Product multi-dimensional demand analysis method and system based on natural language processing

Abstract

The invention relates to a product multi-dimensional demand analysis method and system based on natural language processing, and the method specifically comprises the steps: carrying out user feedback text mining through a natural language processing model, and collecting demand data; feature clustering is carried out on the collected demand data, and importance ranking of demands is carried out; performing demand priority ranking and demand classification in the demand management tool; and designing application scene simulation to carry out a demand verification experiment, and carrying out resource allocation based on the adjusted demand. Therefore, according to the technical scheme, text mining and data analysis are carried out by applying the pre-trained BERT model, user demands can be collected and analyzed in multiple dimensions more comprehensively, and the demand decision-making efficiency can be improved by clustering, sorting and classifying the demands.

Description

Technical Field

[0001] The present invention relates to the field of big model application technology, and specifically proposes a product multi-dimensional demand analysis method and system based on natural language processing. Through the text mining and data analysis capabilities of the big model, in-depth analysis of user needs is performed to improve the comprehensiveness and accuracy of demand analysis and optimize the product development process. Background Art

[0002] With the improvement of computing power and the accumulation of big data, large models such as BERT and GPT in deep learning models have developed rapidly. These models have powerful data processing and feature extraction capabilities, and have demonstrated excellent performance in text mining, natural language processing, image recognition and other fields. They can not only process massive amounts of data, but also extract deep features and patterns from them, providing accurate prediction and decision support for various application scenarios.

[0003] In the process of product development, demand dimension analysis is a crucial part, which can help product managers clearly understand the needs and expectations of users and ensure that the product can meet the real needs of the market. At the same time, through multi-dimensional demand analysis, product managers can also identify the core functions and competitive advantages of the product, laying a solid foundation for the successful launch of the product.

[0004] However, in the existing technology, product managers mainly rely on market research, user interviews and other methods to collect requirements in product development. These methods have many shortcomings, such as limited research samples and strong subjectivity of user feedback, which leads to the fact that the collected requirements are often not comprehensive and accurate. In addition, the existing technology also lacks a systematic analysis and priority sorting mechanism, making it difficult for product managers to make effective decisions when faced with numerous requirements.

[0005] Therefore, the present invention aims to provide a large model-assisted product multi-dimensional demand analysis method to solve the problems raised in the above-mentioned background technology. Through the text mining and data analysis capabilities of the large model, user needs can be collected and analyzed more comprehensively, the accuracy of the needs can be improved, and a systematic analysis process can be provided to automatically cluster, sort and classify the needs, thereby greatly improving the work efficiency of product managers and being able to more comprehensively evaluate the commercial value and implementation difficulty of the needs. Summary of the invention

[0006] In order to address the deficiencies of the prior art, the present invention proposes a method and system for multi-dimensional product demand analysis based on natural language processing.

[0007] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0008] A product multi-dimensional demand analysis method based on natural language processing, characterized by comprising:

[0009] S10. Collect demand data and conduct text mining of user feedback through natural language processing models;

[0010] S20. Performing feature clustering on the demand data, and ranking the demand importance based on the demand data;

[0011] S30. According to the results of the demand importance ranking, the demand priorities are sorted and the demand data is classified based on the demand management tool;

[0012] S40. Design application scenario simulations to conduct demand verification experiments, and adjust demand based on verification results;

[0013] S50. Allocate resources based on adjusted requirements in the project management tool.

[0014] Further, the step S10 specifically includes:

[0015] S101. Use the pre-trained BERT model to perform sentiment analysis and keyword extraction on the user feedback text;

[0016] S102. Using the extracted keywords and sentiment analysis results, identify user needs and market trends.

[0017] Further, the step S20 specifically includes:

[0018] S201. Use a preset algorithm to perform feature clustering on demand data and identify demand patterns and demand correlations;

[0019] S202. Construct a relative importance matrix between different requirements, use the hierarchical analysis method to calculate the weight of each requirement, and sort them.

[0020] Further, the step S30 specifically includes:

[0021] S301. According to the results of the order of importance of the requirements, based on the Jira requirements management tool, set the priority scores according to the business value and technical feasibility, and display the requirements in order;

[0022] S302. Use the Kano model to classify needs into essential needs, one-dimensional needs, and exciting needs, and calculate the satisfaction coefficient.

[0023] Further, the step S40 specifically includes:

[0024] S301. Use AB testing method to design demand verification experiment, and compare the user acceptance and effect of different implementation solutions according to the experimental results;

[0025] S302. Adjust the demand implementation plan using a decision tree algorithm based on the experimental results.

[0026] Further, the step S50 specifically includes:

[0027] Based on the demand implementation plan, Project management tools are used for project planning, and genetic algorithms are used to optimize resource allocation.

[0028] Furthermore, the step S10 further includes:

[0029] Collect demand data from different user groups through online questionnaires.

[0030] In addition, the present invention also relates to a product multi-dimensional demand analysis system based on natural language processing, which is characterized by comprising:

[0031] Data collection module, used to collect demand data and conduct user feedback text mining through natural language processing models;

[0032] A feature clustering module, used to perform feature clustering on the demand data and sort the demand importance based on the demand data;

[0033] The demand management module is configured in the demand management tool to prioritize requirements and classify demand data;

[0034] The experimental design module is used to design application scenario simulations to conduct demand verification experiments and adjust the requirements based on the verification results;

[0035] The resource allocation module is configured in the project management tool and is used to allocate resources based on the adjusted requirements.

[0036] In addition, the present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0037] The memory is used to store operation instructions;

[0038] The processor is used to execute the above method by calling the operation instruction.

[0039] In addition, the present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0040] The present invention discloses a method and system for multi-dimensional demand analysis of products based on natural language processing, including the following steps: mining user feedback text through a natural language processing (NLP) model to collect demand data; clustering the collected demand data by features, and ranking the importance of the demand; prioritizing and classifying the demand in a demand management tool; designing application scenario simulations to conduct demand verification experiments, and allocating resources based on the adjusted demand. Therefore, the technical solution can collect and analyze user needs more comprehensively and in multiple dimensions by applying a pre-trained BERT model for text mining and data analysis, and can improve the efficiency of demand decision-making by clustering, ranking and classifying the demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for analyzing multi-dimensional product requirements based on natural language processing provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of the structure of a product multi-dimensional demand analysis system based on natural language processing provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0045] Those skilled in the art can understand that, unless otherwise stated, the singular forms "one", "an", "said" and "the" used herein may also include plural forms, and the "first", "second", etc., are only used to distinguish and define objects for the purpose of introducing the scheme clearly, and do not limit the objects themselves. Of course, the objects defined by "first" and "second" may be the same terminal, device, user, etc., or the same type of terminal, device and user. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0046] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0047] On the one hand, it also involves a product multi-dimensional demand analysis method and system based on natural language processing, whose structure is as follows Figure 1 As shown,

[0048] Including: S10. Collect demand data and conduct user feedback text mining through natural language processing (NLP) model;

[0049] Collect the needs and suggestions of different user groups, extract potential user needs and market trends, analyze market research data, and identify users' emotional tendencies towards products, including:

[0050] S101. Demand data survey: Use online questionnaires to conduct surveys and collect data on demand, where user satisfaction = (Σ satisfaction score) / (total number of scorers)

[0051] S102. Natural language processing (NLP) model for text mining: preprocessing the demand data text and loading the BERT model for text sentiment analysis and keyword extraction, where sentiment analysis score = BERT (text), keywords = ExtractKeywords (BERT output);

[0052] S20. Perform feature clustering on the demand data to identify demand patterns and correlations, and rank the importance of the demands;

[0053] Specifically include:

[0054] S201. Demand feature clustering: select clustering features, run the DBSCAN algorithm to cluster demand, and analyze the clustering results, where the core point distance = the point distance within MinPts;

[0055] S202. Identify demand patterns: Based on demand data, use the Apriori algorithm to mine association rules and analyze association rules, where support = number of frequent item sets / total number of transactions;

[0056] S203. Demand correlation analysis: Use Pearson correlation coefficient for correlation analysis;

[0057] S204. Order of importance of requirements: Construct a relative importance matrix between different requirements, use the analytic hierarchy process (AHP) to calculate the weight of each requirement, and order them, where weight = eigenvector / sum of eigenvectors.

[0058] S205. Business value assessment: By predicting cash flow, discounting cash flow, and using the NPV (net present value) method to assess business value, specifically, NPV = Σ(cash flow in the tth year / (1+discount rate)^t).

[0059] S206. Technical feasibility assessment: Conduct technical research based on demand data, and make maturity judgments based on the research data to assess feasibility.

[0060] S30. According to the results of the demand importance ranking, the demand priorities are sorted and the demand data is classified based on the demand management tool;

[0061] Specifically include:

[0062] S301. Requirements Prioritization: Use Jira to prioritize requirements based on the requirements importance ranking results. Specifically, priority score = business value * technical feasibility;

[0063] S302. Demand data classification: Design and implement Kano questionnaires to collect users’ perceptions and expectations of each demand item.

[0064] Data analysis: The collected Kano questionnaire data is sorted and analyzed. According to the results of the data analysis, the demand items are divided into exciting needs, one-dimensional needs, and essential needs, which helps to understand users' expectations and satisfaction with different needs.

[0065] Satisfaction coefficient calculation: Calculate the satisfaction coefficient based on the classified needs, specifically: Satisfaction coefficient = (number of exciting needs + number of one-dimensional needs) / total number of needs. This coefficient can reflect the user's satisfaction level with the overall needs, and whether the product has fully considered the user's needs and expectations when designing;

[0066] S303. Determine the processing order: Based on the demand priority sorting results and data classification results, use the Gantt chart to visually manage the demand processing order.

[0067] S40. Design application scenario simulations to conduct demand verification experiments, and adjust demand based on verification results;

[0068] It should be noted that the specific process is as follows:

[0069] S301. Use Unity to perform 3D simulation of product application scenarios, define test and control groups, use AB testing methods to design demand verification experiments, and compare user acceptance and effects of different implementation solutions based on experimental results;

[0070] S302. Adjust the demand implementation plan using a decision tree algorithm based on the experimental results.

[0071] S50. Allocate resources based on adjusted requirements in project management tools;

[0072] Specifically include:

[0073] S501. Based on the demand implementation plan, use Project management tools to plan the project to optimize development time and resource allocation;

[0074] S502. Using genetic algorithms to optimize resource allocation

[0075] S60. Real-time tracking of demand status is used to manage the life cycle of demand, conduct continuous integration and delivery, and automate the process of demand realization to ensure that demand is efficiently converted into product features;

[0076] Specifically include:

[0077] S601. Define validation rules: Use business rules or data models to define the expected format, scope, and constraints of data;

[0078] S602. Select verification tools: Select appropriate programming languages ​​or data processing software, including Python's Pandas library, and determine which functions or methods to use for data verification;

[0079] S603. Write and execute verification code: Write code to check whether the field meets the defined verification rules, verify the input data, and record the verification results;

[0080] S604. Handle verification failure: If the data does not pass the verification, generate an error message, provide feedback, and give modification suggestions.

[0081] Through the natural language processing (NLP) model, user feedback text mining is carried out to collect demand data; the collected demand data is clustered by features and the importance of the demands is ranked; the demands are prioritized and classified in the demand management tool; application scenario simulation is designed to conduct demand verification experiments, and resources are allocated based on the adjusted demands. Therefore, this technical solution can collect and analyze user needs more comprehensively by applying the pre-trained BERT model for text mining and data analysis, and can improve the efficiency of demand decision-making by clustering, ranking and classifying the demands.

[0082] The following is another embodiment of applying the multi-dimensional product demand analysis method based on natural language processing to a product manager in charge of product development, including the following steps:

[0083] 1. User feedback text mining and market research data analysis

[0084] 1.1NLP model for text mining:

[0085] Text preprocessing: clean the collected user feedback and remove irrelevant characters and stop words;

[0086] BERT model loading: load the pre-trained BERT model for sentiment analysis and keyword extraction;

[0087] Sentiment analysis: Input a user feedback "The interface of this product is too ugly and inconvenient to use." The BERT model outputs a sentiment analysis score of -0.8 (indicating negative sentiment);

[0088] Keyword extraction: extract the keywords "interface", "ugly", "usage", and "inconvenient" from the above text;

[0089] 1.2 Market research data analysis:

[0090] Data loading: Load the Excel file of market research;

[0091] Data cleaning: remove duplicate and invalid data;

[0092] Data analysis: Count the number of positive and negative feedback;

[0093] Pain point identification: Calculate the pain point score. For example, if the total number of feedbacks is 1000 and the number of negative feedbacks is 300, then the pain point score = 300 / 1000 = 0.3;

[0094] 2. Demand feature clustering and importance ranking

[0095] 2.1 Demand feature clustering:

[0096] Select clustering features: Select keywords in user feedback as clustering features;

[0097] Run DBSCAN: set MinPts to 5, core point distance to 0.5, and perform clustering;

[0098] Analyze clustering results: get different categories of requirements, such as interface design, user experience, etc.

[0099] 2.2 Identify demand patterns:

[0100] Data preparation: prepare the required data after clustering;

[0101] Run Apriori: set the minimum support to 0.2 and mine association rules;

[0102] Analyze association rules: For example, it is found that "ugly interface" and "inconvenient to use" often appear together, with a support of 0.25;

[0103] 2.3 Demand correlation analysis:

[0104] Calculate correlation coefficient: Use Pearson correlation coefficient to calculate the correlation between different requirements;

[0105] Correlation judgment: For example, the correlation coefficient between "interface design" and "user satisfaction" is found to be 0.7, indicating a strong correlation;

[0106] 2.4 Order of importance of requirements:

[0107] Construct a judgment matrix: Based on expert evaluation, construct a relative importance matrix between different requirements;

[0108] Calculate weights: Use the analytic hierarchy process to calculate the weights of each requirement;

[0109] Consistency check: ensure that the consistency ratio of the judgment matrix is ​​less than 0.1;

[0110] 2.5 Commercial Value Assessment:

[0111] Forecast cash flow: forecast cash flow for the next five years based on market demand;

[0112] Discounted Cash Flow: Discount the cash flows using a 10% discount rate;

[0113] Calculate NPV: NPV = Σ(cash flow in year t / (1+0.1)^t) = 10 million yuan;

[0114] 2.6 Technical feasibility assessment:

[0115] Technical research: research the maturity of relevant technologies;

[0116] Maturity judgment: judge whether the technology is at a mature stage;

[0117] Feasibility assessment: assessing technical feasibility based on maturity and technical team capabilities;

[0118] 3. Application in Demand Management Tools

[0119] 3.1 Requirements Prioritization:

[0120] Create requirements: Create all collected requirements in Jira according to the requirements importance ranking results;

[0121] Set priority: Set the priority score based on business value and technical feasibility. For example, if the business value of a requirement is RMB 8 million and the technical feasibility is 0.8, then the priority score = 800*0.8 = 640;

[0122] 3.2 Demand data classification:

[0123] Demand identification: Identify all collected demand data;

[0124] Kano Questionnaire: Design the Kano Questionnaire and collect user feedback;

[0125] Data analysis: Analyze the questionnaire results and classify the needs into essential needs, one-dimensional needs, excitement needs, etc.;

[0126] Demand classification: calculate the satisfaction coefficient. For example, if the number of excitement needs is 10, the number of one-dimensional needs is 20, and the total number of needs is 50, then the satisfaction coefficient = (10 + 20) / 50 = 0.6;

[0127] 3.4 Determine the processing order of impact analysis, confidence assessment, and development cost estimation

[0128] 1) Influence analysis: define influence indicators (such as number of users, usage frequency, etc.), collect data and draw influence maps;

[0129] 2) Confidence assessment: Confidence scores are assessed through expert surveys and data aggregation;

[0130] 3). Development cost estimation: Select analogous projects and estimate the current project cost based on their cost adjustments;

[0131] 4). Determine the processing order: Based on the requirements priority sorting results and data classification results, use the Gantt chart to visually manage the requirements processing order.

[0132] In addition, another aspect is a product multi-dimensional demand analysis system based on natural language processing, whose structure is as follows: Figure 2 As shown, including:

[0133] The data collection module 201 is used to collect demand data and perform user feedback text mining through a natural language processing model;

[0134] A feature clustering module 202 is used to perform feature clustering on the demand data and to sort the demand importance based on the demand data;

[0135] The demand management module 203 is configured in the demand management tool and is used to perform demand priority sorting and demand data classification;

[0136] The experiment design module 204 is used to design application scenario simulation to perform demand verification experiments and adjust the demand according to the verification results;

[0137] The resource allocation module 205 is configured in the project management tool and is used to allocate resources based on the adjusted requirements.

[0138] Further, the data collection module 201 is specifically used for:

[0139] Use the pre-trained BERT model to perform sentiment analysis and keyword extraction on the user feedback text;

[0140] The extracted keywords and sentiment analysis results are used to identify user needs and market trends.

[0141] Further, the feature clustering module 202 is specifically used for:

[0142] If interface data with the same application name and interface set version number exists, the reporting operation will not be performed and the existing interface data information will be returned.

[0143] Furthermore, the demand management module 203 is also used for:

[0144] According to the results of the importance sorting of requirements, based on the Jira requirement management tool, set priority scores according to business value and technical feasibility, and sort and display the requirements;

[0145] The Kano model is used to classify needs into essential needs, one-dimensional needs, and excitement needs, and the satisfaction coefficient is calculated.

[0146] Furthermore, the experimental design module 204 is also used for:

[0147] Use AB testing method to design demand verification experiments, and compare user acceptance and effects of different implementation solutions based on experimental results;

[0148] Based on the experimental results, a decision tree algorithm is used to adjust the demand implementation plan.

[0149] Furthermore, the resource allocation module 205 is also used for:

[0150] Based on the demand implementation plan, Project management tools are used for project planning, and genetic algorithms are used to optimize resource allocation.

[0151] By using this system, the above method can be executed and the corresponding technical effects can be achieved.

[0152] An embodiment of the present invention further provides an electronic device for executing the above method, as an implementation device of the method, comprising a processor and a memory;

[0153] A memory, used for storing operation instructions;

[0154] The processor is used to execute a product multi-dimensional demand analysis method based on natural language processing provided in any embodiment of the present application by calling an operation instruction.

[0155] As an example, Figure 3A schematic diagram of the structure of an electronic device applicable to an embodiment of the present application is shown, and the electronic device 300 includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as being connected through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one. It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the specific structure of the electronic device 300. In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. Optionally, the electronic device may also include a display screen 305 for displaying images, or receiving user operation instructions when necessary.

[0156] The processor 301 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 304 may include a receiver and a transmitter. The transceiver 304 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0157] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0158] The processor 301 may also include one or more processing units, for example: the processor 301 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and / or a neural network processor (Neural-network Processing Unit, NPU), etc. Different processing units can be independent devices or integrated into one or more processors. Among them, the controller can be the nerve center and command center of the electronic device 300. The controller can generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory can also be set in the processor 301 for storing instructions and data. In some embodiments, the memory in the processor 301 is a cache memory. The memory can save instructions or data that the processor 301 has just used or circulated.

[0159] The processor 301 can run the multi-dimensional product demand analysis method based on natural language processing provided in the embodiment of the present application. The processor 301 may include different devices. For example, when the CPU and GPU are integrated, the CPU and the GPU can cooperate to execute the multi-dimensional product demand analysis method based on natural language processing provided in the embodiment of the present application. Part of the algorithm is executed by the CPU, and the other part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0160] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0161] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or may include a high-speed random access memory, or may include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0162] Optionally, the memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the product multi-dimensional demand analysis method based on natural language processing provided in any embodiment of the present application.

[0163] The memory 303 can be used to store computer executable program codes, which include instructions. The processor 301 executes various functional applications and data processing of the electronic device 300 by running the instructions stored in the memory 303. The memory 303 may include a program storage area and a data storage area. Among them, the program storage area may store the code of the operating system, application program, etc. The data storage area may store data created during the use of the electronic device 300 (such as images, videos, etc. collected by the camera application), etc.

[0164] The memory 303 may also store one or more computer programs corresponding to the product multi-dimensional demand analysis method based on natural language processing provided in the embodiment of the present application. The one or more computer programs are stored in the above-mentioned memory 303 and are configured to be executed by the one or more processors 301. The one or more computer programs include instructions, and the above-mentioned instructions can be used to execute each step in the above-mentioned corresponding embodiment.

[0165] Of course, the code of the product multi-dimensional demand analysis method based on natural language processing provided in the embodiment of the present application can also be stored in an external memory.

[0166] The display screen 305 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 300 may include 1 or N display screens 305, where N is a positive integer greater than 1. The display screen 305 can be used to display information input by a user or information provided to a user and various graphical user interfaces (GUI). For example, the display screen 305 can display photos, videos, web pages, or files.

[0167] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0168] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0169] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0171] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0173] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A product multi-dimensional demand analysis method based on natural language processing, characterized in that: include: S10. Collect demand data and conduct text mining of user feedback through natural language processing models; S20. Performing feature clustering on the demand data, and ranking the demand importance based on the demand data; S30. According to the results of the demand importance ranking, the demand priorities are sorted and the demand data is classified based on the demand management tool; S40. Design application scenario simulations to conduct demand verification experiments, and adjust demand based on verification results; S50. Allocate resources based on adjusted requirements in the project management tool.

2. The method according to claim 1, characterized in that The step S10 specifically includes: S101. Use the pre-trained BERT model to perform sentiment analysis and keyword extraction on the user feedback text; S102. Using the extracted keywords and sentiment analysis results, identify user needs and market trends.

3. The method according to claim 1, characterized in that The step S20 specifically includes: S201. Use a preset algorithm to perform feature clustering on demand data and identify demand patterns and demand correlations; S202. Construct a relative importance matrix between different requirements, use the hierarchical analysis method to calculate the weight of each requirement, and sort them.

4. The method according to claim 1, characterized in that: The step S30 specifically includes: S301. According to the results of the order of importance of the requirements, based on the Jira requirements management tool, set the priority scores according to the business value and technical feasibility, and display the requirements in order; S302. Use the Kano model to classify needs into essential needs, one-dimensional needs, and exciting needs, and calculate the satisfaction coefficient.

5. The method according to claim 1, characterized in that The step S40 specifically includes: S301. Use AB testing method to design demand verification experiment, and compare the user acceptance and effect of different implementation solutions according to the experimental results; S302. Adjust the demand implementation plan using a decision tree algorithm based on the experimental results.

6. The method according to claim 1, characterized in that The step S50 specifically includes: Based on the demand implementation plan, Project management tools are used for project planning, and genetic algorithms are used to optimize resource allocation.

7. The method according to claim 1, characterized in that The step S10 further includes: Collect demand data from different user groups through online questionnaires.

8. A product multi-dimensional demand analysis system based on natural language processing, characterized in that: include: Data collection module, used to collect demand data and conduct user feedback text mining through natural language processing models; A feature clustering module, used to perform feature clustering on the demand data and sort the demand importance based on the demand data; The demand management module is configured in the demand management tool to prioritize requirements and classify demand data; The experimental design module is used to design application scenario simulations to conduct demand verification experiments and adjust the requirements based on the verification results; The resource allocation module is configured in the project management tool and is used to allocate resources based on the adjusted requirements.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store operation instructions; The processor is used to execute the method according to any one of claims 1 to 7 by calling the operation instruction.

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

Images