Complex product research and development oriented user experience attribute extraction and analysis method and system

Abstract

The invention provides a complex product research and development-oriented user experience attribute extraction and analysis method and system, and relates to the technical field of data analysis, the user experience attribute extraction and analysis method comprises the following steps: obtaining user generated content UGC related to a target new product, and preprocessing to obtain a target UGC data set; a target UGC data set is converted into a field-specific corpus, a BERT-based sentence embedding model is constructed, sentences are converted into high-dimensional sentence embedding vectors and clustered, user experience attributes obtained through clustering are integrated, the weight of each user experience attribute is calculated, an attribute system is generated, and iterative optimization is carried out. According to the method, through semantic analysis of the context, it is ensured that the extracted attributes better meet the actual requirements of the user; and carrying out integration and weight distribution on the user experience attributes obtained by clustering, generating an attribute system, carrying out iterative optimization, and outputting an optimized target attribute system to meet the requirements of user experience guidance and complex product research and development.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and specifically to a method and system for extracting and analyzing user experience attributes for complex product development. Background Art

[0002] With the rapid development of new generation information technology, the decision-making environment has become increasingly dynamic and complex, especially in the field of complex product research and development. Traditional user experience attribute design methods usually rely on predefined fixed attribute sets, which may be applicable in static environments, but the limitations of this approach become particularly obvious in rapidly changing market and technology environments. Traditional attribute systems are often based on standard literature or historical data, lack sensitivity to real-time market dynamics and user needs, and are difficult to adapt to the rapid evolution of today's technological innovation and market needs.

[0003] In the related technologies, in the face of the challenges of rapidly changing market and technological environments, traditional systems that rely on static attribute sets find it difficult to capture and reflect immediate changes in consumer preferences and behavioral trends. For example, consumer purchasing behavior and product preferences may change significantly in a short period of time, and traditional methods find it difficult to quickly adapt to these changes. Data-driven analytical methods provide a new way to address these challenges. Using user-generated content (UGC), including online comments, social media interactions, and direct user feedback, these real-time data can directly capture consumer behavior and preferences, providing immediate feedback for the continuous optimization of complex product development and services.

[0004] However, many existing user experience analysis systems rely on preset standard attribute sets, resulting in significant response lags when dealing with actual user experience; and are usually based on manually set attribute weight allocation schemes, which is not only highly subjective but also difficult to fully reflect the needs of actual users. Faced with complex, diverse and dynamic user experience data, existing models often lack flexibility in attribute extraction and weight allocation, making it difficult to achieve real-time response and dynamic adjustment. Summary of the invention

[0005] In response to the shortcomings of the existing technology, the present application provides a user experience attribute extraction and analysis method and system for complex product development, which solves the current problems in user experience attribute analysis, such as lack of flexibility in attribute extraction and weight allocation, difficulty in achieving real-time response and dynamic adjustment, and poor effectiveness and accuracy.

[0006] To achieve the above objectives, this application is implemented through the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for extracting and analyzing user experience attributes for complex product development, which includes: obtaining user-generated content (UGC) related to a target new product, and preprocessing it to obtain a target UGC data set; converting the target UGC data set into a domain-specific corpus for use in complex product development; constructing a BERT-based sentence embedding model to convert a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information; clustering sentences using sentence embedding vectors to determine potential user experience attributes; integrating the user experience attributes obtained by clustering, and calculating the weight of each user experience attribute to perform weight allocation; based on the results of the weight allocation, generating an attribute system and performing iterative optimization, and outputting the optimized target attribute system to meet the needs of user experience orientation and complex product development.

[0008] According to the first aspect of the embodiment of the present application, the aforementioned acquisition of user-generated content UGC related to the target new product and preprocessing to obtain the target UGC data set may specifically include the following steps: determining the target new product and keywords related to the target new product, and defining a related keyword list based on the characteristics of the new product; obtaining a UGC data set containing each keyword in the keyword list through an API interface or a web page parsing method; and performing data cleaning, deduplication, anonymization and formatting on the raw data in the UGC data set to obtain the target UGC data set.

[0009] According to the first aspect of the embodiment of the present application, the aforementioned conversion of the target UGC dataset into a domain-specific corpus for use in complex product development may specifically include the following steps: dividing the target UGC dataset into sentence-level datasets for fine-grained text analysis; performing lexical analysis and word segmentation processing, and using natural language processing tools to decompose each sentence in the sentence-level dataset into a sequence of words; constructing a domain-specific vocabulary, aggregating the words of all sentences to form a domain corpus; defining corpus quality assessment indicators to ensure the relevance and accuracy of the corpus; evaluating the quality of the corpus by calculating the value of the corpus quality assessment indicator, and if the corpus quality assessment indicator does not reach a preset threshold, re-dividing the target UGC dataset into sentence-level datasets;

[0010] Among them, the corpus quality evaluation index satisfies the expression:

[0011]

[0012] Among them, Q is the corpus quality evaluation index, N relevant Represents the number of relevant sentences extracted; N total Represents the total number of sentences in the corpus; N errors Indicates the number of errors or inconsistencies found in the corpus.

[0013] According to the first aspect of the embodiment of the present application, the aforementioned construction of a BERT-based sentence embedding model converts a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information. Specifically, the following steps may be included: loading a pre-trained BERT model, and fine-tuning it according to the domain corpus to obtain a domain-specific target BERT model; for each sentence in the sentence-level dataset, generating a high-dimensional sentence embedding vector using the target BERT model; representing the set of multiple sentence embedding vectors in matrix form, and introducing a piecewise soft relative cosine similarity measurement method to capture the semantic relationship between sentences.

[0014] According to the first aspect of the embodiment of the present application, the aforementioned clustering of sentences using sentence embedding vectors to determine potential user experience attributes may specifically include the following steps: using the UMAP algorithm to reduce the dimension of the sentence embedding vectors to a two-dimensional or three-dimensional space to obtain a vector set after dimensionality reduction; using the HDBSCAN algorithm to density cluster the reduced data, and automatically identify the cluster structure and noise points in the data to obtain clustering results; based on the clustering results, adjusting the hyperparameters of the UMAP algorithm and the HDBSCAN algorithm; wherein the hyperparameters of the UMAP algorithm include the number of neighbors and the minimum distance; the hyperparameters of the HDBSCAN algorithm include the minimum cluster size and the minimum number of samples; using preset evaluation indicators to evaluate the clustering results and select the optimal clustering model; the preset evaluation indicators include: silhouette coefficient, Calinski-Harabasz index and Davies Bouldin index; according to the clustering results, identifying the sentence set corresponding to each cluster, and determining the identified sentence set as a potential user experience attribute.

[0015] According to the first aspect of the embodiment of the present application, the user experience attributes obtained by clustering are integrated, and the weight of each user experience attribute is calculated to perform weight distribution. Specifically, the following steps may be included: extracting keywords in each attribute cluster corresponding to the user experience attribute, and constructing an attribute word set; using CountVectorizer to convert the attribute word set into a feature vector, and counting the frequency of occurrence of each word in the attribute cluster; calculating the attribute-level word frequency-inverse document frequency of each word to measure the importance of each word relative to the whole; calculating the weight of each attribute set, and normalizing the weight of each attribute set to obtain a first relative weight; calculating the second relative weight of each word in the attribute set to which it belongs, to characterize the importance of the word in the attribute set.

[0016] According to the first aspect of the embodiment of the present application, the aforementioned attribute system is generated and iteratively optimized based on the result of weight distribution, and the optimized target attribute system is output to meet the needs of user experience orientation and complex product development. Specifically, the following steps may be included: according to the first relative weight of the attribute set and the second relative weight of the attribute word, the first K attributes with higher weights are selected to construct the attribute system, wherein K is a positive integer; using a similarity measurement method, the similarity between attribute sets is calculated, and attribute sets with similarities higher than a preset similarity threshold are merged to reduce redundancy; wherein the similarity threshold is determined based on the average and standard deviation of multiple similarities; iteratively performing attribute merging and weight recalculation operations until the attribute system is stable, and outputting the optimized target attribute system and its corresponding target weight.

[0017] In the second aspect, an embodiment of the present application provides a user experience attribute extraction and analysis system for complex product development, which includes: an acquisition module, a first conversion module, a second conversion module, a clustering module, an integration module and an iterative optimization module; wherein the acquisition module is used to acquire user-generated content UGC related to the target new product, and pre-process it to obtain a target UGC data set; the first conversion module is used to convert the target UGC data set into a domain-specific corpus for use in complex product development; the second conversion module is used to build a BERT-based sentence embedding model, and convert a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information; the clustering module is used to cluster sentences using sentence embedding vectors to determine potential user experience attributes; the integration module is used to integrate the user experience attributes obtained by clustering, and calculate the weight of each user experience attribute to perform weight allocation; the iterative optimization module is used to generate an attribute system and perform iterative optimization based on the results of weight allocation, and output the optimized target attribute system to meet the needs of user experience orientation and complex product development.

[0018] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method for extracting and analyzing user experience attributes for complex product development in the aforementioned first aspect is implemented.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a program or instruction, which, when executed by a processor, implements the user experience attribute extraction and analysis method for complex product development in the aforementioned first aspect.

[0020] This application provides a method and system for extracting and analyzing user experience attributes for complex product development. Compared with the prior art, it has the following beneficial effects:

[0021] This application proposes a method for extracting and analyzing user experience attributes, which is based on user-generated content (UGC) and combined with natural language processing technology for automated processing. This application converts the target UGC data set into a corpus, introduces a sentence embedding model based on BERT, enhances the semantic understanding ability of attribute extraction, and ensures the accuracy of the analysis results. The sentence embedding model converts a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information, and clusters the sentences to determine potential user experience attributes; through semantic analysis of the context, it is ensured that the extracted attributes are more in line with the actual needs of users; then the user experience attributes obtained by clustering are integrated and weighted, an attribute system is generated and iteratively optimized, and the optimized target attribute system is output to meet the needs of user experience orientation and complex product development. The present invention application can effectively process long texts and large-scale corpora, reduce computational complexity, and provide more reliable data support for complex product development. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a flow chart of a method for extracting and analyzing user experience attributes for complex product development provided in an embodiment of the present application;

[0024] Figure 2 yes Figure 1 An exemplary flow chart of S120;

[0025] Figure 3 It is a structural diagram of a user experience attribute extraction and analysis system for complex product development provided by an embodiment of the present application;

[0026] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0029] The embodiments of the present application provide a method and system for extracting and analyzing user experience attributes for complex product development, thereby solving the problems of lack of flexibility in attribute extraction and weight allocation, difficulty in achieving real-time response and dynamic adjustment, and poor effectiveness and accuracy in current user experience attribute analysis.

[0030] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0031] With the rapid development of new generation information technology, the decision-making environment has become increasingly dynamic and complex, especially in the field of complex product research and development. Traditional user experience attribute design methods usually rely on predefined fixed attribute sets, which may be applicable in static environments, but the limitations of this approach become particularly obvious in rapidly changing market and technology environments. Traditional attribute systems are often based on standard literature or historical data, lack sensitivity to real-time market dynamics and user needs, and are difficult to adapt to the rapid evolution of today's technological innovation and market needs.

[0032] In the face of the challenges of rapidly changing market and technological environments, traditional systems that rely on static attribute sets have difficulty capturing and reflecting immediate changes in consumer preferences and behavioral trends. For example, consumer purchasing behavior and product preferences may change significantly in a short period of time, and traditional methods have difficulty adapting to these changes quickly. Therefore, building a user experience attribute analysis system that can dynamically integrate user-generated content (UGC) and continuously update it becomes the key to solving this problem.

[0033] Data-driven analysis methods provide a new way to address these challenges. Leveraging UGC, including online comments, social media interactions, and direct user feedback, these real-time data can directly capture consumer behaviors and preferences, providing instant feedback for the continuous optimization of complex product development and services. However, many existing user experience analysis systems have not yet fully utilized these real-time data sources, lack effective dynamic update mechanisms, and still rely on preset standard attribute sets, resulting in significant response lags when responding to actual user experience.

[0034] In addition, traditional methods are usually based on manually set attribute weight allocation schemes, which is not only highly subjective, but also difficult to fully reflect the actual needs of users. Faced with complex, diverse and dynamic user experience data, existing models often lack flexibility in attribute extraction and weight allocation, and it is difficult to achieve real-time response and dynamic adjustment. Therefore, how to use UGC data for automated attribute extraction and optimize attribute weight allocation in a data-driven manner is a key issue in improving the effectiveness and accuracy of user experience attribute analysis systems. Specifically, the existing technology has the following defects:

[0035] (1) High Subjectivity: Since user experience analysis is often highly subjective, attribute systems that rely on experts or users to manually define attributes often carry personal biases and tend to reflect individual experience and understanding, but are difficult to fully and objectively reflect the real experience and needs of all users. For example, in product design or service optimization, the attributes set by experts may rely too much on their knowledge of specific fields and ignore the real feelings and feedback of ordinary users in actual use. This bias will cause decision makers to be unable to accurately grasp user needs and preferences when developing or optimizing complex products, which in turn affects the effectiveness of decision-making and market competitiveness.

[0036] (2) Difficulty in processing massive amounts of data: UGC data, including comments, feedback, social media posts, etc., are often unstructured data and are huge in volume. Traditional manual processing methods are not only time-consuming and labor-intensive, but also fail to fully utilize the potential decision-making information contained therein. When faced with millions or even billions of UGC data, manual definition and analysis of these data appear to be inadequate and cannot efficiently extract valuable user experience information. Existing attribute systems also lack the ability to automatically process large amounts of data, which makes them unable to respond quickly to market changes and capture changes in user needs in a timely manner.

[0037] (3) Insufficient semantic understanding: UGC data usually contains a large amount of unstructured data, such as long text, pictures, videos, etc., while existing decision-making systems are mostly limited to the analysis and processing of short text. For long text content generated by users, traditional methods based on keyword matching or simple text analysis are difficult to accurately capture the contextual relationships and deep semantic information. Especially for user comments and feedback containing complex semantic structures, such methods can often only identify surface keywords and cannot deeply understand the user's true intentions in the comments. For example, a user may mention multiple positive and negative experiences when evaluating a certain mobile phone. Traditional analysis methods are likely to only focus on the positive or negative words, while ignoring the specific scenarios and contextual details contained in the evaluation. This lack of semantic analysis has led to the existing user experience analysis system being ineffective when processing complex UGC data.

[0038] (4) Dynamic attribute weights are difficult to adjust: Traditional attribute systems usually rely on predefined fixed weights. The attribute weights are set when the system is designed and remain unchanged during the subsequent analysis process. This fixed weight approach makes it difficult to reflect the dynamic nature of user needs over time. In actual applications, user needs and market environment are constantly changing, and the importance of certain attributes may change significantly in different time periods or different market scenarios. For example, in the smartphone market, early consumers may pay more attention to the hardware performance of the phone, such as the processor and memory, but as technology develops, users may pay more attention to the camera's shooting effect or the smoothness of the system. Traditional attribute systems cannot dynamically adjust weights based on these changes, causing the analysis results to lag behind market dynamics and fail to accurately reflect the latest user needs.

[0039] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0040] The following first introduces a user experience attribute extraction and analysis method for complex product development provided by an embodiment of the present application.

[0041] The present application embodiment provides a flow chart of a method for extracting and analyzing user experience attributes for complex product development, such as Figure 1 As shown, the user experience attribute extraction and analysis method may include the following steps S110-S160.

[0042] S110: Acquire user-generated content (UGC) related to the target new product, and perform preprocessing to obtain a target UGC data set.

[0043] S120, convert the target UGC dataset into a domain-specific corpus for complex product development.

[0044] S130. Build a sentence embedding model based on BERT to convert a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information.

[0045] S140: Cluster the sentences using the sentence embedding vectors to determine potential user experience attributes.

[0046] S150: Integrate the user experience attributes obtained through clustering, and calculate the weight of each user experience attribute to perform weight distribution.

[0047] S160. Based on the results of weight distribution, an attribute system is generated and iterative optimization is performed, and an optimized target attribute system is output to meet the needs of user experience orientation and complex product development.

[0048] The above is a specific implementation method of a user experience attribute extraction and analysis method for complex product development provided by the embodiment of this application. It can be understood that the user experience data in the target UGC data set is used to automatically generate a user experience attribute system through an advanced text mining algorithm, reducing human intervention and improving efficiency. This application also introduces an optimization algorithm for large-scale corpus processing to reduce the consumption of computing resources, improve the efficiency of the attribute system generation process, and accelerate the complex product development cycle.

[0049] Specifically, this application proposes a method for extracting and analyzing user experience attributes, which is based on user-generated content (UGC) and combined with natural language processing technology for automated processing. This application converts the target UGC dataset into a corpus and introduces a sentence embedding model based on BERT to enhance the semantic understanding ability of attribute extraction and ensure the accuracy of the analysis results. The sentence embedding model converts a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information, and clusters sentences to determine potential user experience attributes; through semantic analysis of the context, it is ensured that the extracted attributes are more in line with the actual needs of users.

[0050] Furthermore, the present application integrates and weights the user experience attributes obtained by clustering, generates an attribute system and performs iterative optimization, and outputs an optimized target attribute system to meet the needs of user experience orientation and complex product development. The present invention application can effectively process long texts and diverse corpora, reduce computational complexity, and provide more reliable data support for complex product development.

[0051] In one example, the aforementioned acquisition of user generated content (UGC) related to the target new product and preprocessing to obtain a target UGC dataset, that is, the aforementioned S110 may specifically include the following steps:

[0052] S210, determining a target new product and keywords related to the target new product, and defining a list of related keywords based on the characteristics of the new product;

[0053] S220, obtaining a UGC data set including each keyword in the keyword list through an API interface or a web page parsing method;

[0054] S230: Clean, deduplicate, anonymize and format the original data in the UGC data set to obtain a target UGC data set.

[0055] In some embodiments, Figure 2 As shown, the aforementioned conversion of the target UGC dataset into a domain-specific corpus for complex product development, that is, the aforementioned S120 may specifically include the following steps:

[0056] S310, dividing the target UGC dataset into sentence-level datasets to facilitate fine-grained text analysis;

[0057] S320, performing lexical analysis and word segmentation processing, using a natural language processing tool to decompose each sentence in the sentence-level data set into a word sequence;

[0058] S330, construct a domain-specific vocabulary, summarize the words of all sentences, and form a domain corpus;

[0059] S340, define corpus quality assessment indicators to ensure the relevance and accuracy of the corpus;

[0060] S350, evaluating the quality of the corpus by calculating the value of the corpus quality evaluation index, and re-dividing the target UGC data set into sentence-level data sets when the corpus quality evaluation index does not reach a preset threshold.

[0061] Exemplarily, the corpus quality assessment index satisfies the expression:

[0062]

[0063] Among them, Q is the corpus quality evaluation index, N relevant Represents the number of relevant sentences extracted; N total Represents the total number of sentences in the corpus; N errors Indicates the number of errors or inconsistencies found in the corpus.

[0064] It should be noted that through the above-mentioned quality assessment indicators, the constructed domain corpus can be quantitatively evaluated to ensure the high quality and high relevance of the corpus, which can lay a solid foundation for subsequent analysis.

[0065] In some embodiments, the aforementioned construction of a sentence embedding model based on BERT converts a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information, that is, the aforementioned S130 may specifically include the following steps:

[0066] S410, loading the pre-trained BERT model, and fine-tuning it according to the domain corpus to obtain a domain-specific target BERT model;

[0067] S420, for each sentence in the sentence-level dataset, generate a high-dimensional sentence embedding vector using the target BERT model;

[0068] S430, representing a set of multiple sentence embedding vectors in matrix form, and introducing a piecewise soft relative cosine similarity measurement method to capture the semantic relationship between sentences.

[0069] It should be noted that the piecewise soft relative cosine similarity SSRcos introduced in this application is an improved similarity measurement method; the piecewise soft relative cosine similarity SSRcos satisfies the expression:

[0070]

[0071] in, This similarity measurement method can more accurately capture the semantic relationship between sentences and improve the accuracy of subsequent clustering.

[0072] It should also be noted that this similarity measurement method overcomes the shortcomings of traditional cosine similarity in high-dimensional space through segmentation processing and soft similarity calculation, more accurately captures the semantic differences between sentences, and improves the discrimination of embedded vectors. Its characteristics are as follows:

[0073] (1) Embedding segmentation: The sentence embedding vectors U and V are segmented into T′ sub-vectors. This segmentation allows the similarity calculation to consider the local context of the sub-regions in the embedding, which is likely to capture the changes in the semantic importance of different parts of the sentence embedding.

[0074] (2) Mean centering: Before similarity calculation, each segment U τ and V τ Perform mean centering. This step reduces the impact of absolute magnitude differences between segments and focuses the similarity measurement on the relative distribution of values ​​within each segment.

[0075] (3) Soft similarity measurement: similarity between segment components It is calculated using a soft similarity function based on the Euclidean distance. This introduces a nonlinear and more tolerant similarity measure compared to the traditional strictly linear cosine similarity.

[0076] (4) Cross-segment aggregation: The final similarity measure is the average of the similarities calculated for each segment. This aggregation assumes that each segment has equal importance in contributing to the overall similarity score.

[0077] In an embodiment of the present application, by introducing a sentence embedding technology based on BERT and combining it with an improved similarity measurement method—soft relative cosine similarity SSRcos, the semantic analysis capability is effectively enhanced. Traditional methods often have difficulty understanding the contextual relationships when processing long texts, resulting in the omission of important information when extracting attributes. The present invention deeply embeds user-generated content through the BERT model, and combines SSRcos for semantic similarity measurement, which can more accurately capture the contextual relationships in the text. By comparing the embedded vectors in segments, SSRcos not only improves the ability to understand the semantics of long texts, but also effectively solves the limitations of traditional cosine similarity when processing high-dimensional vectors.

[0078] In some embodiments, the aforementioned clustering of sentences using sentence embedding vectors to determine potential user experience attributes, that is, the aforementioned S140 may specifically include the following steps:

[0079] S510, using the UMAP algorithm to reduce the sentence embedding vector to a two-dimensional or three-dimensional space, and obtain a vector set after the dimension reduction. It can be understood that the goal of the UMAP algorithm is to keep the original high-dimensional data set A = {α1, α2, …, α N}, where The UMAP algorithm attempts to find a low-dimensional representation β = {β1,β2,…,β N},in This is achieved by optimizing the following cross entropy loss function:

[0080]

[0081] in, q ij =(1+a(β i -β j ) 2b ) -1 . p ij Indicates the selection of α in high-dimensional space j As α i The probability of a neighbor is based on α i The Gaussian distribution with adaptive bandwidth (local density adjustment) is calculated as the center.

[0082] Specifically, Where d(α i ,α j ) is the distance metric, ρ i is to αi The nearest neighbor distance, σ i Adjust the decay rate of the Gaussian kernel in the local neighborhood. ij Indicates the selection of β in the low-dimensional representation j As β i The probability of a neighbor is defined by a generalized Cauchy distribution: Where a and b are fitting parameters that reflect the topological structure of high-dimensional data. This process helps ensure that the reduced-dimensional data still reflects the structural characteristics of the original data.

[0083] S520, using the HDBSCAN algorithm to perform density clustering on the reduced-dimensional data, automatically identifying the cluster structure and noise points in the data to obtain clustering results. It can be understood that in order to adapt to the formation of clusters under multi-dimensional user experience data, the algorithm constructs a mutually reachable distance graph based on the core distance, which is defined as follows:

[0084] d mreach-σ (β i ,β j )=

[0085] max(core σ (β i ),core σ (β j ),d(β i ,β j ))

[0086] Among them, d(β i ,β j ) is the point β i ,β j The Euclidean distance between core σ (β) is the core distance from point β to its σth nearest neighbor.

[0087] S530. Based on the clustering results, adjust the hyperparameters of the UMAP algorithm and the HDBSCAN algorithm; wherein the hyperparameters of the UMAP algorithm include the number of neighbors and the minimum distance; and the hyperparameters of the HDBSCAN algorithm include the minimum cluster size and the minimum number of samples.

[0088] S540, using preset evaluation indicators to evaluate the clustering results and select the optimal clustering model; the preset evaluation indicators include: Silhouette Coefficient, Calinski-Harabasz Index and Davies Bouldin Index.

[0089] For example, the calculation formula of the silhouette coefficient is as follows:

[0090]

[0091] Where a(i) is the average distance between point i and other points in its cluster, and b(i) is the average distance between point i and all points in the nearest non-cluster.

[0092] The calculation formula of Calinski-Harabasz index is as follows:

[0093]

[0094] Where N is the total number of points, k is the number of clusters, Tr(B k ) is the trace of the inter-cluster scatter matrix, Tr(W k ) is the trace of the within-cluster scatter matrix.

[0095] The calculation formula of Davies Bouldin Index is as follows:

[0096]

[0097] where k is the number of clusters, σ i is all elements in cluster i to the centroid c i The average distance, c i and c j is the centroid of clusters i and j, d(c i ,c j ) is the center of mass c i and c j The distance between.

[0098] S550: According to the clustering result, identify the sentence set corresponding to each cluster, and determine the identified sentence set as a potential user experience attribute.

[0099] In the embodiment of the present application, the UMAP algorithm is used to embed the high-dimensional vector Dimensionality reduction to low-dimensional space Where d′<<d; This application also uses the HDBSCAN algorithm to perform density clustering on the reduced-dimensional data and automatically identify clusters and noise points of different densities. By combining the UMAP algorithm and the HDBSCAN algorithm, the complexity of high-dimensional data is effectively reduced, while avoiding the limitation of the number of preset clusters, and can adaptively discover potential user experience attribute clusters.

[0100] In some embodiments, the user experience attributes obtained by clustering are integrated, and the weight of each user experience attribute is calculated to perform weight distribution, that is, the aforementioned S150 may specifically include the following steps:

[0101] S610: Extract keywords from each attribute cluster corresponding to the user experience attribute to construct an attribute word set A. c={t1,t2,…,t k}.

[0102] S620 , using CountVectorizer to convert the attribute word set into a feature vector, and counting the frequency of occurrence of each word in the attribute cluster.

[0103] S630: Calculate the attribute-level term frequency-inverse document frequency of each word to measure the importance of each word relative to the whole.

[0104] S640: Calculate the weight of each attribute set, and normalize the weight of each attribute set to obtain a first relative weight.

[0105] S650: Calculate the second relative weight of each word in the attribute set to which it belongs, so as to represent the importance of the word in the attribute set.

[0106] In the embodiments of the present application, it can be understood that the present application accurately calculates the weights of attribute words, highlights important words in a specific attribute set, eliminates the unreasonable influence of high-frequency common words on weight distribution, ensures the scientificity and objectivity of the attribute system, and ensures that the generated attribute system can accurately reflect the actual preferences and needs of users by adjusting the weights of high-frequency and low-frequency attributes.

[0107] In some embodiments, the aforementioned attribute system is generated and iteratively optimized based on the result of weight distribution, and the optimized target attribute system is output to meet the needs of user experience orientation and complex product development. That is, the aforementioned S160 may specifically include the following steps:

[0108] S710, selecting first K attributes with higher weights according to the first relative weight of the attribute set and the second relative weight of the attribute word, and constructing an attribute system, where K is a positive integer;

[0109] S720, using a similarity measurement method to calculate the similarity between attribute sets, and merge attribute sets whose similarity is higher than a preset similarity threshold to reduce redundancy; wherein the similarity threshold is determined based on an average value and a standard deviation of multiple similarities;

[0110] S730, iteratively perform attribute merging and weight recalculation operations until the attribute system is stable, and output an optimized target attribute system and its corresponding target weight.

[0111] In the embodiments of the present application, it can be understood that the present application automatically identifies and merges similar or repeated attribute sets by calculating the similarity and threshold between attribute sets, reduces redundancy, and optimizes the structure of the attribute system to make it more refined and efficient.

[0112] In some embodiments, the present application provides a user experience attribute extraction and analysis system 800 for complex product development, such as Figure 3 As shown, the user experience attribute extraction and analysis system 800 may include the following modules:

[0113] An acquisition module 810 is used to acquire user-generated content (UGC) related to the target new product and perform preprocessing to obtain a target UGC data set;

[0114] A first conversion module 820, for converting the target UGC dataset into a domain-specific corpus for complex product development;

[0115] The second conversion module 830 is used to build a sentence embedding model based on BERT, and convert a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information;

[0116] A clustering module 840, for clustering sentences using sentence embedding vectors to determine potential user experience attributes;

[0117] An integration module 850 is used to integrate the user experience attributes obtained through clustering and calculate the weight of each user experience attribute to perform weight distribution;

[0118] The iterative optimization module 860 is used to generate an attribute system and perform iterative optimization based on the result of weight distribution, and output an optimized target attribute system to meet the needs of user experience orientation and complex product development.

[0119] According to an embodiment of the present application, any multiple modules among the acquisition module 810, the first conversion module 820, the second conversion module 830, the clustering module 840, the integration module 850 and the iterative optimization module 860 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0120] In some embodiments, the acquisition module 810 may be specifically used to:

[0121] Identify target new products and keywords related to them, and define a list of related keywords based on the characteristics of the new products;

[0122] Obtain a UGC data set containing each keyword in the keyword list through an API interface or a web page parsing method;

[0123] The original data in the UGC dataset is cleaned, deduplicated, anonymized and formatted to obtain the target UGC dataset.

[0124] In some embodiments, the first conversion module 820 may be specifically used to:

[0125] Divide the target UGC dataset into sentence-level datasets to facilitate fine-grained text analysis;

[0126] Perform lexical analysis and word segmentation, using natural language processing tools to decompose each sentence in the sentence-level dataset into a sequence of words;

[0127] Build a domain-specific vocabulary, aggregate the words of all sentences, and form a domain corpus;

[0128] Define corpus quality assessment metrics to ensure the relevance and accuracy of the corpus;

[0129] The quality of the corpus is evaluated by calculating the values ​​of the corpus quality evaluation indicators. If the corpus quality evaluation indicators do not reach the preset threshold, the target UGC dataset is re-divided into sentence-level datasets.

[0130] In some embodiments, the second conversion module 830 may be specifically used to:

[0131] Load the pre-trained BERT model and fine-tune it according to the domain corpus to obtain a domain-specific target BERT model;

[0132] For each sentence in the sentence-level dataset, a high-dimensional sentence embedding vector is generated using the target BERT model;

[0133] The set of multiple sentence embedding vectors is represented as a matrix, and the piecewise soft relative cosine similarity measurement method is introduced to capture the semantic relationship between sentences.

[0134] In some embodiments, the clustering module 840 may be specifically used to:

[0135] The UMAP algorithm is used to reduce the dimension of the sentence embedding vector to two-dimensional or three-dimensional space to obtain a vector set after dimension reduction;

[0136] The HDBSCAN algorithm is used to perform density clustering on the reduced-dimensional data, automatically identifying the cluster structure and noise points in the data to obtain the clustering results;

[0137] Based on the clustering results, the hyperparameters of the UMAP algorithm and the HDBSCAN algorithm are adjusted; the hyperparameters of the UMAP algorithm include the number of neighbors and the minimum distance; the hyperparameters of the HDBSCAN algorithm include the minimum cluster size and the minimum number of samples;

[0138] Use the preset evaluation indicators to evaluate the clustering results and select the optimal clustering model; the preset evaluation indicators include: silhouette coefficient, Calinski-Harabasz index and Davies Bouldin index;

[0139] According to the clustering results, the sentence set corresponding to each cluster is identified, and the identified sentence set is determined as a potential user experience attribute.

[0140] In some embodiments, the integration module 850 may be specifically used to:

[0141] Extract keywords from each attribute cluster corresponding to the user experience attributes and construct an attribute word set;

[0142] Use CountVectorizer to convert the attribute word set into a feature vector and count the frequency of each word in the attribute cluster;

[0143] Calculate the attribute-level term frequency-inverse document frequency of each word to measure the importance of each word relative to the whole;

[0144] Calculate the weight of each attribute set, and normalize the weight of each attribute set to obtain a first relative weight;

[0145] The second relative weight of each word in the attribute set to which it belongs is calculated to represent the importance of the word in the attribute set.

[0146] In some embodiments, the iterative optimization module 860 may be specifically used to:

[0147] According to the first relative weight of the attribute set and the second relative weight of the attribute word, the first K attributes with higher weights are selected to construct an attribute system, where K is a positive integer;

[0148] Using a similarity measurement method, the similarity between attribute sets is calculated, and attribute sets with similarities higher than a preset similarity threshold are merged to reduce redundancy; wherein the similarity threshold is determined based on an average value and a standard deviation of multiple similarities;

[0149] Iterate the attribute merging and weight recalculation operations until the attribute system is stable, and output the optimized target attribute system and its corresponding target weights.

[0150] Figure 3 Each module in the system shown has the function of implementing each step in the aforementioned user experience attribute extraction and analysis method for complex product development, and can achieve its corresponding technical effect. For the sake of brevity, it will not be repeated here.

[0151] In some embodiments, the present application provides an electronic device, the structure diagram of the electronic device is as follows Figure 4 shown.

[0152] The electronic device may include a processor 910 and a memory 920 storing computer program instructions.

[0153] Specifically, the processor 910 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0154] The memory 920 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 920 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 920 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 920 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 920 is a non-volatile solid-state memory.

[0155] The memory 920 may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory 920 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the user experience attribute extraction and analysis methods for complex product development in the above-mentioned embodiments.

[0156] The processor 910 reads and executes computer program instructions stored in the memory 920 to implement any one of the user experience attribute extraction and analysis methods for complex product development in the above embodiments.

[0157] In one example, the electronic device may further include a communication interface 930 and a bus 900. Figure 4 As shown, the processor 910, the memory 920, and the communication interface 930 are connected via a bus 900 and communicate with each other.

[0158] The communication interface 930 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0159] Bus 900 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 900 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0160] In addition, in combination with the user experience attribute extraction and analysis method for complex product development in the above embodiments, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the user experience attribute extraction and analysis methods for complex product development in the above embodiments is implemented.

[0161] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0162] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0163] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0164] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0165] In summary, compared with the prior art, this application has the following beneficial effects:

[0166] 1. This application greatly improves the efficiency and accuracy of attribute system generation through data-driven algorithms. In traditional methods, the extraction of attributes depends on the manual definition of experts, which is not only time-consuming but also susceptible to subjective bias, resulting in the lack of real-time and scientific nature of the generated attribute system. However, the present invention, by combining modern natural language processing technology, can automatically extract decision attributes from massive user-generated content UGC, significantly reducing manual intervention.

[0167] 2. This application effectively reduces the computational complexity by optimizing the computational architecture. Similarity calculations based on the traditional BERT model, especially large-scale text embedding and comparison tasks, often require a lot of computing resources, resulting in increased time and cost. This invention greatly reduces the time and resource consumption of repeated calculations by pre-calculating sentence embeddings and combining the improved algorithm of SSRcos.

[0168] 3. This application ensures that the extracted attributes are more in line with the actual needs of users through semantic analysis of the context; then the user experience attributes obtained by clustering are integrated and weighted, an attribute system is generated and iteratively optimized, and the optimized target attribute system is output to meet the needs of user experience orientation and complex product development. This invention application can effectively process long texts and diverse corpora, reduce computational complexity, and provide more reliable data support for complex product development.

[0169] 4. This application has broad application prospects. In addition to its excellent performance in multi-attribute group decision-making problems, the present invention can also be applied to a variety of scenarios, such as user experience analysis, market research, product evaluation, etc. In market research, companies can use the present invention to extract consumers' real needs and preferences and optimize product design; in user experience analysis, the platform can monitor user feedback in real time and adjust service content to improve user satisfaction. The wide applicability of the present invention enables it to provide strong data support in various complex decision-making scenarios, helping companies and organizations better cope with the rapidly changing market environment and diverse user needs.

[0170] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A user experience attribute extraction and analysis method for complex product development, characterized in that: include: Obtain user-generated content (UGC) related to the target new product and perform preprocessing to obtain the target UGC dataset; Convert the target UGC dataset into a domain-specific corpus for complex product development; Construct a sentence embedding model based on BERT to convert a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information; Clustering the sentences using the sentence embedding vectors to determine potential user experience attributes; Integrate the user experience attributes obtained by clustering, and calculate the weight of each user experience attribute to perform weight distribution; Based on the results of weight distribution, an attribute system is generated and iteratively optimized, and the optimized target attribute system is output to meet the needs of user experience orientation and complex product development.

2. The user experience attribute extraction and analysis method for complex product development as claimed in claim 1, characterized in that: The obtaining of user generated content (UGC) related to the target new product and preprocessing to obtain a target UGC dataset includes: Determine target new products and keywords related to the target new products, and define a list of related keywords based on the characteristics of the new products; Obtaining a UGC data set containing each keyword in the keyword list through an API interface or a web page parsing method; The original data in the UGC data set is cleaned, deduplicated, anonymized and formatted to obtain a target UGC data set.

3. The user experience attribute extraction and analysis method for complex product development as claimed in claim 1, characterized in that: The step of converting the target UGC dataset into a domain-specific corpus for use in complex product development includes: Dividing the target UGC dataset into sentence-level datasets to facilitate fine-grained text analysis; Performing lexical analysis and word segmentation processing, using natural language processing tools to decompose each sentence in the sentence-level data set into a word sequence; Build a domain-specific vocabulary, aggregate the words of all sentences, and form a domain corpus; Define corpus quality assessment metrics to ensure the relevance and accuracy of the corpus; The quality of the corpus is evaluated by calculating the value of the corpus quality evaluation index, and when the corpus quality evaluation index does not reach a preset threshold, the target UGC data set is re-divided into sentence-level data sets; Among them, the corpus quality evaluation index satisfies the expression: Among them, Q is the corpus quality evaluation index, N relevant Represents the number of relevant sentences extracted; N total Represents the total number of sentences in the corpus; N errors Indicates the number of errors or inconsistencies found in the corpus.

4. The user experience attribute extraction and analysis method for complex product development as claimed in claim 3, characterized in that: The BERT-based sentence embedding model is constructed to convert a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information, including: Load the pre-trained BERT model and fine-tune it according to the domain corpus to obtain a domain-specific target BERT model; For each sentence in the sentence-level dataset, generating a high-dimensional sentence embedding vector using the target BERT model; The set of multiple sentence embedding vectors is represented as a matrix, and a piecewise soft relative cosine similarity measurement method is introduced to capture the semantic relationship between sentences.

5. The user experience attribute extraction and analysis method for complex product development as claimed in claim 1, characterized in that: The clustering of sentences using the sentence embedding vectors to determine potential user experience attributes includes: Using the UMAP algorithm to reduce the dimension of the sentence embedding vector to a two-dimensional or three-dimensional space to obtain a vector set after dimension reduction; The HDBSCAN algorithm is used to perform density clustering on the reduced-dimensional data, automatically identifying the cluster structure and noise points in the data to obtain the clustering results; Based on the clustering results, adjusting the hyperparameters of the UMAP algorithm and the HDBSCAN algorithm; wherein the hyperparameters of the UMAP algorithm include the number of neighbors and the minimum distance; and the hyperparameters of the HDBSCAN algorithm include the minimum cluster size and the minimum number of samples; Using preset evaluation indicators to evaluate the clustering results and select the optimal clustering model; the preset evaluation indicators include: silhouette coefficient, Calinski-Harabasz index and Davies Bouldin index; According to the clustering results, the sentence set corresponding to each cluster is identified, and the identified sentence set is determined as a potential user experience attribute.

6. The user experience attribute extraction and analysis method for complex product development as claimed in claim 1, characterized in that: The step of integrating the user experience attributes obtained through clustering and calculating the weight of each user experience attribute to perform weight distribution includes: Extracting keywords from each attribute cluster corresponding to the user experience attribute to construct an attribute word set; CountVectorizer is used to convert the attribute word set into a feature vector, and the occurrence frequency of each word in the attribute cluster is counted; Calculate the attribute-level term frequency-inverse document frequency of each word to measure the importance of each word relative to the whole; Calculate the weight of each attribute set, and normalize the weight of each attribute set to obtain a first relative weight; The second relative weight of each word in the attribute set to which it belongs is calculated to represent the importance of the word in the attribute set.

7. The user experience attribute extraction and analysis method for complex product development as claimed in claim 6, characterized in that: Based on the result of weight distribution, the attribute system is generated and iteratively optimized, and the optimized target attribute system is output to meet the needs of user experience orientation and complex product development, including: According to the first relative weight of the attribute set and the second relative weight of the attribute word, the first K attributes with higher weights are selected to construct an attribute system, where K is a positive integer; Using a similarity measurement method, the similarity between attribute sets is calculated, and attribute sets with similarities higher than a preset similarity threshold are merged to reduce redundancy; wherein the similarity threshold is determined based on an average value and a standard deviation of a plurality of the similarities; Iterate the attribute merging and weight recalculation operations until the attribute system is stable, and output the optimized target attribute system and its corresponding target weights.

8. A user experience attribute extraction and analysis system for complex product development, characterized in that: include: An acquisition module is used to acquire user-generated content (UGC) related to the target new product and perform preprocessing to obtain a target UGC dataset; A first conversion module, for converting the target UGC dataset into a domain-specific corpus for complex product development; A second conversion module is used to build a sentence embedding model based on BERT, which converts a large number of sentences in the corpus into high-dimensional sentence embedding vectors to capture semantic information; A clustering module, for clustering sentences using the sentence embedding vectors to determine potential user experience attributes; An integration module, used to integrate the user experience attributes obtained by clustering, and calculate the weight of each user experience attribute to perform weight distribution; The iterative optimization module is used to generate an attribute system and perform iterative optimization based on the results of weight distribution, and output the optimized target attribute system to meet the needs of user experience orientation and complex product development.

9. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements a user experience attribute extraction and analysis method for complex product development as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the user experience attribute extraction and analysis method for complex product development as described in any one of claims 1 to 7 is implemented.

Images