CN115564529A - Voice navigation control method and device, computer terminal and storage medium - Google Patents

Voice navigation control method and device, computer terminal and storage medium Download PDF

Info

Publication number
CN115564529A
CN115564529A CN202211245923.4A CN202211245923A CN115564529A CN 115564529 A CN115564529 A CN 115564529A CN 202211245923 A CN202211245923 A CN 202211245923A CN 115564529 A CN115564529 A CN 115564529A
Authority
CN
China
Prior art keywords
client
voice
navigation control
voice data
control method
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
CN202211245923.4A
Other languages
Chinese (zh)
Inventor
程丽华
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.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank Co Ltd
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 Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202211245923.4A priority Critical patent/CN115564529A/en
Publication of CN115564529A publication Critical patent/CN115564529A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1822—Parsing for meaning understanding
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/60—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/12—Messaging; Mailboxes; Announcements
    • H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/086—Recognition of spelled words

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Business, Economics & Management (AREA)
  • Signal Processing (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Artificial Intelligence (AREA)
  • Child & Adolescent Psychology (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Economics (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Library & Information Science (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of voice navigation, and discloses a voice navigation control method, a device, a computer terminal and a storage medium, wherein the method comprises the following steps: when the voice communication is carried out with a client, the voice data of the client is obtained and recorded, and the semantic recognition and the emotion recognition are carried out on the voice data to generate a client image; analyzing related products suitable for the customer and corresponding business dialogues according to the customer portrait, and presenting the business dialogues on a screen of a salesman for prompting; if the client transacts the product, performing a voice transaction process, recording the transacted voice of the user, generating a confirmation message and sending the confirmation message to the client; and after the client finishes the voice communication, generating recommendation information and recommending the related products to the user. The client transaction evidence is left, and meanwhile, the prompt is provided for the speech skills of the business personnel, so that the areas in which the clients are interested are discovered as much as possible.

Description

Voice navigation control method and device, computer terminal and storage medium
Technical Field
The present invention relates to the field of voice navigation, and in particular, to a voice navigation control method, apparatus, computer terminal, and storage medium.
Background
In the field of financial science and technology, customers usually conduct business transaction through telephone, however, recording measures are not taken in most of the business transaction. The client disputes the transaction service, and no evidence can be provided when the client denies the acceptance of terms and product recommendation. Meanwhile, communication between the service staff and the client is instant, the client needs are grasped, and the use degree of the telephone operation varies from person to person, so that the product recommendation efficiency is not high, the client needs cannot be completely explored, the business opportunity cannot be hidden, and the service staff cannot find out the product in which the user is interested in a short conversation process.
Disclosure of Invention
In view of this, the present invention provides a voice navigation control method, apparatus, computer terminal and storage medium applicable to the fields of financial technology, etc.
In a first aspect, the present application provides a voice navigation control method, including:
when the voice communication is carried out with a client, the voice data of the client is obtained and recorded, and the semantic recognition and the emotion recognition are carried out on the voice data to generate a client image;
analyzing related products suitable for the customer and corresponding business dialogues according to the customer portrait, and presenting the business dialogues on a screen of a salesman for prompting;
if the client transacts the product, performing a product transaction flow, recording the transaction voice of the user, generating a confirmation message and sending the confirmation message to the client;
and after the client finishes the voice communication, generating recommendation information and recommending the related products to the user.
Further, the voice navigation control method further includes: acquiring dialogue voices of a salesman and a client, analyzing the semantics of the dialogue voices of the salesman, and searching whether sensitive words exist or not;
and if the sensitive words are searched, performing quality evaluation on the voice of the salesman according to the semantics of the conversation voice, and determining and reporting the voice.
Further, the voice navigation control method further includes: the method comprises the steps of obtaining the performance of all the salesmen, sequencing the performance of all the salesmen from high to low, obtaining the voice data of the salesmen with the front rank according to the sequencing result, carrying out the jargon analysis from the voice data, obtaining the jargon meeting the preset conditions and storing the jargon in a database.
Further, the voice navigation control method, presenting the business conversation on a screen of an attendant for prompting, includes: when the operator and the client carry out voice communication, the dialect stored in the database is selected as a prompt word to be used by the operator according to the current communication content and related products.
Further, the voice navigation control method, where the generating recommendation information recommends the relevant product to the user, includes:
and pushing the message through a short message or through a related application, and sending the link of the related product to the client.
Further, the voice navigation control method includes the following steps:
inputting the voice data into a semantic recognition model to obtain corresponding semantic characters;
the emotion recognition includes:
and inputting the voice data into an emotion recognition model to obtain emotion change which is associated with the semantic words in the voice data and changes along with time.
Further, the voice navigation control method, the generating the client representation includes:
and determining keywords in the voice data according to the semantic words corresponding to the emotion change, and determining the customer portrait according to the keywords.
In a second aspect, the present application further provides a voice navigation control device, including:
the recognition module is used for acquiring and recording voice data of a client when the voice communication is carried out with the client, and carrying out semantic recognition and emotion recognition on the voice data to generate a client image;
the prompting module is used for analyzing related products suitable for the customer and corresponding business techniques according to the customer portrait, and presenting the business techniques on a screen of a salesman for prompting;
the recording module is used for performing a product handling process if a client handles a product, recording the handling voice of the user, generating a confirmation short message and sending the confirmation short message to the client;
and the recommendation module is used for generating recommendation information and recommending the related products to the user after the voice communication of the client is finished.
In a third aspect, the present application further provides a computer terminal, which includes a processor and a memory, where the memory stores a computer program, and the computer program executes the voice navigation control method when running on the processor.
In a fourth aspect, the present application further provides a readable storage medium storing a computer program, which when executed on a processor performs the voice navigation control method.
The invention relates to the field of voice navigation, and discloses a voice navigation control method, a device, a computer terminal and a storage medium, wherein the method comprises the following steps: when the voice communication is carried out with a client, the voice data of the client is obtained and recorded, and the semantic recognition and the emotion recognition are carried out on the voice data to generate a client image; analyzing related products suitable for the customer and corresponding business dialogues according to the customer portrait, and presenting the business dialogues on a screen of a salesman for prompting; if the client transacts the product, performing a voice transaction process, recording the transacted voice of the user, generating a short message and sending the short message to the client; and after the client finishes the voice communication, generating recommendation information and recommending the related products to the user. When a client transacts business, the client transaction evidence can be left, meanwhile, a prompt is provided for the voice operation of a business clerk, the client portrait is generated by analyzing the semantics and emotion in real time, so that the related products which can be recommended to the user can be obtained, the fields in which the client is interested can be explored as far as possible, the business efficiency is higher, and the prompt is provided after the business transaction is finished, so that the better after-sale service experience is provided for the client, the probability of the user in the interest of the related products is improved, and the business promotion efficiency is improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings required to be used in the embodiments will be briefly described below, and it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope of the present invention. Like components are numbered similarly in the various figures.
FIG. 1 is a schematic flow chart illustrating a voice navigation control method according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for processing a voice of an operator according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an operator interface according to an embodiment of the present application;
fig. 4 shows a schematic structural diagram of a voice navigation control device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Hereinafter, the terms "including", "having", and their derivatives, which may be used in various embodiments of the present invention, are only intended to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be construed as first excluding the existence of, or adding to, one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.
Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as those defined in commonly used dictionaries) should be interpreted as having a meaning that is consistent with their contextual meaning in the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in various embodiments of the present invention.
In the field of financial science and technology, the situation of conversation and communication with a customer handling financial services can be involved, the technical scheme of the application is applied to the process of voice service handling of the customer, for example, in the financial industry, the service handling is usually communicated and handled with a salesman, or can be handled with an intelligent customer service, in the handling process, the voice of the customer can be recorded, semantics and emotion in the service handling process are analyzed in real time, so that customer images can be generated, the preference and the concerned things of the customer can be known, and products can be better recommended.
The technical solution of the present application will be described below with specific examples.
Example 1
As shown in fig. 1, the voice navigation control method of the present application includes:
and S100, when the voice communication is carried out with the client, acquiring and recording the voice data of the client, carrying out semantic recognition and emotion recognition on the voice data, and generating a client image.
When a customer transacts business of a bank or a financial industry, the business can be transacted in a telephone calling mode, and the business transaction can be credit card transaction or financial product transaction and the like. When the client performs the transaction in the aspect, the client can have a conversation with service personnel or an intelligent voice system to perform related service transaction, and the words spoken in the transaction process are recorded into voice data.
The voice data of the client can be recorded independently, and rough segmentation is carried out in a sentence-by-sentence mode, and after the specific voice data is obtained, subsequent processing is carried out.
Semantic recognition and emotion recognition aiming at the voice data are two independent works, and the semantics and the emotion of the voice data can be respectively obtained through a semantic recognition model and an emotion recognition model. It will be appreciated that semantic recognition requires the conversion of speech data into corresponding text, in order to determine what the client meant for the word. Emotion recognition is the need to determine what the current emotion is when a client is saying this period.
For the two models, a semantic library and an emotion library can be established, the voice data in the semantic library and the emotion library are labeled, and then the appropriate machine learning model is used for learning. Taking an emotion recognition model as an example, selecting a proper emotion library, such as a Chinese emotion library, wherein the emotion library has one thousand pieces of voice data, and if the emotion recognition model is labeled with 6 emotions, selecting 800 pieces of the one thousand pieces of voice data as a training set to train the model, and after the training is finished, using the remaining 200 pieces of voice data as a test set to test, wherein if the recognition success rate is greater than the designated probability, the model training is successful.
Specifically, the models may be hidden markov models, neural networks, and the like, and for different language systems, a model needs to be trained separately, and according to actual use conditions, the model is updated periodically, such as in semantic recognition, and a character library needs to be extended and updated to recognize more characters. For the emotion recognition models, it is also necessary to recognize more emotional features, or to classify emotions more finely, and the like, and these models need to be improved, and the update of these models can be realized by setting the update time.
When speaking, the emotion of the part of the speaker that is really intended is different, for example, for the part that is indifferent, the tone of voice is not very intense, the tone of voice is gentle and even ambiguous, and for the part that is intended, the part that is emphasized is clear, the situations that the tone is higher, the energy is larger, or the tone of voice is rapid exist, that is, in a sentence, the emotion of the person is fluctuated, that is, the emotion of the user is analyzed through the scale, tone and the like in the voice data, after the emotion and the semantics are analyzed, the important point in the words spoken by the client in the sentence can be known, and the field that the client intends is determined through the information that is exposed carelessly in the language.
Specifically, the semantic recognition may be performed by using a semantic recognition model, the complete speech data may be segmented first during the recognition, and the segmentation may be performed in a time-based manner or in an energy-based manner, so that each word in the speech data is separated, and then recognized one by one, and finally, the whole sentence is obtained. It can be understood that semantic recognition modes of different languages are different, different recognition models need to be used for the languages used by the client, and if the languages are non-Chinese, a translation program needs to be added on the basis of the recognition models to assist the service staff to know the speaking content of the opposite party.
The speech data is segmented during emotion recognition, for the convenience of subsequent customer portrait generation work, the segmentation mode of emotion recognition can be the same as that during semantic recognition, the emotion tendency of user speaking in different periods in a sentence is acquired by segmenting the complete speech data, and simultaneously, because the segmentation mode of the semantic recognition is the same, the recognition result of each word and the corresponding emotion recognition result are in one-to-one correspondence, so that the content concerned by the user can be recognized and obtained from the association of semantics and emotion and the emotion change along with the change of time, and the subsequent customer portrait generation is facilitated.
For example, a speech is divided into 20 segments, each segment is a character, 20 characters are obtained after semantic recognition, a sentence break is determined through time intervals between the characters, emotion recognition is carried out after the same segmentation processing, emotion corresponding to the 20 characters is obtained, association between emotion and semantics is formed, the attitude change trend of a client is grasped through emotion change of the client, and preparation is made for making a corresponding dialect next.
The client image refers to a personal description formed for the areas of interest and preference of the client, and the client related to the present application is a personal user, so that a personal user representation is generated. The method mainly reflects the field concerned by the client, and meanwhile, the client can conduct business transaction more than once through voice, so that the client portrait can be updated by combining with the prior client portrait, and the client portrait is further improved.
Specifically, when the customer portrait is generated, the customer is labeled with four dimensions of activity attribute, consumption, behavior and content, if the attribute is gender and age calendar and the like, the consumption refers to the consumption habit and purchase intention of the user, the behavior refers to the behavior period, frequency, access path and the like of the user, and the content is a platform, a common service and the like which are interested by the user.
The content of the above dimensions can be determined by searching keywords, wherein the behaviors and consumption are determined by combining emotions, for example, in a sentence, the emotion of a client who mentions a certain type of product is judged to be apathy, which indicates that the client does not intend to the product, and if the emotion is a question or a happy emotion, which indicates that the client is interested in the product, the emotion can be classified into the intention to do so.
When the customer portrait is generated, keywords such as some financial related words or words appearing in high frequency are extracted from semantics, then corresponding emotions of the words are obtained, how the mind of the customer is when the customer speaks the words is determined, and therefore the analyzed result is filled in each dimension of the portrait to determine the customer portrait or update the customer portrait.
Further, as shown in fig. 2, the step S100 may further include:
step S110, obtaining the dialogue voice of the salesman and the client, analyzing the semanteme of the salesman, and searching whether sensitive words exist.
In order to standardize the expression of the operator, the expression of the operator is also stored and analyzed so as to ensure that the expression of the operator is accurate and meets the specified service attitude, and therefore, whether the utterance of the operator meets the requirement or not is determined by setting up sensitive words. If the sensitive word is not found in the voice data of the business member, the word of the business member is appropriate, and the process directly proceeds to step S130, and if the sensitive word exists, the word of the business member may violate the rule.
Specifically, the sensitive words in this step may be inelegant words and some words unsuitable for communication, or some words that may involve internal confidentiality, and the like, and these sensitive words may be stored in a sensitive word thesaurus, and when performing sensitive word detection, the sensitive word thesaurus is matched with a sentence obtained by semantic analysis, and when any one sensitive word is matched, it is considered that the word is retrieved, otherwise, it is considered that the word is not retrieved.
And step S120, if the sensitive words are searched, performing quality evaluation on the voice of the salesman according to the semantics of the conversation voice, and reporting.
When the sensitive word is detected, reporting the voice data and evaluating the quality. When reporting, the report can be stored in a database, and meanwhile, the superior of the salesman is reminded of paying attention to the processing according to the organizational structure relationship of the salesman. The quality evaluation is to perform semantic processing on the voice data when the operator communicates at this time, determine whether the meaning of the whole sentence is irregular in the sentence with the sensitive word, and evaluate the voice quality of the operator according to the result.
Specifically, the quality evaluation may determine whether the voice quality of the operator is in accordance with the specification, perform voice quality evaluation according to the number of the sensitive words, the weight of the sensitive words, and the like, determine the voice quality of the operator, upload the data to the corresponding leader, and perform final judgment by the leader directly belonging to the operator.
And step S130, acquiring the performance of all the salesmen, sequencing the performance of all the salesmen from high to low, acquiring the voice data of a preset number of salesmen at the front of the ranking according to the sequencing result, carrying out the conversational analysis from the voice data, and storing the conversational analysis meeting the preset conditions into a database.
The performance is the sales promotion result of the product sales promotion of the salesperson, the performance data can be obtained through the administrative system, and the sales promotion language of the salesperson with good performance can have a desirable place, so that the salesperson can analyze which businesses increase the transaction success rate according to the voice data of the salesperson with the front ranking.
Therefore, while the voice data of the client is analyzed, the voice data of the business personnel is also stored, and meanwhile, the voice data of the business personnel at the front rank is analyzed according to the performance ranking of the business personnel, and the keywords in the voice data are extracted to determine the key words of the business personnel. For example, voice data of a business member with the highest performance 10 is taken, voice data for obtaining the transaction is screened out, relevant keywords in the voice data are obtained according to the product of the transaction, then the dialect in the voice data is extracted, and the most efficient dialect is determined through the integration of a plurality of voice data.
The dialect meeting the preset condition in this embodiment refers to the dialect obtained by analyzing the voice data of the high-performance salesman.
For example, these dialects may be a set of sentences or keywords, and statistics are performed on these dialects to determine the success rate of each dialects and the association between each type of product, and these are stored in the database according to the success rate and the association between the corresponding products. After the customer portrait is generated or updated, relevant products judged according to the customer portrait are selected from the database and displayed on a display screen of an operator, and the operator is prompted to promote sales according to the statement.
And step S200, analyzing related products suitable for the client and corresponding business dialogues according to the client portrait, and presenting the business dialogues on a screen of a salesman for prompting.
The client portrait reflects the attributes of the client in all dimensions, belongs to the data form expression of the attributes of the client and can be used for analyzing the products suitable for the client.
After the customer portrait is obtained, products interested by the customer can be analyzed according to the portrait so as to mine the potential of the customer. For example, through two dimensions of consumption and behavior, the types, namely categories, of products in which the customers are interested can be determined, and then the types are explored to find products which are not contacted by the customers but are probably interested.
For example, if a client is a 25-year-old man who learns the subject and transacts some debt-based financial products, the business transaction is a deposit card account opening, and meanwhile transacts a regular deposit, the financial concept of the user can be considered to be a robust concept, the robust financial product can be considered to be the interest of the user, and the mobile capital of the user is probably not abundant according to the age judgment, so that a suitable robust financial product can be recommended to the user, for example, a financial product which can be flexibly accessed without a closed period, or a financial product with low or even no commission charge, and the products are used as related products to be presented to a salesman as a result after the client figures are analyzed, and the salesman is prompted to recommend according to the products. For example, the customer is recommended to have regular money to buy some robust financial products that can be flexibly accessed.
According to the related products, the system can generate some promotion dialogs for current operators, for example, when recommending high-risk investment products or low-risk investment products, the operators can enable clients to have better understanding and better receiving degree of the products through different introduction and explanation modes, so that the corresponding dialogs can be selected according to differences of specific products, the selected dialogs can prompt the operators to perform topic cut-in and recommendation according to the dialogs in a mode of displaying on a screen, and the recommendation of the dialogs can be understood as suggestion and prompt for the operators and does not need to be forcibly performed by the operators.
The dialogs are from the database, that is, the dialogs generated in step S130 above, which are associated with the current voice call can be determined by matching keywords in the current voice call, and the corresponding promotion language can be generated according to the formats of the dialogs and the related services. The salesperson can conduct recommendations of additional services while transacting products for the customer based on these promotional languages to mine potential business opportunities for the customer.
After semantic analysis, the sentences can be displayed on a screen by using different colors for different words to prompt a service staff, wherein the words are concerned by the client and the words are not concerned by the client.
As shown in fig. 3, for the schematic diagram of the computer interface when the service staff and the client communicate with each other, the generated client drawings, the matched products, the semantic analysis, the emotion analysis and the recommended dialogues can be displayed according to the arrangement in fig. 3, so as to tell the service staff what the current client needs, and how to suggest the conversation mode, so as to help the service staff give a prompt when not wanting how to recommend the products to the client at a certain time, and help the service staff to make service development and promote the products.
And step S300, if the client transacts the product, performing a product transaction process, recording the transaction voice of the user, generating a confirmation message and sending the confirmation message to the client.
When a client transacts a product, the client enters a product transaction flow, and can understand that the financial product transaction needs to sign a contract, no matter the financial product is purchased, or the credit card, account number and other services are transacted, the contract is needed, so according to the transacted product category, corresponding contract terms can be generated on a display screen of a clerk, key parts in the terms are processed in a thickening mode and the like, the clerk reads the key parts to the client, and the client confirms whether to transact the product or not by voice.
In a feasible embodiment, the intelligent voice system can also be used for reading the terms, prompting the user to speak corresponding keywords to confirm whether to handle the product, recording the handling process, namely recording the voice of the user when answering the handling process, and determining that the client knows the risk and responsibility of handling the product according to the intention of the client by taking the recorded contents as evidence, so that the problem that the client complains and repudiates the transaction due to loss and the like can be avoided.
The confirmation short message has the effect similar to a receipt and a certificate, when the client finishes handling, the client is informed that the business is successfully handled through the feedback of the confirmation short message, on one hand, the evidence of the notification is left, and on the other hand, the client has a feedback feeling after handling the business, so that the service experience of the client is improved, and meanwhile, the evidence of the completion of the business handling is kept on the hand of the client, so that the traceability of the whole business handling process is ensured.
And step S400, after the client finishes the voice communication, generating recommendation information and recommending the related products to the user.
The recommendation information in this step refers to recommendation information carrying the related products, and may be in the form of a link or a message, where the link of the related product is pushed to an account under the name of a client through a related APP, or may be directly sent to a mobile phone of the user through a short message, so as to ensure that the user can see the related information again after the user finishes a call.
It is understood that, in step S200, although the relevant information is presented to the business staff, in the current voice communication, the business that the client needs to handle is not the business analyzed by the client figure in the embodiment, but the business that the client itself wants to handle. Thus, in communication with the business, these extended services may not be processed at that time, so the push message may be re-sent once more, and if the customer sees the connection and the message is intended, it may look further, thereby increasing the chance of trading.
According to the voice navigation control method, voice data are recorded and processed when voice communication is conducted on the client, analysis of the voice data of the client and analysis of voice data of a salesman are achieved, so that the voice quality of the salesman can be checked, the client image of the client can be analyzed, and potential commercial value of the client can be discovered. The method optimizes the client demand and the service promotion, perfects the whole promotion process, and increases the collection of user preference data to perfect the portrait of the client. Meanwhile, voice data processing is carried out on the high-performance salesman according to the voice data of the salesman, the reason of good performance of the salesman is analyzed, and the method is popularized, so that the overall level and efficiency of the salesman are improved, the transaction rate of the business is further improved, and the sales promotion capability of the business is greatly improved. In addition, when the product is traded, the voice evidence of the client is recorded by recording and publicizing and reading contract conditions, and the short message is fed back, so that the client can trace the transaction after finishing the transaction with the client, the client is proved to finish the transaction voluntarily by the evidence, and the risk of repenting and complaint of the client due to various reasons is avoided.
Example 2
As shown in fig. 4, the present application also provides a voice navigation control apparatus, including:
the recognition module 10 is used for acquiring and recording voice data of a client when performing voice communication with the client, and performing semantic recognition and emotion recognition on the voice data to generate a client image;
a prompt module 20, configured to analyze, according to the customer representation, a relevant product suitable for the customer and a corresponding business conversation, and present the business conversation on a screen of a salesman for prompting;
the recording module 30 is used for performing a voice transaction process if a client transacts a product, recording the transacted voice of the user, generating a short message and sending the short message to the client;
and the recommending module 40 is used for generating recommending information and recommending the related products to the user after the client finishes the voice communication.
The application also provides a computer terminal, which comprises a processor and a memory, wherein the memory stores a computer program, and the computer program executes the voice navigation control method when running on the processor.
The present application also provides a readable storage medium storing a computer program which, when executed on a processor, performs the voice navigation control method.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, each functional module or unit in each embodiment of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part of the technical solution that contributes to the prior art in essence can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention.

Claims (10)

1. A voice navigation control method is characterized by comprising the following steps:
when the voice communication is carried out with a client, the voice data of the client is obtained and recorded, and the semantic recognition and the emotion recognition are carried out on the voice data to generate a client picture;
analyzing related products suitable for the customer and corresponding business dialogues according to the customer portrait, and presenting the business dialogues on a screen of a salesman for prompting;
if the client transacts the product, performing a product transaction flow, recording the transaction voice of the user, generating a confirmation message and sending the confirmation message to the client;
and after the client finishes the voice communication, generating recommendation information and recommending the related products to the user.
2. The voice navigation control method of claim 1, further comprising: acquiring dialogue voices of a salesman and a client, analyzing the semantics of the dialogue voices of the salesman, and searching whether sensitive words exist or not;
and if the sensitive words are searched, performing quality evaluation on the voice of the salesman according to the semantics of the conversation voice, and reporting.
3. The voice navigation control method of claim 2, further comprising: the method comprises the steps of obtaining the performance of all the salesmen, sequencing the performance of all the salesmen from high to low, obtaining the voice data of the salesmen with the preset number at the front of the ranking according to the sequencing result, carrying out the jargon analysis from the voice data, obtaining the jargon meeting the preset condition and storing the jargon in a database.
4. The voice navigation control method of claim 3, wherein the presenting the business conversation on a screen of an attendant for prompting comprises: when the operator and the client carry out voice communication, the dialect stored in the database is selected as a prompt word to be used by the operator according to the current communication content and related products.
5. The voice navigation control method of claim 1, wherein the generating recommendation information to recommend the related product to the user comprises:
and pushing the message through a short message or through a related application, and sending the link of the related product to the client.
6. The voice navigation control method of claim 1, wherein the semantic recognition comprises:
inputting the voice data into a semantic recognition model to obtain corresponding semantic characters;
the emotion recognition includes:
and inputting the voice data into an emotion recognition model to obtain emotion change which is associated with the semantic words in the voice data and changes along with time.
7. The voice navigation control method of claim 6, wherein generating the client representation comprises:
and determining keywords in the voice data according to the semantic words corresponding to the emotion change, and determining the customer portrait according to the keywords.
8. A voice navigation control device, comprising:
the recognition module is used for acquiring and recording voice data of a client when the voice communication is carried out with the client, and carrying out semantic recognition and emotion recognition on the voice data to generate a client image;
the prompting module is used for analyzing related products suitable for the customer and corresponding business dialogues according to the customer portrait, and presenting the business dialogues on a screen of a salesman for prompting;
the recording module is used for performing a product handling process if a client handles a product, recording the handling voice of the user, generating a confirmation short message and sending the confirmation short message to the client;
and the recommendation module is used for generating recommendation information and recommending the related products to the user after the voice communication of the client is finished.
9. A computer terminal, characterized in that it comprises a processor and a memory, said memory storing a computer program which, when run on said processor, executes the voice navigation control method of any one of claims 1 to 7.
10. A readable storage medium, characterized in that it stores a computer program which, when run on a processor, performs the voice navigation control method of any one of claims 1 to 7.
CN202211245923.4A 2022-10-12 2022-10-12 Voice navigation control method and device, computer terminal and storage medium Pending CN115564529A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211245923.4A CN115564529A (en) 2022-10-12 2022-10-12 Voice navigation control method and device, computer terminal and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211245923.4A CN115564529A (en) 2022-10-12 2022-10-12 Voice navigation control method and device, computer terminal and storage medium

Publications (1)

Publication Number Publication Date
CN115564529A true CN115564529A (en) 2023-01-03

Family

ID=84745213

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211245923.4A Pending CN115564529A (en) 2022-10-12 2022-10-12 Voice navigation control method and device, computer terminal and storage medium

Country Status (1)

Country Link
CN (1) CN115564529A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117764459A (en) * 2024-02-22 2024-03-26 山邮数字科技(山东)有限公司 enterprise management system and method based on intelligent data analysis and processing

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117764459A (en) * 2024-02-22 2024-03-26 山邮数字科技(山东)有限公司 enterprise management system and method based on intelligent data analysis and processing
CN117764459B (en) * 2024-02-22 2024-04-26 山邮数字科技(山东)有限公司 Enterprise management system and method based on intelligent data analysis and processing

Similar Documents

Publication Publication Date Title
US11455475B2 (en) Human-to-human conversation analysis
KR101883185B1 (en) Robot automatic counselling method and system with determined scenario using machine-learning
US8145562B2 (en) Apparatus and method for fraud prevention
CN109767787B (en) Emotion recognition method, device and readable storage medium
US9014363B2 (en) System and method for automatically generating adaptive interaction logs from customer interaction text
US10210867B1 (en) Adjusting user experience based on paralinguistic information
US10770062B2 (en) Adjusting a ranking of information content of a software application based on feedback from a user
US11082554B2 (en) Method for conversion and classification of data based on context
CN108256098B (en) Method and device for determining emotional tendency of user comment
CN111625632A (en) Question-answer pair recommendation method, device, equipment and storage medium
EP4036823A1 (en) Customization platform and method for service quality evaluation product
KR102100214B1 (en) Method and appratus for analysing sales conversation based on voice recognition
US20230290344A1 (en) Systems and methods for formatting informal utterances
US20150220618A1 (en) Tagging relations with n-best
Subramaniam et al. Business intelligence from voice of customer
EP3910493A1 (en) Systems and methods for determining a response to a user query
CN114357126A (en) Intelligent question-answering system
CN113051380A (en) Information generation method and device, electronic equipment and storage medium
CN115564529A (en) Voice navigation control method and device, computer terminal and storage medium
CN116579351B (en) Analysis method and device for user evaluation information
KR20210009266A (en) Method and appratus for analysing sales conversation based on voice recognition
Vysotska et al. Sentiment Analysis of Information Space as Feedback of Target Audience for Regional E-Business Support in Ukraine.
CN110765242A (en) Method, device and system for providing customer service information
Chang et al. Using Machine Learning to Extract Insights from Consumer Data
CN113971581A (en) Robot control method and device, terminal equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination