Methods, devices, electronic equipment, and storage media for generating personalized weight loss suggestions

Abstract

This application provides a method, apparatus, electronic device, and storage medium for generating customized weight loss suggestions, belonging to the field of artificial intelligence technology. The method includes: acquiring obesity survey information and survey communication information corresponding to a target customer based on a preset obesity information survey project; determining a target general suggestion from a set of preset candidate general suggestions based on the obesity survey information; performing speech recognition based on the survey communication information to obtain the corresponding target customer's communication content information; determining a target prompt word template from a set of preset candidate prompt word templates based on the target customer's obesity survey information; inputting the target prompt word template and communication content information into a pre-trained weight loss service model to generate personalized suggestion information; and determining a target customized weight loss suggestion based on the target general suggestion and personalized suggestion information. This application embodiment can provide customers with consistently high-quality customized weight loss service information.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, electronic device, and storage medium for generating customized weight loss suggestions. Background Technology

[0002] In health management services, especially offline personalized weight loss services, employees collect and analyze client information face-to-face to provide tailored advice and services. However, the professional competence of employees responsible for personalized services varies, making it difficult to guarantee consistent service quality. Problems such as low communication efficiency, incomplete information gathering, and low service standardization exist. Therefore, how to provide clients with consistently high-quality and customized weight loss services has become a pressing technical challenge. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, electronic device, and storage medium for generating customized weight loss suggestions, aiming to provide customers with stable and high-quality customized weight loss service information.

[0004] To achieve the above objectives, a first aspect of this application proposes a method for generating customized weight loss suggestions, the method comprising:

[0005] Based on the pre-set obesity information survey project, obtain obesity survey information and survey communication information corresponding to the target customers;

[0006] Based on the obesity survey information, a target general recommendation is determined from a set of pre-set candidate general recommendations;

[0007] Based on the survey communication information, speech recognition information is performed to obtain the communication content information corresponding to the target customer;

[0008] Based on the obesity survey information corresponding to the target customer, a target prompt word template is determined from a plurality of preset candidate prompt word templates;

[0009] The target prompt word template and the communication content information are input into a pre-trained weight loss service model to generate personalized suggestion information through the weight loss service model.

[0010] Based on the general recommendations and the personalized recommendations, customized weight loss recommendations are determined.

[0011] In some embodiments, determining the target general recommendation from a set of pre-defined candidate general recommendations based on the obesity survey information includes:

[0012] Based on the obesity survey information, an obesity characteristic analysis is performed on the obesity manifestations of the target customers to obtain obesity characteristic information;

[0013] Based on the obesity feature information and a plurality of preset typical feature information, feature matching is performed to obtain typical feature matching information; wherein, each of the typical feature information corresponds to a candidate general suggestion;

[0014] Based on the typical feature matching information, the corresponding candidate general suggestions are determined as the target general suggestions.

[0015] In some embodiments, before determining the target general suggestion from a set of pre-defined candidate general suggestions based on the obesity survey information, the method further includes pre-configuring the candidate general suggestions, specifically including:

[0016] Obtain a historical service dataset, wherein the historical service dataset includes multiple weight loss suggestion information, and each weight loss suggestion information corresponds to one of the obesity feature information;

[0017] The obesity features commonly found in the historical service dataset are identified as typical features, and the weight loss suggestions corresponding to each typical feature are integrated to obtain multiple candidate general suggestions.

[0018] In some embodiments, the obesity survey information includes customer status information and customer needs information. The step of determining a target prompt word template from a set of preset candidate prompt word templates based on the obesity survey information corresponding to the target customer includes:

[0019] The obesity assessment criteria for the target customer are determined based on the customer status information; wherein, the customer status information includes customer age information, customer gender information, and customer dietary information;

[0020] Based on the aforementioned customer needs information, determine the target customer's weight loss needs information;

[0021] Based on the obesity assessment criteria and the weight loss needs information, a target prompt word template is determined from a set of preset candidate prompt word templates.

[0022] In some embodiments, obtaining obesity survey information and survey communication information corresponding to the target customer based on a preset obesity information survey item includes:

[0023] According to the preset obesity information survey project, the target employees conduct survey communication with the target customers to obtain the obesity survey information and the survey communication information;

[0024] After inputting the target prompt word template and the communication content information into a pre-trained weight loss service model to generate personalized suggestion information through the weight loss service model, the method further includes:

[0025] Based on the communication content information, voice role recognition is performed to obtain first voice data corresponding to the target employee and second voice data corresponding to the target customer;

[0026] Based on the first voice data, semantic recognition is performed to obtain employee voice recognition information;

[0027] The employee voice recognition information is analyzed according to the preset employee service evaluation criteria to obtain the corresponding employee evaluation information.

[0028] Based on the second voice data, voice emotion analysis is performed to obtain the target customer's satisfaction information;

[0029] The service evaluation information of the target employee is obtained based on the employee evaluation information and the satisfaction information.

[0030] In some embodiments, after determining the target-customized weight loss recommendations based on the target general recommendations and the personalized recommendation information, the process includes:

[0031] The obesity survey information, communication content information, and customized weight loss suggestions of the target customers are used to generate a weight loss service knowledge graph;

[0032] The weight loss service knowledge graph is continuously updated based on the target customer's subsequent weight loss actions to obtain the target updated knowledge graph;

[0033] Based on the weight loss service knowledge graph and the goal update knowledge graph, weight loss effect analysis is performed, and goal adjustment suggestions are generated.

[0034] In some embodiments, before inputting the target prompt word template and the communication content information into a pre-trained weight loss service model to generate personalized suggestion information through the weight loss service model, the method further includes pre-training with the weight loss service model, specifically including:

[0035] Acquire weight loss knowledge data; wherein, the weight loss knowledge data includes theoretical knowledge data adapted to different customer status information;

[0036] Obtain a model training set; wherein the model training set includes multiple weight loss service training samples corresponding to different customer status information, and each weight loss service training sample is configured with corresponding suggestion sample information;

[0037] Based on the weight loss service training samples corresponding to the same customer status information and the weight loss knowledge data, the original weight loss service big model is input to generate suggested training information;

[0038] The comparison is performed between the suggested training information and the suggested sample information corresponding to the weight loss service training sample to obtain the comparison deviation data.

[0039] The model parameters of the weight loss service big model are updated based on the comparison bias data to obtain the pre-trained weight loss service big model.

[0040] To achieve the above objectives, a second aspect of this application provides a customized weight loss suggestion generation device, the device comprising:

[0041] The obesity information survey module is used to obtain obesity survey information and survey communication information corresponding to the target customers based on preset obesity information survey items.

[0042] A general suggestion providing module is used to determine a target general suggestion from a set of multiple candidate general suggestions based on the obesity survey information;

[0043] The speech recognition module is used to perform speech recognition based on the survey communication information to obtain the communication content information corresponding to the target customer;

[0044] The prompt word template determination module is used to determine the target prompt word template from a plurality of preset candidate prompt word templates based on the obesity survey information corresponding to the target customer;

[0045] The large model analysis module is used to input the target prompt word template and the communication content information into a pre-trained large model for weight loss services, so as to generate personalized suggestion information through the large model for weight loss services;

[0046] The weight loss suggestion module is used to determine customized weight loss suggestions based on the general suggestions for the target and the personalized suggestion information.

[0047] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the customized weight loss suggestion generation method described in the first aspect.

[0048] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the customized weight loss suggestion generation method described in the first aspect.

[0049] The customized weight loss suggestion generation method, device, electronic device, and storage medium proposed in this application obtain obesity survey information and survey communication information of target customers according to a preset obesity information survey project. Based on the obesity survey information, a target general suggestion is determined from a number of preset candidate general suggestions. Then, based on the survey communication information, speech recognition information is performed to obtain the corresponding communication content information of the target customer. Based on the obesity survey information of the corresponding target customer, a target prompt word template is determined from a number of preset candidate prompt word templates. The target prompt word template and communication content information are input into a pre-trained weight loss service big model to generate personalized suggestion information through the weight loss service big model. Based on the target general suggestion and personalized suggestion information, a target customized weight loss suggestion is determined. Therefore, this application obtains obesity survey information and survey communication information of target customers, and uses the obesity survey information to obtain general suggestions tailored to the target customers, thereby obtaining basic suggestion information for solving the target customers' obesity problems. Then, it uses the communication content information with the target customers and the adapted target prompt word template to input into a pre-trained weight loss service model to generate personalized suggestion information for the target customers. By combining the general suggestion information and the personalized suggestion information, it determines the customized weight loss suggestions for the target customers, which can specifically solve the weight loss needs of the target customers and provide a stable and high-quality customized weight loss service. Attached Figure Description

[0050] Figure 1 This is a flowchart of the customized weight loss suggestion generation method provided in the embodiments of this application;

[0051] Figure 2 yes Figure 1 The flowchart of step S102 in the document;

[0052] Figure 3 yes Figure 1 The flowchart preceding step S102;

[0053] Figure 4 yes Figure 1 The flowchart of step S104 in the process;

[0054] Figure 5 yes Figure 1 The flowchart preceding step S105;

[0055] Figure 6 yes Figure 1 The flowchart following step S106;

[0056] Figure 7 yes Figure 1 The flowchart following step S105;

[0057] Figure 8This is a schematic diagram of the customized weight loss suggestion generation device provided in the embodiments of this application;

[0058] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0062] Artificial intelligence (AI) is a new branch of computer science that studies, develops, and applies theories, methods, technologies, and systems to simulate, extend, and expand human intelligence. It aims to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thought. Furthermore, AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results.

[0063] Large-scale artificial intelligence models refer to machine learning models with extremely large parameters (usually over a billion) and complex computational structures. They are typically capable of processing massive amounts of data and performing various complex tasks, such as natural language processing and image recognition.

[0064] Natural Language Processing (NLP): NLP uses computers to process, understand, and utilize human language (such as Chinese and English). NLP is a branch of artificial intelligence and an interdisciplinary field of computer science and linguistics, often referred to as computational linguistics. NLP includes syntactic analysis, semantic analysis, and discourse understanding. It is commonly used in machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, intent recognition, information extraction and filtering, text classification and clustering, and opinion mining. It involves data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computation.

[0065] This application provides a method, apparatus, electronic device, and storage medium for generating customized weight loss suggestions, aiming to provide customers with stable and high-quality customized weight loss service information.

[0066] The customized weight loss suggestion generation method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the customized weight loss suggestion generation method in this application embodiment is described.

[0067] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0068] Foundational technologies in artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0069] The customized weight loss suggestion generation method provided in this application relates to the field of artificial intelligence technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the customized weight loss suggestion generation method, but is not limited to the above forms.

[0070] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0071] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0072] Figure 1 This is an optional flowchart of the customized weight loss suggestion generation method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0073] Step S101: Based on the preset obesity information survey items, obtain obesity survey information and survey communication information corresponding to the target customers;

[0074] Step S102: Based on obesity survey information, determine the target general recommendation from a set of pre-set candidate general recommendations;

[0075] Step S103: Based on the survey communication information, perform voice recognition to obtain the corresponding target customer's communication content information;

[0076] Step S104: Based on the obesity survey information of the corresponding target customer, determine the target prompt word template from a number of preset candidate prompt word templates;

[0077] Step S105: Input the target prompt word template and communication content information into the pre-trained weight loss service big model to generate personalized suggestion information through the weight loss service big model;

[0078] Step S106: Based on the general and personalized recommendations for the target, determine the target-customized weight loss recommendations.

[0079] Steps S101 to S106 as shown in the embodiments of this application involve obtaining obesity survey information and survey communication information of the target customer according to a preset obesity information survey project, determining the target general suggestion from a plurality of preset candidate general suggestions based on the obesity survey information, then performing speech recognition based on the survey communication information to obtain the corresponding target customer's communication content information, determining the target prompt word template from a plurality of preset candidate prompt word templates based on the corresponding target customer's obesity survey information, inputting the target prompt word template and communication content information into a pre-trained weight loss service big model to generate personalized suggestion information through the weight loss service big model, and determining the target customized weight loss suggestion based on the target general suggestion and personalized suggestion information. Therefore, this application obtains obesity survey information and survey communication information of target customers, and uses the obesity survey information to obtain general suggestions tailored to the target customers, thereby obtaining basic suggestion information for solving the target customers' obesity problems. Then, it uses the communication content information with the target customers and the adapted target prompt word template to input into a pre-trained weight loss service model to generate personalized suggestion information for the target customers. By combining the general suggestion information and the personalized suggestion information, it determines the customized weight loss suggestions for the target customers, which can specifically solve the weight loss needs of the target customers and provide a stable and high-quality customized weight loss service.

[0080] In step S101 of some embodiments, obesity survey information and survey communication information corresponding to the target customer are obtained according to the preset obesity information survey items. The obesity information survey items are used to obtain information related to weight loss of the target customer, and are used to capture information such as the target customer's basic information, lifestyle habits, eating habits, exercise habits, weight loss experience and expectations for weight loss services.

[0081] Obtain survey communication information from interactions with target clients based on an obesity information survey project to supplement the obesity survey data. Through the obesity information survey project, obesity survey information from target clients is collected using standardized methods. Simultaneously, communication with target clients yields survey communication information, allowing for the gathering of more information, capturing non-quantitative information such as target clients' expectations and motivations for weight loss, and their attitudes towards customized weight loss services, as well as supplementary information to the obesity survey data.

[0082] Obesity survey information and survey communication information are both obtained based on obesity information survey projects. The difference is that obesity survey information is data obtained directly through obesity information survey projects, while survey communication information is voice communication data obtained during communication with target customers.

[0083] In some embodiments, obesity survey information and survey communication information corresponding to the target customers are obtained through questionnaires. Employees communicate with the target customers, and based on the survey questions, the employees communicate with the target customers to complete the questionnaire. The completed questionnaire data constitutes the obesity survey information. The voice communication data obtained from the communication between the employee and the target customer constitutes the survey communication information. The questionnaire can be paper-based or electronic. If it is paper-based, it needs to be converted to electronic data for subsequent processing.

[0084] In some embodiments, specialized artificial intelligence (AI) can be used to communicate with target customers. The AI ​​communicates with target customers through pre-set obesity information survey projects, thereby obtaining obesity survey information and survey communication information. Using AI-configured voice packages allows for more standardized information collection, resulting in obesity survey information and survey communication information.

[0085] In step S102 of some embodiments, target general recommendations suitable for the target customer are determined from a series of pre-set candidate general recommendations based on the collected obesity survey information. Obesity survey information obtained through standardization can quickly filter out target general recommendations applicable to the target customer from multiple pre-set candidate general recommendations. Target general recommendations refer to suggestions applicable to target customers with specific obesity characteristics derived from the analysis of obesity survey information, providing the most basic weight loss guidance.

[0086] Please see Figure 2 In some embodiments, step S102 may include, but is not limited to, steps S201 to S203:

[0087] Step S201: Based on the obesity survey information, analyze the obesity characteristics of the target customers to obtain obesity characteristic information;

[0088] Step S202: Based on the obesity feature information, feature matching is performed with multiple preset typical feature information to obtain typical feature matching information; wherein, each typical feature information corresponds to a candidate general suggestion;

[0089] Step S203: Based on the typical feature matching information, the corresponding candidate general suggestions are determined as the target general suggestions.

[0090] In step S201 of some embodiments, the obesity manifestations of the target customer are analyzed in depth based on the collected obesity survey information to identify and extract obesity characteristic information. Obesity characteristic information refers to the obesity characteristics exhibited by the target customer, involving indicators such as the target customer's weight, body fat percentage, and body shape.

[0091] In step S202 of some embodiments, since there is a certain correlation between the causes of obesity and the corresponding obesity characteristics, and there are several common causes of obesity, corresponding typical characteristic information can be obtained for these common causes. This typical characteristic information is also common obesity characteristic information for customers, and corresponding candidate general suggestions are configured for these common typical characteristic information. The candidate general suggestions are basic suggestions applicable to the corresponding typical characteristic information.

[0092] Based on the obesity characteristic information obtained from the target customer, feature matching is performed with multiple existing typical characteristic information to determine whether there is matching typical characteristic information, thus obtaining typical characteristic matching information.

[0093] In step S203 of some embodiments, typical feature information is determined based on typical feature matching information, and the corresponding candidate general suggestion is determined as the target general suggestion.

[0094] Through steps S201 to S203, obesity characteristic information can be obtained in response to the obesity survey information of the target customer, and then matched with multiple existing common typical characteristic information to obtain corresponding target general suggestions, providing the target customer with suitable basic weight loss guidance information.

[0095] Please see Figure 3 In some embodiments, steps S301 to S302 may be included, but are not limited to, before step S102:

[0096] Step S301: Obtain historical service dataset, wherein the historical service dataset includes multiple weight loss suggestion information, and each weight loss suggestion information corresponds to a type of obesity feature information;

[0097] Step S302: Common obesity features in the historical service dataset are identified as typical features, and the weight loss suggestions corresponding to each typical feature are integrated to obtain multiple candidate general suggestions.

[0098] In step S301 of some embodiments, a historical service dataset is obtained. The historical service dataset includes multiple weight loss suggestion information, each of which corresponds to a type of obesity characteristic information. This data is accumulated from past customer service experience and includes weight loss suggestion information for various obesity situations.

[0099] In step S302 of some embodiments, common obesity characteristics are identified from historical service datasets and determined as typical characteristics. These typical characteristics represent the common types and characteristics of obesity among a broad customer group. Weight loss suggestions corresponding to these typical characteristics are integrated to form multiple candidate general suggestions. These candidate general suggestions are weight loss strategies and suggestions that have repeatedly appeared and proven effective in historical data, providing a standardized starting point for customized weight loss services for target customers and ensuring service consistency and quality.

[0100] Through steps S301 to S302, a series of candidate general suggestions can be formed based on historical experience and data analysis. These suggestions will be used in step S102 to match with the obesity characteristic information of the target customer in order to determine the final target general suggestion.

[0101] In step S103 of some embodiments, the survey communication information is identified using speech recognition technology to obtain the communication content information with the target customer. In some embodiments, if the person communicating with the target customer is an employee, the employee's voice data is collected in advance to obtain the corresponding employee's voice information, so as to better distinguish the voice information of the employee and the target customer when performing speech recognition on the survey communication information, and obtain accurate communication content information.

[0102] In step S104 of some embodiments, the obesity survey information provides target customers with information including but not limited to weight, eating habits, lifestyle, and weight loss goals. A target prompt template can be determined from a plurality of pre-set candidate prompt templates.

[0103] Please see Figure 4 In some embodiments, the obesity survey information includes customer status information and customer demand information, and step S104 may include, but is not limited to, steps S401 to S403:

[0104] Step S401: Determine the obesity assessment criteria for the target customer based on the customer status information; wherein, the customer status information includes customer age information, customer gender information, and customer dietary information;

[0105] Step S402: Determine the weight loss needs of the target customers based on customer needs information;

[0106] Step S403: Based on obesity assessment criteria and weight loss needs information, determine the target prompt word template from multiple preset candidate prompt word templates.

[0107] In step S401 of some embodiments, the obesity survey information includes customer status information and customer needs information. The customer status information covers the customer's basic information, including customer age information, customer gender information, and customer diet information. Customer diet information: customers of different ages and genders may face different health risks and weight loss challenges. Dietary habits directly affect obesity status and the feasibility of weight loss. Dietary habits can be obtained indirectly by analyzing the target customer's location or directly by obtaining eating data.

[0108] The obesity assessment criteria for target customers need to be adjusted based on different customer age, gender, and dietary information. Obesity assessment criteria are the standard information for assessing the obesity status of target customers.

[0109] In step S402 of some embodiments, the weight loss needs information of the target customer is determined based on the customer needs information, including the target customer's weight loss goals, expected results and personal preferences, so as to better meet the needs of the target customer.

[0110] In step S403 of some embodiments, the most suitable target prompt word template for the target customer is determined from a plurality of preset candidate prompt word templates, combining obesity assessment criteria and weight loss demand information. Each preset candidate prompt word template is configured with an assessment weight corresponding to the obesity assessment criteria and weight loss plan information matching the weight loss demand information.

[0111] In some embodiments, the target customer's dietary information can be indirectly represented based on the target customer's location. Then, the specific obesity assessment criteria can be determined through the customer's age and gender information. The target customer's expected weight loss goal and the time required to achieve the expected goal can be analyzed through the customer's demand information to determine the target customer's weight loss demand information. The target prompt word template can be determined from a number of preset candidate prompt word templates.

[0112] By accurately determining the target prompt template that matches the target customer through steps S401 to S403, the objective situation and customer needs of the target customer can be better aligned, thereby enhancing the pertinence and effectiveness of the weight loss service and improving its personalization.

[0113] In step S105 of some embodiments, the adapted target prompt word template and the communication content information obtained by speech recognition are input into a pre-trained weight loss service big model to obtain personalized suggestion information for the corresponding target customer.

[0114] The weight loss service big data model is an artificial intelligence big data model. The artificial intelligence big data model can provide more accurate and personalized services, predict the specific obstacles that target customers may encounter in the weight loss process, and provide corresponding solutions.

[0115] Please see Figure 5 In some embodiments, steps S501 to S505 may be included, but are not limited to, before step S105:

[0116] Step S501: Obtain weight loss knowledge data; wherein, the weight loss knowledge data includes theoretical knowledge data adapted to different customer status information;

[0117] Step S502: Obtain the model training set; wherein, the model training set includes multiple weight loss service training samples corresponding to different customer status information, and each weight loss service training sample is configured with corresponding suggestion sample information.

[0118] Step S503: Based on the weight loss service training samples and weight loss knowledge data corresponding to the same customer status information, input them into the original weight loss service big model to generate suggested training information;

[0119] Step S504: Compare the suggested training information and suggested sample information corresponding to the weight loss service training samples to obtain comparison deviation data;

[0120] Step S505: Update the model parameters of the weight loss service big model based on the comparison deviation data to obtain the pre-trained weight loss service big model.

[0121] In step S501 of some embodiments, weight loss knowledge data is obtained. The weight loss knowledge data includes knowledge theories adapted to different customer status information, such as theoretical knowledge in the fields of nutrition, kinesiology and health psychology.

[0122] In step S502 of some embodiments, a model training set is obtained. The model training set includes multiple weight loss service training samples corresponding to different customer status information. Each weight loss service training sample is configured with corresponding suggestion sample information. The weight loss service training samples are based on experience data obtained from providing weight loss services to customers in the past, which can help the large artificial intelligence model learn and understand the relationship between different customer status information and suggestion sample information.

[0123] In step S503 of some embodiments, weight loss service training samples and weight loss knowledge data corresponding to the same customer status information are input into the original weight loss service big model to generate suggested training information, thereby enabling the original weight loss service big model to learn how to generate suggested information based on the customer status.

[0124] In some implementations, different training datasets can be constructed based on different ages, genders, and regions, so that when using the large-scale weight loss service model later, the target prompt word templates can be used to enable the large-scale weight loss service model to provide accurate personalized suggestions.

[0125] In step S504 of some embodiments, the suggested training information and suggested sample information corresponding to the weight loss service training samples are compared to obtain comparison deviation data. The comparison deviation data is used to evaluate whether the suggested information generated by the large model of the weight loss service is accurate.

[0126] In step S505 of some embodiments, the model parameters of the weight loss service big model are updated based on the comparison deviation data to obtain a pre-trained weight loss service big model. The accuracy of the suggestion information generated by the weight loss service big model is characterized by the comparison deviation data, so as to further fine-tune the model parameters to improve the accuracy and reliability of the weight loss service big model until the suggestion training information generated by the weight loss service big model is similar to the suggestion sample information.

[0127] Steps S501 to S505 ensure that the large-scale weight loss service model has undergone sufficient preprocessing and training before generating personalized weight loss suggestions, and is able to provide personalized suggestions based on customer status information.

[0128] In step S106 of some embodiments, the target general suggestions and personalized suggestions are combined to determine the target customized weight loss suggestions and generate a specific customized weight loss plan. The customized weight loss plan not only considers the target customer's health status, lifestyle habits and weight loss goals, but also the target customer's preference information and possible weight loss obstacles, thereby realizing a customized weight loss service for the target customer.

[0129] Please see Figure 6In some embodiments, steps S106 may include, but are not limited to, steps S601 to S603:

[0130] Step S601: Generate a weight loss service knowledge graph from the target customer's obesity survey information, communication content information, and target-customized weight loss suggestions;

[0131] Step S602: Continuously update the weight loss service knowledge graph based on the target customer's subsequent weight loss operations to obtain the target updated knowledge graph;

[0132] Step S603: Analyze the weight loss effect based on the weight loss service knowledge graph and the goal update knowledge graph, and generate goal adjustment suggestions.

[0133] In step S601 of some embodiments, the obesity survey information, communication content information, and customized weight loss suggestions of the target customer are integrated to generate a weight loss service knowledge graph. The weight loss service knowledge graph is a structured data representation that links the target customer's personal data, communication data, and weight loss suggestions to form a comprehensive information view. This helps the target customer understand their current status and also provides a reference framework for continuously providing weight loss services.

[0134] In step S602 of some embodiments, subsequent information on the target customer's weight loss operations based on the target-customized weight loss advice is obtained, and the weight loss service knowledge graph is continuously updated to obtain the target-updated knowledge graph, thereby reflecting the target customer's weight loss status in real time, such as changes in weight and changes in energy intake.

[0135] In step S603 of some embodiments, weight loss effect analysis is performed based on the weight loss service knowledge graph and the goal update knowledge graph, and corresponding goal adjustment suggestions are generated. Goal adjustment suggestions refer to weight loss suggestions updated according to the actual weight loss situation of the target customer.

[0136] In some embodiments, a weight loss service knowledge graph and a goal update knowledge graph can be input into a large model to update or supplement the recommendation information and obtain goal adjustment recommendations.

[0137] Through steps S601 to S603, dynamic adjustments can be made based on the target customer's feedback and weight loss progress, and suggestions can be optimized according to the actual situation to obtain target adjustment suggestions. This ensures that the target customer is always on the optimal weight loss path, enhances the flexibility of the weight loss method, and provides the target customer with more accurate and feasible suggestions, thereby improving the quality of weight loss services.

[0138] Please see Figure 7In some embodiments, step S101 involves obtaining obesity survey information and survey communication information by conducting surveys and communications between target employees and target customers. Steps following S105 may include, but are not limited to, steps S701 to S705.

[0139] Step S701: Based on the communication content information, perform voice role recognition to obtain the first voice data of the corresponding target employee and the second voice data of the corresponding target customer;

[0140] Step S702: Perform semantic recognition based on the first voice data to obtain employee voice recognition information;

[0141] Step S703: Analyze the service content of employee voice recognition information according to the preset employee service evaluation criteria to obtain the corresponding employee evaluation information;

[0142] Step S704: Perform voice emotion analysis based on the second voice data to obtain the target customer's satisfaction information;

[0143] Step S705: Obtain the service evaluation information of the target employees based on employee evaluation information and satisfaction information.

[0144] In step S701 of some embodiments, voice role recognition is performed based on communication content information to distinguish the voice data of target employees and target customers, thereby obtaining the first voice data of the corresponding target employee and the second voice data of the corresponding target customer.

[0145] In step S702 of some embodiments, semantic recognition is performed on the first speech data to obtain employee speech recognition information. A neural network model trained using natural language processing techniques can be used to perform semantic recognition on the first speech data.

[0146] In step S703 of some embodiments, the employee's voice recognition information is analyzed for service content according to preset employee service evaluation criteria to obtain employee evaluation information. The target employee's voice content is compared with the preset employee service evaluation criteria to assess whether the target employee has followed the established service process and used appropriate service language. This helps to identify potential problems and areas for improvement in the weight loss service process and obtain employee evaluation information.

[0147] The employee service evaluation criteria include service indicators such as service integrity, friendliness, communication skills, judgment, and guidance skills. Target employees can be scored based on these service indicators to obtain employee evaluation information.

[0148] In step S704 of some embodiments, voice emotion analysis is performed based on the second voice data of the target customer to obtain customer satisfaction information. By analyzing the intonation and emotion factors in the target customer's voice, the target customer's satisfaction with the customized weight loss service provided by the target employee can be assessed.

[0149] In step S705 of some embodiments, service evaluation information of the target employees is obtained by combining employee evaluation information and target customer satisfaction information. This service evaluation information not only helps improve the quality of customized weight loss services but also provides a basis for employee training and performance management.

[0150] Steps S701 to S705 provide a service evaluation process for target employees, which can provide feedback to target employees by providing service evaluation information, thereby helping to further improve the quality of weight loss services.

[0151] In a complete embodiment, a tablet device can be used as an information collection device. The tablet device stores an electronic questionnaire for an obesity information survey, and records the communication between the target employee and the target customer to obtain survey communication information. Obesity survey information is obtained from the completed electronic questionnaire. The tablet device then transmits the obtained obesity survey information and survey communication information to a dedicated server for analysis. Some steps with low computing power requirements can also be directly analyzed by the tablet device, such as analyzing the obesity survey information of the target customer to obtain corresponding obesity characteristic information. This information is then matched with several existing typical characteristic information to determine the matching typical characteristic information and obtain corresponding candidate general suggestions as target general suggestions.

[0152] The server extracts customer status information related to the target customer from obesity survey data, determines the obesity assessment criteria for the target customer, and extracts the target customer's needs information to obtain weight loss needs information. Based on the obesity assessment criteria and weight loss needs information, a target prompt word template is selected from multiple pre-configured candidate prompt word templates to obtain more personalized suggestions tailored to the target customer. Then, speech recognition is performed on the survey communication information to obtain the communication content information, and the communication content information and the target prompt word template are input into a pre-trained weight loss service model to generate personalized suggestions.

[0153] The system feeds back both general and personalized recommendations to the target client via tablet devices. Based on these recommendations, customized weight loss suggestions are determined. These suggestions can be used by the target client's staff to help generate a specific, customized weight loss plan, or they can be generated directly by the tablet or server and then communicated to the target client.

[0154] This application embodiment obtains obesity survey information and communication information of target customers based on a preset obesity information survey project. Based on the obesity survey information, it determines a target general suggestion from multiple preset candidate general suggestions. Then, based on the communication information, it performs speech recognition to obtain the corresponding communication content information of the target customer. Based on the obesity survey information of the corresponding target customer, it determines a target prompt word template from multiple preset candidate prompt word templates. The target prompt word template and communication content information are input into a pre-trained weight loss service model to generate personalized suggestion information. Based on the target general suggestion and personalized suggestion information, a target-customized weight loss suggestion is determined. Therefore, this application obtains the obesity survey information and communication information of target customers, and uses the obesity survey information to obtain target general suggestions adapted to the target customers, thereby obtaining basic suggestion information to solve the target customers' obesity problems. Then, it uses the communication content information with the target customers and the adapted target prompt word template to input into a pre-trained weight loss service model to generate personalized suggestion information for the target customers. By combining the target general suggestion and personalized suggestion information, a target-customized weight loss suggestion is determined, which can specifically solve the weight loss needs of target customers and provide a stable and high-quality customized weight loss service.

[0155] Please see Figure 8 This application also provides a customized weight loss suggestion generation device, which can implement the above-mentioned customized weight loss suggestion generation method. The device includes:

[0156] The obesity information survey module is used to obtain obesity survey information and survey communication information corresponding to the target customers based on preset obesity information survey items.

[0157] A general recommendation provision module is used to determine a target general recommendation from multiple pre-set candidate general recommendations based on obesity survey information;

[0158] The speech recognition module is used to recognize speech information based on survey communication information to obtain the communication content information of the corresponding target customers;

[0159] The prompt word template determination module is used to determine the target prompt word template from multiple preset candidate prompt word templates based on obesity survey information of the corresponding target customers;

[0160] The large model analysis module is used to input target prompt word templates and communication content information into a pre-trained large model for weight loss services, so as to generate personalized suggestion information through the large model for weight loss services;

[0161] The weight loss advice module is used to determine customized weight loss recommendations based on general and personalized advice information.

[0162] The specific implementation of this customized weight loss suggestion generation device is basically the same as the specific implementation of the customized weight loss suggestion generation method described above, and will not be repeated here.

[0163] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned customized weight loss suggestion generation method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0164] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0165] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0166] The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 using the customized weight loss suggestion generation method of the embodiments of this application.

[0167] The input / output interface 903 is used to implement information input and output;

[0168] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0169] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0170] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0171] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described customized weight loss suggestion generation method.

[0172] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0173] The customized weight loss suggestion generation method, device, electronic device, and storage medium provided in this application embodiment obtain the obesity survey information and survey communication information of the target customer according to the preset obesity information survey project, and determine the target general suggestion from a preset number of candidate general suggestions based on the obesity survey information. Then, based on the survey communication information, speech recognition information is performed to obtain the corresponding communication content information of the target customer. Based on the obesity survey information of the corresponding target customer, the target prompt word template is determined from a preset number of candidate prompt word templates. The target prompt word template and communication content information are input into a pre-trained weight loss service big model to generate personalized suggestion information through the weight loss service big model. Based on the target general suggestion and personalized suggestion information, the target customized weight loss suggestion is determined. Therefore, this application obtains obesity survey information and survey communication information of target customers, and uses the obesity survey information to obtain general suggestions tailored to the target customers, thereby obtaining basic suggestion information for solving the target customers' obesity problems. Then, it uses the communication content information with the target customers and the adapted target prompt word template to input into a pre-trained weight loss service model to generate personalized suggestion information for the target customers. By combining the general suggestion information and the personalized suggestion information, it determines the customized weight loss suggestions for the target customers, which can specifically solve the weight loss needs of the target customers and provide a stable and high-quality customized weight loss service.

[0174] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0175] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0176] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0177] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0178] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0179] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, or indirect coupling or communication connection between the apparatus or units, and may be electrical, mechanical, or other forms.

[0181] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0183] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0184] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for generating customized weight loss suggestions, characterized in that, The method includes: Based on the pre-set obesity information survey project, obtain obesity survey information and survey communication information corresponding to the target customers; Based on the obesity survey information, a target general recommendation is determined from a set of pre-set candidate general recommendations; Based on the survey communication information, speech recognition information is performed to obtain the communication content information corresponding to the target customer; Based on the obesity survey information corresponding to the target customer, a target prompt word template is determined from a plurality of preset candidate prompt word templates; The target prompt word template and the communication content information are input into a pre-trained weight loss service model to generate personalized suggestion information through the weight loss service model. Based on the general recommendations and the personalized recommendations, customized weight loss recommendations are determined.

2. The method according to claim 1, characterized in that, The step of determining the target general recommendation from a set of pre-set candidate general recommendations based on the obesity survey information includes: Based on the obesity survey information, an obesity characteristic analysis is performed on the obesity manifestations of the target customers to obtain obesity characteristic information; Based on the obesity feature information and a plurality of preset typical feature information, feature matching is performed to obtain typical feature matching information; wherein, each of the typical feature information corresponds to a candidate general suggestion; Based on the typical feature matching information, the corresponding candidate general suggestions are determined as the target general suggestions.

3. The method according to claim 2, characterized in that, Before determining the target general suggestion from a set of pre-defined candidate general suggestions based on the obesity survey information, the method further includes pre-configuring a set of candidate general suggestions, specifically including: Obtain a historical service dataset, wherein the historical service dataset includes multiple weight loss suggestion information, and each weight loss suggestion information corresponds to one of the obesity feature information; The obesity features commonly found in the historical service dataset are identified as typical features, and the weight loss suggestions corresponding to each typical feature are integrated to obtain multiple candidate general suggestions.

4. The method according to claim 1, characterized in that, The obesity survey information includes customer status information and customer needs information. The step of determining a target prompt word template from a set of preset candidate prompt word templates based on the obesity survey information corresponding to the target customer includes: The obesity assessment criteria for the target customer are determined based on the customer status information; wherein, the customer status information includes customer age information, customer gender information, and customer dietary information; Based on the aforementioned customer needs information, determine the target customer's weight loss needs information; Based on the obesity assessment criteria and the weight loss needs information, a target prompt word template is determined from a set of preset candidate prompt word templates.

5. The method according to claim 1, characterized in that, The process of obtaining obesity survey information and communication information corresponding to the target customer based on preset obesity information survey items includes: According to the preset obesity information survey project, the target employees conduct survey communication with the target customers to obtain the obesity survey information and the survey communication information; After inputting the target prompt word template and the communication content information into a pre-trained weight loss service model to generate personalized suggestion information through the weight loss service model, the method further includes: Based on the communication content information, voice role recognition is performed to obtain first voice data corresponding to the target employee and second voice data corresponding to the target customer; Based on the first voice data, semantic recognition is performed to obtain employee voice recognition information; The employee voice recognition information is analyzed according to the preset employee service evaluation criteria to obtain the corresponding employee evaluation information. Based on the second voice data, voice emotion analysis is performed to obtain the target customer's satisfaction information; The service evaluation information of the target employee is obtained based on the employee evaluation information and the satisfaction information.

6. The method according to claim 1, characterized in that, After determining the target-customized weight loss recommendations based on the target general recommendations and the personalized recommendation information, the process includes: The obesity survey information, communication content information, and customized weight loss suggestions of the target customers are used to generate a weight loss service knowledge graph; The weight loss service knowledge graph is continuously updated based on the target customer's subsequent weight loss actions to obtain the target updated knowledge graph; Based on the weight loss service knowledge graph and the goal update knowledge graph, weight loss effect analysis is performed, and goal adjustment suggestions are generated.

7. The method according to claim 4, characterized in that, Before inputting the target prompt word template and the communication content information into the pre-trained weight loss service model to generate personalized suggestion information through the weight loss service model, the process also includes pre-training with the weight loss service model, specifically including: Acquire weight loss knowledge data; wherein, the weight loss knowledge data includes theoretical knowledge data adapted to different customer status information; Obtain a model training set; wherein the model training set includes multiple weight loss service training samples corresponding to different customer status information, and each weight loss service training sample is configured with corresponding suggestion sample information; Based on the weight loss service training samples corresponding to the same customer status information and the weight loss knowledge data, the original weight loss service big model is input to generate suggested training information; The comparison is performed between the suggested training information and the suggested sample information corresponding to the weight loss service training sample to obtain the comparison deviation data. The model parameters of the weight loss service big model are updated based on the comparison bias data to obtain the pre-trained weight loss service big model.

8. A device for generating customized weight loss suggestions, characterized in that, The device includes: The obesity information survey module is used to obtain obesity survey information and survey communication information corresponding to the target customers based on preset obesity information survey items. A general suggestion providing module is used to determine a target general suggestion from a set of multiple candidate general suggestions based on the obesity survey information; The speech recognition module is used to perform speech recognition based on the survey communication information to obtain the communication content information corresponding to the target customer; The prompt word template determination module is used to determine the target prompt word template from a plurality of preset candidate prompt word templates based on the obesity survey information corresponding to the target customer; The large model analysis module is used to input the target prompt word template and the communication content information into a pre-trained large model for weight loss services, so as to generate personalized suggestion information through the large model for weight loss services; The weight loss suggestion module is used to determine customized weight loss suggestions based on the general suggestions for the target and the personalized suggestion information.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the customized weight loss suggestion generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the customized weight loss suggestion generation method according to any one of claims 1 to 7.

Images