Product optimization suggestion generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a product optimization suggestion generation method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for financial science and technology scenes. The method comprises the steps of obtaining a product demand document of a first product, and obtaining original user behavior characteristics of an interaction object and the first product; performing index extraction on the product demand document to obtain a product optimization index; performing behavior feature extraction on the original user behavior features to obtain target behavior features of the interaction object; performing user portrait construction on the interaction object based on the target behavior characteristics to obtain a target user portrait; performing information extraction on the market feedback information of the second product to obtain a preliminary product optimization suggestion of the first product; and performing suggestion generation based on the product optimization index, the target user portrait and the preliminary product optimization suggestion to obtain a target product optimization suggestion of the first product. According to the embodiment of the invention, the accuracy of product optimization suggestions can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology and is applicable to financial technology scenarios, and in particular to a method and device for generating product optimization suggestions, an electronic device, and a storage medium. Background Art

[0002] Product design is an iterative product technology that integrates market data, user needs, and other information to rapidly generate optimization recommendations and assist in decision-making. Product design can be applied across multiple scenarios. For example, in finance, insurance product design primarily relies on product managers determining the product's features and functionality based on market demand and risk assessment. Typically, product design begins with an evaluation based on user feedback and market performance of the current product, generating optimization recommendations, which are then used for product design. However, in actual application, ambiguous requirements and unclear product direction may exist, impacting the accuracy of these recommendations.

[0003] Therefore, how to improve the accuracy of product optimization suggestions has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a method and device for generating product optimization suggestions, an electronic device and a storage medium, aiming to improve the accuracy of product optimization suggestions.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application provides a method for generating product optimization suggestions, the method comprising:

[0006] Obtaining a product requirement document for a first product, and obtaining original user behavior characteristics of an interaction object and the first product;

[0007] Extracting indicators from the product requirement document to obtain product optimization indicators;

[0008] Performing behavior feature extraction on the original user behavior feature to obtain the target behavior feature of the interaction object;

[0009] Constructing a user profile for the interactive object based on the target behavior characteristics to obtain a target user profile for the interactive object;

[0010] Extracting information from pre-acquired market feedback information for the second product to obtain preliminary product optimization suggestions for the first product; wherein the product category of the second product is the same as that of the first product;

[0011] Suggestions are generated based on the product optimization index, the target user portrait and the preliminary product optimization suggestions to obtain target product optimization suggestions for the first product.

[0012] In some embodiments, generating a recommendation based on the product optimization index, the target user profile, and the preliminary product optimization recommendation to obtain a target product optimization recommendation for the first product includes:

[0013] Perform function design based on the product optimization indicators, the target user profile, and the preliminary product optimization suggestions to obtain target product functions;

[0014] Perform product design based on the target product functions to obtain an initial product prototype;

[0015] Performing product testing on the initial product prototype to obtain prototype test feedback information;

[0016] Information is integrated based on the prototype test feedback information and the preliminary product optimization suggestions to obtain the target product optimization suggestions for the first product.

[0017] In some embodiments, extracting the pre-acquired market feedback information of the second product to obtain preliminary product optimization suggestions for the first product includes:

[0018] performing function preference identification on the market feedback information of the second product to obtain a function preference of the second product;

[0019] Performing user emotion recognition on the market feedback information of the second product to obtain an emotional preference for the second product;

[0020] performing trend identification on the market feedback information of the second product to obtain original product trend information;

[0021] generating function optimization suggestion information based on the second product function preference and the second product emotional preference;

[0022] Information integration is performed based on the function optimization suggestion information and the product trend information to obtain the preliminary product optimization suggestion for the first product.

[0023] In some embodiments, constructing a user profile for the interactive object based on the target behavior characteristics to obtain a target user profile of the interactive object includes:

[0024] Clustering the interacting objects based on the target behavior characteristics to obtain an object group;

[0025] For each of the object groups, performing demand analysis on the target behavior characteristics to obtain group demand characteristics, and performing emotion analysis on the target behavior characteristics to obtain group emotion characteristics;

[0026] Generate a profile of the target group based on the group demand characteristics and the group emotional characteristics to obtain a group user profile;

[0027] For each object group, the group user portrait is determined as the user portrait of each of the interactive objects in the object group to obtain the target user portrait of the interactive object.

[0028] In some embodiments, extracting indicators from the product requirement document to obtain product optimization indicators includes:

[0029] Extracting indicator entities from the product requirement document to obtain candidate optimization indicators;

[0030] Perform semantic analysis on the product requirement document to obtain target optimization demands;

[0031] The alternative optimization indicators are quantified based on the target optimization requirements to obtain the product optimization indicators.

[0032] In some embodiments, extracting behavior features from the original user behavior features to obtain target behavior features of the interactive object includes:

[0033] Performing feature preprocessing on the original user behavior features to obtain original behavior coding features;

[0034] Performing behavior extraction on the original behavior coding features to obtain initial behavior features;

[0035] The initial behavior features are screened based on preset behavior rules to obtain the target behavior features of the interactive object.

[0036] In some embodiments, performing feature preprocessing on the original user behavior features to obtain original behavior coding features includes:

[0037] Performing data cleaning on the original user behavior features to obtain cleaned interaction features;

[0038] performing standardization processing on the cleaning interaction feature to obtain a standardized interaction feature;

[0039] Perform feature coding processing on the standardized interaction features to obtain the original behavior coding features.

[0040] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a device for generating product optimization suggestions, the device comprising:

[0041] A first product information acquisition module is used to obtain a product requirement document for a first product and obtain original user behavior characteristics of an interaction object and the first product;

[0042] An indicator extraction module, used to extract indicators from the product requirement document to obtain product optimization indicators;

[0043] A behavior feature extraction module is used to extract the behavior features of the original user behavior features to obtain the target behavior features of the interaction object;

[0044] A user portrait construction module is used to construct a user portrait of the interactive object based on the target behavior characteristics to obtain a target user portrait of the interactive object;

[0045] a second product information extraction module configured to extract information from pre-acquired market feedback information about a second product to obtain preliminary product optimization suggestions for the first product; wherein the product category of the second product is the same as that of the first product;

[0046] A product suggestion generation module is used to generate suggestions based on the product optimization index, the target user portrait and the preliminary product optimization suggestions to obtain a target product optimization suggestion for the first product.

[0047] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0048] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0049] The product optimization suggestion generation method and device, electronic device, and storage medium proposed in this application obtain the product requirements document for the first product, obtain the original user behavior characteristics of the interactive object and the first product, perform indicator extraction on the product requirements document to obtain product optimization indicators, and perform behavior feature extraction on the original user behavior characteristics to obtain the target behavior characteristics of the interactive object. This ensures that the optimization work closely aligns with the core product requirements and actual user behavior. Furthermore, based on the target behavior characteristics, a user profile is constructed for the interactive object to obtain the target user profile of the interactive object, making the optimization direction more precise and directly addressing the core needs of the target user group. Next, market feedback information for a second product in the same product category is extracted to obtain preliminary product optimization suggestions, which can identify market trends and guide the design of the first product. Finally, based on the product optimization indicators, target user profile, and preliminary product optimization suggestions, suggestions are generated to obtain target product optimization suggestions for the first product. These suggestions are not only comprehensive and feasible, but can significantly improve the accuracy of product optimization suggestions, helping to enhance the product's user experience and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flowchart of a method for generating product optimization suggestions provided by an embodiment of the present application;

[0051] Figure 2 yes Figure 1 Flowchart of step S102 in FIG.

[0052] Figure 3 yes Figure 1 Flowchart of step S105 in FIG.

[0053] Figure 4 yes Figure 3 Flowchart of step S302 in FIG.

[0054] Figure 5 yes Figure 3 Flowchart of step S304 in FIG.

[0055] Figure 6 yes Figure 5 Flowchart of step S502 in FIG.

[0056] Figure 7 yes Figure 1 Flowchart of step S106 in FIG.

[0057] Figure 8 This is a schematic diagram of the structure of the device for generating product optimization suggestions provided in an embodiment of the present application;

[0058] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0060] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0062] First, let’s analyze some of the terms used in this application:

[0063] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner 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 thinking. It also encompasses the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0064] Natural language processing (NLP): NLP uses computers to process, understand, and apply human languages (such as Chinese and English). A branch of artificial intelligence, NLP is an interdisciplinary field between computer science and linguistics, often referred to as computational linguistics. Natural language processing encompasses grammatical analysis, semantic analysis, and discourse comprehension. Natural language processing is commonly used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis, and opinion mining. It encompasses data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research related to language processing, and linguistics research related to language computing.

[0065] Information Extraction: A text processing technology that extracts specified types of entity, relationship, event, and other factual information from natural language text and forms structured data output. Information extraction is a technology that extracts specific information from text data. Text data is composed of some specific units, such as sentences, paragraphs, and chapters. Text information is composed of some small specific units, such as characters, words, phrases, sentences, paragraphs, or a combination of these specific units. Extracting noun phrases, names, place names, etc. from text data is all text information extraction. Of course, the information extracted by text information extraction technology can be of various types.

[0066] Product design is a product iteration technique that integrates market data, user needs, and other information to quickly generate optimization suggestions and assist in decision-making. Product design can be applied to multiple scenarios. For example, in the financial sector, the design of insurance products primarily involves product managers determining the features and functions of insurance products based on market demand and risk assessment.

[0067] Typically, when designing a product, the product manager first evaluates the current product based on user feedback and market performance, draws product optimization recommendations, and then designs the product based on these recommendations. However, in actual application, there may be ambiguous requirements, unclear product direction, and difficulty in determining the core product functions. These factors affect the accuracy of the product optimization recommendations, and consequently, the progress of product design and the quality of the product.

[0068] In addition, since product design relies on the personal abilities of product managers, in actual use, product managers have limited time and energy, making it difficult to conduct comprehensive analysis. Consequently, the product may become outdated before it is launched, user feedback may not be timely after the product is launched, making it difficult to iterate and optimize the product, or there may be many similar products on the market, making it difficult to highlight differentiated advantages. These situations may also affect the accuracy of product optimization suggestions.

[0069] Based on this, the embodiments of the present application provide a method and device for generating product optimization suggestions, an electronic device, and a storage medium, aiming to improve the accuracy of product optimization suggestions.

[0070] The product optimization suggestion generating method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the product optimization suggestion generating method in the embodiments of the present application is described.

[0071] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0072] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0073] The product optimization suggestion generation method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The product optimization suggestion generation method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the product optimization suggestion generation method, etc., but is not limited to the above forms.

[0074] The present application can be used in many general or special computer system environments or configurations. For example: 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, distributed computing environments including any of the above systems or devices, and the like. The present 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, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0075] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0076] Figure 1 This is an optional flowchart of the method for generating product optimization suggestions provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0077] Step S101: obtaining a product requirement document of a first product and obtaining original user behavior characteristics of an interaction object and the first product;

[0078] Step S102: extracting indicators from the product requirement document to obtain product optimization indicators;

[0079] Step S103, extracting behavioral features from the original user behavioral features to obtain target behavioral features of the interaction object;

[0080] Step S104: constructing a user profile for the interaction object based on the target behavior characteristics to obtain a target user profile of the interaction object;

[0081] Step S105: extracting information from the pre-acquired market feedback information of the second product to obtain preliminary product optimization suggestions for the first product; wherein the product category of the second product is the same as that of the first product;

[0082] Step S106: Generate recommendations based on the product optimization indicators, the target user profile, and the preliminary product optimization recommendations to obtain target product optimization recommendations for the first product.

[0083] In the steps S101 to S106 shown in the embodiment of the present application, by obtaining the product requirement document of the first product, obtaining the original user behavior characteristics of the interactive object and the first product, and extracting indicators from the product requirement document to obtain product optimization indicators, and extracting behavior characteristics from the original user behavior characteristics to obtain the target behavior characteristics of the interactive object, it is ensured that the product design closely fits the core needs of the product and the actual behavior of the user. Furthermore, based on the target behavior characteristics, a user portrait of the interactive object is constructed to obtain the target user portrait of the interactive object, so that the optimization direction is more accurate and can directly hit the core needs of the target user group. Then, the market feedback information of the second product of the same product category is extracted to obtain preliminary product optimization suggestions, which can identify market trends and guide the design of the first product. Finally, based on the product optimization indicators, target user portraits and preliminary product optimization suggestions, suggestions are generated to obtain target product optimization suggestions for the first product, which are not only comprehensive and feasible, but can also significantly improve the accuracy of product optimization suggestions, and help improve the user experience and market competitiveness of the product.

[0084] In step S101 of some embodiments, the product requirement document for the first product is compiled by the product manager to determine the content of the core optimization objectives of the first product. This product requirement document achieves traceability of "demand-solution-verification" by clarifying indicators, functions, and data closed loops, reflecting the core value of the big model in the precision and quantification of requirements. For example:

[0085] In the FinTech scenario, the product requirements document for health insurance products is:

[0086] Product Objective: Based on big model-driven data analysis, optimize the user experience and conversion efficiency of health insurance products, and focus on improving the following indicators:

[0087] User retention: 30-day policy renewal rate increased by 15%;

[0088] Conversion efficiency: The conversion rate of the insurance application process increased from 22% to 30%;

[0089] NPS improvement: Net Promoter Score improved from +35 to +50;

[0090] Functional requirements: Realize intelligent underwriting and automated claims processing;

[0091] Data support: Analyze user insurance purchase history, claims complaint texts, and the market performance of competing health insurance products to output quantifiable product optimization suggestions.

[0092] Interaction partners are users who interact with the first product through channels such as the product platform and product webpage. Interactions include, but are not limited to, purchases, comments, feedback, and browsing. Therefore, the original user behavior features are the interaction partners' purchase, comment, feedback, and browsing behaviors for the first product.

[0093] See also Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S203:

[0094] Step S201: extract indicator entities from the product requirement document to obtain candidate optimization indicators;

[0095] Step S202: semantically analyze the product requirement document to obtain target optimization requirements;

[0096] Step S203: quantify the candidate optimization indicators based on the target optimization requirement to obtain product optimization indicators.

[0097] In steps S201 to S203 shown in the embodiment of the present application, by extracting indicator entities from the product requirement document, potential optimization points can be quickly identified and at least one alternative optimization indicator can be obtained. Next, a semantic analysis is performed on the product requirement document to deeply explore the core optimization demands in the document to ensure the accuracy of the optimization direction. Finally, the alternative optimization indicators are quantified based on the target optimization demands to obtain product optimization indicators, which not only improves the pertinence and efficiency of product optimization, but also helps to improve the accuracy of product optimization suggestions.

[0098] In step S203 of some embodiments, indicator entities can be extracted from the product requirement document using a pre-trained entity extraction model to obtain at least one candidate optimization indicator. The entity extraction model can be, but is not limited to, a large model, a deep learning-based extraction model (such as a BiLSTM-CRF combination model or a BERT model), a statistical learning model (such as a hidden Markov model (HMM) and a conditional random field model (CRF)), etc. However, the training data for the entity extraction model needs to be combined with specific application scenarios and trained using annotated product requirement documents.

[0099] In step S202 of some embodiments, a pre-trained semantic analysis model is used to perform semantic analysis on the product requirement document to obtain the optimization requirements corresponding to each candidate optimization indicator. The semantic analysis model can be a large model, a BERT model, a Word2Vec model, etc., but is not limited thereto.

[0100] In another embodiment, the same large model can be used to simultaneously implement indicator entity extraction and semantic analysis of the product requirement document to obtain alternative optimization indicators and target optimization demands.

[0101] Finally, the target optimization demands are matched with the alternative optimization indicators, and then the matched indicators are quantified, that is, specific quantitative standards or thresholds are set to obtain product optimization indicators.

[0102] For example, in a fintech scenario, the product requirements document for health insurance products is:

[0103] Product Objective: Based on big model-driven data analysis, optimize the user experience and conversion efficiency of health insurance products, and focus on improving the following indicators:

[0104] User retention: 30-day policy renewal rate increased by 15%;

[0105] Conversion efficiency: The conversion rate of the insurance application process increased from 22% to 30%;

[0106] NPS improvement: Net Promoter Score improved from +35 to +50;

[0107] Functional requirements: Realize intelligent underwriting and automated claims processing;

[0108] Data support: Analyze user insurance purchase history, claims complaint texts, and the market performance of competing health insurance products to output quantifiable product optimization suggestions.

[0109] By extracting indicator entities from the product requirement document, three alternative optimization indicators are obtained: user retention rate, insurance conversion rate, and NPS.

[0110] By conducting semantic analysis on the product requirement document, we obtained the target optimization demands, namely: increase user retention rate by 15%, increase insurance conversion rate to 30%, and increase NPS to +50.

[0111] Finally, the target optimization demands were quantified against the alternative optimization indicators to obtain product optimization indicators, which were: user retention rate - increased by 15%, insurance conversion rate - increased to 30%, and NPS - increased to +50.

[0112] See also Figure 3In some embodiments, step S103 may include but is not limited to steps S301 to S303:

[0113] Step S301, performing feature preprocessing on the original user behavior features to obtain original behavior coding features;

[0114] Step S302, extracting behavior from the original behavior coding features to obtain initial behavior features;

[0115] Step S303: Screening the initial behavior features based on preset behavior rules to obtain target behavior features of the interaction object.

[0116] In the steps S301 to S303 shown in the embodiment of the present application, by pre-processing the original user behavior features, it is possible to eliminate outliers and deviations in the data and obtain cleaner and standardized original behavior coding features. Next, behavior extraction is performed on the original behavior coding features to extract key information about user behavior and form initial behavior features, which helps to focus on the core behavior patterns of users. Finally, the initial behavior features are screened based on preset behavior rules to eliminate irrelevant or redundant features, accurately lock in the target behavior features that are directly related to the interactive object, and help improve the relevance and accuracy of the features.

[0117] See also Figure 4 In some embodiments, step S301 may include but is not limited to steps S401 to S403:

[0118] Step S401: clean the original user behavior features to obtain cleaned interaction features;

[0119] Step S402, normalizing the cleaning interaction features to obtain standardized interaction features;

[0120] Step S403: performing feature coding processing on the standardized interaction features to obtain original behavior coding features.

[0121] In the steps S401 to S403 shown in the embodiment of the present application, by performing data cleaning on the original user behavior features, errors, duplications or irrelevant information in the original user behavior features can be eliminated, thereby ensuring the accuracy and consistency of the interaction features. Next, the cleaned interaction features are standardized to eliminate the dimensional differences between different features, which helps to improve the stability and accuracy of data analysis. Finally, the standardized interaction features are feature coded to convert them into a format that is easy for computers to process, while retaining key information to form original behavior coding features, providing efficient and reliable data input for subsequent behavior extraction and model training.

[0122] In step S401 of some embodiments, data cleaning includes but is not limited to the following steps: deduplication processing (eliminating duplicate records), missing value processing (filling or removing incomplete data), and outlier detection (excluding data outside a reasonable range).

[0123] For example, for health insurance products, multiple conversations between the same interacting party and product customer service are merged to avoid duplicate session information. Furthermore, if the interacting party has not commented on or provided feedback about the health insurance product, the corresponding data field is filled with a preset value, such as 0. If the interacting party frequently comments on or purchases health insurance products within a short period of time, these are marked as outliers and filtered out.

[0124] In step S402 of some embodiments, the cleaning interaction features after cleaning are standardized, such as by unifying the time granularity and the numerical unit, etc., to help improve the stability and accuracy of data analysis.

[0125] In step S403 of some embodiments, one-hot encoding, binary encoding, etc. can be used to perform feature encoding processing on the standardized interaction features to obtain original behavior encoding features, which is conducive to improving the efficiency of subsequent processing.

[0126] In step S302 of some embodiments, at least one initial behavior feature is obtained by extracting behavior features from the original behavior coding features using a pre-trained behavior recognition model. Alternatively, a large model may be used to extract behavior features from the original behavior coding features, without limitation.

[0127] For example, for health insurance products, the interaction object A has the following initial behavior characteristics towards health insurance products:

[0128] Browse health insurance products multiple times;

[0129] Posted two feedback comments in the product discussion forum and contacted product customer service several times;

[0130] After purchasing the health insurance product, a comment was posted in the comment section;

[0131] Initiate a refund request 2 days after purchasing a health insurance product;

[0132] Purchasing health insurance products again 10 days after the refund;

[0133] An accident occurred 7 months after purchasing the health insurance product, and the claim amount was 5,000 yuan.

[0134] It should be noted that the preset behavioral rules include but are not limited to: purchasing products, refunds, comments, etc. In health insurance products, the preset behavioral rules can be purchasing health insurance products (insurance), claim settlement, renewal or cancellation, etc.

[0135] In step S303 of some embodiments, based on preset behavior rules, a target behavior feature is obtained by screening out a feature that can reflect the actual operation behavior of the interactive object on the first product from a plurality of initial behavior features.

[0136] For example, for health insurance products, by screening multiple initial behavioral characteristics of interaction object A and health insurance products, the following target behavioral characteristics are obtained:

[0137] When purchasing health insurance products;

[0138] Initiate a refund request 2 days after purchasing a health insurance product;

[0139] Purchasing health insurance products again 10 days after the refund;

[0140] An accident occurred 7 months after purchasing the health insurance product, and the claim amount was 5,000 yuan.

[0141] It's understandable that the target behavioral characteristics obtained after screening are key data closely related to the interactive subject's sales and market performance in the first product. Analyzing these target behavioral characteristics allows for a more accurate understanding of the interactive subject's actual needs and preferences for the first product. This not only helps identify potential issues and areas for improvement in the first product's use, but also provides strong data support for the first product's optimization strategy, thereby driving continuous product improvement and enhancing market competitiveness.

[0142] See also Figure 5 In some embodiments, step S104 may also include but is not limited to steps S501 to S504:

[0143] Step S501: clustering the interaction objects based on the target behavior characteristics to obtain object groups;

[0144] Step S502: for each target group, performing demand analysis on the target behavior characteristics to obtain group demand characteristics, and performing emotion analysis on the target behavior characteristics to obtain group emotion characteristics;

[0145] Step S503: Generate a profile of the target group based on the group demand characteristics and group emotion characteristics to obtain a group user profile;

[0146] Step S504 : for each object group, the group user portrait is determined as the user portrait of each interactive object in the object group to obtain the target user portrait of the interactive object.

[0147] Steps S501 to S504 shown in the embodiment of the present application can reduce the clustering of interactive objects based on target behavioral characteristics by clustering the interactive objects based on target behavioral characteristics. Subsequently, for each object group, the target behavioral characteristics are subjected to demand analysis and sentiment analysis to obtain group demand characteristics and group sentiment characteristics, thereby excavating the deep common characteristics of the group, and generating a portrait of the object group based on the group demand characteristics and group sentiment characteristics to obtain a group user portrait, which helps to grasp the overall trend of the user group at a macro level. Finally, the group user portrait determines the user portrait of each interactive object in the object group, thereby achieving accurate understanding and classification of each interactive object.

[0148] In step S501 of some embodiments, methods such as the K-Means algorithm and the DBSCAN algorithm may be used to cluster the interactive objects based on target behavior characteristics to obtain object groups, each of which includes multiple interactive users.

[0149] In step S502 of some embodiments, for each object group, the target behavior characteristics corresponding to the object group are obtained, and the target behavior characteristics are subjected to demand analysis using topic modeling. Specifically, the target behavior characteristics can be subjected to demand topic modeling using an LDA model to obtain the group's demand characteristics.

[0150] In addition, a pre-trained sentiment analysis model can be used to perform sentiment analysis on target behavior characteristics to obtain group sentiment characteristics; wherein the sentiment analysis model can be a BERT model, a support vector machine model, a neural network model, etc., but is not limited thereto.

[0151] In step S503 of some embodiments, a large model may be used to generate a profile of the target group based on group demand characteristics and group sentiment characteristics to obtain a group user profile, wherein the group user profile is used to guide the first product to perform different recommendation / sales / maintenance actions for different target groups.

[0152] For example, if the group object portrait is an insured object, more user rights and interests can be allocated when maintaining this group object in the future. This idea needs to be reflected in subsequent product design.

[0153] It is understandable that the object group includes multiple interactive objects, and the group user portrait corresponding to the group object is the user portrait of each interactive object.

[0154] In other embodiments, the same large model may be used to simultaneously cluster the interactive objects and construct a group user portrait for each object group, that is, to use a large model to execute the embodiments illustrated in steps S501 to S503 above.

[0155] See also Figure 6 In some embodiments, step S105 includes but is not limited to steps S601 to S605:

[0156] Step S601, performing function preference identification on the market feedback information of the second product to obtain the function preference of the second product;

[0157] Step S602: Perform user emotion recognition on the market feedback information of the second product to obtain the emotional preference of the second product;

[0158] Step S603: performing trend identification on the market feedback information of the second product to obtain original product trend information;

[0159] Step S604: generating function optimization suggestion information based on the second product function preference and the second product emotional preference;

[0160] Step S605 : integrating the function optimization suggestion information and the product trend information to obtain preliminary product optimization suggestions for the first product.

[0161] In steps S601 to S605 shown in the embodiment of the present application, by performing functional preference identification, user emotion identification, and trend identification on the market feedback information of the second product, the second product functional preference, the second product emotional preference, and the original product trend information are obtained, which helps to accurately identify the user's functional preference and emotional preference for the product, and study and judge the development direction of the market. Furthermore, based on the second product functional preference and the second product emotional preference, functional optimization suggestion information is generated, and then the functional optimization suggestion information and the product trend information are integrated to obtain preliminary product optimization suggestions, which helps to improve the accuracy of the product optimization suggestions, can more accurately guide the optimization design of the first product, design products that meet user preferences and conform to market trends, and maintain market competitiveness.

[0162] In some embodiments, the second product is of the same product category as the first product, and is a product of the same type, but the second product is a competitor of the first product in the market. There can be multiple second products, but there can only be one first product.

[0163] Since the second product is a competing product, it is difficult to obtain internal information about the product. Therefore, the market feedback information of the second product is relevant data obtained through public channels, including but not limited to: functional information of the second product, user evaluation information of the second product, and market performance information of the second product.

[0164] It is understandable that by obtaining market feedback data from competitors, we (the first product) can adjust our product strategy more quickly and maintain market competitiveness based on the performance of competitors' products. If competitors launch new features but the results are not good, we can optimize our own products based on the market response of competitors to seize the market.

[0165] Based on this, we can identify the functional preferences of users for the second product by performing functional information identification on the functional information in the market feedback information of the second product. We can also identify which functions in the second product are highly praised, and provide ideas for the product optimization design of the first product.

[0166] By performing user sentiment recognition on the user evaluation information in the market feedback for the second product, users' emotional preferences for the second product can be determined. This allows users to assess their evaluations of the second product and, consequently, determine the market response to the second product. If the emotional preference for the second product indicates a high degree of user favorability, the first product can incorporate the excellent design ideas of the second product during its optimization design. If the emotional preference for the second product indicates a low degree of user favorability, the first product should avoid incorporating the design ideas of the second product during its optimization design.

[0167] By performing trend identification on the market performance information in the market feedback information of the second product, product trend information of the second product can be obtained, thereby knowing the market share and development trend of similar products in the market.

[0168] In some embodiments, the same large model can be used to perform function preference identification, user emotion identification, and trend identification on the market feedback information of the second product to obtain the second product function preference, the second product emotion preference, and the original product trend information.

[0169] It is understandable that the user's emotional preference for the second product includes some emotional preference information for the functions of the second product. Based on this emotional preference information for the functions, it can be determined which product functions are more valuable for application, and this function can be introduced when designing the first product.

[0170] For example, among health insurance products, users have a higher evaluation of the shorter insurance review time in the second product. Therefore, the generated function optimization suggestion information includes: "Optimization suggestion: shorten the insurance review time."

[0171] In step S605 of some embodiments, the function optimization suggestion information and the product trend information are integrated to obtain preliminary product optimization suggestions. The preliminary product optimization suggestions are preliminary ideas to guide the product design of the first product. However, since they are based on the second product, they are not completely applicable to the first product. Therefore, product design still needs to be combined with the actual situation of the first product.

[0172] See also Figure 7 In some embodiments, step S106 may include but is not limited to steps S701 to S704:

[0173] Step S701: Perform function design based on product optimization indicators, target user profiles, and preliminary product optimization suggestions to obtain target product functions;

[0174] Step S702: Perform product design based on the target product function to obtain an initial product prototype;

[0175] Step S703: Perform product testing on the initial product prototype to obtain prototype test feedback information;

[0176] Step S704 : integrating information based on the prototype test feedback information and the preliminary product optimization suggestions to obtain target product optimization suggestions for the first product.

[0177] In steps S701 to S704 shown in the embodiment of the present application, by performing functional design based on product optimization indicators, target user portraits and preliminary product optimization suggestions, at least one target product function is obtained, which can meet the requirements of product optimization indicators and meet the functional needs of interactive objects, thereby improving the pertinence and accuracy of product design. On this basis, product design is performed according to the target product function to obtain an initial product prototype, and product testing is performed on the initial product prototype, which can verify the feasibility of the product function and can be verified before the product is released to avoid design errors. Finally, information integration is performed based on prototype test feedback information and preliminary product optimization suggestions, and the target product optimization suggestions obtained are not only comprehensive, but also have high feasibility and accuracy, ensuring that the first product designed based on the target product optimization suggestion can not only meet user needs, but also have high market competitiveness.

[0178] It's important to note that different target user profiles correspond to different interaction objects with their own desired functionality. For example, in health insurance products, if the target user profile is the insured, then the product design requires the addition of a function to allocate benefits to these interaction objects. Preliminary product optimization recommendations include product features with high preference or recommended for introduction.

[0179] Therefore, in step S701 of some embodiments, it is necessary to perform function design in combination with the target user portrait and preliminary product optimization suggestions, and adjust the importance of the function based on the product optimization index to obtain the target product function required by the first product in the current product design.

[0180] In step S702 of some embodiments, based on the target product's functionality, a digital tool is used to draw the basic layout and functional modules of the first product, resulting in a prototype sketch. During the design process, attention should be paid to the user interface and user experience. Furthermore, the prototype sketch is converted into a structured wireframe, clarifying the page layout, functional location, and interaction logic. Finally, an interactive visual scheme for the first product is designed, resulting in an initial product prototype.

[0181] In step S703 of some embodiments, the initial product prototype is subjected to product testing. The product testing process includes but is not limited to the following steps:

[0182] Determine product testing objectives, including login, browsing, purchase, refund, and customer service consultation;

[0183] Determine the product testing tool type, design product test cases based on the product testing tool type, and generate product test scripts based on the product test cases;

[0184] Execute the product test script and obtain prototype test feedback information, wherein the prototype test feedback information includes product function verification results and user interface test results.

[0185] After product testing of the initial product prototype, the prototype test feedback information is integrated with the preliminary product optimization suggestions to obtain the target product optimization suggestions, which are used to guide the product design of the first product.

[0186] In some embodiments, the same pre-trained large model can be used to execute the specific implementation method indicated by the above-mentioned product optimization suggestion generation method. By extracting information from the product requirement document of the first product and the corresponding product requirement document, and combining the market feedback information of the second product to generate preliminary product optimization suggestions for the first product, the product design cycle can be shortened, and accurate and comprehensive product optimization suggestions can be obtained, helping product managers to perform product iterative optimization more efficiently and improve decision-making quality and user experience.

[0187] See also Figure 8 The embodiment of the present application further provides a device for generating product optimization suggestions, which can implement the above-mentioned method for generating product optimization suggestions. The device includes:

[0188] The first product information acquisition module 801 is used to obtain the product requirement document of the first product and obtain the original user behavior characteristics of the interaction object and the first product;

[0189] The indicator extraction module 802 is used to extract indicators from the product requirement document to obtain product optimization indicators;

[0190] The behavior feature extraction module 803 is used to extract the original user behavior features to obtain the target behavior features of the interaction object;

[0191] A user portrait construction module 804 is used to construct a user portrait of the interactive object based on the target behavior characteristics to obtain a target user portrait of the interactive object;

[0192] The second product information extraction module 805 is used to extract information from the pre-acquired market feedback information of the second product to obtain preliminary product optimization suggestions for the first product; wherein the product category of the second product is the same as that of the first product;

[0193] The product suggestion generation module 806 is used to generate suggestions based on the product optimization index, the target user profile and the preliminary product optimization suggestions to obtain the target product optimization suggestions for the first product.

[0194] The specific implementation of the product optimization suggestion generating device is basically the same as the specific embodiment of the above-mentioned product optimization suggestion generating method, and will not be repeated here.

[0195] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method for generating product optimization suggestions. The electronic device can be any smart terminal, such as a tablet computer or an in-vehicle computer.

[0196] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0197] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an 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 the present application;

[0198] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. 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 by the processor 901 to execute the product optimization suggestion generation method of the embodiments of this application;

[0199] Input / output interface 903, used to implement information input and output;

[0200] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0201] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0202] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0203] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned product optimization suggestion generating method.

[0204] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0205] The product optimization suggestion generation method and device, electronic device and storage medium provided in the embodiment of the present application obtain the product requirement document of the first product, obtain the original user behavior characteristics of the interactive object and the first product, extract indicators from the product requirement document to obtain product optimization indicators, and extract behavior characteristics from the original user behavior characteristics to obtain the target behavior characteristics of the interactive object, thereby ensuring that the optimization work is closely aligned with the core needs of the product and the actual behavior of the user. Furthermore, a user portrait of the interactive object is constructed based on the target behavior characteristics to obtain the target user portrait of the interactive object, making the optimization direction more accurate and able to directly hit the core needs of the target user group. Then, information extraction is performed on the market feedback information of the second product of the same product category to obtain preliminary product optimization suggestions, which can identify market trends and guide the design of the first product. Finally, suggestions are generated based on the product optimization indicators, target user portraits and preliminary product optimization suggestions to obtain target product optimization suggestions for the first product. This is not only comprehensive and feasible, but can also significantly improve the accuracy of product optimization suggestions and help improve the user experience and market competitiveness of the product.

[0206] The embodiments described in the embodiments of this application are intended to more clearly illustrate 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. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0207] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0208] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0209] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0210] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0211] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0212] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0213] The units described above as separate components may or may not be physically separate, and 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 these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0214] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0215] If the integrated unit is implemented in the form of 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 the present application, 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, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0216] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A method for generating product optimization suggestions, characterized in that: The method comprises: Obtaining a product requirement document for a first product, and obtaining original user behavior characteristics of an interaction object and the first product; Extracting indicators from the product requirement document to obtain product optimization indicators; Performing behavior feature extraction on the original user behavior feature to obtain the target behavior feature of the interaction object; Constructing a user profile for the interactive object based on the target behavior characteristics to obtain a target user profile for the interactive object; Extracting information from pre-acquired market feedback information for the second product to obtain preliminary product optimization suggestions for the first product; wherein the product category of the second product is the same as that of the first product; Suggestions are generated based on the product optimization index, the target user portrait and the preliminary product optimization suggestions to obtain target product optimization suggestions for the first product.

2. The method according to claim 1, characterized in that Generating a suggestion based on the product optimization index, the target user profile, and the preliminary product optimization suggestion to obtain a target product optimization suggestion for the first product includes: Perform function design based on the product optimization indicators, the target user profile, and the preliminary product optimization suggestions to obtain target product functions; Perform product design based on the target product functions to obtain an initial product prototype; Performing product testing on the initial product prototype to obtain prototype test feedback information; Information is integrated based on the prototype test feedback information and the preliminary product optimization suggestions to obtain the target product optimization suggestions for the first product.

3. The method according to claim 1, characterized in that The extracting of the pre-acquired market feedback information of the second product to obtain preliminary product optimization suggestions for the first product includes: performing function preference identification on the market feedback information of the second product to obtain a function preference of the second product; Performing user emotion recognition on the market feedback information of the second product to obtain an emotional preference for the second product; performing trend identification on the market feedback information of the second product to obtain original product trend information; generating function optimization suggestion information based on the second product function preference and the second product emotional preference; Information integration is performed based on the function optimization suggestion information and the product trend information to obtain the preliminary product optimization suggestion for the first product.

4. The method according to claim 1, wherein The constructing a user profile of the interactive object based on the target behavior characteristics to obtain a target user profile of the interactive object includes: Clustering the interactive objects based on the target behavior characteristics to obtain an object group; For each of the object groups, performing demand analysis on the target behavior characteristics to obtain group demand characteristics, and performing emotion analysis on the target behavior characteristics to obtain group emotion characteristics; Generate a profile of the target group based on the group demand characteristics and the group emotional characteristics to obtain a group user profile; For each object group, the group user portrait is determined as the user portrait of each of the interactive objects in the object group to obtain the target user portrait of the interactive object.

5. The method according to any one of claims 1 to 4, characterized in that The extracting of indicators from the product requirement document to obtain product optimization indicators includes: Extracting indicator entities from the product requirement document to obtain candidate optimization indicators; Perform semantic analysis on the product requirement document to obtain target optimization demands; The alternative optimization indicators are quantified based on the target optimization requirements to obtain the product optimization indicators.

6. The method according to any one of claims 1 to 4, characterized in that The extracting behavior features from the original user behavior features to obtain target behavior features of the interaction object includes: Performing feature preprocessing on the original user behavior features to obtain original behavior coding features; Performing behavior extraction on the original behavior coding features to obtain initial behavior features; The initial behavior features are screened based on preset behavior rules to obtain the target behavior features of the interaction object.

7. The method according to claim 6, characterized in that The performing feature preprocessing on the original user behavior features to obtain original behavior coding features includes: Performing data cleaning on the original user behavior features to obtain cleaned interaction features; performing standardization processing on the cleaning interaction feature to obtain a standardized interaction feature; Perform feature coding processing on the standardized interaction features to obtain the original behavior coding features.

8. A device for generating product optimization suggestions, characterized in that: The device comprises: A first product information acquisition module is used to obtain a product requirement document for a first product and obtain original user behavior characteristics of an interaction object and the first product; An indicator extraction module, configured to extract indicators from the product requirement document to obtain product optimization indicators; A behavior feature extraction module is used to extract the behavior features of the original user behavior features to obtain the target behavior features of the interaction object; A user portrait construction module is used to construct a user portrait of the interactive object based on the target behavior characteristics to obtain a target user portrait of the interactive object; a second product information extraction module configured to extract information from pre-acquired market feedback information about a second product to obtain preliminary product optimization suggestions for the first product; wherein the product category of the second product is the same as that of the first product; A product suggestion generation module is used to generate suggestions based on the product optimization index, the target user portrait and the preliminary product optimization suggestions to obtain a target product optimization suggestion for the first product.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images