment and storage medium
CN114328867A (en) Method and device for intelligent interruption in man-machine dialogue
JP2016001399A (en) Relevance determination device, model learning device, method, and program
US12141540B2 (en)Message mapping and combination for intent classification
CN112992128B (en)Training method, device and system of intelligent voice robot
CN113555011A (en)Electric power industry customer service center voice translation modeling method, system and medium
US12204864B2 (en)Dynamic semantic role classification
CN116437011A (en)Method, device, equipment, storage medium and product for intelligently answering user demands
CN117975937A (en)Multi-tone word voice processing method and device and readable storage medium
CN109788128A (en) Incoming call prompting method, incoming call prompting device and terminal equipment
CN116129915A (en)Identity recognition method, voice quality inspection method and related equipment
CN112632234B (en)Man-machine interaction method and device, intelligent robot and storage medium
CN114254088A (en) The Construction Method of Auto-responder Model and Auto-responder Method

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp