WO2019140851A1 - 电话销售提示方法、电子装置及可读存储介质 - Google Patents

电话销售提示方法、电子装置及可读存储介质 Download PDF

Info

Publication number
WO2019140851A1
WO2019140851A1 PCT/CN2018/089721 CN2018089721W WO2019140851A1 WO 2019140851 A1 WO2019140851 A1 WO 2019140851A1 CN 2018089721 W CN2018089721 W CN 2018089721W WO 2019140851 A1 WO2019140851 A1 WO 2019140851A1
Authority
WO
WIPO (PCT)
Prior art keywords
keyword
preset
voice
user
telemarketing
Prior art date
Application number
PCT/CN2018/089721
Other languages
English (en)
French (fr)
Inventor
郭红英
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019140851A1 publication Critical patent/WO2019140851A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/5175—Call or contact centers supervision arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/64—Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations
    • H04M1/65—Recording arrangements for recording a message from the calling party
    • H04M1/656—Recording arrangements for recording a message from the calling party for recording conversations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/42221—Conversation recording systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/5183—Call or contact centers with computer-telephony arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
    • H04M2201/38—Displays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
    • H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2203/00—Aspects of automatic or semi-automatic exchanges
    • H04M2203/10—Aspects of automatic or semi-automatic exchanges related to the purpose or context of the telephonic communication
    • H04M2203/1058—Shopping and product ordering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/74—Details of telephonic subscriber devices with voice recognition means

Definitions

  • the present application relates to the field of computer technologies, and in particular, to a telephone sales prompting method, an electronic device, and a readable storage medium.
  • the agent uses the telemarketing system for sales, the agent communicates with the customer via a softphone in the telesales system. During the telesales process, the agent is required to confirm all the information confirmed by the customer on the phone according to the compliance requirements.
  • the agent In order to prevent the agent from missing some content that needs to be confirmed by the customer, the agent needs to confirm and record the confirmation according to the compliance requirements. However, since the agent needs to confirm more items, there are often cases of missing or wrongly selected items, and only by The agent relies on his own memory to record. When the number of confirmed items is large, it is easy for the agent to forget which confirmation items have been recorded and which confirmation items have not been recorded.
  • the purpose of the present application is to provide a method for prompting a telemarketing, an electronic device, and a readable storage medium, which are intended to prompt an agent to omit items that need to be confirmed in the sales of the telephone, thereby improving sales efficiency.
  • a first aspect of the present application provides an electronic device including a memory, a processor, and a memory sales prompting system executable on the processor, the phone selling The prompting system is implemented by the processor to implement the following steps:
  • the second aspect of the present application further provides a method for prompting a telemarketing, the method comprising:
  • a third aspect of the present application further provides a computer readable storage medium storing a telemarketing prompting system, the telemarketing reminding system being executable by at least one processor And causing the at least one processor to perform the steps of the telemarketing cue method as described above.
  • the telemarketing reminding method, system and readable storage medium provided by the present application record the conversation in the connected telephone after monitoring the call made by the user based on the telemarketing system after the user calls the call based on the telesales system Voice, identifying and analyzing the conversation voice, recording a keyword in the conversation voice that matches a preset keyword in the compliance file, and determining that the compliance file is not matched when the preset condition is met Pre-set keywords, and prompting the user to the unmatched preset keywords, so that the user can be effectively prompted to confirm the items to be confirmed, so that the agent can know in time that the missing items in the telephone sales need to be confirmed. Matters to improve sales efficiency.
  • FIG. 1 is a schematic diagram of an operating environment of a preferred embodiment of a telemarketing reminder system 10 of the present application;
  • FIG. 2 is a schematic flowchart diagram of an embodiment of a method for prompting a telemarketing of the present application.
  • first, second and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. .
  • features defining “first” and “second” may include at least one of the features, either explicitly or implicitly.
  • the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.
  • FIG. 1 is a schematic diagram of an operating environment of a preferred embodiment of the telemarketing reminder system 10 of the present application.
  • the telemarketing reminder system 10 is installed and operated in the electronic device 1.
  • the electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13.
  • Figure 1 shows only the electronic device 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 is at least one type of readable computer storage medium, which in some embodiments may be an internal storage unit of the electronic device 1, such as a hard disk or memory of the electronic device 1.
  • the memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), and a secure digital device. (Secure Digital, SD) card, flash card, etc.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 is configured to store application software and various types of data installed in the electronic device 1, such as program codes of the telemarketing prompting system 10, and the like.
  • the memory 11 can also be used to temporarily store data that has been output or is about to be output.
  • the processor 12 in some embodiments, may be a central processing unit (CPU), a microprocessor or other data processing chip for running program code or processing data stored in the memory 11, for example
  • the telemarketing reminder system 10 or the like is executed.
  • the display 13 in some embodiments may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like.
  • the display 13 is configured to display information processed in the electronic device 1 and a user interface for displaying visualization, such as keywords recorded after voice recognition, matched keywords, unmatched keywords, checked items Box and so on.
  • the components 11-13 of the electronic device 1 communicate with one another via a system bus.
  • the telemarketing reminder system 10 includes at least one computer readable instructions stored in the memory 11, the at least one computer readable instructions being executable by the processor 12 to implement various embodiments of the present application.
  • Step S1 monitoring the call of the user based on the telephone sales system call.
  • the user can be a seat.
  • the system used by the telemarketing system to conduct telephone sales for agents may be a software system installed on a computer.
  • the user can make a call to the customer via a softphone in the telesales system.
  • the telemarketing reminder system 10 can be embedded directly into the telesales system, for example, can be a gadget in the telesales system, so the telemarketing system 10 can directly monitor the calls made by the user.
  • the telemarketing reminder system 10 can also be an application software independent of the telesales system, at which point the telemarketing reminder system 10 can be associated with a voice tool for making a call in a telemarketing system or telesales system (eg, Binding), when it is detected that the telemarketing system dials out the phone or the voice tool is activated, the telesales system 10 automatically starts running and monitors whether the call is successful.
  • a voice tool for making a call in a telemarketing system or telesales system (eg, Binding)
  • step S2 after the user's call based on the telemarketing system is turned on, the conversation voice in the connected telephone is recorded.
  • the conversation voice during the call is recorded in real time.
  • the recorded conversational voice can be saved in memory.
  • Step S3 Perform recognition and analysis on the conversation voice, and record a keyword in the conversation voice that matches a preset keyword in the compliance file.
  • step S4 when the preset condition is met, the preset keywords that are not matched in the compliance file are determined.
  • the satisfying the preset condition may be, for example, the duration of the call reaches a preset duration.
  • the preset duration can be set according to actual needs. For example, it can be set according to the length of time normally required by the agent and the customer to make a telephone call (for example, 15 minutes), and the preset duration can be less than the length of time usually required for a telephone sale.
  • the meeting the preset condition may also be the end of the call, and the dialogue voice recorded during the current pass may be identified and analyzed after the call ends. It is also possible to identify and analyze the conversation voice in real time during the call. It is also possible to identify and analyze the conversation voice at intervals during the call, and the interval duration can be set according to actual needs, for example, 1 minute, 2 minutes, and the like.
  • the Compliance Document includes several preset keywords. Different preset keywords correspond to different items to be verified. For example, one of the items to be verified may be whether the identity information of the customer is verified, and the corresponding preset keyword may be, for example, an identity card. One of the items to be verified may also be whether the address of the customer is verified, and the corresponding preset keyword may be, for example, an address, an address, or the like.
  • the compliance file may be automatically identified to generate a corresponding keyword set, and the keyword set includes a plurality of preset keywords.
  • OCR Optical Character Recognition
  • the words in the extracted compliance file of the OCR recognition are segmented.
  • an N-gram model a Hidden Markov Model (HMM), and a maximum are used.
  • the Maximum Entropy Model is used for word segmentation.
  • the word segmentation algorithm can include: forward maximum match, reverse maximum match, two-way maximum match, and shortest path algorithm. Match each participle in the compliance document with each keyword in the pre-established confirmation item keyword library to determine a number of preset keywords included in the compliance document.
  • the pre-established confirmation item keyword library may include various keywords for confirmation, such as ID card, telephone number, address, income, education, and the like.
  • the speech end point detection technology may be used to distinguish the voice signal and the non-speech signal in the recorded conversation speech, and the invalid speech segment is removed. Noise, determining the start and end endpoints of each valid speech segment, helps to improve the accuracy of subsequent speech analysis.
  • speech recognition can be performed. For example, feature extraction can be performed, and the speech signal is converted into a feature stream of the acoustic feature vector as a compact representation of the speech signal. This representation is often referred to as an observation. The extraction of observations ensures that enough information is included for identification.
  • an acoustic model is constructed using Hidden Markov Model (HMM), which is used to map acoustic observations into word units, and then N-Gram is used to construct a language model for representing local grammar/language information, including words.
  • HMM Hidden Markov Model
  • N-Gram is used to construct a language model for representing local grammar/language information, including words.
  • the possibility information of the sequence the semantic unit of the mapped word unit is distinguished.
  • the frame synchronization algorithm is utilized in speech recognition so that the speech recognition matching is performed at each frame of the extracted speech, thereby generating a maximum likelihood candidate with the end frame of each frame as the start frame and the best matching sequence as the end frame. word.
  • the maximum likelihood candidate word is obtained as a plurality of keywords obtained by finally identifying and analyzing a number of valid speech segments extracted from the dialogue speech.
  • the existing speech recognition algorithm can also be used to identify and analyze the speech voice, which is not limited herein.
  • the keywords in the conversation voice that match the respective preset keywords in the compliance file can be found and recorded. It can be understood that when the conversation voice includes a keyword that is the same as or similar to a certain preset keyword in the compliance file, the preset keyword in the compliance file is considered to be successfully matched. For example, if one of the preset keywords is “ID card” and the “ID card” is included in the voice of the conversation, the preset keyword “ID card” can be considered as being successfully matched. Or, if one of the preset keywords is "home address”, when the "home address” is included in the voice of the conversation, since the "home address” and the "home address” are similar, the preset keyword "address” can be considered as being successfully matched.
  • each of the preset keywords includes a calling party keyword and a called party keyword
  • the conversation voice includes the main voice.
  • the called party voice and the called party voice, the calling party voice is the voice sent by the agent, and the called party voice is the voice sent by the client.
  • a keyword matching the calling party keyword in the conversation voice is derived from the calling party voice
  • a keyword matching the called party keyword in the conversation voice is derived from the called party voice.
  • Recording a keyword in the conversation voice that matches a preset keyword in the compliance file includes: recording a keyword in the calling party voice that matches the calling party keyword, and/or recording the called party voice The keyword that matches the called party keyword.
  • the calling party keyword may be “ID card”, and the called party keyword may be any 18 digits.
  • the calling party keyword “identity card” is considered. "The match is successful; if the voice is analyzed and the customer answers the ID number, if the 18-digit number is searched in the called party's voice, the called party's keyword is considered to be successfully matched.
  • the keyword regarding the identity card is considered to be successfully matched as long as the keyword "identity card” is searched in the calling party's voice, or the 18-digit number is searched in the called party's voice.
  • the keyword “ID card” is searched in the calling party voice, and the 18-digit number is also searched in the called party voice, that is, the calling party voice includes the main character.
  • the keyword matching the party keyword is also included in the called party voice, and the keyword matching the called party keyword is considered to be successfully matched.
  • step S5 the user is prompted to the unmatched preset keyword, that is, the item to be confirmed that the agent is not currently verified.
  • the present embodiment records the conversation voice in the connected telephone after the telephone of the user's call based on the telephone sales system is turned on by monitoring the telephone of the user's call based on the telephone sales system. Performing a recognition analysis on the voice, recording a keyword in the conversation voice that matches a preset keyword in the compliance file, and determining a preset keyword that is not matched in the compliance file when the preset condition is met, And prompting the user to the unmatched preset keyword, so that the user can be effectively prompted to confirm the item to be confirmed yet, preventing the agent from missing the item to be confirmed in the telephone sales, and improving the sales efficiency.
  • the compliance file further includes a check item box corresponding to each of the preset keywords
  • the telemarketing reminding system 10 is
  • the processor 12 executes the following steps: checking a check box corresponding to the successfully matched preset keyword in the compliance file.
  • ticked for example, you can tick the check box or fill in the preset color inside the check box. Therefore, the items confirmed by the agent and the customer can be automatically checked, and the items to be confirmed can be manually checked without the agent, thereby further improving the sales efficiency.
  • the step of: prompting when all the preset keywords in the compliance file are all successfully matched The user performs subsequent operations. After all the items to be confirmed in the compliance document have been verified, the agent can be prompted to proceed to the next step, avoiding wasted time and manual check-checking, which further improves sales efficiency.
  • FIG. 2 is a schematic flowchart of an embodiment of a method for prompting a telemarketing of the present application.
  • the method for prompting a telemarketing includes the following steps:
  • Step S10 monitoring the call of the user based on the telephone sales system call.
  • the user can be a seat.
  • the system used by the telemarketing system to conduct telephone sales for agents may be a software system installed on a computer.
  • the user can make a call to the customer via a softphone in the telesales system.
  • the telemarketing reminder system 10 can be embedded directly into the telesales system, for example, can be a gadget in the telesales system, so the telemarketing system 10 can directly monitor the calls made by the user.
  • the telemarketing reminder system 10 can also be an application software independent of the telesales system, at which point the telemarketing reminder system 10 can be associated with a voice tool for making a call in a telemarketing system or telesales system (eg, Binding), when it is detected that the telemarketing system dials out the phone or the voice tool is activated, the telesales system 10 automatically starts running and monitors whether the call is successful.
  • a voice tool for making a call in a telemarketing system or telesales system (eg, Binding)
  • Step S20 after the user's call based on the telemarketing system is turned on, the conversation voice in the connected phone is recorded.
  • the conversation voice during the call is recorded in real time.
  • the recorded conversational voice can be saved in memory.
  • Step S30 Perform recognition and analysis on the conversation voice, and record a keyword in the conversation voice that matches a preset keyword in the compliance file.
  • Step S40 When the preset condition is met, determine a preset keyword that is not matched in the compliance file.
  • the satisfying the preset condition may be, for example, the duration of the call reaches a preset duration.
  • the preset duration can be set according to actual needs. For example, it can be set according to the length of time normally required by the agent and the customer to make a telephone call (for example, 15 minutes), and the preset duration can be less than the length of time usually required for a telephone sale.
  • the meeting the preset condition may also be the end of the call, and the dialogue voice recorded during the current pass may be identified and analyzed after the call ends. It is also possible to identify and analyze the conversation voice in real time during the call. It is also possible to identify and analyze the conversation voice at intervals during the call, and the interval duration can be set according to actual needs, for example, 1 minute, 2 minutes, and the like.
  • the Compliance Document includes several preset keywords. Different preset keywords correspond to different items to be verified. For example, one of the items to be verified may be whether the identity information of the customer is verified, and the corresponding preset keyword may be, for example, an identity card. One of the items to be verified may also be whether the address of the customer is verified, and the corresponding preset keyword may be, for example, an address, an address, or the like.
  • the compliance file may be automatically identified to generate a corresponding keyword set, and the keyword set includes a plurality of preset keywords.
  • OCR Optical Character Recognition
  • OCR Optical Character Recognition
  • an N-gram model a Hidden Markov Model (HMM), and a maximum are used.
  • the Maximum Entropy Model is used for word segmentation.
  • the word segmentation algorithm can include: forward maximum match, reverse maximum match, two-way maximum match, and shortest path algorithm.
  • the pre-established confirmation item keyword library may include various keywords for confirmation, such as ID card, telephone number, address, income, education, and the like.
  • the speech end point detection technology may be used to distinguish the voice signal and the non-speech signal in the recorded conversation speech, and the invalid speech segment is removed. Noise, determining the start and end endpoints of each valid speech segment, helps to improve the accuracy of subsequent speech analysis.
  • speech recognition can be performed. For example, feature extraction can be performed, and the speech signal is converted into a feature stream of the acoustic feature vector as a compact representation of the speech signal. This representation is often referred to as an observation. The extraction of observations ensures that enough information is included for identification.
  • an acoustic model is constructed using Hidden Markov Model (HMM), which is used to map acoustic observations into word units, and then N-Gram is used to construct a language model for representing local grammar/language information, including words.
  • HMM Hidden Markov Model
  • N-Gram is used to construct a language model for representing local grammar/language information, including words.
  • the possibility information of the sequence the semantic unit of the mapped word unit is distinguished.
  • the frame synchronization algorithm is utilized in speech recognition so that the speech recognition matching is performed at each frame of the extracted speech, thereby generating a maximum likelihood candidate with the end frame of each frame as the start frame and the best matching sequence as the end frame. word.
  • the maximum likelihood candidate word is obtained as a plurality of keywords obtained by finally identifying and analyzing a plurality of valid speech segments extracted from the dialogue voice.
  • the existing speech recognition algorithm can also be used to identify and analyze the speech voice, which is not limited herein.
  • the keywords in the conversation voice that match the respective preset keywords in the compliance file can be found and recorded. It can be understood that when the conversation voice includes a keyword that is the same as or similar to a certain preset keyword in the compliance file, the preset keyword in the compliance file is considered to be successfully matched. For example, if one of the preset keywords is “ID card” and the “ID card” is included in the voice of the conversation, the preset keyword “ID card” can be considered as being successfully matched. Or, if one of the preset keywords is "home address”, when the "home address” is included in the voice of the conversation, since the "home address” and the "home address” are similar, the preset keyword "address” can be considered as being successfully matched.
  • each of the preset keywords includes a calling party keyword and a called party keyword
  • the conversation voice includes the main voice.
  • the called party voice and the called party voice, the calling party voice is the voice sent by the agent, and the called party voice is the voice sent by the client.
  • a keyword matching the calling party keyword in the conversation voice is derived from the calling party voice
  • a keyword matching the called party keyword in the conversation voice is derived from the called party voice.
  • Recording a keyword in the conversation voice that matches a preset keyword in the compliance file includes: recording a keyword in the calling party voice that matches the calling party keyword, and/or recording the called party voice The keyword that matches the called party keyword.
  • the calling party keyword may be “ID card”, and the called party keyword may be any 18 digits.
  • the calling party keyword “identity card” is considered. "The match is successful; if the voice is analyzed and the customer answers the ID number, if the 18-digit number is searched in the called party's voice, the called party's keyword is considered to be successfully matched.
  • the keyword regarding the identity card is considered to be successfully matched as long as the keyword "identity card” is searched in the calling party's voice, or the 18-digit number is searched in the called party's voice.
  • the keyword “ID card” is searched in the calling party voice, and the 18-digit number is also searched in the called party voice, that is, the calling party voice includes the main character.
  • the keyword matching the party keyword is also included in the called party voice, and the keyword matching the called party keyword is considered to be successfully matched.
  • step S50 the user is prompted to the unmatched preset keyword, that is, the item to be confirmed that the agent is not currently verified.
  • the present embodiment records the conversation voice in the connected telephone after the telephone of the user's call based on the telephone sales system is turned on by monitoring the telephone of the user's call based on the telephone sales system. Performing a recognition analysis on the voice, recording a keyword in the conversation voice that matches a preset keyword in the compliance file, and determining a preset keyword that is not matched in the compliance file when the preset condition is met, And prompting the user to the unmatched preset keyword, so that the user can be effectively prompted to confirm the item to be confirmed yet, preventing the agent from missing the item to be confirmed in the telephone sales, and improving the sales efficiency.
  • the compliance file further includes a check item box corresponding to each of the preset keywords
  • the telemarketing prompting method further includes the following steps. : Check the check box corresponding to the matching preset keyword in the compliance file. When ticked, for example, you can tick the check box or fill in the preset color inside the check box. Therefore, the items confirmed by the agent and the customer can be automatically checked, and the items to be confirmed can be manually checked without the agent, thereby further improving the sales efficiency.
  • the telemarketing prompting method further includes the step of prompting the user to perform subsequent operations when all the preset keywords in the compliance file are all successfully matched. After all the items to be confirmed in the compliance document have been verified, the agent can be prompted to proceed to the next step, avoiding wasted time and manual check-checking, which further improves sales efficiency.
  • the present application also provides a computer readable storage medium storing a telemarketing reminder system executable by at least one processor to cause the at least one processor.
  • a telemarketing reminder system executable by at least one processor to cause the at least one processor.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and can also be implemented by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Human Computer Interaction (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请涉及一种电话销售提示方法、电子装置及可读存储介质，该方法包括：监测用户基于电话销售系统呼叫的电话；在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音；对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字；在满足预设条件时，确定所述合规文件中未被匹配的预设关键字；提示用户所述未被匹配的预设关键字。本申请可以有效的提示用户当前还没有被核实的待确认项目，使坐席及时获知其在电话销售中遗漏的需要确认的事项，提高销售效率。

Description

电话销售提示方法、电子装置及可读存储介质
优先权申明
本申请基于巴黎公约申明享有2018年1月16日递交的申请号为CN 201810038832.0、名称为“电话销售提示方法、电子装置及可读存储介质”中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及计算机技术领域，尤其涉及一种电话销售提示方法、电子装置及可读存储介质。
背景技术
坐席使用电话销售系统进行销售时，通过电话销售系统中的软电话与客户进行沟通。在电话销售过程中，坐席需按合规要求，将所有规定的与客户确认的信息在电话中一一进行确认。
为了避免坐席遗漏一些需与客户确认的内容，坐席需按合规要求确认并记录确认事项，但是由于坐席需要确认的事项较多，经常会出现漏选或选错确认事项的情况，且仅由坐席靠自身记忆来进行记录，在确认事项数量较多时，坐席往往容易忘记哪些确认事项已记录，哪些确认事项未被记录。
发明内容
本申请的目的在于提供一种电话销售提示方法、电子装置及可读存储介质，旨在提示坐席在电话销售中遗漏的需要确认的事项，提高销售效率。
为实现上述目的，本申请第一方面提供一种电子装置，所述电子 装置包括存储器、处理器，所述存储器上存储有可在所述处理器上运行的电话销售提示系统，所述电话销售提示系统被所述处理器执行时实现如下步骤：
监测用户基于电话销售系统呼叫的电话；
在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音；
对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字；
在满足预设条件时，确定所述合规文件中未被匹配的预设关键字；
提示用户所述未被匹配的预设关键字。
此外，为实现上述目的，本申请第二方面还提供一种电话销售提示方法，所述方法包括：
监测用户基于电话销售系统呼叫的电话；
在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音；
对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字；
在满足预设条件时，确定所述合规文件中未被匹配的预设关键字；
提示用户所述未被匹配的预设关键字。
进一步地，为实现上述目的，本申请第三方面还提供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电话销售提示系统，所述电话销售提示系统可被至少一个处理器执行，以使所述至少一个 处理器执行如上述的电话销售提示方法的步骤。
本申请提出的电话销售提示方法、系统及可读存储介质，通过监测用户基于电话销售系统呼叫的电话，在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音，对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字，在满足预设条件时，确定所述合规文件中未被匹配的预设关键字，并提示用户所述未被匹配的预设关键字，从而可以有效的提示用户当前还没有被核实的待确认项目，使坐席及时获知其在电话销售中遗漏的需要确认的事项，提高销售效率。
附图说明
图1为本申请电话销售提示系统10较佳实施例的运行环境示意图；
图2为本申请电话销售提示方法一实施例的流程示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，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，都属于本申请保护的范围。
需要说明的是，在本申请中涉及“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征 可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。
本申请提供一种电话销售提示系统。请参阅图1，是本申请电话销售提示系统10较佳实施例的运行环境示意图。
在本实施例中，所述的电话销售提示系统10安装并运行于电子装置1中。该电子装置1可包括，但不仅限于，存储器11、处理器12及显示器13。图1仅示出了具有组件11-13的电子装置1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
所述存储器11为至少一种类型的可读计算机存储介质，所述存储器11在一些实施例中可以是所述电子装置1的内部存储单元，例如该电子装置1的硬盘或内存。所述存储器11在另一些实施例中也可以是所述电子装置1的外部存储设备，例如所述电子装置1上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，所述存储器11还可以既包括所述电子装置1的内部存储单元也包括外部存储设备。所述存储器11用于存储安装于所述电子装置1的应用软件及各类数据，例如所述电话销售提示系统10的程序代码等。所述存储器11还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU)，微处理器或其他数据处理芯片，用于运行所述存储器11中存储的程序代码或处理数据，例如执行所述电话销售 提示系统10等。
所述显示器13在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode，有机发光二极管)触摸器等。所述显示器13用于显示在所述电子装置1中处理的信息以及用于显示可视化的用户界面，例如语音识别后记录的关键字、已匹配的关键字、未匹配的关键字、勾选项目框等。所述电子装置1的部件11-13通过系统总线相互通信。
电话销售提示系统10包括至少一个存储在所述存储器11中的计算机可读指令，该至少一个计算机可读指令可被所述处理器12执行，以实现本申请各实施例。
其中，上述电话销售提示系统10被所述处理器12执行时实现如下步骤：
步骤S1，监测用户基于电话销售系统呼叫的电话。
本实施例中，用户可以为坐席。电话销售系统为坐席进行电话销售时所采用的系统，例如，可以为安装于计算机上的一软件系统。用户可以通过电话销售系统中的软电话向客户呼出电话。
电话销售提示系统10可以直接嵌入电话销售系统中，例如，可以为电话销售系统中的一个小工具，因此电话销售系统10可以直接监测到用户呼叫的电话。
电话销售提示系统10还可以为独立于电话销售系统的一个应用软件，此时电话销售提示系统10可以与电话销售系统或电话销售系统中的用于拨打电话的语音工具之间建立关联关系(例如绑定)，在监测到电话销售系统拨出电话或者语音工具启动时，则该电话销售系统10自动开始运行，并监测电话是否呼叫成功。
步骤S2，在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音。
本实施例中，在坐席呼叫客户的电话接通时，则实时记录呼叫过程中的对话语音。可以将记录的对话语音保存在存储器内。
步骤S3，对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字。
步骤S4，在满足预设条件时，确定所述合规文件中未被匹配的预设关键字。
所述满足预设条件例如可以为：通话时长达到预设时长。预设时长的大小可以根据实际需要进行设置，例如可以根据坐席与客户一次电话销售通常需要的时长进行设置(如15分钟)，预设时长可以小于一次电话销售通常需要的时长。
本实施例中，所述满足预设条件还可以为通话结束，可以在通话结束后对本次通过过程中记录的对话语音进行识别分析。也可以在通话过程中实时的对对话语音进行识别分析。还可以在通话过程中每隔一段时间对对话语音进行识别分析，所间隔的时长可以根据实际需要进行设置，例如1分钟、2分钟等等。
合规文件中包括若干预设关键字。不同的预设关键字分别对应不同的待核实项目。例如，其中一项待核实项目可以为是否核实过客户的身份信息，对应的预设关键字例如可以为身份证。其中一项待核实项目还可以为是否核实过客户的地址，对应的预设关键字例如可以为住址、地址等。本实施例中，针对不同合规文件，还可针对合规文件进行自动识别以生成对应的关键字集合，该关键字集合中包含若干预设关键字。具体地，可先利用OCR(Optical Character Recognition， 光学字符识别)对合规文件进行字符识别，以识别出合规文件中的文字。然后，对OCR识别提取的合规文件中的文字进行分词，本实施例中，可采用N元文法统计模型(N-gram Model)、隐马尔科夫模型(Hidden Markov Model，简称HMM)、最大熵模型(Maximum Entropy Model)来进行分词，分词算法可包括：正向最大匹配，反向最大匹配，双向最大匹配，最短路径算法。将合规文件中的各个分词与预先建立的确认事项关键字库中的各个关键字进行匹配，以确定出合规文件中所包含的若干预设关键字。例如，预先建立的确认事项关键字库中可包含各个需确认事项的关键字，如身份证、电话、住址、收入、学历等等。
具体地，在一种可选的实施方式中，在对对话语音进行识别分析时，可先利用语音端点检测技术分辨出记录的对话语音中的语音信号和非语音信号，去除无效的语音片段和噪音，确定每个有效语音片段的开始和结束端点，有利于提高后续语音分析的准确度。在提取出有效的语音片段后，可对其进行语音识别，例如，可进行特征提取，将语音信号转化为声学特征矢量的特征流，作为语音信号的简洁表示。这种表示通常被称作观察值。观察值的提取可保证包含足够的信息用来识别。然后，利用隐马尔可夫模型(HMM)构建声学模型，用于将声学观察值映射为字词单元，再采用N-Gram来构建语言模型，用于表示局部的语法/语言信息，包括了词序列的可能性信息，将映射的字词单元进行语义结构的区分。在语音识别时利用帧同步算法，使得语音识别匹配在提取的语音的每一帧处进行，从而产生以每一帧为起始帧、最佳匹配序列的终结帧为结束帧的最大似然候选词。该最大似然候选词即作为最终对对话语音提取出的若干有效语音片段进行 识别分析后得到的若干关键词。当然，也可以利用现有的语音识别算法对对话语音进行识别分析，在此不做限定。
在完成对对话语音的识别分析后，可查找并记录对话语音中与合规文件中的各个预设关键字匹配的关键字。可以理解的是，在对话语音中包含与合规文件中的某一预设关键字相同或者词义相近的关键字时，即可认为合规文件中的该预设关键字被匹配成功。例如，其中一预设关键字为“身份证”，在对话语音中包含“身份证”时，即可认为预设关键字“身份证”被成功匹配。或者，其中一预设关键字为“住址”，在对话语音中包含“住宅地址”时，由于“住宅地址”与“住址”词义相近，即可认为预设关键字“住址”被成功匹配。
为了进一步提高核实的准确性，确保客户针对坐席提出的核实项目做出了相应的回答，每一所述预设关键字包括主叫方关键字和被叫方关键字，所述对话语音包括主叫方语音和被叫方语音，主叫方语音即为坐席发出的语音，被叫方语音即为客户发出的语音。所述对话语音中与所述主叫方关键字匹配的关键字来源于所述主叫方语音，所述对话语音中与所述被叫方关键字匹配的关键字来源于所述被叫方语音。记录所述对话语音中与合规文件中的预设关键字所匹配的关键字包括：记录主叫方语音中与主叫方关键字所匹配的关键字，和/或，记录被叫方语音中与被叫方关键字所匹配的关键字。以待核实项目为身份信息为例，主叫方关键字可以为“身份证”，被叫方关键字可以为任意18位数字。例如，为了确保坐席正确核实客户的身份信息，在坐席与客户通话的过程中，若在坐席发出的主叫方语音中搜索到关键字“身份证”，则认为主叫方关键字“身份证”被匹配成功；若对语音进行分析后判断客户回答了身份证号码，如在客户发出的被叫方 语音中搜索到18位数字，则认为被叫方关键字被匹配成功。在一种可选的实施方式中，只要主叫方语音中搜索到关键字“身份证”，或者被叫方语音中搜索到18位数字，则认为关于身份证的关键字被成功匹配。在另一种可选的实施方式中，需满足主叫方语音中搜索到关键字“身份证”，而且被叫方语音中也要搜索到18位数字，即主叫方语音中包含与主叫方关键字所匹配的关键字，同时，被叫方语音中也包含与被叫方关键字所匹配的关键字，才认为关于身份证的关键字被成功匹配。
可以理解的是，对于每一项待核实项目来说，所对应的主叫方关键字和被叫方关键字均匹配成功时，则认为该待核实项目所对应的预设关键字匹配成功。
步骤S5，提示用户所述未被匹配的预设关键字，即提示坐席当前未被核实的待确认项目。
与现有技术相比，本实施例通过监测用户基于电话销售系统呼叫的电话，在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音，对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字，在满足预设条件时，确定所述合规文件中未被匹配的预设关键字，并提示用户所述未被匹配的预设关键字，从而可以有效的提示用户当前还没有被核实的待确认项目，防止坐席在电话销售中遗漏需要确认的事项，提高销售效率。
在一可选的实施例中，在上述实施例的基础上，所述合规文件还 包括与各个所述预设关键字一一对应的勾选项目框，所述电话销售提示系统10被所述处理器12执行时还实现如下步骤：勾选所述合规文件中的被匹配成功的预设关键字所对应的勾选项目框。勾选时，例如可以在勾选项目框中打上勾，或者在勾选项目框内部填充预设颜色等等。从而能够自动勾选坐席与客户确认过的项目，无需坐席手动勾选待确认项目，进一步提高了销售效率。
在一可选的实施例中，所述电话销售提示系统10被所述处理器12执行时，还实现如下步骤：在所述合规文件中的所有预设关键字全部被成功匹配时，提示用户进行后续操作。在合规文件中的所有待确认项目均被核实完成后，则可以提示坐席进行下一步的操作，避免坐席浪费时间进行人工勾选确认等操作，进一步提高了销售效率。
如图2所示，图2为本申请电话销售提示方法一实施例的流程示意图，该电话销售提示方法包括以下步骤：
步骤S10，监测用户基于电话销售系统呼叫的电话。
本实施例中，用户可以为坐席。电话销售系统为坐席进行电话销售时所采用的系统，例如，可以为安装于计算机上的一软件系统。用户可以通过电话销售系统中的软电话向客户呼出电话。
电话销售提示系统10可以直接嵌入电话销售系统中，例如，可以为电话销售系统中的一个小工具，因此电话销售系统10可以直接监测到用户呼叫的电话。
电话销售提示系统10还可以为独立于电话销售系统的一个应用软件，此时电话销售提示系统10可以与电话销售系统或电话销售系统中的用于拨打电话的语音工具之间建立关联关系(例如绑定)，在 监测到电话销售系统拨出电话或者语音工具启动时，则该电话销售系统10自动开始运行，并监测电话是否呼叫成功。
步骤S20，在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音。
本实施例中，在坐席呼叫客户的电话接通时，则实时记录呼叫过程中的对话语音。可以将记录的对话语音保存在存储器内。
步骤S30，对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字。
步骤S40，在满足预设条件时，确定所述合规文件中未被匹配的预设关键字。
所述满足预设条件例如可以为：通话时长达到预设时长。预设时长的大小可以根据实际需要进行设置，例如可以根据坐席与客户一次电话销售通常需要的时长进行设置(如15分钟)，预设时长可以小于一次电话销售通常需要的时长。
本实施例中，所述满足预设条件还可以为通话结束，可以在通话结束后对本次通过过程中记录的对话语音进行识别分析。也可以在通话过程中实时的对对话语音进行识别分析。还可以在通话过程中每隔一段时间对对话语音进行识别分析，所间隔的时长可以根据实际需要进行设置，例如1分钟、2分钟等等。
合规文件中包括若干预设关键字。不同的预设关键字分别对应不同的待核实项目。例如，其中一项待核实项目可以为是否核实过客户的身份信息，对应的预设关键字例如可以为身份证。其中一项待核实项目还可以为是否核实过客户的地址，对应的预设关键字例如可以为住址、地址等。本实施例中，针对不同合规文件，还可针对合规文件 进行自动识别以生成对应的关键字集合，该关键字集合中包含若干预设关键字。具体地，可先利用OCR(Optical Character Recognition，光学字符识别)对合规文件进行字符识别，以识别出合规文件中的文字。然后，对OCR识别提取的合规文件中的文字进行分词，本实施例中，可采用N元文法统计模型(N-gram Model)、隐马尔科夫模型(Hidden Markov Model，简称HMM)、最大熵模型(Maximum Entropy Model)来进行分词，分词算法可包括：正向最大匹配，反向最大匹配，双向最大匹配，最短路径算法。将合规文件中的各个分词与预先建立的确认事项关键字库中的各个关键字进行匹配，以确定出合规文件中所包含的若干预设关键字。例如，预先建立的确认事项关键字库中可包含各个需确认事项的关键字，如身份证、电话、住址、收入、学历等等。
具体地，在一种可选的实施方式中，在对对话语音进行识别分析时，可先利用语音端点检测技术分辨出记录的对话语音中的语音信号和非语音信号，去除无效的语音片段和噪音，确定每个有效语音片段的开始和结束端点，有利于提高后续语音分析的准确度。在提取出有效的语音片段后，可对其进行语音识别，例如，可进行特征提取，将语音信号转化为声学特征矢量的特征流，作为语音信号的简洁表示。这种表示通常被称作观察值。观察值的提取可保证包含足够的信息用来识别。然后，利用隐马尔可夫模型(HMM)构建声学模型，用于将声学观察值映射为字词单元，再采用N-Gram来构建语言模型，用于表示局部的语法/语言信息，包括了词序列的可能性信息，将映射的字词单元进行语义结构的区分。在语音识别时利用帧同步算法，使得语音识别匹配在提取的语音的每一帧处进行，从而产生以每一帧为 起始帧、最佳匹配序列的终结帧为结束帧的最大似然候选词。该最大似然候选词即作为最终对对话语音提取出的若干有效语音片段进行识别分析后得到的若干关键词。当然，也可以利用现有的语音识别算法对对话语音进行识别分析，在此不做限定。
在完成对对话语音的识别分析后，可查找并记录对话语音中与合规文件中的各个预设关键字匹配的关键字。可以理解的是，在对话语音中包含与合规文件中的某一预设关键字相同或者词义相近的关键字时，即可认为合规文件中的该预设关键字被匹配成功。例如，其中一预设关键字为“身份证”，在对话语音中包含“身份证”时，即可认为预设关键字“身份证”被成功匹配。或者，其中一预设关键字为“住址”，在对话语音中包含“住宅地址”时，由于“住宅地址”与“住址”词义相近，即可认为预设关键字“住址”被成功匹配。
为了进一步提高核实的准确性，确保客户针对坐席提出的核实项目做出了相应的回答，每一所述预设关键字包括主叫方关键字和被叫方关键字，所述对话语音包括主叫方语音和被叫方语音，主叫方语音即为坐席发出的语音，被叫方语音即为客户发出的语音。所述对话语音中与所述主叫方关键字匹配的关键字来源于所述主叫方语音，所述对话语音中与所述被叫方关键字匹配的关键字来源于所述被叫方语音。记录所述对话语音中与合规文件中的预设关键字所匹配的关键字包括：记录主叫方语音中与主叫方关键字所匹配的关键字，和/或，记录被叫方语音中与被叫方关键字所匹配的关键字。以待核实项目为身份信息为例，主叫方关键字可以为“身份证”，被叫方关键字可以为任意18位数字。例如，为了确保坐席正确核实客户的身份信息，在坐席与客户通话的过程中，若在坐席发出的主叫方语音中搜索到关 键字“身份证”，则认为主叫方关键字“身份证”被匹配成功；若对语音进行分析后判断客户回答了身份证号码，如在客户发出的被叫方语音中搜索到18位数字，则认为被叫方关键字被匹配成功。在一种可选的实施方式中，只要主叫方语音中搜索到关键字“身份证”，或者被叫方语音中搜索到18位数字，则认为关于身份证的关键字被成功匹配。在另一种可选的实施方式中，需满足主叫方语音中搜索到关键字“身份证”，而且被叫方语音中也要搜索到18位数字，即主叫方语音中包含与主叫方关键字所匹配的关键字，同时，被叫方语音中也包含与被叫方关键字所匹配的关键字，才认为关于身份证的关键字被成功匹配。
可以理解的是，对于每一项待核实项目来说，所对应的主叫方关键字和被叫方关键字均匹配成功时，则认为该待核实项目所对应的预设关键字匹配成功。
步骤S50，提示用户所述未被匹配的预设关键字，即提示坐席当前未被核实的待确认项目。
与现有技术相比，本实施例通过监测用户基于电话销售系统呼叫的电话，在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音，对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字，在满足预设条件时，确定所述合规文件中未被匹配的预设关键字，并提示用户所述未被匹配的预设关键字，从而可以有效的提示用户当前还没有被核实的待确认项目，防止坐席在电话销售中遗漏需要确认的事项，提高销售效率。
在一可选的实施例中，在上述实施例的基础上，所述合规文件还包括与各个所述预设关键字一一对应的勾选项目框，该电话销售提示方法还包括如下步骤：勾选所述合规文件中的被匹配成功的预设关键字所对应的勾选项目框。勾选时，例如可以在勾选项目框中打上勾，或者在勾选项目框内部填充预设颜色等等。从而能够自动勾选坐席与客户确认过的项目，无需坐席手动勾选待确认项目，进一步提高了销售效率。
在一可选的实施例中，该电话销售提示方法还包括如下步骤：在所述合规文件中的所有预设关键字全部被成功匹配时，提示用户进行后续操作。在合规文件中的所有待确认项目均被核实完成后，则可以提示坐席进行下一步的操作，避免坐席浪费时间进行人工勾选确认等操作，进一步提高了销售效率。
此外，本申请还提供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电话销售提示系统，所述电话销售提示系统可被至少一个处理器执行，以使所述至少一个处理器执行如上述实施例中的电话销售提示方法的步骤，该电话销售提示方法的步骤S10、S20、S30等具体实施过程如上文所述，在此不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固 有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件来实现，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的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(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上参照附图说明了本申请的优选实施例，并非因此局限本申请的权利范围。上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。另外，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本领域技术人员不脱离本申请的范围和实质，可以有多种变型方案实现本申请，比如作为一个实施例的特征可用于另一实施例而得到又一实施例。凡在运用本申请的技术构思之内所作的任何修改、等同替换和改进，均应在本申请的权利范围之内。

Claims (20)

  1. 一种电子装置，其特征在于，所述电子装置包括存储器、处理器，所述存储器上存储有可在所述处理器上运行的电话销售提示系统，所述电话销售提示系统被所述处理器执行时实现如下步骤：
    监测用户基于电话销售系统呼叫的电话；
    在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音；
    对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字；
    在满足预设条件时，确定所述合规文件中未被匹配的预设关键字；
    提示用户所述未被匹配的预设关键字。
  2. 如权利要求1所述的电子装置，其特征在于，所述合规文件还包括与各个所述预设关键字一一对应的勾选项目框，所述电话销售提示系统被所述处理器执行时还实现如下步骤：
    勾选所述合规文件中被成功匹配的预设关键字所对应的勾选项目框。
  3. 如权利要求1所述的电子装置，其特征在于，所述电话销售提示系统被所述处理器执行时还实现如下步骤：
    若所述合规文件中的所有预设关键字全部被成功匹配，则提示用户当前所有预设关键字已全部匹配，以提醒用户可以进行后续操作。
  4. 如权利要求2所述的电子装置，其特征在于，所述电话销售提示系统被所述处理器执行时还实现如下步骤：
    若所述合规文件中的所有预设关键字全部被成功匹配，则提示用 户当前所有预设关键字已全部匹配，以提醒用户可以进行后续操作。
  5. 如权利要求1所述的电子装置，其特征在于，所述预设条件为：通话时长达到预设时长，或者，通话结束。
  6. 如权利要求2所述的电子装置，其特征在于，所述预设条件为：通话时长达到预设时长，或者，通话结束。
  7. 如权利要求1所述的电子装置，其特征在于，每一所述预设关键字包括主叫方关键字和被叫方关键字，所述对话语音包括主叫方语音和被叫方语音，所述记录所述对话语音中与合规文件中的预设关键字所匹配的关键字包括：
    记录主叫方语音中与主叫方关键字所匹配的关键字，和/或，记录被叫方语音中与被叫方关键字所匹配的关键字。
  8. 如权利要求2所述的电子装置，其特征在于，每一所述预设关键字包括主叫方关键字和被叫方关键字，所述对话语音包括主叫方语音和被叫方语音，所述记录所述对话语音中与合规文件中的预设关键字所匹配的关键字包括：
    记录主叫方语音中与主叫方关键字所匹配的关键字，和/或，记录被叫方语音中与被叫方关键字所匹配的关键字。
  9. 一种电话销售提示方法，其特征在于，所述方法包括：
    监测用户基于电话销售系统呼叫的电话；
    在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音；
    对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字；
    在满足预设条件时，确定所述合规文件中未被匹配的预设关键 字；
    提示用户所述未被匹配的预设关键字。
  10. 如权利要求9所述的电话销售提示方法，其特征在于，所述合规文件还包括与各个所述预设关键字一一对应的勾选项目框，该方法还包括：
    勾选所述合规文件中被成功匹配的预设关键字所对应的勾选项目框。
  11. 如权利要求9所述的电话销售提示方法，其特征在于，该方法还包括：若所述合规文件中的所有预设关键字全部被成功匹配，则提示用户当前所有预设关键字已全部匹配，以提醒用户可以进行后续操作。
  12. 如权利要求10所述的电话销售提示方法，其特征在于，该方法还包括：若所述合规文件中的所有预设关键字全部被成功匹配，则提示用户当前所有预设关键字已全部匹配，以提醒用户可以进行后续操作。
  13. 如权利要求9所述的电话销售提示方法，其特征在于，所述预设条件为：通话时长达到预设时长，或者，通话结束。
  14. 如权利要求10所述的电话销售提示方法，其特征在于，所述预设条件为：通话时长达到预设时长，或者，通话结束。
  15. 如权利要求9所述的电话销售提示方法，其特征在于，每一所述预设关键字包括主叫方关键字和被叫方关键字，所述对话语音包括主叫方语音和被叫方语音，所述记录所述对话语音中与合规文件中的预设关键字所匹配的关键字包括：
    记录主叫方语音中与主叫方关键字所匹配的关键字，和/或，记 录被叫方语音中与被叫方关键字所匹配的关键字。
  16. 如权利要求10所述的电话销售提示方法，其特征在于，每一所述预设关键字包括主叫方关键字和被叫方关键字，所述对话语音包括主叫方语音和被叫方语音，所述记录所述对话语音中与合规文件中的预设关键字所匹配的关键字包括：
    记录主叫方语音中与主叫方关键字所匹配的关键字，和/或，记录被叫方语音中与被叫方关键字所匹配的关键字。
  17. 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上存储有电话销售提示系统，所述电话销售提示系统被处理器执行时实现如下步骤：
    监测用户基于电话销售系统呼叫的电话；
    在用户基于所述电话销售系统呼叫的电话接通后，记录接通的电话中的对话语音；
    对所述对话语音进行识别分析，记录所述对话语音中与合规文件中的预设关键字所匹配的关键字；
    在满足预设条件时，确定所述合规文件中未被匹配的预设关键字；
    提示用户所述未被匹配的预设关键字。
  18. 如权利要求17所述的计算机可读存储介质，其特征在于，所述合规文件还包括与各个所述预设关键字一一对应的勾选项目框，该方法还包括：
    勾选所述合规文件中被成功匹配的预设关键字所对应的勾选项目框。
  19. 如权利要求17所述的计算机可读存储介质，其特征在于， 该方法还包括：若所述合规文件中的所有预设关键字全部被成功匹配，则提示用户当前所有预设关键字已全部匹配，以提醒用户可以进行后续操作。
  20. 如权利要求18所述的计算机可读存储介质，其特征在于，该方法还包括：若所述合规文件中的所有预设关键字全部被成功匹配，则提示用户当前所有预设关键字已全部匹配，以提醒用户可以进行后续操作。
PCT/CN2018/089721 2018-01-16 2018-06-03 电话销售提示方法、电子装置及可读存储介质 WO2019140851A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810038832.0 2018-01-16
CN201810038832.0A CN108234785B (zh) 2018-01-16 2018-01-16 电话销售提示方法、电子装置及可读存储介质

Publications (1)

Publication Number Publication Date
WO2019140851A1 true WO2019140851A1 (zh) 2019-07-25

Family

ID=62641232

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/089721 WO2019140851A1 (zh) 2018-01-16 2018-06-03 电话销售提示方法、电子装置及可读存储介质

Country Status (2)

Country Link
CN (1) CN108234785B (zh)
WO (1) WO2019140851A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108986826A (zh) * 2018-08-14 2018-12-11 中国平安人寿保险股份有限公司 自动生成会议记录的方法、电子装置及可读存储介质
CN111124145B (zh) * 2018-11-01 2023-05-16 奇酷互联网络科技（深圳）有限公司 信息输入方法、移动终端及存储装置
CN110796495A (zh) * 2019-10-31 2020-02-14 北京明略软件系统有限公司 一种实现信息处理的方法、装置、计算机存储介质及终端

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004012431A1 (en) * 2002-07-29 2004-02-05 British Telecommunications Public Limited Company Improvements in or relating to information provision for call centres
CN102082879A (zh) * 2009-11-27 2011-06-01 华为技术有限公司 呼叫中心语音检测的方法、装置及系统
CN102456344A (zh) * 2010-10-22 2012-05-16 中国电信股份有限公司 基于语音识别技术分析客户行为特征的系统及方法
CN102625005A (zh) * 2012-03-05 2012-08-01 广东天波信息技术股份有限公司 具有服务质量实时监督功能的呼叫中心系统及其实现方法
CN105141787A (zh) * 2015-08-14 2015-12-09 上海银天下科技有限公司 服务录音的合规检查方法及装置
CN105975514A (zh) * 2016-04-28 2016-09-28 朱宇光 一种自动质检方法及系统
US20170161378A1 (en) * 2015-12-02 2017-06-08 International Business Machines Corporation Expansion of a question and answer database

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6035017A (en) * 1997-01-24 2000-03-07 Lucent Technologies Inc. Background speech recognition for voice messaging applications
CN102868836B (zh) * 2012-09-17 2015-08-05 北京讯鸟软件有限公司 用于呼叫中心的真人话术系统及其实现方法
CN104301554A (zh) * 2013-07-18 2015-01-21 中兴通讯股份有限公司 一种对客服人员的服务质量进行质检的装置及方法
CN106297788B (zh) * 2016-08-19 2019-11-29 美的集团股份有限公司 控制方法及控制装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004012431A1 (en) * 2002-07-29 2004-02-05 British Telecommunications Public Limited Company Improvements in or relating to information provision for call centres
CN102082879A (zh) * 2009-11-27 2011-06-01 华为技术有限公司 呼叫中心语音检测的方法、装置及系统
CN102456344A (zh) * 2010-10-22 2012-05-16 中国电信股份有限公司 基于语音识别技术分析客户行为特征的系统及方法
CN102625005A (zh) * 2012-03-05 2012-08-01 广东天波信息技术股份有限公司 具有服务质量实时监督功能的呼叫中心系统及其实现方法
CN105141787A (zh) * 2015-08-14 2015-12-09 上海银天下科技有限公司 服务录音的合规检查方法及装置
US20170161378A1 (en) * 2015-12-02 2017-06-08 International Business Machines Corporation Expansion of a question and answer database
CN105975514A (zh) * 2016-04-28 2016-09-28 朱宇光 一种自动质检方法及系统

Also Published As

Publication number Publication date
CN108234785B (zh) 2020-08-04
CN108234785A (zh) 2018-06-29

Similar Documents

Publication Publication Date Title
CN109587360B (zh) 电子装置、应对话术推荐方法和计算机可读存储介质
US10777207B2 (en) Method and apparatus for verifying information
CN109493850B (zh) 成长型对话装置
CN109147797B (zh) 基于声纹识别的客服方法、装置、计算机设备及存储介质
WO2018149209A1 (zh) 语音识别方法、电子设备以及计算机存储介质
CN107481720B (zh) 一种显式声纹识别方法及装置
US11545139B2 (en) System and method for determining the compliance of agent scripts
WO2020215554A1 (zh) 语音识别方法、装置、设备及计算机可读存储介质
US11238854B2 (en) Facilitating creation and playback of user-recorded audio
US8478594B2 (en) Systems and methods for automatically determining culture-based behavior in customer service interactions
US8285539B2 (en) Extracting tokens in a natural language understanding application
WO2018233137A1 (zh) 电子装置、进线身份识别方法和计算机可读存储介质
WO2019140851A1 (zh) 电话销售提示方法、电子装置及可读存储介质
JPWO2016092807A1 (ja) 話者識別装置および話者識別用の登録音声の特徴量登録方法
JP2010079235A (ja) 個人（オーディ）情報を含まないメディア・ストリームを保存する方法
WO2016141697A1 (zh) 临时联系人的存储方法及装置
WO2020024415A1 (zh) 声纹识别处理方法、装置、电子设备及存储介质
KR20210114328A (ko) 통화 녹음 정보 관리방법, 이를 위한 컴퓨터 프로그램
CN109388695B (zh) 用户意图识别方法、设备及计算机可读存储介质
CN108280089A (zh) 识别异常来电的方法及设备
CN111326142A (zh) 基于语音转文本的文本信息提取方法、系统和电子设备
KR101705228B1 (ko) 전자문서생성장치 및 그 동작 방법
CN113064983A (zh) 语义检测方法、装置、计算机设备及存储介质
CN113822029A (zh) 客服辅助方法、装置和系统
US20240127800A1 (en) Automated validation of information exchanged during interactions

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18900838

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 20.10.2020.)

122 Ep: pct application non-entry in european phase

Ref document number: 18900838

Country of ref document: EP

Kind code of ref document: A1