System and method for generating sales script on basis of causal large model, and electronic device

Abstract

A system and method for generating a sales script on the basis of a causal large model, and an electronic device. The system comprises: a user recognition module, which is configured to recognize basic information of a user, the basic information comprising user questions and context information related to the user; a scheme matching module, which is configured to acquire a business causal scheme that matches the basic information; a product processing module, which is configured to acquire product association information on the basis of the context information and the business causal scheme; and a sales script generation module, which is configured to acquire a target sales script corresponding to the basic information, the business causal scheme and the product association information.

Description

System, method and electronic device for generating speech based on causal big model

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese patent application number 2024108865018 filed with the China Patent Office on July 3, 2024, entitled “System, method and electronic device for generating speech based on causal big model”, the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the field of intelligent customer service technology, and more specifically, to a system, method, and electronic device for generating speech based on a causal large model. Background Art

[0004] With the continuous development of artificial intelligence, intelligent customer service robots are widely used in various business fields.

[0005] Currently, users seeking information or product information in a specific business area typically interact with intelligent customer service bots. These bots can identify the text messages entered by users and then, using their pre-configured responses, search for the most relevant response to the user's text message. However, this approach only mechanically responds to user questions and fails to truly understand user intent, making it impossible to provide valuable product recommendations.

[0006] Therefore, how to provide a technical solution for a method of generating speech with higher accuracy has become a technical problem that needs to be solved urgently. Summary of the Invention

[0007] The purpose of the present disclosure is to provide a system, method and electronic device for generating speech based on a causal large model. The technical solution of the present disclosure can achieve accurate positioning of user intentions, and thus can provide users with effective and high-quality speech content containing business product suggestions, provide users with valuable auxiliary information, and enhance user experience.

[0008] The present disclosure provides a system for generating speech based on a causal big model, comprising: a user identification module, configured to identify basic information of a user, wherein the basic information includes: user questions and contextual information related to the user; a solution matching module, configured to obtain a business causal solution that matches the basic information; a product processing module, configured to obtain product-related information based on the contextual information and the business causal solution, wherein the product-related information includes: product explanation text, product business data and product demand forecast information; a speech generation module, configured to obtain target speech corresponding to the basic information, the business causal solution and the product-related information.

[0009] The system provided by this disclosure identifies the user's question and contextual information, matches them to a business causal solution, then derives product-related information based on the contextual information and business causal solution, and finally uses this information to obtain the corresponding target speech. This disclosure can accurately locate user intent, thereby providing users with effective, high-quality speech content containing business and product suggestions, providing users with valuable auxiliary information and improving the user experience.

[0010] Optionally, the solution matching module is configured to: retrieve multiple product solution causal chains that match the user problem from a preset solution document; annotate the multiple product solution causal chains through user information and product configuration documents to obtain multiple annotated product solution causal chains; and obtain the business causal solution based on the multiple annotated product solution causal chains, the user problem and the target solution matching model.

[0011] This method retrieves solutions matching the user's problem from pre-set solution documents, annotates them based on user information and product configuration documents, and finally outputs target product recommendations using a target solution matching model. This method can accurately identify user intent and improve the accuracy of product recommendations, allowing users to easily understand product information, improving user experience and marketing accuracy.

[0012] Optionally, the solution matching module is configured to: perform matching calculations with the three stage documents in the preset solution document based on the contextual information to obtain multiple matching values; use the solutions corresponding to the matching values ​​located before the preset positions in the multiple matching values ​​as the multiple product solution causal chains; wherein, the first stage document in the preset solution document includes: product type and product planning; the second stage document includes: product parameters of each product in the product type; the third stage document includes: product name and product application scenario of each product and product core terms.

[0013] This disclosure conducts a matching analysis between the contextual information of the user's question and the three-stage documents to obtain multiple product solution causal chains, which can be closer to user needs and improve the accuracy of user intent positioning.

[0014] Optionally, the solution matching module is configured as follows: if it is confirmed that the product name of each product solution causal chain in the multiple product solution causal chains and the user information are consistent with the product elements in the product configuration document, then it is marked as a valid solution; if it is confirmed that the product name of each product solution causal chain in the multiple product solution causal chains and the user information are inconsistent with the product elements in the product configuration document, then it is marked as an invalid solution, and invalid reason text information is generated; wherein, the valid solution and the invalid solution constitute the multiple marked product solution causal chains.

[0015] This disclosure compares the product names, user information and product configuration documents of the product solution causal chain for consistency, and then labels multiple product solution causal chains to obtain accurate product information and improve the accuracy of product recommendations.

[0016] Optionally, the solution matching module is configured to: generate prompt text corresponding to the multiple labeled product solution causal chains and the user question; input the prompt text into the target solution matching model to obtain the business causal solution; wherein, the target solution matching model is obtained by training a large language model.

[0017] The present disclosure generates prompt text that meets the target solution matching model and then inputs it into the model to obtain a business causal solution, thereby ensuring the accuracy of the product solution causal chain recommendation.

[0018] Optionally, the product processing module includes: a product explanation sub-module, a data processing sub-module and a demand prediction sub-module; wherein the product explanation sub-module is configured to determine the standard question corresponding to the user question; retrieve the product terms content matching the standard question from the product terms document; generate the product explanation text according to the standard question, the product terms content and the target large language model; the data processing sub-module is configured to calculate the product business data corresponding to the business causal scheme when confirming that the user needs the product business data; the demand prediction sub-module is configured to predict the product demand prediction information associated with the user's conversation data.

[0019] The present disclosure generates and predicts relevant needs of users through sub-modules in the product processing module, which can achieve accurate positioning of users and subsequently provide users with valuable speech content information.

[0020] Optionally, the product explanation submodule is configured to: use a trained semantic vector model to calculate the user question and preset standard sentences to obtain a vector distance set; obtain a target sentence in the vector distance set that is less than a set threshold; and use the sentence corresponding to the minimum value of the vector distance in the target sentence as the standard question.

[0021] The present disclosure processes and analyzes user questions and preset standard sentences through a trained semantic vector model to determine the corresponding standard questions, so as to accurately retrieve product terms and content related to user needs.

[0022] Optionally, the product explanation submodule is configured to: confirm that the vector distances in the vector distance set are not less than the set threshold, then record the user question; set a standard sentence corresponding to the user question, and iteratively update the trained semantic vector model.

[0023] The present disclosure records user questions and updates the semantic vector model, thereby improving the accuracy and breadth of the semantic vector model.

[0024] Optionally, the product explanation submodule is configured to: input the preset standard sentences and the original product terms content into the large language model to obtain the actual reference product terms; verify and mark the actual reference product terms to determine the product terms reference content; and construct the product terms document based on the preset standard sentences, the product terms reference content and the product information of each product.

[0025] The present disclosure verifies and annotates the retrieved actual reference product terms and constructs a corresponding product terms document, thereby improving the accuracy of the final constructed document.

[0026] Optionally, the product explanation submodule is configured to: generate prompt information corresponding to the standard questions, the product terms content, the user questions, the conversation context data and the situational information; input the prompt information into the target large language model, and output the product explanation text; wherein, the target large language model is obtained by training the initial large model through a training data set; the training data set includes: user question samples, product demand samples, user situation samples, product terms samples and explanation text samples.

[0027] This disclosure generates product explanation text by inputting relevant prompt information into the target large language model, which is both efficient and convenient, and can also improve the user experience. The target large language model is trained with a training dataset, allowing it to output different product explanation texts for different scenarios and products, improving the model's practicality.

[0028] Optionally, the product processing module further includes an information collection module, and the information collection module is configured to collect user information based on the context information and the business cause-effect scheme.

[0029] Optionally, the speech generation module is configured to: generate a model input text corresponding to the basic information, the business causal scheme and the product association information; input the model input text into a trained causal model to obtain the target speech.

[0030] This application discloses that by inputting user-related information into a trained causal model to obtain target speech, it can provide users with high-quality and valuable product-related speech content and provide users with effective auxiliary suggestions for selecting business products.

[0031] The present disclosure also provides a method for generating speech based on a causal big model, comprising: identifying basic information of a user, wherein the basic information includes: user questions and contextual information related to the user; obtaining a business causal solution that matches the basic information; obtaining product-related information based on the contextual information and the business causal solution, wherein the product-related information includes: product explanation text, product business data and product demand forecast information; obtaining target speech corresponding to the basic information, the business causal solution and the product-related information.

[0032] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the aforementioned method for generating speech based on a causal big model.

[0033] The present disclosure also provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the aforementioned method for generating speech based on a causal large model can be implemented.

[0034] The present disclosure also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it can implement the aforementioned method of generating speech based on a causal big model. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solution of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments of the present disclosure. It should be understood that the following drawings only illustrate the embodiments of the present disclosure and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0036] FIG1 is a system diagram of speech generation based on a causal model according to an embodiment of the present disclosure;

[0037] FIG2 is a flow chart of a method for generating speech based on a causal model according to an embodiment of the present disclosure;

[0038] FIG3 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present disclosure will be described below with reference to the accompanying drawings in the embodiments of the present disclosure.

[0040] It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. At the same time, in the description of this disclosure, the terms "first," "second," etc., are used only to distinguish the description and are not to be understood as indicating or implying relative importance.

[0041] With the emergence and development of artificial intelligence and big model technologies, current approaches, such as general-purpose big models, can directly provide specific business solutions (such as insurance solutions or causal chains for financial product solutions) related to user questions to meet user needs and improve product marketing efficiency. For example, big models in the insurance field can provide answers to basic FAQs or popular product recommendations based on user questions. However, these answers are based on the model's pre-defined response logic and fail to provide users with precise, supportive recommendations. When matching user needs with products, static matching logic is often employed. This requires users to provide a large amount of cumbersome information at once, leaving them to delve deeper and provide detailed information before their specific needs can be further confirmed. The resulting solutions are also one-off solutions. Adjustments require users to modify the information form and resubmit it to generate a matching solution. This fails to proactively and dynamically identify user needs and provide more appropriate planning and sales pitches. Furthermore, when users want to understand the terms and conditions of a particular product, current intelligent customer service agents often provide general explanations or simply output lengthy, verbose textual descriptions of the terms and conditions, which can easily confuse users and make them confused. On the other hand, directly generating corresponding broad copy can easily lead to misunderstandings, fabricated terms, and incorrect product explanations that mislead users.

[0042] It can be seen from the above-mentioned related technologies that the existing technology has poor accuracy in locating user intentions, and the reply content given cannot provide effective suggestions to users, cannot plan products for users, and the user experience is poor.

[0043] In light of this, the disclosed embodiments provide a method for generating sales pitches based on a large causal model. This method, after identifying a user's question and contextual information, can obtain a matching business causal solution. This information can then be used to obtain product-related information associated with the user. Finally, the resulting content can be used to generate a corresponding target sales pitch. This disclosed embodiment can accurately pinpoint user intent, and the resulting target sales pitch can provide users with effective product planning suggestions, improving response quality and user experience.

[0044] The overall structure of the speech generation system based on the causal model provided by the embodiment of the present disclosure is exemplarily described below with reference to FIG1 .

[0045] As shown in FIG1 , an embodiment of the present disclosure provides a system for generating speech based on a causal large model. The system for generating speech based on a causal large model may include: a user identification module 110, a solution matching module 120, a product processing module 130, and a speech generation module 140. Among them, the product processing module 130 also includes: a product explanation submodule 131, a data processing submodule 132, a demand prediction submodule 133, and an information collection module 134. Through the mutual interaction between the modules in the system shown in FIG1 of the present disclosure, personalized product planning can be carried out for users, and users can be given high-quality target speech, so that users can select corresponding products in a targeted manner through the suggestion information in the target speech.

[0046] The specific functions of each module in FIG1 are exemplarily described below.

[0047] In the embodiment of the present disclosure, the user identification module 110 is configured to identify basic information of the user, wherein the basic information includes: user questions and context information related to the user.

[0048] For example, a user can interact with an intelligent customer service robot in a business field through a terminal device, and the large model agent combination deployed by the intelligent customer service robot can recognize the conversation content input by the user. The user question currently expressed by the user is identified through the user question agent; the user context agent can identify the current context information of the user. For example, taking the insurance business field as an example, the user question is "buy insurance for my daughter", and the context information can be "number of children: 1, gender of the child: female, stage of life: marriage and childbearing period", etc. Among them, the large model agent combination can be obtained by training a specific data set in a specific scenario (for example, the insurance business field). It can be understood that in actual applications, text recognition models or models in other natural language processing can also be used to recognize the content of the user's conversation, and the embodiments of the present disclosure are not limited to this.

[0049] In the embodiment of the present disclosure, the solution matching module 120 is configured to obtain a business causal solution that matches the basic information.

[0050] For example, the solution matching module 120 can first search the preset solution document in the large model based on the user question understood by the pre-set agent, and extract the N solutions that are most relevant to the user question (as an example of a causal chain of multiple product solutions). Then, the N solutions obtained above are annotated in combination with the product configuration document to obtain multiple annotated product solution causal chains. Among them, taking the insurance business as an example, the insurance product configuration document can provide the insurance requirement elements of each insurance product (for example, the elements can be three parts: insured age range, insured occupation range, health requirement range), and whether it is on sale. It should be understood that the content of the product configuration document can be adaptively adjusted for different business scenarios, and the embodiments of the present disclosure are not limited to this. Finally, the N annotated product solution causal chains after the above annotating are combined with the user question and input into the target solution matching model to obtain the business causal solution output by the model. For example, taking the above-mentioned example of buying insurance for the daughter, the business causal solution is: buy insurance for the daughter -> medical insurance, critical illness insurance, accident insurance.

[0051] In an embodiment of the present disclosure, the solution matching module 120 is configured to perform matching calculations with the three stage documents in the preset solution document based on the contextual information to obtain multiple matching values; and use the solutions corresponding to the matching values ​​located before the preset positions in the multiple matching values ​​as the multiple product solution causal chains; wherein the first stage document in the preset solution document includes: product type and product planning; the second stage document includes: product parameters of each product in the product type; the third stage document includes: product name and product application scenario of each product and product core terms.

[0052] For example, in the embodiment of the present disclosure, the insurance business field is taken as an example for explanation, and the insurance business content is divided into three-stage solution documents according to the planning stage of the intelligent insurance planner. The solution documents are all constructed in the form of a causal chain. The left side of the causal chain is the user demand, the right side is the solution, and the middle is connected by '->' (for example, the user hopes to renew the insurance after the claim -> Changxiang'an Long-term Medical Insurance (insurance product name) -> guaranteed renewal for 20 years). Among them, the first stage document may include: the initial planning (as an example of product planning) and the major types of insurance explained to the user (as an example of product type). The second stage document may include: after determining the insurance type, giving the recommended logic of the main parameters under the specific insurance type, such as the insurance amount, premium range, etc. (as an example of product parameters). The third stage document may include: the specific product name and the problem to be solved (as an example of a product application scenario), as well as the core content of the product terms (as an example of the core terms of the product) to recommend specific products and match the specific preferences of users. For example, consider a solution called Darwin 8 Pilot Edition Critical Illness Insurance. The product's application scenario involves the need for income loss protection due to critical illness. The core product terms and conditions stipulate that the first major illness benefit for 120 types is 100% of the basic insured amount. It is understood that the first, second, and third stage documents can be designed and generated as needed, and the disclosed embodiments are not limited thereto.

[0053] Optionally, the solution matching module 120 can perform matching calculations between the user context involved in the user problem (as an example of context information) and the user context set in the preset solution document. For example, if the user context is consistent, the item in the document will be added with 0.5 points, and if it is inconsistent, the item will be deducted with 0.2 points. Finally, the sum is calculated to obtain the final matching value for each item in the three-stage document, where the matching values ​​are sorted from large to small, and the solutions in the first N positions (as an example of the preset positions) are the N product solution causal chains (that is, N solutions) that are most relevant to the user problem. It should be noted that N is a positive integer, and its value can be set as needed. The matching calculation method can also be flexibly adjusted according to the actual application scenario, and the embodiments of the present disclosure are not limited to this.

[0054] In the embodiment of the present disclosure, the solution matching module 120 is configured to mark a solution as a valid solution if it is confirmed that the product name of each product solution causal chain in the multiple product solution causal chains and the user information are consistent with the product elements in the product configuration document; if it is confirmed that the product name of each product solution causal chain in the multiple product solution causal chains and the user information are inconsistent with the product elements in the product configuration document, it is configured to mark it as an invalid solution and generate invalid reason text information; wherein, the valid solution and the invalid solution constitute the multiple marked product solution causal chains.

[0055] For example, the solution matching module 120 can extract the product names in N product solution causal chains, and then check and match them according to the product configuration documents and the collected user context (such as user age, occupation, and health) to confirm whether the content elements (as an example of product elements) are consistent. If there are any inconsistencies (such as age inconsistency, occupation inconsistency, health inconsistency, or the product has been removed from the shelves, etc.), then "invalid solution" will be noted on the basis of the product solution causal chain, and text information of the invalid reason will be given (such as age inconsistency, occupation inconsistency, health inconsistency, or the product has been removed from the shelves). Otherwise, "valid solution" will be noted on the basis of the product solution causal chain. After the N product solution causal chains are labeled, N labeled product solution causal chains can be obtained.

[0056] In an embodiment of the present disclosure, the solution matching module 120 is configured to generate prompt text corresponding to the multiple labeled product solution causal chains and the user question; input the prompt text into the target solution matching model to obtain the business causal solution; wherein, the target solution matching model is obtained by training a large language model.

[0057] For example, the solution matching module 120 writes the processed N annotated product solution causal chains and the user question into a prompt (as an example of prompt text), then calls the target solution matching model and inputs the prompt into the target solution matching model to obtain a business causal solution. For example, the user question is: What insurance should an infant buy? The business causal solution ultimately output from the N annotated product solution causal chains is a causal diagram supplemented with user needs: Infancy -> Medical Insurance (Insurance Type); Infancy -> Critical Illness Insurance (Insurance Type); Infancy -> Accident Insurance (Insurance Type); Infancy -> Education Fund Insurance (Insurance Type).

[0058] In an embodiment of the present disclosure, the product processing module 130 is configured to obtain product-related information based on the contextual information and the business causal scheme, wherein the product-related information includes: product explanation text, product business data and product demand forecast information.

[0059] For example, the product processing module 130 may formulate a next communication strategy (as an example of product-related information) based on the business cause-effect scenario and the user context.

[0060] In the embodiment of the present disclosure, the data processing submodule 132 is configured to calculate the product business data corresponding to the business causal scheme when it is confirmed that the user needs the product business data.

[0061] For example, if it is determined that the insured amount and premium need to be calculated (as an example of product business data), the data processing submodule 132 is scheduled to calculate the insured amount and premium of the corresponding product.

[0062] In the embodiment of the present disclosure, the demand prediction submodule 133 is configured to predict the product demand prediction information associated with the user's conversation data.

[0063] For example, based on the current multi-round communication content with the user and the extracted user questions, user scenarios, and business causal solutions, the user's possible further potential needs (as an example of product demand forecast information) are inferred. For example, the user has a 5-year-old daughter who may have more colds and fevers and needs a medical insurance product that covers outpatient care. It is understandable that the demand forecasting submodule 133 can store lists of different types of products corresponding to the user's potential needs, and the user's potential needs can be predicted through matching and searching. Other inference methods can also be used in actual applications, and the embodiments of the present disclosure are not limited to this.

[0064] In the embodiment of the present disclosure, the information collection module 134 can collect information that may need to be provided by the user based on the current contextual information and business cause-and-effect scheme, so that the AI ​​planner (that is, the intelligent customer service robot) can further converge the user's explanation of the selection of specific products or product parameters. At this time, the information collection module 134 can be called for processing. For example, in the insurance business, when calculating product premiums and insured amounts, users are required to provide age information; selecting product types (mid-range medical care or million-dollar medical care) requires users to provide premium budgets, etc. The information collection module 134 can collect information after obtaining the user's authorization, so as to more accurately locate the user's intentions.

[0065] In addition, if the user is matched with a specific product and wants to obtain the terms and conditions of the product, the product explanation submodule 131 can be scheduled to output the product explanation text, which is relatively concise and easy for the user to understand.

[0066] The specific implementation functions of the product explanation submodule 131 are exemplarily described below.

[0067] In the embodiment of the present disclosure, the product explanation submodule 131 is configured to determine the standard question corresponding to the user question; retrieve the product terms content that matches the standard question from the product terms document; and generate the product explanation text based on the standard question, the product terms content and the target large language model.

[0068] For example, to effectively retrieve matching product solution causal chains and corresponding product terms for users, the product explanation submodule 131 first normalizes the collected user questions. This means analyzing and processing the user questions to determine standard questions (referred to as standard questions). Then, using these determined standard questions as search parameters, it retrieves matching product terms from the pre-deployed product terms document. By combining the trained target large language model with the user questions, standard questions, and product terms, it can generate concise, easy-to-understand product explanation text for users.

[0069] In the embodiment of the present disclosure, the product explanation submodule 131 is configured to use the trained semantic vector model to calculate the user question and the preset standard sentence to obtain a vector distance set; obtain the target sentence in the vector distance set that is less than a set threshold; and use the sentence corresponding to the minimum value in the vector distance in the target sentence as the standard question.

[0070] For example, the trained semantic vector model is used to calculate the distance between the user question and the pre-planned preset standard question (as the preset standard sentence) (where the smaller the vector distance, the more similar they are), and all the preset standard questions that are less than the set threshold are taken out. Then, the one with the smallest vector distance is selected as the standard question for this user question.

[0071] It should be noted that the trained semantic vector model is obtained by training with raw data. Raw data includes user question samples and their corresponding standard question samples. For example, a user question sample might be: "Can I get insurance tomorrow if I buy it today?"; a standard question sample might be: "What is the waiting period?" The literal meanings of these two questions differ significantly, making it unreasonable to directly use an off-the-shelf semantic model. Therefore, we prepare possible user questions and standard questions for each product and input them into the semantic model training to ultimately obtain a trained semantic vector model that can be adapted to different products.

[0072] In the embodiment of the present disclosure, the product explanation submodule 131 is configured to confirm that the vector distances in the vector distance set are not less than the set threshold, then record the user question; set the standard sentence corresponding to the user question, and iteratively update the trained semantic vector model.

[0073] For example, if there is no preset standard question smaller than the set threshold in the trained semantic vector model, the user question will be used as the standard question and an exception record log will be generated. Subsequently, the corresponding standard question will be reset based on this user question, and the semantic vector model will be iteratively updated and trained to improve the accuracy of standard question matching.

[0074] In the embodiment of the present disclosure, the product explanation submodule 131 is configured to input the preset standard sentences and the original product terms content into the large language model to obtain the actual reference product terms; verify and mark the actual reference product terms to determine the product terms reference content; and construct the product terms document based on the preset standard sentences, the product terms reference content and the product information of each product.

[0075] For example, to ensure the effectiveness of product terms retrieval, taking the insurance business field as an example, the following terms extraction solution is used to construct a product terms document:

[0076] Based on all pre-prepared standard questions, the original product terms (here, dozens of pages of original terms) are input into the large model (as an example of a large language model) for retrieval, outputting the actual reference product terms. Insurance experts then annotate the standard questions and answers (i.e., the actual reference product terms), marking any that make sense as acceptable and providing reference content for any that do not. These two steps yield meaningful product terms reference content and corresponding standard questions. All of these product terms reference content and corresponding standard questions are integrated into a single document, resulting in a product terms document. Subsequently, targeted product terms content can be retrieved from the product terms document based on the standard questions.

[0077] In addition, considering that the standard questions may not be comprehensive, this disclosure will also uniformly enter or read from relevant terminals the types of terms that must be included in each product (for example, basic protection content, optional protection content, insurance requirements: occupation, gender, age, health, etc., underwriting company, waiting period, claims method, hesitation period, etc.) to improve the accuracy of subsequent retrieval.

[0078] In the embodiment of the present disclosure, the product explanation submodule 131 is configured to generate prompt information corresponding to the standard questions, the product terms content, the user questions, the conversation context data and the situational information; input the prompt information into the target large language model, and output the product explanation text; wherein, the target large language model is obtained by training the initial large model through a training data set; the training data set includes: user question samples, product demand samples, user situation samples, product terms samples and explanation text samples.

[0079] For example, the product explanation submodule 131 can prepare a training data set for training the initial large model, wherein the training data set includes: user question samples, currently concerned products (as an example of product demand samples), user context samples (for example, user occupation, usage scenarios, etc.), product terms samples and explanation text samples. Among them, the product terms samples contain general product knowledge and the core documents corresponding to each product, as well as related FAQs, key content, etc. The text composed of user question samples, currently concerned products, user contexts and product terms samples is used as the input data of the initial large model, and the explanation text samples are used as the output data of the initial large model for training and fine-tuning to obtain the target large language model for the product of the corresponding scenario.

[0080] Afterwards, the retrieved product terms are combined with the solution previously given by the agent, the user's question, the current user situation (i.e., situational information), and the user's conversation context data to form a prompt (as an example of the prompt information in the product explanation submodule 131); the prompt is input into the target large language model trained above to finally generate the product explanation text.

[0081] Through the product explanation submodule 131 in the above-mentioned embodiment of the present disclosure, it is possible to provide the product explanation of the solution required by the user based on the user's specific situation and problem, and it is targeted and concise, allowing the user to understand the suggestions and solutions given by the planner in a concise and clear manner, thereby improving the user experience.

[0082] In the embodiment of the present disclosure, the speech generation module 140 is configured to obtain target speech relative to the basic information, the business cause-effect scheme and the product association information.

[0083] For example, based on the information output by all the previous modules, the target words that will be output to the user can be obtained. The target words are easy to understand, which can enable users to fully understand the planned product content and provide users with valuable auxiliary suggestions.

[0084] In the embodiment of the present disclosure, the speech generation module 140 is configured to generate a model input text corresponding to the basic information, the business causal scheme and the product association information; and input the model input text into the trained causal model to obtain the target speech.

[0085] For example, the speech generation module 140 can write the user question, user context, business causal solution, and product-related information into a final prompt (as an example of model input text). The final prompt is input into the trained causal big model to output the target speech. Among them, the trained causal big model is obtained by training the big model (such as GPT4) on a specific data set in a specific scenario. The trained causal big model can better serve the future in a specific scenario and provide users with target speech containing reasonable product recommendations.

[0086] The following is an illustrative description of the implementation process of generating speech based on the causal big model provided by the embodiment of the present disclosure with reference to FIG2 .

[0087] Please refer to Figure 2, which is a flow chart of a method for generating speech based on a causal big model provided by an embodiment of the present disclosure. The method for generating speech based on a causal big model may include: S210, identifying the basic information of the user, wherein the basic information includes: user questions and contextual information related to the user. S210, obtaining a business causal solution that matches the basic information. S230, obtaining product-related information based on the contextual information and the business causal solution, wherein the product-related information includes: product explanation text, product business data and product demand forecast information. S240, obtaining target speech relative to the basic information, the business causal solution and the product-related information.

[0088] The above process is explained below as an example.

[0089] In an embodiment of the present disclosure, S220 may include: S221, retrieving multiple product solution causal chains that match the user problem from a preset solution document; S222, annotating the multiple product solution causal chains through user information and product configuration documents to obtain multiple annotated product solution causal chains; S223, obtaining the business causal solution based on the multiple annotated product solution causal chains, the user problem and the target solution matching model.

[0090] In an embodiment of the present disclosure, S221 may include: performing matching calculations with the three stage documents in the preset solution document based on the contextual information to obtain multiple matching values; using the solutions corresponding to the matching values ​​located before the preset positions in the multiple matching values ​​as the multiple product solution causal chains; wherein the first stage document in the preset solution document includes: product type and product planning; the second stage document includes: product parameters of each product in the product type; the third stage document includes: product name and product application scenario of each product and product core terms.

[0091] In an embodiment of the present disclosure, S222 may include: if it is confirmed that the product name of each product solution causal chain in the multiple product solution causal chains and the user information are consistent with the product elements in the product configuration document, then it is marked as a valid solution; if it is confirmed that the product name of each product solution causal chain in the multiple product solution causal chains and the user information are inconsistent with the product elements in the product configuration document, then it is marked as an invalid solution, and invalid reason text information is generated; wherein, the valid solution and the invalid solution constitute the multiple marked product solution causal chains.

[0092] In an embodiment of the present disclosure, S223 may include: generating prompt text corresponding to the multiple labeled product solution causal chains and the user questions; inputting the prompt text into the target solution matching model to obtain the business causal solution; wherein, the target solution matching model is obtained by training a large language model.

[0093] In an embodiment of the present disclosure, S230 may include: S231, a product explanation submodule determines a standard question corresponding to the user question; retrieves product terms content matching the standard question from a product terms document; generates the product explanation text based on the standard question, the product terms content and the target large language model; S232, a data processing submodule calculates the product business data corresponding to the business causal scheme when confirming that the user needs the product business data; S233, a demand prediction submodule predicts the product demand prediction information associated with the user's conversation data.

[0094] In an embodiment of the present disclosure, S231 may include: using a trained semantic vector model to calculate the user question and the preset standard sentence to obtain a vector distance set; obtaining a target sentence in the vector distance set that is less than a set threshold; and taking the sentence corresponding to the minimum value in the vector distance in the target sentence as the standard question.

[0095] In an embodiment of the present disclosure, S231 may include: confirming that the vector distances in the vector distance set are not less than the set threshold, then recording the user question; setting a standard sentence corresponding to the user question, and iteratively updating the trained semantic vector model.

[0096] In an embodiment of the present disclosure, S231 may include: inputting preset standard statements and original product terms content into a large language model to obtain actual reference product terms; verifying and marking the actual reference product terms to determine the product terms reference content; and constructing the product terms document based on the preset standard statements, the product terms reference content, and the product information of each product.

[0097] In an embodiment of the present disclosure, S231 may include: generating prompt information corresponding to the standard question, the product term content, the user question, the conversation context data and the situational information; inputting the prompt information into the target large language model and outputting the product explanation text; wherein, the target large language model is obtained by training the initial large model through a training data set; the training data set includes: user question samples, product demand samples, user situation samples, product term samples and explanation text samples.

[0098] In an embodiment of the present disclosure, S240 may include: generating a model input text corresponding to the basic information, the business causal scheme and the product association information; inputting the model input text into a trained causal model to obtain the target speech.

[0099] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific implementation process of the above-described method S210 to S240 can refer to the corresponding process in the aforementioned system and will not be elaborated here.

[0100] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the operation of the method corresponding to any of the above methods provided in the above embodiments can be implemented.

[0101] The embodiments of the present disclosure further provide a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to any of the above methods provided in the above embodiments.

[0102] As shown in Figure 3, an electronic device 300 provided by an embodiment of the present disclosure includes: a memory 310, a processor 320, and a computer program stored in the memory 310 and executable on the processor 320, wherein the processor 320 reads the program from the memory 310 through the bus 330 and executes the program to implement a method as in any of the above embodiments.

[0103] Processor 320 can process digital signals and can include various computing architectures, such as a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of multiple instruction sets. In some examples, processor 320 can be a microprocessor.

[0104] The memory 310 can store instructions executed by the processor 320 or data related to the execution of instructions. These instructions and / or data may include code to implement some or all of the functions of one or more modules described in the embodiments of the present disclosure. The processor 320 of the embodiment of the present disclosure can be configured to execute the instructions in the memory 310 to implement the method shown above. The memory 310 includes dynamic random access memory, static random access memory, flash memory, optical storage, or other memory known to those skilled in the art.

[0105] The above description is merely an embodiment of the present disclosure and does not limit the scope of protection of the present disclosure. For those skilled in the art, the present disclosure may be subject to various modifications and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the scope of protection of the present disclosure. It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0106] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

[0107] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element. Industrial Applicability

[0108] The system, method and electronic device for generating speech based on a causal big model provided by the present disclosure achieve accurate positioning of user intentions, and can provide users with effective, high-quality speech content containing business product suggestions, provide users with valuable auxiliary information, and enhance user experience.

Claims

1. A system for generating conversation scripts based on a causal large model, characterized in that, It includes: A user identification module configured to identify the basic information of the user, where the basic information includes: user questions and context information related to the user; A solution matching module configured to obtain a business cause-and-effect solution that matches the basic information; A product processing module configured to obtain product association information according to the context information and the business cause-and-effect solution, where the product association information includes: product explanation text, product business data, and product demand prediction information; A script generation module configured to obtain a target script corresponding to the basic information, the business cause-and-effect solution, and the product association information.

2. The system according to claim 1, characterized in that The solution matching module is configured to: Retrieve multiple product solution cause-and-effect chains that match the user questions from a preset solution document; Annotate the multiple product solution cause-and-effect chains through user information and a product configuration document to obtain multiple annotated product solution cause-and-effect chains; Obtain the business cause-and-effect solution according to the multiple annotated product solution cause-and-effect chains, the user questions, and a target solution matching model.

3. The system according to claim 2, wherein, The solution matching module is configured to: Calculate the matching degrees between the context information and three-stage documents in the preset solution document respectively to obtain multiple matching degree values; Use the solutions corresponding to the matching degree values before the preset position among the multiple matching degree values as the multiple product solution cause-and-effect chains; Among them, the first-stage document in the preset solution document includes: product types and product plans; the second-stage document includes: product parameters of each product in the product type; the third-stage document includes: product names, product application scenarios, and product core terms of each product.

4. The system according to claim 2 or 3, characterized in that, The solution matching module is configured to: If it is confirmed that the product names of each product solution cause-and-effect chain in the multiple product solution cause-and-effect chains and the user information are consistent with the product elements in the product configuration document, mark them as valid solutions; If it is confirmed that the product names of each product solution cause-and-effect chain in the multiple product solution cause-and-effect chains and the user information are inconsistent with the product elements in the product configuration document, mark them as invalid solutions and generate invalid reason text information; Among them, the valid solutions and the invalid solutions constitute the multiple annotated product solution cause-and-effect chains.

5. The system according to claim 2 or 3, wherein The solution matching module is configured to: Generate a prompt text corresponding to the multiple annotated product solution cause-and-effect chains and the user questions; Input the prompt text into the target solution matching model to obtain the business cause-and-effect solution; where the target solution matching model is obtained by training a large language model.

6. The system according to any one of claims 1-5, characterized in that The product processing module includes: a product explanation sub-module, a data processing sub-module, and a demand prediction sub-module; where The product explanation sub-module is configured to determine a standard question corresponding to the user question; retrieve product clause content that matches the standard question from a product clause document; generate the product explanation text according to the standard question, the product clause content, and a target large language model. The data processing sub-module is configured to calculate the product service data corresponding to the service causal scheme when it is confirmed that the user needs the product service data; The demand forecasting sub-module is configured to forecast the product demand forecasting information associated with the user's conversation data.

7. The system according to claim 6, wherein The product explanation sub-module is configured as follows: Calculate the user question and the preset standard statements using the trained semantic vector model to obtain a set of vector distances; Obtain the target statements in the set of vector distances that are less than the set threshold; Use the statement corresponding to the minimum value in the vector distances of the target statements as the standard question.

8. The system according to claim 7, wherein The product explanation sub-module is configured as follows: If it is confirmed that the vector distances in the set of vector distances are all not less than the set threshold, record the user question; Set the standard statement corresponding to the user question and iteratively update the trained semantic vector model.

9. The system according to any one of claims 6-8, characterized in that, The product explanation sub-module is configured as follows: Input the preset standard statements and the original product clause content into the large language model to obtain the actual reference product clauses; Verify and annotate the actual reference product clauses to determine the product clause reference content; Construct the product clause document based on the preset standard statements, the product clause reference content, and the product information of each product.

10. The system according to any one of claims 6-9, characterized in that, The product explanation sub-module is configured as follows: Generate prompt information corresponding to the standard question, the product clause content, the user question, the conversation context data, and the scenario information; Input the prompt information into the target large language model to output the product explanation text; Wherein, the target large language model is obtained by training an initial large model with a training data set; the training data set includes: user question samples, product demand samples, user scenario samples, product clause samples, and explanation text samples.

11. The system according to any one of claims 1-10, characterized in that, The product processing module further includes an information collection module, and the information collection module is configured to: collect user information based on the scenario information and the service causal scheme.

12. The system according to any one of claims 1-11, characterized in that, The conversation script generation module is configured as follows: Generate a model input text corresponding to the basic information, the service causal scheme, and the product association information; Input the model input text into the trained causal large model to obtain the target conversation script.

13. A method for generating conversation scripts based on a causal large model, characterized in that, It includes: Identify the basic information of the user, where the basic information includes: user questions and scenario information related to the user; Obtain the service causal scheme that matches the basic information; According to the scenario information and the service causal scheme, obtain product association information, where the product association information includes: product explanation text, product service data, and product demand forecasting information; Obtain the target conversation script corresponding to the basic information, the service causal scheme, and the product association information.

14. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, wherein the computer program, when run by a processor, executes the method according to claim 13.

15. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and running on the processor. When the computer program is run by the processor, it executes the method described in claim 13.

16. A computer program product, characterized in that, The computer program product includes a computer program. When the computer program is run by a processor, it executes the method described in claim 13.

Images