CN115063154A

CN115063154A - Interest-degree-based service recommendation method, device, terminal and storage medium

Info

Publication number: CN115063154A
Application number: CN202210725044.5A
Authority: CN
Inventors: 朱益兴; 陈子意; 于欣璐; 陈杭; 李骁
Original assignee: Ping An Bank Co Ltd
Current assignee: Ping An Bank Co Ltd
Priority date: 2022-06-23
Filing date: 2022-06-23
Publication date: 2022-09-16

Abstract

The embodiment of the application discloses a service recommendation method, a device, a terminal and a storage medium based on interestingness. According to the method and the device, in the process that the seat personnel recommend services to the client personnel based on the specified service scenes, the conversation text in the conversation voice is obtained in real time, when other service scenes appear in the conversation text, the interest degree of the client personnel in the other service scenes is recognized based on the conversation text and the conversation voice of the client personnel in the conversation voice, if the interest degree is larger than the preset interest degree, the recommendation information of the other service scenes can be generated according to the service information of the other service scenes, the recommendation information of the other service scenes is displayed on the seat personnel side, so that the seat personnel recommend the services to the client personnel according to the recommendation information of the other service scenes, the recommendation of the service scenes which are interested in the client is achieved, and the success rate of service recommendation can be improved.

Description

Interest-degree-based service recommendation method, device, terminal and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a service recommendation method and apparatus based on interestingness, a terminal, and a storage medium.

Background

With the rapid development of financial science and technology and social economy, the range of related businesses of banks is more and more extensive. In order to expand the customer group, when new services are released, service recommendation needs to be performed on the customers, and the recommendation can be performed in a telephone mode and the like. However, when recommending services to clients, all clients are recommended by telephone, face-to-face or other methods, and in the process of recommending services to clients, service recommendation is performed to clients only according to the current service scenario, which cannot meet the service requirements of clients, resulting in a low success rate of service recommendation.

Disclosure of Invention

The embodiment of the application provides a service recommendation method, device, terminal and storage medium based on interestingness, and the success rate of service recommendation can be improved.

The embodiment of the application provides a service recommendation method based on interestingness, which comprises the following steps:

acquiring conversation voice of a client person and an agent person in a current business scene;

acquiring a conversation text from the conversation voice, and determining whether other service scenes appear in the conversation or not based on the conversation text;

if so, extracting text characteristic information based on the conversation text, and extracting voice characteristic information based on the voice information of the client personnel in the conversation voice;

identifying the interest degree of the client personnel in the other service scenes based on the text characteristic information and the voice characteristic information;

and if the interest degree is greater than a preset threshold value, generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes, and displaying the service scene guide information to the seat personnel.

Correspondingly, the embodiment of the present application further provides a service recommendation device based on the interestingness, including:

the first acquisition unit is used for acquiring the conversation voice of the client personnel and the seat personnel in the current service scene;

the second acquisition unit is used for acquiring a conversation text from the conversation voice and determining whether other service scenes appear in the conversation or not based on the conversation text;

the extraction unit is used for extracting text characteristic information based on the conversation text and extracting voice characteristic information based on the voice information of the client in the conversation voice if the conversation text is in the conversation text;

the recognition unit is used for recognizing the interest degree of the client personnel in the other service scenes based on the text characteristic information and the voice characteristic information;

and the display unit is used for generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes if the interest degree is greater than a preset threshold value, and displaying the service scene guide information to the seat personnel.

In some embodiments, the identification unit comprises:

the processing subunit is used for performing emotion recognition processing on the text characteristic information and the voice characteristic information to obtain the current emotion score of the client;

a first determining subunit, configured to determine a degree of interest of the client person in the other business scenario based on the current emotion score.

In some embodiments, the first determining subunit is specifically configured to:

acquiring a preset corresponding relation table, wherein the preset corresponding relation table comprises a plurality of preset emotion scores and a plurality of preset interest degrees, and different preset emotion scores correspond to different preset interest degrees;

and determining a preset interest degree corresponding to the current emotion score from the preset corresponding relation table to obtain the interest degree of the client personnel in the other service scenes.

In some embodiments, the second acquisition unit comprises:

the extraction subunit is used for extracting the service key words related to the service scenes from the dialog text;

a judging subunit, configured to judge whether the service keyword is a keyword corresponding to the current service scenario;

a second determining subunit, configured to determine that the other service scenarios do not occur in the dialog if the service keyword is a keyword corresponding to the current service scenario;

and a third determining subunit, configured to determine that the other service scenarios occur in the dialog if the service keyword is not a keyword corresponding to the current service scenario.

In some embodiments, the display unit comprises:

the first acquiring subunit is used for acquiring the handled services of the client staff from the handled service information of the client staff to obtain the handled services;

a fourth determining subunit, configured to determine, according to the service information of the other service scenarios, a target service corresponding to the other service scenarios;

a fifth determining subunit, configured to determine, according to the transacted service and the target service, a recommended service recommended to the client person;

and the second obtaining subunit is configured to obtain the service scene information of the recommended service, and obtain the service scene guidance information.

In some embodiments, the fifth determining subunit is specifically configured to:

and if the transacted business does not comprise the target business, obtaining the recommended business based on the target business.

if the transacted business comprises the target business, acquiring other businesses with the same business type as the target business;

and selecting the service which is not included in the transacted service from the other services to obtain the recommended service.

Correspondingly, the embodiment of the present application further provides a terminal, which includes a memory, a processor, and a computer program stored in the storage and executable on the processor, where the processor executes any one of the interestingness-based service recommendation methods provided in the embodiments of the present application.

Correspondingly, the embodiment of the application also provides a storage medium, wherein the storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the service recommendation method based on the interestingness.

According to the method and the device, the conversation text in the conversation voice is obtained in real time in the process that the seat personnel recommend the business to the client personnel based on the specified business scene, when other business scenes appear in the conversation text, the interest degree of the client personnel in the other business scenes is identified based on the conversation text of the client personnel in the conversation voice and the conversation voice, if the interest degree is larger than the preset interest degree, the recommendation information of the other business scenes can be generated according to the business information of the other business scenes, and the recommendation information of the other business scenes is displayed on the seat personnel side, so that the seat personnel recommend the business to the client personnel according to the recommendation information of the other business scenes, the recommendation of the business scenes which are interested in the client is realized, and the success rate of the business recommendation can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flowchart of a service recommendation method based on interestingness according to an embodiment of the present application.

Fig. 2 is a flowchart illustrating another service recommendation method based on interestingness according to an embodiment of the present application.

Fig. 3 is a block diagram of a structure of a service recommendation device based on interestingness according to an embodiment of the present application.

Fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides a service recommendation method, device, storage medium and terminal based on interestingness. Specifically, the service recommendation method based on the interestingness in the embodiment of the present application may be executed by a terminal, where the terminal may be a device such as a server. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and a big data and artificial intelligence platform.

For example, the terminal may be a server, and the server may obtain the conversation voice between the client person and the seat person in the current service scene; acquiring a conversation text from the conversation voice, and determining whether other service scenes appear in the conversation or not based on the conversation text; if so, extracting text characteristic information based on the conversation text, and extracting voice characteristic information based on the voice information of the client in the conversation voice; recognizing the interest degree of the client personnel in other service scenes based on the text characteristic information and the voice characteristic information; and if the interest degree is greater than the preset threshold value, generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes, and displaying the service scene guide information to the seat personnel.

Based on the above problems, embodiments of the present application provide a service recommendation method, device, terminal, and storage medium based on interestingness, which can improve the success rate of service recommendation.

The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.

The embodiment of the present application provides a service recommendation method based on interestingness, which may be executed by a terminal or a server.

Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a service recommendation method based on interestingness according to an embodiment of the present application. The specific process of the interest-degree-based service recommendation method can be as follows:

101. and acquiring the conversation voice of the client personnel and the seat personnel in the current service scene.

In the embodiment of the present application, the current service scenario refers to a service recommended to a customer by an agent of a current service provider. The service provider refers to a party, such as a bank, that can provide service for the user, and the current service scenario may be one of banking services, such as handling a credit card. The seat personnel refers to the staff of the service provider, such as a salesman or a customer service.

The conversation voice refers to real-time conversation audio of a client person and an agent person, and the agent person and the client person can carry out conversation in various ways, such as telephone conversation, face-to-face conversation, video conversation and the like.

For example, when the seat personnel communicate with the client personnel based on the current business scene, the conversation audio of the seat personnel and the client personnel is collected in real time to obtain conversation voice.

102. And acquiring dialog text from the dialog voice, and determining whether other service scenes appear in the dialog based on the dialog text.

The dialog text obtained from the dialog Speech may be obtained by an ASR (Automatic Speech Recognition) technology, which is a technology for converting human Speech into text.

For example, the obtained dialog speech is converted into text by ASR technology, and a dialog text corresponding to the dialog speech is obtained.

The other service scenarios refer to service scenarios different from the current service scenario, for example, the current service scenario may be a credit card transaction recommendation, and the other service scenarios may be bank card transaction recommendations.

In some embodiments, in order to improve the success rate of service recommendation, the step "determining whether other service scenes appear in the dialog based on the dialog text" may include the following operations:

extracting service keywords related to the service scene from the dialog text;

judging whether the service key words are key words corresponding to the current service scene;

if the service key words are key words corresponding to the current service scene, determining that other service scenes do not appear in the conversation;

and if the service key words are not the key words corresponding to the current service scene, determining that other service scenes appear in the conversation.

The service keyword refers to a keyword associated with a service scenario, for example, the service keyword may be: a business name, etc. a variety of words that may represent a business scenario.

For example, the dialog text may be "what action a credit card has", and then extracting the service keywords from the dialog text may be: a credit card.

The keywords corresponding to the current service scenario may be: the current service name may alternatively be a word representing the current service scenario.

For example, the current service scenario may be a personal financial service, and the keywords corresponding to the current service scenario may be: and (6) financing.

Further, matching the service keywords extracted from the dialog text with the keywords corresponding to the current service scene to determine whether the service keywords are the keywords corresponding to the current service scene.

In some embodiments, in order to improve the accuracy of the matching result, similarity matching may be performed between the service keyword and the keyword of the current service scene, and if the similarity between the service keyword and the keyword of the current service scene is greater than or equal to a preset similarity, the service keyword may be determined as the keyword corresponding to the current service scene; or if the similarity of the two is smaller than the preset similarity, determining that the service keyword is not the keyword corresponding to the current service scene.

For example, matching the service keyword with the keyword corresponding to the current service scene to obtain that the similarity between the service keyword and the keyword corresponding to the current service scene is greater than the preset similarity, the service keyword can be determined to be the keyword corresponding to the current service scene, and thus it can be determined that no other service scene occurs in the conversation between the current seat staff and the client staff.

For another example, by matching the service keyword with the keyword corresponding to the current service scene, and obtaining that the similarity between the service keyword and the keyword corresponding to the current service scene is smaller than the preset similarity, it can be determined that the service keyword is not the keyword corresponding to the current service scene, and thus it can be determined that other service scenes occur in the conversation between the current seat staff and the client staff.

103. And if so, extracting text characteristic information based on the dialog text, and extracting voice characteristic information based on the voice information of the client in the dialog voice.

The voice information refers to voice audio of the client person extracted from the conversation voice.

In the embodiment of the application, the feature extraction is performed on the dialogue text through the text feature extraction model, and the feature extraction is performed on the voice information through the voice feature extraction model.

For example, inputting a dialog text into a text feature extraction model, and performing feature extraction on the dialog text through the text feature extraction model to obtain text feature information of the dialog text; and inputting the voice information into a voice feature extraction model, and performing feature extraction on the voice information through the voice feature extraction model to obtain the voice feature information of the voice information.

The voice feature extraction model is developed on the basis of a Meta open-source voice pre-training model XLSR-53. XLSR-53 is a multilingual voice pre-training model trained on 53-language data for a total of 5 ten thousand (6) hours using the structure of the self-supervised voice pre-training model wav2vec2 (a voice pre-training model sourced by Meta corporation) by Meta.

Wherein the training of the text feature extraction model may include: using the published Chinese text pre-training model chinese-BERT-wwm (the open-source Chinese BERT model) as the initial model, 60epochs were continuously trained on the chinese-BERT-wwm model using only the textual information of the emotional training data. Wherein an Adam optimizer is used, and the learning rate is set to 0.00001 of exponemental decay. The loss function of the model remains the same as the initial model, chinese-BERT-wwm.

104. And identifying the interest degree of the client personnel in other service scenes based on the text characteristic information and the voice characteristic information.

In some embodiments, in order to make a specific service recommendation according to the preference of the customer person, the step "identifying the interest level of the customer person in other service scenarios based on the text feature information and the voice feature information" may include the following operations:

performing emotion recognition processing on the text characteristic information and the voice characteristic information to obtain the current emotion score of the client;

the level of interest of the customer person in other business scenarios is determined based on the current sentiment score.

In the embodiment of the application, emotion recognition processing is performed on the text characteristic information and the voice characteristic information through an emotion recognition model.

Specifically, text characteristic information and voice characteristic information are input into an emotion recognition model, the text characteristic information and the voice characteristic information are fused through the emotion recognition model to obtain fused characteristic information, and then emotion scores corresponding to the fused characteristic information are calculated through the emotion recognition model to obtain current emotion scores.

In the embodiment of the application, the emotion scores which can be calculated by the emotion recognition model can include a plurality of preset emotion scores, namely, the emotion score value range, and different emotion scores in the emotion score value range can correspond to different emotion categories.

For example, the sentiment score value may range from an integer of-3 to 3. Where 0 may represent a neutral mood with no positive or negative mood tendencies. +1, +2, +3 represent positive emotions, and the greater the number, the greater the positive intensity in turn. -1, -2 and-3 represent negative emotions, and the negative intensity increases in sequence with smaller numbers.

In some embodiments, to accurately identify the business in which the customer person is interested, the step "determining the level of interest of the customer person in other business scenarios based on the current emotional score" may include the following operations:

acquiring a preset corresponding relation table;

and determining a preset interest degree corresponding to the current emotion score from the preset corresponding relation table to obtain the interest degree of the client personnel in other service scenes.

The preset corresponding relation table comprises a plurality of preset emotion scores and a plurality of preset interest degrees, and different preset emotion scores correspond to different preset interest degrees.

For example, the plurality of preset sentiment scores may include: -3, -2, -1, 0, 1, 2, 3; the plurality of preset interest levels may include: 0. 10, 20, 30, 60, 80, 100. The corresponding relation table of the preset emotion scores and the preset interest degrees is as follows: a preset emotion score-3 corresponds to a preset interest degree 0; the preset emotion score-2 corresponds to a preset interest degree 10; the preset mood score-1 corresponds to a preset interest degree 20; the preset emotion score 0 corresponds to a preset interest degree 30; the preset emotion score 1 corresponds to a preset interest level 60; the preset emotion score 2 corresponds to a preset interest level 80; the preset emotion score 3 corresponds to a preset interest level 100. If the current mood score is: 3, obtaining a preset interest degree corresponding to the emotion score 3 from the preset corresponding relation table as follows: 100 and thus the level of interest of the customer personnel in other business scenarios is 100.

105. And if the interest degree is greater than the preset threshold value, generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes, and displaying the service scene guide information to the seat personnel.

The preset threshold value is also a preset interest degree, and the preset interest degree indicates whether a reference interest degree for recommending other service scenes for the client personnel is provided. If the degree of interest of the client personnel in other service scenes is greater than a preset threshold value, the fact that the degree of interest of the client personnel in other service scenes is high can be determined, and other service scenes can be recommended for the client personnel; if the degree of interest of the client personnel in other service scenes is smaller than the preset threshold, it can be determined that the degree of interest of the client personnel in other service scenes is low, and other service scenes do not need to be recommended to the client personnel.

Wherein the service scenario guide information indicates a service scenario that can be recommended to the customer.

In some embodiments, in order to improve the service recommendation efficiency, the step "generating service scenario guidance information according to the service information already handled by the client personnel and the service information of other service scenarios" may include the following operations:

acquiring the transacted business of the client staff from the transacted business information of the client staff to obtain the transacted business;

determining target services corresponding to other service scenes according to the service information of the other service scenes;

determining a recommended service recommended to a client person according to the handled service and the target service;

and acquiring the service scene information of the recommended service to obtain service scene guide information.

The transacted service refers to a service that is transacted by a client in a service provided by a current service provider.

For example, the services currently provided by the service provider may include: the service A, the service B, the service C, the service D and the like, the service handling information of the client personnel at the current service provider is obtained, and the services handled by the client personnel at the current service provider are obtained as follows: and the business A can obtain the transacted business of the client personnel as follows: service a.

The target service refers to a service corresponding to another service scenario. The service information of other service scenes may include service names, service types, and the like of other service scenes, and the target service corresponding to other service scenes is obtained according to the service information.

In some embodiments, in order to improve the service recommendation efficiency, the step "determining a recommended service to recommend to a client person according to the handled service and the target service" may include the following operations:

For example, the transacted business for a customer staff member may be: the service a, the service B, and the target service corresponding to other service scenarios may be: and the service C can determine that the target service does not exist in the services already handled by the client personnel, namely the client personnel do not handle the target service, and at the moment, the target service can be used as a recommended service.

and selecting the services which are not included in the transacted services from other services to obtain the recommended services.

For example, the transacted business for a customer staff member may be: the service a, the service B, and the target service corresponding to other service scenarios may be: and the service A can determine that the target service exists in the handled services of the client personnel, and can acquire other services with the same service type as the target service.

Specifically, since the interest level of the client person in the target service is higher, it can be ensured that the interest level of the client person is also higher for other services of the same service type as the target service, and the service of the same service type as the target service can be obtained from the services provided by the service provider, so as to obtain other services.

For example, the target service may be: the service type of the service a may be a first service type, and then the service of the first service type is obtained from the service provided by the service provider, and the obtained other services may be: service C, service D.

Further, the business which is not handled by the client personnel, namely the business which is not included in the handled business, is determined from other businesses and is used as the recommended business.

For example, other services may be: service C, service D, the services that the client personnel have transacted may be: and the service A and the service B can determine that the client personnel have higher interest in the service C and the service D, and do not handle the service C and the service D, and at the moment, the service C or the service D can be used as a recommended service.

After the recommended service is determined, the service scene information of the recommended service may be acquired, and the service scene information of the recommended service is used as service scene guide information. The service scene information may recommend the service introduction details of the service, including various service information such as the service type and the service usage. And then, displaying the service scene guide information to the seat personnel so that the seat personnel recommend services to the client personnel according to the service scene guide information, thereby recommending the services with higher interest degree to the client personnel and improving the success rate of service recommendation.

The embodiment of the application discloses a service recommendation method based on interestingness, which comprises the following steps: acquiring conversation voice of a client person and an agent person in a current business scene; acquiring a conversation text from the conversation voice, and determining whether other service scenes appear in the conversation or not based on the conversation text; if yes, extracting text characteristic information based on the conversation text, and extracting voice characteristic information based on voice information of the client in the conversation voice; recognizing the interest degree of the client personnel in other service scenes based on the text characteristic information and the voice characteristic information; and if the interest degree is greater than the preset threshold value, generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes, and displaying the service scene guide information to the seat personnel. Therefore, the success rate of service recommendation can be improved.

Based on the above description, the service recommendation method based on interestingness of the present application will be further described by way of example. Referring to fig. 2, fig. 2 is a schematic flowchart of another interest-based service recommendation method provided in an embodiment of the present application, and taking an example that the interest-based service recommendation method is applied to a server, a specific process may be as follows:

201. and in the process that the seat personnel carry out conversation to the client personnel based on the specified service, the server collects the conversation voice of the seat personnel and the client personnel in real time.

In the embodiment of the application, the application scenario may be a bank scenario, and the designated service may be a deposit service. When the seat personnel and the client personnel carry out conversation communication based on the deposit service, the server can collect conversation voice of the seat personnel and the client personnel.

202. And when recognizing that other services appear in the dialog text corresponding to the dialog voice, the server acquires the dialog text and the voice information corresponding to the dialog text.

Firstly, the server converts the collected dialogue speech into a dialogue text through an ASR technology, and then judges whether other services except the specified service appear in the dialogue text.

Specifically, whether other services except the specified service appear in the dialog text or not is judged, and the matching can be carried out through service keywords, namely keywords related to the service are extracted from the dialog text, then the keywords of the specified service are obtained, the keywords extracted from the dialog text are matched with the keywords of the specified service, if the matching is successful, it is determined that no other services appear in the dialog text, and if the matching is failed, it is determined that other services appear in the dialog text.

When other services appear in the dialog text, the dialog text and the voice information in the dialog voice when other services appear can be obtained.

203. The server identifies the level of interest of the customer personnel in other services based on the dialog text and the speech information.

Specifically, the dialog text and the voice information are input into the emotion recognition model. Firstly, feature extraction is carried out on voice information through a voice feature extraction module of an emotion recognition model to obtain voice features, and feature extraction is carried out on a conversation text through a text feature extraction module of the emotion recognition model to obtain text features.

Further, feature fusion processing is carried out on the extracted voice features and the extracted text features to obtain connection features of the voice features and the text features, then the emotion recognition model can carry out calculation processing based on the connection features to obtain emotion scores of the client, and finally interestingness corresponding to the emotion scores is obtained from a relation table of the emotion scores and the interestingness, so that interestingness of the client to other services is obtained.

204. And if the interest degree is greater than the preset interest degree, generating service recommendation information according to the service information of other services, and displaying the service recommendation information to the seat personnel.

Specifically, when the interest degree of the client person in the other services is greater than the preset interest degree, it may be determined that the interest degree of the client person in the other services is higher, and the service recommendation information may be generated according to the service information of the other services.

The service recommendation information comprises: service information of other services such as service name, service type, and service content of other services.

Specifically, the server can send the service recommendation information to the terminal corresponding to the agent, the service recommendation information is displayed to the agent through the terminal associated with the agent, when the agent looks up the service recommendation information, other services can be recommended to the client, the service recommendation range is expanded, meanwhile, service recommendation is performed to the client according to the service which the client is interested in, and the success rate of service recommendation can be improved.

The embodiment of the application discloses a service recommendation method based on interestingness, which comprises the following steps: in the process that the seat personnel carry out conversation to the client personnel based on the specified service, the server collects the conversation voice of the seat personnel and the client personnel in real time, when other services appear in a conversation text corresponding to the conversation voice, the conversation text and the voice information corresponding to the conversation text are obtained, the server identifies the interest degree of the client personnel in the other services based on the conversation text and the voice information, if the interest degree is larger than the preset interest degree, service recommendation information is generated according to the service information of the other services, and the service recommendation information is displayed to the seat personnel, so that the seat personnel can recommend according to the services in which the client personnel are interested, and the success rate of service recommendation can be improved.

In order to better implement the service recommendation method based on the interestingness provided by the embodiment of the present application, the embodiment of the present application further provides a service recommendation device based on the interestingness based service recommendation method. The meaning of the noun is the same as that in the service recommendation method based on the interestingness, and specific implementation details can refer to the description in the method embodiment.

Referring to fig. 3, fig. 3 is a block diagram illustrating a structure of a service recommendation device based on interestingness according to an embodiment of the present application, where the device includes:

a first obtaining unit 301, configured to obtain a conversation voice between a client and an agent in a current service scene;

a second obtaining unit 302, configured to obtain a dialog text from the dialog voice, and determine whether another service scenario occurs in the dialog based on the dialog text;

an extracting unit 303, configured to, if yes, extract text feature information based on the dialog text, and extract voice feature information based on voice information of the client person in the dialog voice;

an identifying unit 304, configured to identify a degree of interest of the customer person in the other service scenario based on the text feature information and the voice feature information;

a display unit 305, configured to generate service scene guidance information according to the service information handled by the client staff and the service information of the other service scenes if the interest degree is greater than a preset threshold, and display the service scene guidance information to the agent staff.

In some embodiments, the identifying unit 304 may include:

In some embodiments, the first determining subunit may be specifically configured to:

In some embodiments, the second obtaining unit 302 may include:

a second determining subunit, configured to determine that the other service scenario does not occur in the dialog if the service keyword is a keyword corresponding to the current service scenario;

In some embodiments, presentation unit 305 may include:

In some embodiments, the fifth determining subunit may be specifically configured to:

The embodiment of the application discloses a service recommendation device based on interestingness, which obtains conversation voice of a client and an agent in a current service scene through a first obtaining unit 301, obtains a conversation text from the conversation voice through a second obtaining unit 302, determines whether other service scenes appear in a conversation or not based on the conversation text, if so, extracts text characteristic information based on the conversation text and voice characteristic information based on voice information of the client in the conversation voice, if so, an identifying unit 304 identifies the interestingness of the client to the other service scenes based on the text characteristic information and the voice characteristic information, if so, a display unit 305 generates service scene guide information according to the service information transacted by the client and the service information of the other service scenes, and displaying the service scene guide information to the seat personnel. Therefore, the success rate of service recommendation can be improved.

Correspondingly, the embodiment of the application also provides a terminal, and the terminal can be a server. As shown in fig. 4, fig. 4 is a schematic structural diagram of a terminal provided in the embodiment of the present application. The terminal 400 includes a processor 401 having one or more processing cores, a memory 402 having one or more computer-readable storage media, and a computer program stored on the memory 402 and executable on the processor. The processor 401 is electrically connected to the memory 402. Those skilled in the art will appreciate that the terminal structures shown in the figures are not intended to be limiting of the terminal, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The processor 401 is a control center of the terminal 400, connects various parts of the entire terminal 400 using various interfaces and lines, performs various functions of the terminal 400 and processes data by running or loading software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby monitoring the entire terminal 400.

In this embodiment, the processor 401 in the terminal 400 loads instructions corresponding to processes of one or more application programs into the memory 402 according to the following steps, and the processor 401 runs the application programs stored in the memory 402, thereby implementing various functions:

obtaining conversation voice of client personnel and seat personnel in the current business scene;

if so, extracting text characteristic information based on the conversation text, and extracting voice characteristic information based on the voice information of the client in the conversation voice;

recognizing the interest degree of the client personnel in other service scenes based on the text characteristic information and the voice characteristic information;

and if the interest degree is greater than the preset threshold value, generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes, and displaying the service scene guide information to the seat personnel.

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

Optionally, as shown in fig. 4, the terminal 400 further includes: a touch display 403, a radio frequency circuit 404, an audio circuit 405, an input unit 406, and a power supply 407. The processor 401 is electrically connected to the touch display screen 403, the radio frequency circuit 404, the audio circuit 405, the input unit 406, and the power source 407. Those skilled in the art will appreciate that the terminal configuration shown in fig. 4 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The touch display screen 403 may be used for displaying a graphical user interface and receiving operation instructions generated by a user acting on the graphical user interface. The touch display screen 403 may include a display panel and a touch panel. Among other things, the display panel may be used to display messages input by or provided to the user and various graphical user interfaces of the terminal, which may be made up of graphics, text, icons, video, and any combination thereof. Alternatively, the Display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. The touch panel may be used to collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel using any suitable object or accessory such as a finger, a stylus pen, and the like), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Alternatively, the touch panel may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives a touch message from the touch sensing device, converts the touch message into touch point coordinates, sends the touch point coordinates to the processor 401, and can receive and execute a command sent by the processor 401. The touch panel may overlay the display panel, and when the touch panel detects a touch operation thereon or nearby, the touch panel may transmit the touch operation to the processor 401 to determine the type of the touch event, and then the processor 401 may provide a corresponding visual output on the display panel according to the type of the touch event. In the embodiment of the present application, the touch panel and the display panel may be integrated into the touch display screen 403 to realize input and output functions. However, in some embodiments, the touch panel and the touch panel can be implemented as two separate components to perform the input and output functions. That is, the touch display screen 403 may also be used as a part of the input unit 406 to implement an input function.

In the embodiment of the present application, a game application is executed by the processor 401 to generate a graphical user interface on the touch display screen 403, where a virtual scene on the graphical user interface includes at least one skill control area, and the skill control area includes at least one skill control. The touch display screen 403 is used for presenting a graphical user interface and receiving an operation instruction generated by a user acting on the graphical user interface.

The rf circuit 404 may be configured to transmit and receive rf signals to establish wireless communication with a network device or other terminals through wireless communication, and to transmit and receive signals with the network device or other terminals.

The audio circuit 405 may be used to provide an audio interface between the user and the terminal through a speaker, a microphone. The audio circuit 405 may transmit the electrical signal converted from the received audio data to a speaker, and convert the electrical signal into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 405 and converted into audio data, which is then processed by the audio data output processor 401 and then transmitted to, for example, another terminal via the radio frequency circuit 404, or the audio data is output to the memory 402 for further processing. The audio circuit 405 may also include an earbud jack to provide communication of peripheral headphones with the terminal.

The input unit 406 may be used to receive input numbers, character messages, or user characteristic messages (e.g., fingerprints, irises, facial messages, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

The power supply 407 is used to power the various components of the terminal 400. Optionally, the power source 407 may be logically connected to the processor 401 through a power management system, so as to implement functions of managing charging, discharging, power consumption management, and the like through the power management system. The power supply 407 may also include one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, or any other component.

Although not shown in fig. 4, the terminal 400 may further include a camera, a sensor, a wireless fidelity module, a bluetooth module, etc., which are not described in detail herein.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.

As can be seen from the above, the terminal provided in this embodiment obtains the dialogue voices of the client and the seat in the current service scene; acquiring a conversation text from the conversation voice, and determining whether other service scenes appear in the conversation or not based on the conversation text; if so, extracting text characteristic information based on the conversation text, and extracting voice characteristic information based on the voice information of the client in the conversation voice; recognizing the interest degree of the client personnel in other service scenes based on the text characteristic information and the voice characteristic information; and if the interest degree is greater than the preset threshold value, generating service scene guide information according to the service information transacted by the client personnel and the service information of other service scenes, and displaying the service scene guide information to the seat personnel.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, where the computer programs can be loaded by a processor to execute the steps in any one of the service recommendation methods based on interestingness provided by the present application. For example, the computer program may perform the steps of:

Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the computer program stored in the storage medium may execute the steps in any service recommendation method based on the interestingness provided in the embodiment of the present application, beneficial effects that any service recommendation method based on the interestingness provided in the embodiment of the present application can achieve may be achieved, for details, see the foregoing embodiments, and are not described herein again.

The service recommendation method, device, storage medium and terminal based on the interestingness provided by the embodiment of the present application are introduced in detail above, a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A service recommendation method based on interestingness is characterized in that the method comprises the following steps:

2. The method of claim 1, wherein the identifying the level of interest of the customer personnel in the other business scenario based on the text feature information and the speech feature information comprises:

performing emotion recognition processing on the text characteristic information and the voice characteristic information to obtain a current emotion score of the client;

determining a level of interest of the customer person in the other business scenario based on the current sentiment score.

3. The method of claim 2, wherein said determining a level of interest in said other business scenario by said customer person based on said current sentiment score comprises:

4. The method of claim 1, wherein the determining whether other traffic scenarios are present in the dialog based on the dialog text comprises:

extracting service keywords related to a service scene from the dialog text;

judging whether the service keywords are keywords corresponding to the current service scene;

5. The method of claim 1, wherein generating the service scenario guidance information according to the service information transacted by the client person and the service information of the other service scenarios comprises:

acquiring the transacted business of the client staff from the transacted business information of the client staff to obtain transacted business;

determining target services corresponding to the other service scenes according to the service information of the other service scenes;

determining a recommended service recommended to the client personnel according to the transacted service and the target service;

and acquiring the service scene information of the recommended service to obtain the service scene guide information.

6. The method of claim 5, wherein determining recommended services to recommend to the client person based on the transacted services and the target services comprises:

7. The method of claim 5, wherein determining recommended services to recommend to the client person based on the transacted services and the target services comprises:

8. An apparatus for recommending services based on interest level, the apparatus comprising:

9. A terminal comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor when executing the program implements the interestingness-based business recommendation method of any of claims 1-7.

10. A storage medium storing a plurality of instructions, the instructions being suitable for being loaded by a processor to execute the method for recommending service based on interest level according to any of claims 1 to 7.