CN117556788A - Content generation method and device and electronic equipment - Google Patents

Abstract

The embodiment of the application discloses a content generation method, a device and electronic equipment, wherein the method comprises the following steps: in the process of communicating with a user by a client service person in a target service scene, acquiring voice content; converting the voice content into text content, and identifying the sender of the voice content so as to add sender identification information to the text content; and constructing a prompt word text for carrying out dialogue with an artificial intelligence AI large language model according to the text content with the sender identification information and the candidate appeal type information in the target service scene so as to carry out main point summary on the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select and add remark information for the voice conversation process. Through this application embodiment, can promote efficiency, reduce human cost.

Description

Content generation method and device and electronic equipment

Technical Field

The present invention relates to the field of information processing technologies, and in particular, to a content generating method and apparatus, and an electronic device.

Background

In the commodity information service system, after-sale problems often occur, and when some problems cannot be agreed between a consumer and a merchant, even when disputes and the like occur, the consumer can complain to the platform side, and the manual customer service of the platform side knows the consumer's appeal in a telephone manner and provides a solution for the consumer. The solutions are often various, and when a platform side manual customer service selects a solution, the problem of paying for a specific solution is usually required to be considered while the satisfaction of consumers is considered.

In particular, when a plurality of different departments are required to cooperatively solve some complex problems, a customer service person who specifically communicates with a consumer may not directly give a solution, but need to transfer to other departments to solve the problem. Therefore, customer service personnel need to think about how to give a solution during the call, and also need to record the call points to make remarks so as to be referred to by the processing personnel of other departments when the call needs to be transferred to the other departments for processing. In addition, customer service personnel are often required to note call points even without having to be handed over to other departments for processing, to facilitate subsequent statistical analysis of various problems or to provide a uniform optimization solution, and so forth. However, this thinking gives a solution and remarks the process of talking points, so that the summarizing ability and hand speed of customer service staff are very examined, and a great deal of labor cost is occupied under the condition of great consultation.

Disclosure of Invention

The application provides a content generation method, a content generation device and electronic equipment, which can improve efficiency and reduce labor cost.

The application provides the following scheme:

A content generation method, comprising:

in the process of communicating with a user by a client service person in a target service scene, acquiring voice content;

converting the voice content into text content, and identifying the sender of the voice content so as to add sender identification information to the text content;

and constructing a prompt word text for carrying out dialogue with an artificial intelligence AI large language model according to the text content with the sender identification information and the candidate appeal type information in the target service scene so as to carry out main point summary on the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select and add remark information for the voice conversation process.

Wherein, still include:

determining a workflow hit by a solution selected for adoption by the customer service personnel;

and determining whether the workflow needs to be transferred to other service personnel for solving, and if so, generating a corresponding work order and transferring the work order to the corresponding service personnel for processing.

Wherein, still include:

and in the process of forwarding the work order, the remark information is provided for other service personnel so that the other service personnel can refer to the work order when processing the work order task.

Wherein, still include:

circularly detecting the state of the work order according to a preset period;

and if the work order is detected to be processed, returning a corresponding notification message to the user.

Wherein, still include:

before constructing the prompt word text, word segmentation and/or sentence breaking processing is carried out on the text content.

Wherein, still include:

and predicting the type of the appeal to which the text content belongs in a keyword matching mode, so that the prompt word text also comprises the predicted type of the appeal information.

And the prompt word text also comprises format information of output content, so that the AI large language model generates content about the main point summary and the solution according to the format information.

A content generating apparatus comprising:

the voice content acquisition unit is used for acquiring voice content in the process of communicating with the user by the client service personnel in the target service scene;

a voice recognition processing unit for converting the voice content into text content and recognizing an issuer of the voice content so as to add issuer identification information to the text content;

and the prompt word text construction unit is used for constructing a prompt word text for carrying out dialogue with an artificial intelligence AI large language model according to text content with sender identification information and candidate appeal type information in the target service scene so as to carry out main point summary on the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select and add remark information for the voice dialogue process.

A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the preceding claims.

An electronic device, comprising:

one or more processors; and

a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the steps of the method of any of the preceding claims.

According to a specific embodiment provided by the application, the application discloses the following technical effects:

according to the embodiment of the application, in the conversation process between the customer service personnel and the user in the specific service scene, the voice content generated by the conversation between the customer service personnel and the user can be obtained, then the voice recognition is carried out, the voice content is converted into the text content, the sender of the voice content is recognized, and the sender identification information is added for the text content. And then, according to the text content with the sender identification information and the candidate appeal type information in the specific service scene, constructing a prompt word text for carrying out dialogue with an artificial intelligence AI large language model so as to carry out main point summary on the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select. Through the mode, intelligent remarks for the voice call process can be realized through the AI large language model, and dependence on experience of customer service personnel, summary capacity, manual input speed and other aspects is reduced, so that efficiency is improved, labor cost is reduced, and more timely feedback can be given, so that user experience can be improved.

Of course, not all of the above-described advantages need be achieved at the same time in practicing any one of the products of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application;

FIG. 2 is a flow chart of a method provided by an embodiment of the present application;

FIG. 3 is a first interface schematic provided in an embodiment of the present application;

FIG. 4 is a second interface schematic provided by an embodiment of the present application;

FIG. 5 is a third interface schematic provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of an apparatus provided by an embodiment of the present application;

fig. 7 is a schematic diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.

In the embodiment of the application, the intelligent key point summary and remark of the customer service and user voice dialogue process can be realized by combining an AI (Artificial Intelligence ) large language model (Large Language Model, LLM, abbreviated as AI large model) with voice recognition and other technologies, and a suggested solution can be provided for customer service personnel to select, so that the efficiency is improved, the dependence on the customer service personnel summarizing capability and hand speed is reduced, and the labor cost is also reduced.

Among them, for ease of understanding, the AI large language model is briefly described below. The AI large Model may refer to a basic Model (Foundation Model), and in particular, may refer to a Model that is trained using massive data, has a huge amount of parameters, and can adapt to a series of downstream tasks. For the AI large model, there is a characteristic that the parameter amount is huge (along with the continuous iteration of the model, the parameter amount generally increases exponentially, from one hundred million to one trillion to one million, and even more) on the parameter scale, and from the mode support, the AI large model gradually develops to support multiple tasks in multiple modes from supporting a single task in a single mode such as picture, image, text, voice, video and the like. That is, the large model generally has high-efficiency understanding capability of multi-mode information, cross-mode sensing capability, migration and execution capability of cross-differentiation tasks, and the like, and may even have multi-mode information sensing capability as embodied by human brain.

From another perspective, the AI large model is a short for an artificial intelligence pre-training large model, and comprises two layers of meanings of the pre-training and the large model, and the two layers of meanings are combined to generate a new artificial intelligence mode, namely, the model can support various downstream applications without fine adjustment after the pre-training is completed on a large-scale data set or with fine adjustment of a small amount of data. That is, the AI large model benefits from its paradigm of "large-scale pretraining plus fine tuning," which can adapt well to different downstream tasks, exhibiting its powerful versatility. The large AI model with universality can obtain excellent performance only by carrying out corresponding fine adjustment in different downstream application scenes under the condition of sharing parameters, and breaks through the limitation that the traditional AI model is difficult to generalize to other tasks.

From the viewpoint of the processing results, the above-described AI large Model also belongs to a Generative Model. Such models not only can "understand" how the data was generated based on the feature predictions, but can also "create" new data based thereon.

In terms of a content generation mode, what content needs to be generated by the AI large model can be "told" through constructing Prompt word (Prompt) text (a language used for interacting with the artificial intelligent model), and the content generated by the AI large model can be enabled to accord with the required expectations and requirements through writing the special form of the Prompt word text.

The AI large model has the capability of creating the content, so the AI large model can be applied to the embodiment of the application to assist customer service personnel to finish the tasks of summary of the key points, giving solutions and the like in the voice call process. That is, in the process that the customer service personnel and the user carry out voice dialogue, specific key points can be generated by the AI large model, and a suggested solution is given, so that the customer service personnel can choose whether to adopt one of the solutions, and the processes that the customer service personnel manually notes the key points of the conversation, think about what solution to adopt according to self experience and the like are omitted.

In specific implementation, some targeted training may be performed on the AI large model first, for example, the historical call record, the summary information of corresponding manual remarks, and the manually given solution information may be used as training data, and input into the AI large model, so that the AI large model obtains the capability of generating the foregoing content. In this embodiment of the present application, the input training data may include information such as user satisfaction corresponding to various pay proportions during training of the AI large model, so that the AI large model can recommend a more reasonable pay proportion when recommending the solution, so as to achieve a balance between the user satisfaction and the pay cost of the platform, and avoid the problems such as user dissatisfaction caused by too low pay proportion or increase of the pay cost of the platform caused by too high pay proportion, which may occur during the manual pay proportion determination process.

Of course, when the AI large model is applied to the scene in the embodiment of the present application, for example, first, the input of the AI large model is usually mainly based on text, for example, the foregoing prompt word text, so that the output content of the AI large model can be controlled relatively well. However, in the embodiment of the present application, particularly, in a scenario where a customer service person performs a voice dialogue with a user, if voice content is directly input into the AI large model, although the AI large model may also have an ability to understand the voice content, the content output by the AI large model may be difficult to be effectively controlled. Therefore, in specific implementation, the related technology of voice-to-text can be combined to construct the prompt word text for dialogue with the AI large model. In the process of constructing the prompt word text, some preprocessing and the like can be performed on text contents converted from the voice in advance, so that the quality of contents generated by the AI large model is further improved.

In addition, since the content of the conversation may have a relatively strong randomness or spoken language in the process of performing a voice conversation with the customer service personnel, for example, some users may speak a lot of content irrelevant to the current appeal in addition to stating the own appeal in the process of performing the conversation with the customer service personnel, and at this time, if the main points are summarized by the AI big model freely, the summarized main points may deviate from the after-sales service scene, and the like. Therefore, in concrete implementation, various types of appeal which may be possessed by a user in scenes such as after-sales service can be summarized in advance, and in concrete construction of a prompt word text for dialogue with the AI large model, besides the text content converted from voice content can be included, the various types of appeal can be input into the AI large model as candidates, so that the AI large model can select content related to the types of appeal in the candidates, and therefore limitation on the freedom degree of content generation of the AI large model is achieved.

Furthermore, in practical applications, there may be situations where the same solution needs to be solved by service personnel of a plurality of different departments, i.e. the customer service personnel currently participating in the voice conversation may not be able to directly solve, but need to be handed over to service personnel of other departments to assist in the solution. In view of this, in the prior art, it is generally necessary to manually create a work order by a customer service person currently participating in a voice conversation, then manually select to which department the work order is handed over, and then manually send a relevant notification message to the user after waiting for a processing result fed back by the customer service person of another department.

In this embodiment of the present application, a plurality of specific workflows may be preset, where a specific workflow may include one or more nodes, and how to generate and forward a work order on each node may be defined in the workflow. In this way, after the content such as the summary of the key points and the proposal of the solution is generated by the AI large model and the customer service personnel selects to adopt a certain solution, intelligent automatic generation and transfer of the work order can be performed according to the information such as the node, the work order generation and transfer mode and the like included in the workflow and the workflow hit by the solution. After that, the processing condition of the work order can be circularly detected, and if the work order is detected to be processed, a notification message can be automatically sent to the user. Therefore, the whole after-sales service flow can realize automation and intellectualization to a greater extent, further promote information, reduce labor cost, shorten waiting time of a user and promote user experience.

From the view of system architecture, referring to fig. 1, the embodiment of the present application may be applied to a merchandise information service system, and may specifically provide a specific intelligent remark service function in a workstation system of a customer service staff. In particular, when a user sends out requirements such as complaints to the platform side, customer service personnel of the platform side can actively initiate voice communication to the user under the necessary condition, so that the user requirements are known in more detail, and solutions and the like are determined in the communication process. In the process of voice communication between customer service personnel and a user, operation options such as 'one-key remarks' can be provided for the customer service personnel, after clicking the options, processing such as voice conversion into text and generation of prompt word text can be performed, key summary content of intelligent remarks can be generated by an AI large model based on specific prompt word text, and suggested solutions and the like can be provided.

Specific embodiments provided in the embodiments of the present application are described in detail below.

First, the embodiment of the application provides a content generation method, referring to fig. 2, the method may specifically include:

s201: and in the process of communicating with the user by the client service personnel in the target service scene, acquiring voice content.

Specifically, after a user initiates a request for complaints or other related after-sales services to a platform side, customer service personnel can receive specific request information in a workbench interface of the customer service personnel, and then enter a detail interface corresponding to the request, for example, a complaint list interface as shown in fig. 3, and content related to information submitted when the user initiates the request can be displayed in the detail interface; if the customer service personnel consider that the detailed requirements of the user need to be further known, the call process with the user can be initiated through options such as 'call initiation' provided in the detail interface, for example, the call process can specifically comprise voice call, video call, and the like. For example, after the call is initiated, a window as shown in fig. 3 may be popped up to show information related to the current call, including the called number and the calling number. After the user side answers successfully, customer service personnel can conduct dialogue with the user so as to know the detailed requirements of the user and communicate specific solutions with the user.

In the prior art, customer service personnel are required to consider how to provide a proper solution for a user while adding remarks to the detail page by summarizing call contents in the call process. In the embodiment of the application, the AI large model can assist the customer service personnel to complete the process of summarizing the content, and the customer service personnel can also give a suggested solution, and the customer service personnel only need to think about whether to adopt the suggestion given by the AI large model. Naturally, before the AI large model generates the content, in order to enable control of the AI large model generated content, the voice content of both parties of the call may be processed first, and therefore, the voice content generated during the call of both parties may be acquired first. Specifically, because the specific call function can be provided by the customer service personnel workbench, the generated voice content can be directly collected in the call process.

S202: the voice content is converted into text content, and an issuer of the voice content is identified to add issuer identification information to the text content.

After the voice content is collected, the voice content may first be converted to text content for the purpose of facilitating construction of specific alert word text, which may be accomplished by voice recognition techniques. Of course, in the embodiment of the present application, specific voice content is continuously generated, so the voice recognition process may also be performed in real time, that is, new text content may be continuously recognized.

In addition, in addition to identifying text content, the sender corresponding to the specific voice content may be identified, that is, who each specific sentence is spoken may be identified, and then the sender identifier may be added to the converted text content. The specific sender identifier may represent the number of a specific customer service person, the nickname of the user, or may represent only the identity distinction of the customer service person or the user.

There are various ways to identify the sender information corresponding to the voice content. For example, recognition of voice features may be included to distinguish them, or keywords or the like contained in specifically recognized text content may be combined to recognize them, or the like.

In the preferred embodiment, besides performing voice recognition and adding the sender identifier, the text content obtained by conversion can be subjected to word segmentation, sentence breaking and other processing, so that the AI large model can more accurately understand specific input content, and meanwhile, the accuracy of the generated content is improved.

For example, for a certain call process, the specific speech is converted into text, sentence breaking is performed, and after the sender identifier is added, the speech can be displayed as:

1 x 2\n. N is equal to n is you good, i is equal to two is hot line, you buy the toilet brush of 7.9 yuan before. Hiccup, the second party applies for after-sale intervention woolen before seeing you, feedback that goods are not received, and the subsequent me sees that express display is sent to you in the morning today, and what is the goods are received or not? N1 2\n I am not there, I say that the address was written wrongly, let him change, he say nothing, then … …

Wherein, "1 x 2" represents a user, "lux" represents a customer service person, "n" represents a line feed, it can be seen that specific text content is sentence-broken, punctuation marks are added, and in addition, whether each sentence is spoken by the customer service person or the user can be displayed, and the like.

S203: and constructing a prompt word text for dialogue with an artificial intelligence AI large language model according to the text content with the sender identification information and the candidate appeal type information in the target service scene so as to summarize the key points of the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select.

After converting the voice content into text content and performing sentence breaking, adding information such as a sender identification, a Prompt word text (Prompt) for dialog with the AI large model may be constructed. Specifically, the prompt word text may include the content of the open dialog to be used for "telling" what the AI big model needs to generate, for example, "you are an official customer service, you need to present a appeal scene according to the problem of the consumer, and provide a solution. Such an open dialog may be generic, i.e. the text of the prompting word may be started with this sentence for a call between different users and different customer service personnel. In addition, format information of output contents may be included in the prompt word text so that the AI large model generates contents on the gist summary and the solution according to the format information. For example, "directly summarize dialog content in the format of \\problem: xxxx\n complaint: xxxx\n solution: xxxx\n complaint scene: xxxx\n', etc.

Furthermore, as described above, candidate appeal types in the target service scene can be provided in the prompt word text, that is, the AI big model can select a specifically matched appeal type from the candidate appeal types, and then the dialogue gist is summarized on the basis, so that a proposed solution is provided, and the content output by the AI big model is prevented from being too random.

For example, for an after-market service scenario, specific possible types of appeal may include: merchant shipping and logistics problems, door-to-door installation, return logistics, shipping logistics other problems, and the like. These types of appeal may be embodied as candidates in the prompt word text.

In a specific implementation, the start dialogue, format information, candidate appeal types and the like of the prompt word text can be universal and can exist in the form of a prompt word template, so that after processing such as voice-to-text processing and the like is completed for different conversation processes, the prompt word text specific to the current conversation process can be generated only by adding specific dialogue content into the template.

For example, for a certain dialog process, the specifically generated prompt text may be:

"you are an official customer service, you need to give a appeal scene according to the consumer's problem, and provide a solution. The following is a chat record of you and consumers, directly summarizing the dialog content in the format of \\ 'question: xxxx\n complaint: xxxx\n solution: xxxx\n complaint scenario: xxxx\n'. The alternatives of the scene are: merchant's shipment and commodity circulation problem, the installation of going to the door, the commodity returned commodity circulation, other problems of shipment commodity circulation, refund, change goods, maintenance, repair send, freight … …, the dialogue is: 1.2 n 03-28:04:37 n. N is equal to n is you good, i is equal to two is hot line, you buy the toilet brush of 7.9 yuan before. Hiccup, the second party applies for after-sale intervention woolen before seeing you, feedback that goods are not received, and the subsequent me sees that express display is sent to you in the morning today, and what is the goods are received or not? N1 2\n i am not there, i am speaking to him, i am speaking to the address wrongly, let him change, he cannot say to the address wrongly, and then. N. times. Shu/n-kappa. N1 2\n then he says. N he says that he then singults, refuses to sign, i am not there, i am how refused to sign, then calls the person sent by that person, and the person does not receive the call. Is you, you are the company's colleague taken? What is the case of a light-down? N1 2\n i don't know. N is unknown. nRu Shu/nQing, he is in the front of that company or how, i see that he has been sent normally, signed up … …'

In addition, in the concrete implementation, before the prompt word text is input into the AI large model, the type of the appeal of the text content obtained by voice recognition can be predicted in a keyword matching mode, so that the predicted type of the appeal information is also included in the prompt word text. Thus, the type of the appeal predicted by keyword matching or the like can be provided to the AI large model as a reference. That is, the AI large model mainly analyzes the input information in a natural language understanding manner, but may supplement the judgment result obtained in a keyword matching manner, so that the AI large model may synthesize various information and generate more accurate content.

It should be noted that, in a specific implementation, the dialog content may be generated in real time and gradually added to the prompt word text template, where, every time a part of new dialog content is added, the AI big model may make some corresponding summary or recommend a solution. Of course, where dialogue content is relatively small, the summarized content or recommended solutions may not be accurate enough, and as new dialogue content increases, AI large models may gradually generate more accurate content.

For example, for a certain dialog process, the user says: "hello, i recently purchased a refrigerator on the x, but i found that buying was expensive because now there was a coupon and the price became much lower after the coupon was superimposed", at which point the AI big model could generate corresponding gist summaries and solution recommendation related content from these conversational content and could be presented to the "outbound remark" location of the pop-up window shown in fig. 3, for example, as shown in fig. 4 (a), could include:

"Intelligent recommendation (1/1)

Description of the problem: how to obtain platform virtual currency

User appeal: virtual currency of the platform

The solution is as follows: obtained by participating in a specified activity, completing a task, etc.

Of course, since the content of the user statement is also limited at this time, the content of the AI large model generation may not be accurate enough. Thereafter, the user then speaks again: "I want to refund me", customer service personnel say: "good help you look at you, you operate refund directly in order, then me gives coupon to you, you can place a new order again, at this time, AI big model can regenerate the main point summary and the solution recommendation related content according to the above dialogue content, for example, as shown in fig. 4 (B):

"Intelligent recommendation (2/2)

Description of the problem: goods and money returned

User appeal: the return of goods is desired

The solution is as follows: providing a refund service.

At this time, if the customer service personnel consider that the generated content is more accurate, the "adopt" option in the interface may be clicked directly, and accordingly, the content generated by the AI large model may be automatically filled into a specific remark input box, for example, as shown in fig. 5 (a), which shows a state after the content generated by the AI large model is filled into the remark input box.

Thereafter, assume that the user continues to ask: "how much can the maximum amount of the offer be given to when i consult again and now superimpose the coupon? ", customer service person answers say: "this help you see, can give two hundred maximum benefits". At this time, the AI large model may continue to regenerate the gist summary and the solution recommendation-related content from the above-described dialogue content, for example, as shown in fig. 5 (B):

"Intelligent recommendation (3/3)

User problem: the consumer wants to refund

User appeal: it is desired to know how much the maximum benefit can be added

The solution is as follows: prompting the consumer to operate the refund in the order and giving the coupon to the consumer, who places the order again.

At this time, the customer service personnel can talk with the user according to the solution suggested by the AI large model, for example, the content about the solution generated by the AI large model can be directly read out without self-thinking about the talk content, and then if the user also indicates approval of the solution, the user can click "adopt" again, so that the content newly generated by the AI large model is filled in the remark input box, and the content which has been filled in before is updated.

Of course, after filling the content generated by the AI big model into the remark input box, customer service personnel can also modify or supplement some content on the basis of the content, and the like, and then, specific remark content can be submitted. The content of a specific remark can be used for subsequent unified analysis to optimize solutions, etc., or, in case of need to be transferred to other service personnel to assist in solutions, the content of a specific remark can be transferred together to other service personnel for reference.

Through the mode, in the process of carrying out voice conversation between the customer service personnel and the user, the AI large model can summarize the conversation content key points in real time or near real time and give suggestions about the solution, so that the dependence on experience of the customer service personnel, manual input speed and the like is reduced.

The remark information can be used for carrying out statistical analysis on the user problems, optimizing solutions and the like. In addition, in practical applications, as described above, some solutions may be implemented by cooperation of different personnel in multiple departments, and in this case, the circulation of worksheets is also involved. In the prior art, a work order needs to be manually created by customer service personnel of the current call, then the work order is manually selected and forwarded, and after the work order is finished, a notification message is manually sent to a user, and the like. In the embodiment of the application, in order to further improve the efficiency and reduce the workload of customer service personnel, various workflows can be created in advance, after a specific solution is adopted, whether the specific solution hits a workflow or not can be automatically judged, and whether the specific solution needs to be transferred to other service personnel for assistance and solving, if so, a work order can be automatically created, and the processing of forwarding the work order can be performed. In the process of transferring the work order, the remark content can be transferred to the other service personnel so that the other service personnel can refer to the work order when processing the work order task. Thereafter, the status of a specific work order may also be detected in a loop with a preset period (e.g., detection every second), and if it is detected that the work order has been processed, a corresponding notification message may be returned to the user.

In summary, through the embodiment of the present application, in a specific service scenario, during a voice dialogue between a customer service person and a user, a voice content generated by a call between two parties may be obtained, and then voice recognition is performed, the voice content is converted into text content, and an issuer of the voice content is identified, and issuer identification information is added to the text content. Then, according to the text content with the sender identification information and the candidate appeal type information in the specific service scene, a prompt word text for carrying out dialogue with an artificial intelligence AI large language model can be constructed so that the AI large language model can carry out main point summary on the voice dialogue process and generate a suggested solution for the customer service personnel to select. Through the mode, intelligent remarks for the voice call process can be realized through the AI large language model, and dependence on experience of customer service personnel, summary capacity, manual input speed and other aspects is reduced, so that efficiency is improved, labor cost is reduced, and more timely feedback can be given, so that user experience can be improved.

It should be noted that, in the embodiments of the present application, the use of user data may be involved, and in practical applications, user specific personal data may be used in the schemes described herein within the scope allowed by applicable legal regulations in the country where the applicable legal regulations are met (for example, the user explicitly agrees to the user to actually notify the user, etc.).

Corresponding to the foregoing method embodiment, the embodiment of the present application further provides a content generating apparatus, referring to fig. 6, where the apparatus may include:

a voice content obtaining unit 601, configured to obtain voice content during a call between a customer service person and a user in a target service scenario;

a voice recognition processing unit 602, configured to convert the voice content into text content, and recognize an issuer of the voice content so as to add issuer identification information to the text content;

and a prompt word text construction unit 603, configured to construct a prompt word text for performing a dialogue with an artificial intelligence AI big language model according to text content with sender identification information and candidate appeal type information in the target service scene, so that the AI big language model performs a summary of the key points of the conversation process, and generates a suggested solution for the customer service personnel to select and add remark information for the voice dialogue process.

In particular, the apparatus may further include:

a workflow determination unit for determining a workflow hit by a solution selected for adoption by the customer service personnel;

And the work order generation and transfer unit is used for determining whether the work order needs to be transferred to other service personnel for solving according to the work flow, and if so, generating a corresponding work order and transferring the work order to the corresponding service personnel for processing.

Additionally, the method can also comprise the following steps:

and the remark information providing unit is used for providing the remark information to the other service staff in the process of forwarding the work order so that the other service staff can refer to the work order when processing the work order task.

Furthermore, the apparatus may further include:

the work order state detection unit is used for circularly detecting the state of the work order according to a preset period;

and the notification message sending unit is used for returning a corresponding notification message to the user if the fact that the work order is processed is detected.

In addition, the apparatus may further include:

and the word segmentation and sentence segmentation processing unit is used for carrying out word segmentation and/or sentence segmentation processing on the text content before constructing the prompt word text.

The resort type prediction unit is used for predicting the resort type of the text content in a keyword matching mode, so that the prompt word text also comprises the predicted resort type information.

In addition, the text of the prompt word also comprises format information of output content, so that the AI large language model generates content about the summary of the key points and the solution according to the format information.

In addition, the embodiment of the application further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method of any one of the foregoing method embodiments.

And an electronic device comprising:

one or more processors; and

a memory associated with the one or more processors for storing program instructions that, when read for execution by the one or more processors, perform the steps of the method of any of the preceding method embodiments.

Fig. 7 illustrates an architecture of an electronic device, which may include a processor 710, a video display adapter 711, a disk drive 712, an input/output interface 713, a network interface 714, and a memory 720, among others. The processor 710, the video display adapter 711, the disk drive 712, the input/output interface 713, the network interface 714, and the memory 720 may be communicatively connected via a communication bus 730.

The processor 710 may be implemented by a general-purpose CPU (Central Processing Unit, processor), microprocessor, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided herein.

The Memory 720 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage device, dynamic storage device, or the like. The memory 720 may store an operating system 721 for controlling the operation of the electronic device 700, and a Basic Input Output System (BIOS) for controlling the low-level operation of the electronic device 700. In addition, a web browser 723, a data storage management system 724, a content generation processing system 725, and the like may also be stored. The content generation processing system 725 may be an application program that specifically implements the operations of the foregoing steps in the embodiments of the present application. In general, when implemented in software or firmware, the relevant program code is stored in memory 720 and executed by processor 710.

The input/output interface 713 is used to connect with an input/output module to enable information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.

The network interface 714 is used to connect communication modules (not shown) to enable communication interactions of the device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).

Bus 730 includes a path to transfer information between various components of the device (e.g., processor 710, video display adapter 711, disk drive 712, input/output interface 713, network interface 714, and memory 720).

It should be noted that although the above devices illustrate only the processor 710, the video display adapter 711, the disk drive 712, the input/output interface 713, the network interface 714, the memory 720, the bus 730, etc., the device may include other components necessary to achieve proper operation in an implementation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the present application, and not all the components shown in the drawings.

From the above description of embodiments, it will be apparent to those skilled in the art that the present application may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in the embodiments or some parts of the embodiments of the present application.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The foregoing has described in detail the methods, apparatuses and electronic devices for generating content provided in the present application, and specific examples have been applied to illustrate the principles and embodiments of the present application, where the foregoing examples are only for aiding in understanding the methods and core ideas of the present application; also, as will occur to those of ordinary skill in the art, many modifications are possible in view of the teachings of the present application, both in the detailed description and the scope of its applications. In view of the foregoing, this description should not be construed as limiting the application.

Claims (10)

1. A content generation method, comprising:

in the process of communicating with a user by a client service person in a target service scene, acquiring voice content;

converting the voice content into text content, and identifying the sender of the voice content so as to add sender identification information to the text content;

and constructing a prompt word text for carrying out dialogue with an artificial intelligence AI large language model according to the text content with the sender identification information and the candidate appeal type information in the target service scene so as to carry out main point summary on the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select and add remark information for the voice conversation process.

2. The method as recited in claim 1, further comprising:

determining a workflow hit by a solution selected for adoption by the customer service personnel;

and determining whether the workflow needs to be transferred to other service personnel for solving, and if so, generating a corresponding work order and transferring the work order to the corresponding service personnel for processing.

3. The method as recited in claim 2, further comprising:

and in the process of forwarding the work order, the remark information is provided for other service personnel so that the other service personnel can refer to the work order when processing the work order task.

4. The method as recited in claim 2, further comprising:

circularly detecting the state of the work order according to a preset period;

and if the work order is detected to be processed, returning a corresponding notification message to the user.

5. The method according to any one of claims 1 to 4, further comprising:

before constructing the prompt word text, word segmentation and/or sentence breaking processing is carried out on the text content.

6. The method according to any one of claims 1 to 4, further comprising:

And predicting the type of the appeal to which the text content belongs in a keyword matching mode, so that the prompt word text also comprises the predicted type of the appeal information.

7. The method according to any one of claim 1 to 4, wherein,

and the prompt word text also comprises format information of output content, so that the AI large language model generates content about the gist summary and the solution according to the format information.

8. A content generating apparatus, comprising:

the voice content acquisition unit is used for acquiring voice content in the process of communicating with the user by the client service personnel in the target service scene;

a voice recognition processing unit for converting the voice content into text content and recognizing an issuer of the voice content so as to add issuer identification information to the text content;

and the prompt word text construction unit is used for constructing a prompt word text for carrying out dialogue with an artificial intelligence AI large language model according to text content with sender identification information and candidate appeal type information in the target service scene so as to carry out main point summary on the conversation process by the AI large language model and generate a suggested solution for the customer service personnel to select and add remark information for the voice dialogue process.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

10. An electronic device, comprising:

one or more processors; and

a memory associated with the one or more processors for storing program instructions that, when read for execution by the one or more processors, perform the steps of the method of any of claims 1 to 7.