Method and apparatus for generating target service, program product, storage medium

Abstract

This application provides a method, apparatus, program product, and storage medium for generating a target service. The method includes: during a conversational interaction with a target account, acquiring first text data and target voice data generated by the target object through the target account during the conversational interaction; extracting N emotional features of the target object from the target text data and target voice data; determining the operation level of the target object performing a target operation in response to the conversational interaction based on the N emotional features; and generating a target service based on the operation level and target parameters. The target parameters include a first parameter and a second parameter. The first parameter includes object features of the target object, and the second parameter includes dynamic operation features performed by the target object through the target account within a historical time period. The target service is a service corresponding to the target operation. This application solves the problem of not being able to generate targeted services in related technologies and achieves the effect of generating targeted services.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method and apparatus for generating target services, a program product, and a storage medium. Background Technology

[0002] In the customer service process, unforeseen issues can disrupt the process, leading to customer complaints. In such cases, customers often exhibit negative emotions during their interactions with customer service. Traditional consumer finance customer service representatives do not assess a customer's emotional state or level of susceptibility to complaints. To reduce subsequent complaints, they typically employ standardized reassurance scripts, failing to provide tailored services to mitigate the potential for further issues. Summary of the Invention

[0003] This application provides a method, apparatus, program product, and storage medium for generating target services, addressing the problem that services cannot be specifically generated in at least some related technologies.

[0004] According to one embodiment of this application, a method for generating a target service is provided, comprising: during a conversational interaction with a target account, acquiring first text data and target speech data generated by a target object through the target account during the conversational interaction; extracting N emotional features of the target object from the target text data and the target speech data, wherein the target text data is determined by the following steps: converting the target speech data into second text data, merging the first text data and the second text data to obtain the target text data, wherein N is a natural number greater than 1; determining the operation level of the target object performing a target operation in the conversational interaction based on the N emotional features; generating a target service based on the operation level and target parameters, wherein the target parameters include a first parameter and a second parameter, the first parameter includes object features of the target object, the second parameter includes dynamic operation features performed by the target object through the target account within a historical time period, and the target service is a service corresponding to the target operation.

[0005] In one exemplary embodiment, during a conversational interaction with a target account, acquiring first text data and target voice data generated by the target object through the target account during the conversational interaction includes: acquiring text data and voice data output by the target object through the target account; obtaining the first text data by extracting data within a preset text range from the text data based on text keywords, wherein the text keywords are keywords determined based on the conversation topic of the conversational interaction; and obtaining the target voice data by extracting data within a preset time range from the voice data based on voice keywords, wherein the voice keywords are keywords determined based on the conversation topic of the conversational interaction.

[0006] In an exemplary embodiment, extracting N emotional features of the target object from the target text data and the target speech data includes: extracting target text features from the target text data based on text sentiment features to obtain a first emotional feature, wherein the text sentiment feature is used to represent the text emotional expression of the target object; extracting target speech features from the target speech data based on acoustic features to obtain a second emotional feature, wherein the acoustic feature is used to represent the speech emotional expression of the target object; and determining the first emotional feature and the second emotional feature as the emotional features.

[0007] In an exemplary embodiment, determining the operation level of the target object performing the target operation in the conversation interaction based on N of the aforementioned emotional features includes: performing a classification operation on the N of the aforementioned emotional features to obtain M groups of emotional features, wherein M is a natural number greater than or equal to 1 and less than or equal to N, wherein each of the aforementioned emotional feature groups includes at least one of the aforementioned emotional features, and each of the aforementioned emotional feature groups has a different emotional level; determining the emotional value of each of the aforementioned emotional feature groups according to a preset weight of the aforementioned emotional level; and determining the aforementioned operation level based on the M of the aforementioned emotional values.

[0008] In one exemplary embodiment, generating a target service based on the aforementioned operation level and target parameters includes: obtaining a first service rule from a service rule base based on the aforementioned operation level and the aforementioned first parameter, and generating a first target service, wherein the service rule base includes service rules for reducing the aforementioned operation level, the service rules include the aforementioned first service rule, and the first target service is used to provide the target object with session interaction data that reduces the aforementioned operation level; obtaining a second service rule from the service rule base based on the aforementioned operation level and the aforementioned second parameter, and generating a second target service, wherein the service rule includes the aforementioned second service rule, and the second target service is used to provide the target object with policy data that reduces the aforementioned operation level; and determining the aforementioned first target service and the aforementioned second target service as the target service.

[0009] In an exemplary embodiment, after generating the target service based on the aforementioned operation level and target parameters, the method further includes: pushing the target service to the target account according to the object characteristics of the target object; collecting feedback information from the target object regarding the target service; and updating the service rule base based on the feedback information, wherein the service rule base includes service rules for reducing the aforementioned operation level.

[0010] According to one embodiment of this application, an apparatus for generating a target service includes: a first acquisition module, configured to acquire first text data and target speech data generated by a target object through the target account during a conversational interaction with a target account; a first extraction module, configured to extract N emotional features of the target object from the target text data and the target speech data, wherein the target text data is determined by the following steps: converting the target speech data into second text data, merging the first text data and the second text data to obtain the target text data, and N being a natural number greater than 1; a first determination module, configured to determine the operation level of the target object performing a target operation in the conversational interaction based on the N emotional features; and a first generation module, configured to generate a target service based on the operation level and target parameters, wherein the target parameters include a first parameter and a second parameter, the first parameter including object features of the target object, the second parameter including dynamic operation features performed by the target object through the target account within a historical time period, and the target service being a service corresponding to the target operation.

[0011] In an exemplary embodiment, the first acquisition module includes: a first acquisition submodule, configured to acquire text data and voice data output by the target object through the target account; a second acquisition submodule, configured to acquire data within a preset text range from the text data based on text keywords to obtain the first text data, wherein the text keywords are keywords determined based on the conversation topic of the conversation interaction; and a third acquisition submodule, configured to acquire data within a preset time range from the voice data based on voice keywords to obtain the target voice data, wherein the voice keywords are keywords determined based on the conversation topic of the conversation interaction.

[0012] In an exemplary embodiment, the first extraction module includes: a first extraction submodule, configured to extract target text features from the target text data based on text sentiment features to obtain a first sentiment feature, wherein the text sentiment feature is used to represent the text sentiment expression of the target object; a second extraction submodule, configured to extract target speech features from the target speech data based on acoustic features to obtain a second sentiment feature, wherein the acoustic feature is used to represent the speech sentiment expression of the target object; and a first determination submodule, configured to determine the first sentiment feature and the second sentiment feature as the sentiment feature.

[0013] In an exemplary embodiment, the first determining module includes: a first execution submodule, configured to perform a classification operation on N of the aforementioned emotional features to obtain M groups of emotional features, wherein M is a natural number greater than or equal to 1 and less than or equal to N, wherein each of the aforementioned emotional feature groups includes at least one of the aforementioned emotional features, and each of the aforementioned emotional feature groups has a different emotional level; a second determining submodule, configured to determine the emotional value of each of the aforementioned emotional feature groups according to a preset weight of the aforementioned emotional level; and a third determining submodule, configured to determine the aforementioned operation level based on the M aforementioned emotional values.

[0014] In an exemplary embodiment, the first generation module includes: a fourth acquisition submodule, configured to acquire a first service rule from a service rule base based on the operation level and the first parameter, and generate a first target service, wherein the service rule base includes service rules for reducing the operation level, the service rules include the first service rule, and the first target service is used to provide the target object with session interaction data for reducing the operation level; a fifth acquisition submodule, configured to acquire a second service rule from the service rule base based on the operation level and the second parameter, and generate a second target service, wherein the service rules include the second service rule, and the second target service is used to provide the target object with policy data for reducing the operation level; and a fourth determination submodule, configured to determine the first target service and the second target service as the target service.

[0015] In one exemplary embodiment, the apparatus further includes: a first push module, configured to generate a target service based on the operation level and target parameters, and then push the target service to the target account according to the object characteristics of the target object; a first collection module, configured to collect feedback information from the target object regarding the target service; and a first update module, configured to update the service rule base based on the feedback information, wherein the service rule base includes service rules for reducing the operation level.

[0016] According to another embodiment of this application, a computer program product is also provided, including a computer program configured to have a processor perform the steps in any of the above method embodiments.

[0017] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the steps in any of the above method embodiments by a processor.

[0018] According to yet another embodiment of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to execute the computer program to perform the steps in any of the above method embodiments.

[0019] This application acquires target text and voice data generated by the target object through the target account during a conversational interaction. N emotional features of the target object are extracted from the target text and voice data. Based on these N emotional features, the operation level of the target object in relation to the conversational interaction is determined. Based on the operation level, the target object's characteristics, and the dynamic operation characteristics performed by the target object through the target account over a historical period, a target service is generated. Because this application can generate a target service based on the target object's emotional state and historical behavioral characteristics during the conversational interaction, it solves the problem of not being able to generate targeted services in related technologies, achieving the effect of targeted service generation. Attached Figure Description

[0020] Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of generating a target service according to an embodiment of this application;

[0021] Figure 2 This is a flowchart of a method for generating a target service according to an embodiment of this application;

[0022] Figure 3 This is a flowchart illustrating a method for generating a target service according to a specific embodiment of this application;

[0023] Figure 4 This is a structural block diagram of an apparatus for generating a target service according to an embodiment of this application. Detailed Implementation

[0024] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0026] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of generating a target service according to an embodiment of this application. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0027] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a method for generating a target service in this embodiment of the application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0028] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0029] This embodiment provides a method for generating a target service. Figure 2 This is a flowchart of a method for generating a target service according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0030] Step S202: During the conversational interaction with the target account, obtain the first text data and target voice data generated by the target object through the target account during the conversational interaction.

[0031] Step S204: Extract N emotional features of the target object from the target text data and the target speech data. The target text data is determined by the following steps: convert the target speech data into second text data, merge the first text data and the second text data to obtain the target text data, where N is a natural number greater than 1.

[0032] Step S206: Determine the operation level of the target object in response to the above-mentioned conversation interaction based on N of the above-mentioned emotional characteristics;

[0033] Optionally, the target action can be a complaint action, and the action level can be a complaint level.

[0034] Step S208: Based on the above operation level and target parameters, generate a target service, wherein the target parameters include a first parameter and a second parameter, the first parameter includes the object characteristics of the target object, the second parameter includes the dynamic operation characteristics of the target object performed by the target account within a historical time period, and the target service is a service corresponding to the target operation.

[0035] Optionally, target characteristics include, but are not limited to, the target's gender, age, occupation, interests, and geographic location. Dynamic operational characteristics include, but are not limited to, the target's recent purchasing behavior, feedback and complaint history, and browsing history. For example, the target's recently purchased products or services can be used to predict potential follow-up services or products. Past feedback and complaint records help identify the target's concerns and potential areas for service improvement.

[0036] Through the above steps, during the conversational interaction with the target account, target text data and target voice data generated by the target object through the target account during the conversational interaction are obtained. N emotional features of the target object are extracted from the target text data and target voice data. Based on the N emotional features, the operation level of the target object in response to the conversational interaction is determined. Based on the operation level, the object characteristics of the target object, and the dynamic operation characteristics performed by the target object through the target account within a historical time period, a target service is generated. Because this application can generate target services based on the target object's emotional state and historical behavioral characteristics during the conversational interaction, it solves the problem of not being able to generate targeted services in related technologies, and achieves the effect of targeted service generation.

[0037] In one exemplary embodiment, during a conversational interaction with a target account, acquiring first text data and target voice data generated by the target object through the target account during the conversational interaction includes: acquiring text data and voice data output by the target object through the target account; obtaining the first text data by extracting data within a preset text range from the text data based on text keywords, wherein the text keywords are keywords determined based on the conversation topic of the conversational interaction; and obtaining the target voice data by extracting data within a preset time range from the voice data based on voice keywords, wherein the voice keywords are keywords determined based on the conversation topic of the conversational interaction.

[0038] Optionally, the conversation topic may be banking account services, with keywords including but not limited to account opening, transfers, account management, deposits, withdrawals, account balances, and bank fees. The conversation topic may be insurance product consultation, with keywords including but not limited to insurance, premiums, coverage amounts, claims, and insurance terms. The conversation topic may be investment consultation, with keywords including but not limited to stocks, funds, bonds, investment returns, risk assessment, asset allocation, and market analysis. The conversation topic may be loan services, with keywords including but not limited to housing loans, personal loans, commercial loans, interest rates, loan terms, repayment plans, and loan conditions. The conversation topic may be credit card services, with keywords including but not limited to credit card applications, credit limit increases, bill inquiries, points redemption, annual fees, and late fees.

[0039] Optionally, for example, when a target user inquires about the claims process for an insurance product with a live customer service representative through a target account, keywords include, but are not limited to, insurance, premium, coverage amount, and claim amount. Text analytics tools and speech recognition technology are used to extract target text data and target speech data containing premium, coverage amount, and claim amount from the text and speech data during the consultation process.

[0040] This embodiment obtains data within a preset range based on keywords, enabling the extraction of valuable data from a large amount of session data. This achieves the goal of improving data utilization and effectively locating the specific needs and problems of the target object.

[0041] In an exemplary embodiment, extracting N emotional features of the target object from the target text data and the target speech data includes: extracting target text features from the target text data based on text sentiment features to obtain a first emotional feature, wherein the text sentiment feature is used to represent the text emotional expression of the target object; extracting target speech features from the target speech data based on acoustic features to obtain a second emotional feature, wherein the acoustic feature is used to represent the speech emotional expression of the target object; and determining the first emotional feature and the second emotional feature as the emotional features.

[0042] Optionally, textual emotional features include, but are not limited to, vocabulary selection, emotional tendency, emotional complexity, emotional context, sentence structure, and rhetorical devices. Acoustic features include, but are not limited to, pitch variation, speech rate and rhythm, volume and intensity, intonation patterns, physical properties of sound, energy, and resonance.

[0043] Optionally, before extracting emotional features, preprocessing can be performed on the target text data and target speech data to improve extraction efficiency and accuracy. Preprocessing includes, but is not limited to, cleaning the target text data, including removing stop words and punctuation marks, and performing stemming or word form restoration, to prepare the data for sentiment analysis. Noise reduction and segmentation preprocessing can be performed on the target speech data to improve the accuracy of speech recognition.

[0044] Optionally, for example, the target audience is conversing with a customer service representative, expressing dissatisfaction with a recently purchased financial product. Target text data: "I am very disappointed. The description on your website is different from the actual financial product! I request an immediate refund." Based on the identification of the above text sentiment features, the following first emotional feature can be extracted: Negative emotion intensity: high; Emotion type: disappointment and anger; Urgency: high. The target audience then communicates with the customer service representative via voice. The target voice data exhibits characteristics of high fundamental frequency, strong sound, and high zero-crossing rate. Based on the identification of the above acoustic features, the following second emotional feature can be extracted: anger.

[0045] This embodiment achieves the goal of improving the accuracy of emotion recognition by combining multimodal emotion recognition of text and speech.

[0046] In an exemplary embodiment, determining the operation level of the target object performing the target operation in the conversation interaction based on N of the aforementioned emotional features includes: performing a classification operation on the N of the aforementioned emotional features to obtain M groups of emotional features, wherein M is a natural number greater than or equal to 1 and less than or equal to N, wherein each of the aforementioned emotional feature groups includes at least one of the aforementioned emotional features, and each of the aforementioned emotional feature groups has a different emotional level; determining the emotional value of each of the aforementioned emotional feature groups according to a preset weight of the aforementioned emotional level; and determining the aforementioned operation level based on the M of the aforementioned emotional values.

[0047] Optionally, the extracted N emotional features are categorized into M emotional feature groups. For example, N=5, M=3, and possible emotional feature groups include anger, anxiety, and satisfaction. An emotional level is assigned to each emotional feature group, such as anger level 3, anxiety level 2, and satisfaction level 1. Weights are assigned to each emotional level according to business needs. For example, anger has the highest weight of 0.5, anxiety is next at 0.3, and satisfaction has the lowest at 0.2. Based on the emotional level and preset weights of each emotional feature group, an emotional value is calculated for each group. For example, if the anger group has an emotional level of 3 and a weight of 0.5, its emotional value is 1.5. The operational level is determined based on the emotional value: the M emotional values ​​are aggregated, weighted averaged, or judged based on a threshold to determine the final operational level. For example, if the anxiety group has an emotional value of 0.6 and the satisfaction group has an emotional value of 0.2, the final operational level might be determined based on the anger group's emotional value of 1.5, as it has the highest weight; the final operational level would be anger - high level.

[0048] This embodiment achieves the goal of effectively optimizing customer service processes, improving customer experience, and reducing the probability of customer complaints by determining the operation level based on emotional characteristics.

[0049] In one exemplary embodiment, generating a target service based on the aforementioned operation level and target parameters includes: obtaining a first service rule from a service rule base based on the aforementioned operation level and the aforementioned first parameter, and generating a first target service, wherein the service rule base includes service rules for reducing the aforementioned operation level, the service rules include the aforementioned first service rule, and the first target service is used to provide the target object with session interaction data that reduces the aforementioned operation level; obtaining a second service rule from the service rule base based on the aforementioned operation level and the aforementioned second parameter, and generating a second target service, wherein the service rule includes the aforementioned second service rule, and the second target service is used to provide the target object with policy data that reduces the aforementioned operation level; and determining the aforementioned first target service and the aforementioned second target service as the target service.

[0050] Optionally, a first target service can be generated based on the operation level, target text data, target voice data, first parameter, and second parameter. The target text data and target voice data can accurately pinpoint the specific reasons why the target object generates the aforementioned emotions. Furthermore, by combining the first parameter and second parameter, the probability of the target object performing the target operation can be effectively reduced.

[0051] Optionally, after analyzing the target text and voice data and determining the target object's action level as "anger - high level," a first service rule is retrieved from the service rule base based on the first parameter: the target object's gender, age, occupation, and interests. The second parameter is also retrieved based on the target object's recent purchasing behavior, feedback and complaint history, and browsing history. For example, a bank wants to reduce customer complaints, especially those related to its investment products, by providing personalized services. The bank has an intelligent customer service platform that can provide customized services based on customer characteristics (gender, age, occupation, interests). For example, the target object's first parameters are: gender - female, age - 40, occupation - financial analyst, interests - investment, reading financial news, golf. The target object's second parameter is: recently frequently browsing a certain type of financial product. Analyzing the first parameter, a female client who is a financial analyst may have in-depth knowledge of complex financial products and expect professional investment advice and high-quality customer service. A 40-year-old client may be in the wealth accumulation stage and have high expectations for asset appreciation and investment returns. A client's interest in investment and financial news indicates a strong focus on market dynamics and investment opportunities. Service guidelines based on profession: Provide timely market analysis and investment advice. Given the client's interest in investment, the bank can provide customized financial news summaries and market updates. Service guidelines based on age: Provide asset allocation advice and wealth management services for clients in the wealth accumulation stage. Combining the above service guidelines, the bank generates the following primary target services: Provide a dedicated investment advisor, offering professional market analysis and investment advice from financial analysts. Regularly send customized financial news summaries and market updates to help clients stay informed about market changes. Secondary target services: Provide personalized asset allocation advice and wealth management services to meet the client's needs during the wealth accumulation stage. Push notifications about preferential services for wealth management products.

[0052] This embodiment, based on the first and second parameters, can provide services closely related to customers, meet their professional needs and personalized services, and effectively reduce customer complaints, improve service effectiveness and customer loyalty.

[0053] In an exemplary embodiment, after generating the target service based on the aforementioned operation level and target parameters, the method further includes: pushing the target service to the target account according to the object characteristics of the target object; collecting feedback information from the target object regarding the target service; and updating the service rule base based on the feedback information, wherein the service rule base includes service rules for reducing the aforementioned operation level.

[0054] Optionally, feedback information includes, but is not limited to, proactive inquiry feedback, emotion recognition feedback, and behavior tracking feedback. Proactive inquiry feedback: After the service is pushed out, intelligent customer service or questionnaires are used to proactively inquire about the target user's satisfaction with the service and suggestions for improvement, rather than relying solely on passive complaints or opinion collection. Emotion recognition feedback: Using sentiment analysis technology, by analyzing the target user's language and behavior during service use (such as through voice recognition and chat log analysis), their emotional feedback on the service is automatically identified, even if the user does not express it directly. Behavior tracking feedback: By analyzing the target account's usage data to observe changes in the target user's behavior, such as whether they have increased account activity or made repeat purchases, the effectiveness and satisfaction of the service can be indirectly assessed.

[0055] Optionally, banks can push these services to users via application programming interfaces (APIs) in the form of personalized notifications, such as through mobile banking apps, emails, or SMS. They can also select the most suitable push method and timing based on the target audience's habits and preferences. For example, if the target audience typically uses the services at night, pushing service information at night may be more effective.

[0056] Optionally, the service rule base contains service rules for downgrading operational levels. These rules are designed based on customer profiles, service history, and behavioral patterns. The bank updates the service rule base based on customer feedback. For example, if a customer provides negative feedback on certain services, the bank analyzes the reasons and adjusts the service rules to improve service quality. This enables the provision of personalized services based on customer characteristics, reducing customer complaint rates while simultaneously improving service quality and customer satisfaction.

[0057] The present invention will now be described in conjunction with specific embodiments:

[0058] Figure 3 This is a flowchart illustrating a method for generating a target service according to a specific embodiment of this application, including the following steps:

[0059] S302, A customer inquires about a financial product with the intelligent customer service system via text and voice.

[0060] S304 uses text analysis tools and speech recognition technology to extract target text data and target speech data containing keywords such as premium, sum insured, and claim amount from text data and speech data during the consultation process;

[0061] S306, for text-based emotion feature recognition, the following first emotion feature is extracted: negative emotion intensity: low, emotion type: anxiety, urgency: high. The target speech data exhibits high fundamental frequency, strong volume, and high zero-crossing rate. Based on the above acoustic features, the following second emotion feature is extracted: urgency.

[0062] S308: The four extracted emotional features are classified into two emotional feature groups: anger and anxiety. An emotional level is assigned to each emotional feature group: anger is level 1, and anxiety is level 3. Based on the emotional level and preset weights, the emotional value for each emotional feature group is calculated: 0.6 for the anxiety group and 0.2 for the anger group. The operational level is determined based on the emotional value: the two emotional values ​​are aggregated, weighted averaged, or judged based on a threshold to determine the final operational level. For example, if the anxiety group's emotional value of 0.6 is greater than the preset threshold and the anger group's emotional value is less than the preset threshold, the final operational level is anxiety - high level.

[0063] S310, based on operational level anxiety - high level predicted customer complaints are likely to be transferred to S312, otherwise transfer to S316;

[0064] S312, Add a "Customer Complaint-Prone" tag;

[0065] S314, the intelligent customer service switches to human customer service, displays the "Easy to Complain" tag, and provides targeted services. These targeted services are determined based on the customer's target characteristics and dynamic operational characteristics. Target characteristics: Gender - Female, Age - 40 years old, Occupation - Financial Analyst, Interests - Investment, Reading Financial News, Golf. Dynamic operational parameters: Frequent browsing of the price fluctuations of a specific financial product. Analyzing these characteristics generates the following first targeted service: Providing professional market analysis and investment advice. Regularly sending customized financial news summaries and market updates to help the customer stay informed about market changes. Second targeted service: Pushing promotional offers for a specific financial product;

[0066] S316, the intelligent customer service continues to provide the following target services: Regularly sending customized financial news summaries and market updates to help customers stay informed about market changes. Second target service: Promoting preferential offers on wealth management products;

[0067] S318, End.

[0068] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0069] This embodiment also provides an apparatus for generating target services, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0070] Figure 4 This is a structural block diagram of an apparatus for generating a target service according to an embodiment of this application, such as... Figure 4 As shown, the device includes:

[0071] The first acquisition module 402 is used to acquire first text data and target voice data generated by the target object through the target account during the conversational interaction with the target account.

[0072] The first extraction module 404 is used to extract N emotional features of the target object from the target text data and the target speech data, wherein the target text data is determined by the following steps: converting the target speech data into second text data, merging the first text data and the second text data to obtain the target text data, and N is a natural number greater than 1.

[0073] The first determining module 406 is used to determine the operation level of the target object in response to the conversation interaction based on N of the above-mentioned emotional characteristics.

[0074] The first generation module 408 is used to generate a target service based on the above-mentioned operation level and target parameters. The target parameters include a first parameter and a second parameter. The first parameter includes the object characteristics of the target object. The second parameter includes the dynamic operation characteristics of the target object performed by the target object through the target account within a historical time period. The target service is a service corresponding to the target operation.

[0075] In an exemplary embodiment, the first acquisition module includes: a first acquisition submodule, configured to acquire text data and voice data output by the target object through the target account; a second acquisition submodule, configured to acquire data within a preset text range from the text data based on text keywords to obtain the first text data, wherein the text keywords are keywords determined based on the conversation topic of the conversation interaction; and a third acquisition submodule, configured to acquire data within a preset time range from the voice data based on voice keywords to obtain the target voice data, wherein the voice keywords are keywords determined based on the conversation topic of the conversation interaction.

[0076] In an exemplary embodiment, the first extraction module includes: a first extraction submodule, configured to extract target text features from the target text data based on text sentiment features to obtain a first sentiment feature, wherein the text sentiment feature is used to represent the text sentiment expression of the target object; a second extraction submodule, configured to extract target speech features from the target speech data based on acoustic features to obtain a second sentiment feature, wherein the acoustic feature is used to represent the speech sentiment expression of the target object; and a first determination submodule, configured to determine the first sentiment feature and the second sentiment feature as the sentiment feature.

[0077] In an exemplary embodiment, the first determining module includes: a first execution submodule, configured to perform a classification operation on N of the aforementioned emotional features to obtain M groups of emotional features, wherein M is a natural number greater than or equal to 1 and less than or equal to N, wherein each of the aforementioned emotional feature groups includes at least one of the aforementioned emotional features, and each of the aforementioned emotional feature groups has a different emotional level; a second determining submodule, configured to determine the emotional value of each of the aforementioned emotional feature groups according to a preset weight of the aforementioned emotional level; and a third determining submodule, configured to determine the aforementioned operation level based on the M aforementioned emotional values.

[0078] In an exemplary embodiment, the first generation module includes: a fourth acquisition submodule, configured to acquire a first service rule from a service rule base based on the operation level and the first parameter, and generate a first target service, wherein the service rule base includes service rules for reducing the operation level, the service rules include the first service rule, and the first target service is used to provide the target object with session interaction data for reducing the operation level; a fifth acquisition submodule, configured to acquire a second service rule from the service rule base based on the operation level and the second parameter, and generate a second target service, wherein the service rules include the second service rule, and the second target service is used to provide the target object with policy data for reducing the operation level; and a fourth determination submodule, configured to determine the first target service and the second target service as the target service.

[0079] In one exemplary embodiment, the apparatus further includes: a first push module, configured to generate a target service based on the operation level and target parameters, and then push the target service to the target account according to the object characteristics of the target object; a first collection module, configured to collect feedback information from the target object regarding the target service; and a first update module, configured to update the service rule base based on the feedback information, wherein the service rule base includes service rules for reducing the operation level.

[0080] Embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0081] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0082] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0083] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0084] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0085] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0086] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0087] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the scope of protection of this application.

Claims

1. A method for generating a target service, characterized in that, include: During a conversational interaction with the target account, first text data and target voice data generated by the target object through the target account during the conversational interaction are acquired; N emotional features of the target object are extracted from the target text data and the target speech data, wherein the target text data is determined by the following steps: converting the target speech data into second text data, merging the first text data and the second text data to obtain the target text data, and N is a natural number greater than 1; Based on N emotional characteristics, determine the operation level at which the target object performs the target operation in response to the conversation interaction; Based on the operation level and target parameters, a target service is generated, wherein the target parameters include a first parameter and a second parameter, the first parameter includes the object characteristics of the target object, the second parameter includes the dynamic operation characteristics of the target object performed by the target account within a historical time period, and the target service is a service corresponding to the target operation.

2. The method according to claim 1, characterized in that, During a conversational interaction with the target account, first text data and target voice data generated by the target object through the target account during the conversational interaction are acquired, including: Acquire the text and voice data output by the target object through the target account; Based on text keywords, data within a preset text range is obtained from the text data to obtain the first text data, wherein the text keywords are keywords determined based on the conversation topic of the conversation interaction; Based on voice keywords, data within a preset time range is obtained from the voice data to obtain the target voice data, wherein the voice keywords are keywords determined based on the conversation topic of the conversation interaction.

3. The method according to claim 1, characterized in that, Extract N emotional features of the target object from the target text data and the target speech data, including: Based on text sentiment features, target text features are extracted from the target text data to obtain a first sentiment feature, wherein the text sentiment feature is used to represent the text sentiment expression of the target object; Based on acoustic features, target speech features are extracted from the target speech data to obtain second emotion features, wherein the acoustic features are used to represent the speech emotion expression of the target object; The first emotional feature and the second emotional feature are identified as the emotional features.

4. The method according to claim 1, characterized in that, Based on N emotional features, the operation level at which the target object performs the target operation in response to the conversation interaction is determined, including: A classification operation is performed on the N emotional features to obtain M emotional feature groups, where M is a natural number greater than or equal to 1 and less than or equal to N, and each emotional feature group includes at least one of the emotional features, and each emotional feature group has a different emotional level. Based on the preset weights of the emotion levels, the emotion value of each emotion feature group is determined; The operation level is determined based on the M emotion values.

5. The method according to claim 1, characterized in that, Based on the operation level and target parameters, a target service is generated, including: Based on the operation level and the first parameter, a first service rule is obtained from the service rule base to generate a first target service. The service rule base includes service rules for reducing the operation level, and the service rules include the first service rule. The first target service is used to provide the target object with session interaction data that reduces the operation level. Based on the operation level and the second parameter, a second service rule is obtained from the service rule base to generate a second target service, wherein the service rule includes the second service rule, and the second target service is used to provide the target object with strategy data to reduce the operation level; The first target service and the second target service are identified as the target service.

6. The method according to claim 1, characterized in that, After generating the target service based on the operation level and target parameters, the method further includes: The target service is pushed to the target account based on the object characteristics of the target object; Collect feedback information from the target object regarding the target service; Based on the feedback information, the service rule base is updated, wherein the service rule base includes service rules for reducing the operation level.

7. An apparatus for generating a target service, characterized in that, include: The first acquisition module is used to acquire first text data and target voice data generated by the target object through the target account during the conversation interaction with the target account. The first extraction module is used to extract N emotional features of the target object from the target text data and the target speech data, wherein the target text data is determined by the following steps: converting the target speech data into second text data, merging the first text data and the second text data to obtain the target text data, and N is a natural number greater than 1; The first determining module is used to determine the operation level of the target object in response to the conversation interaction based on N emotional features; The first generation module is used to generate a target service based on the operation level and target parameters. The target parameters include a first parameter and a second parameter. The first parameter includes the object characteristics of the target object, and the second parameter includes the dynamic operation characteristics of the target object performed by the target account within a historical time period. The target service is a service corresponding to the target operation.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 6.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 6.

Images