Product optimization method, device, equipment, storage medium and program product

Abstract

This application provides a product optimization method, apparatus, device, storage medium, and program product, relating to the fields of data processing and artificial intelligence, and applicable to the fintech field. The method acquires multi-source text data corresponding to the product to be optimized, and determines multiple candidate texts corresponding to the multi-source text data according to preset rules. For any one of these candidate texts, semantic analysis is performed to obtain the corresponding product requirements. These product requirements are then prioritized, and the product to be optimized is optimized based on the prioritized requirements. This improves the accuracy and efficiency of product requirement identification, and by prioritizing multiple product requirements, the key user needs are accurately and efficiently located, thereby improving the effectiveness of product optimization.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a product optimization method, apparatus, device, storage medium, and program product. Background Technology

[0002] With the development of the financial industry, financial products are constantly being introduced and new products are emerging, leading to fierce competition in the financial market. To improve product competitiveness, product teams need to collect user feedback from multiple channels to optimize and update products based on this feedback.

[0003] Currently, the analysis and mining of collected feedback information mainly relies on manual operations to determine user product needs, which are then used to optimize and update the product. However, with the expansion of the user base and the diversification of product processing and usage channels, staff often need to spend a significant amount of time and energy acquiring and organizing user feedback. Furthermore, manually analyzing and mining collected feedback information is highly dependent on personal experience, making it difficult to accurately determine product needs.

[0004] Therefore, existing technologies suffer from low efficiency and accuracy in identifying product needs, making it difficult to quickly and accurately pinpoint users' key needs during product optimization, thus reducing the effectiveness of product optimization. Summary of the Invention

[0005] This application provides a product optimization method, apparatus, device, storage medium, and program product to solve the technical problem that existing technologies are unable to quickly and accurately locate users' key needs, thereby reducing the optimization effect of products.

[0006] Firstly, this application provides a product optimization method, including:

[0007] Obtain multi-source text data corresponding to the product to be optimized, and determine multiple candidate texts corresponding to the multi-source text data according to preset rules. The preset rules include: preset sentence structure and preset keywords.

[0008] For any one of the multiple candidate texts, perform semantic analysis to obtain the corresponding product requirements;

[0009] The requirements for multiple products are prioritized, and the products to be optimized are then optimized based on the prioritized requirements.

[0010] Secondly, this application provides a product optimization device, comprising:

[0011] The acquisition module is used to acquire multi-source text data corresponding to the product to be optimized;

[0012] The determination module is used to determine multiple candidate texts corresponding to multi-source text data according to preset rules, including preset sentence patterns and preset keywords.

[0013] The analysis module is used to perform semantic analysis on any one of multiple candidate texts to obtain the corresponding product requirements.

[0014] The product optimization module is used to prioritize multiple product requirements and optimize the products to be optimized based on the prioritized product requirements.

[0015] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0016] The aforementioned memory stores instructions executed by the computer;

[0017] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0019] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0020] The product optimization method provided in this application obtains multi-source text data corresponding to the product to be optimized, and determines multiple candidate texts corresponding to the multi-source text data according to preset rules. For any one of the multiple candidate texts, semantic analysis is performed on the candidate text to obtain the corresponding product requirements. The multiple product requirements are then prioritized, and the product to be optimized is optimized based on the prioritized product requirements. This improves the accuracy and efficiency of product requirement identification, and by prioritizing multiple product requirements, the key user needs are accurately and efficiently located, thereby improving the effect of product optimization. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0022] Figure 1 A flowchart illustrating a product optimization method provided in this application embodiment. Figure 1 ;

[0023] Figure 2 A flowchart illustrating a product optimization method provided in this application embodiment. Figure 2 ;

[0024] Figure 3 A schematic diagram of the product optimization device provided in this application;

[0025] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0026] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0027] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0028] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.

[0029] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0030] It should be noted that the product optimization methods, apparatus, equipment, storage media and program products provided in this application relate to the fields of data processing and artificial intelligence technology, and can be used in the field of fintech, or in any field other than fintech. The application fields of the product optimization methods, apparatus, equipment, storage media and program products in this application are not limited.

[0031] With the development of the financial industry, financial products are emerging in an endless stream. In order to improve the long-term competitiveness of financial products, financial institutions need to continuously optimize and update their financial products to meet users' needs.

[0032] Existing methods for optimizing financial products mainly rely on manual operation. This involves staff collecting product feedback from multiple channels, analyzing and mining the collected feedback to determine user product needs, and then optimizing and updating the product based on those needs.

[0033] However, with the expansion of the user base and the diversification of product application and usage channels, staff need to spend a significant amount of time collecting feedback from multiple channels and analyzing large amounts of feedback to determine product requirements. Furthermore, the method of manually assessing product requirements lacks objective evaluation criteria and is highly susceptible to overlooking key requirements due to subjective bias.

[0034] Therefore, existing technologies suffer from low efficiency and accuracy in identifying product needs, making it difficult to quickly and accurately pinpoint users' key needs during product optimization, thus reducing the effectiveness of product optimization.

[0035] The product optimization method provided in this application determines multiple candidate texts in the multi-source text data corresponding to the product to be optimized according to preset rules, performs semantic analysis on each candidate text to obtain the corresponding product requirements, prioritizes the multiple product requirements, and optimizes the product to be optimized based on the prioritized product requirements, thereby achieving efficient and accurate positioning of key requirements and improving the product optimization effect.

[0036] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0037] Figure 1 A flowchart illustrating a product optimization method provided in this application embodiment. Figure 1 .like Figure 1 As shown, this method can be applied, for example, to a product optimization device, and the method includes:

[0038] S101. Obtain multi-source text data corresponding to the product to be optimized, and determine multiple candidate texts corresponding to the multi-source text data according to preset rules.

[0039] The preset rules include preset sentence structures and preset keywords.

[0040] Multi-source text data of the product to be optimized is obtained from multiple channels, and the multi-source text data is preprocessed. Then, text analysis is performed on the preprocessed multi-source text data. According to the above-mentioned preset rules, multiple candidate texts are determined from the multi-source text data after text analysis.

[0041] Specifically, syntactic analysis is performed on multi-source text data to obtain the semantic structure of multiple sentences in the multi-source text data. The semantic results of multiple sentences are then labeled, and based on the labels, candidate texts corresponding to the aforementioned preset sentence patterns are obtained from the multi-source text data. Furthermore, based on preset keywords, candidate texts containing at least one preset keyword are obtained from the multiple candidate texts.

[0042] The text analysis methods include, but are not limited to: language recognition, word segmentation, part-of-speech tagging, keyword extraction, and syntactic analysis.

[0043] Optionally, multi-source text data includes, but is not limited to: feedback data within financial apps, customer service ticket data, social media comment data, and document-type data. Document-type data includes, for example, competitor analysis reports, user research documents, and product operation reports.

[0044] Understandably, the above preprocessing includes, but is not limited to: format standardization, invalid data filtering, information anonymization, data deduplication, and structured data output.

[0045] S102. For any one of the multiple candidate texts, perform semantic analysis on the candidate text to obtain the corresponding product requirements.

[0046] Semantic analysis extracts noun entities and requirement keywords from candidate text, along with status descriptions for the noun entities. Noun entities include, but are not limited to, product names and functional modules. Requirement keywords can be, for example, "hope," "suggestion," or "add." Furthermore, the status descriptions include a description of the current state and the required status. Examples of such status descriptions include: "Loading too slowly," or "Automatically calculate product revenue."

[0047] This method uses semantic analysis to determine the product requirements corresponding to each candidate text, which helps to improve the efficiency and accuracy of product requirement determination.

[0048] S103. Prioritize multiple product requirements and optimize the product to be optimized based on the prioritized product requirements.

[0049] According to preset sorting rules, multiple product requirements are prioritized to identify key requirements. These sorting rules, for example, determine the priority weight of each product requirement based on its type, the number of times it is raised within a preset time period, its impact on business processing quality, and its corresponding feature tags. These priority weights are then sorted in descending order.

[0050] After obtaining the priority ranking, the products to be optimized are processed according to this priority ranking. For example, the product requirements in the top N of the priority ranking are optimized, or the product requirements are processed sequentially according to the priority ranking to complete the optimization of the products to be optimized.

[0051] Understandably, the above sorting rules are set based on actual optimization needs, and this application does not impose any restrictions on them.

[0052] This method accurately identifies key requirements among multiple product needs by prioritizing them, optimizes the products to be optimized according to their priority, promptly addresses users' key needs, ensures the effectiveness of product optimization, and improves users' experience with the products.

[0053] The product optimization method provided in this embodiment obtains multi-source text data corresponding to the product to be optimized, and determines multiple candidate texts corresponding to the multi-source text data according to preset rules. For any one of the multiple candidate texts, semantic analysis is performed on the candidate text to obtain the corresponding product requirements. The multiple product requirements are then prioritized and sorted. Based on the sorted product requirements, the product to be optimized is then optimized, which improves the accuracy and efficiency of product requirement identification. By prioritizing multiple product requirements, the key user needs are accurately and efficiently located, thereby improving the effect of product optimization.

[0054] Figure 2 A flowchart illustrating a product optimization method provided in this application embodiment. Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, a possible product optimization method is described in detail, which includes:

[0055] S201. Obtain multi-source text data corresponding to the product to be optimized.

[0056] The explanation of step S201 is similar to that of step S101 above, and will not be repeated here.

[0057] S202. Perform text analysis on the multi-source text data to obtain multiple first text units.

[0058] The first text unit carries a sentence pattern identifier.

[0059] Specifically, language recognition is performed on multi-source text data to obtain the corresponding language type. Based on this language type, word segmentation and part-of-speech tagging are performed on the multi-source text data. For the multiple words that have undergone part-of-speech tagging, the dependency relationships between all words in each sentence are determined, and a syntactic dependency structure tree is constructed based on these dependency relationships. The sentence structure corresponding to each sentence is extracted from this syntactic dependency structure tree, and sentence structure tagging is performed on the aforementioned multi-source text data based on this sentence structure.

[0060] The nodes in the above syntactic dependency structure tree are used to indicate words in a sentence. The directed edges carry the dependency relations between words. For example, the predicate verb in the sentence is abstracted as the root node, the noun in the sentence is determined, and the subject in the noun is determined. The subject is taken as the successor node of the root node, and a directed edge is constructed from the root node to the successor node. The dependency relation carried by the directed edge is the subject-predicate relation.

[0061] For example, after obtaining the syntactic dependency structure tree, the sentence pattern of each sentence is determined based on the dependency relationships between words in the syntactic dependency structure tree, and the sentence pattern is labeled in the multi-source text data to obtain the sentence pattern identifier corresponding to each sentence.

[0062] S203. Based on a preset sentence pattern, determine the second text unit from multiple first text units.

[0063] The second text unit carries a first sentence pattern identifier. The preset sentence pattern is the preset sentence pattern in the preset rules in step S101 above. This preset sentence pattern is used to indicate text whose sentence structure includes a subject-verb-object structure.

[0064] Each first text unit carries a sentence pattern identifier. According to the preset sentence pattern, the first text unit carrying the first sentence pattern identifier is determined as the second text unit. The first sentence pattern identifier is used to indicate that the sentence pattern of the corresponding text includes a subject-verb-object structure.

[0065] S204. Determine candidate texts from a plurality of second text units that include at least one preset keyword.

[0066] The preset keywords are the preset keywords in the preset rules in step S101 above. Each word in the second text unit carries a part-of-speech tag. Based on this, combined with word parsing, it is determined whether there are words in the second text unit that semantically match at least one preset keyword. If there are words in the second text unit that match at least one preset keyword, the second text unit is determined as a candidate text.

[0067] Optionally, the aforementioned preset keywords may include, for example, "hope," "suggestion," "hopefully," "too slow," and "inconvenient." These preset keywords are set based on actual needs, and this application does not impose any restrictions on them.

[0068] S205. For any one of the multiple candidate texts, perform text analysis on the candidate text to obtain the corresponding evaluation label.

[0069] The evaluation tags indicate the type of user evaluation of the optimized product. These tags include a first tag, a second tag, and a third tag. The first tag represents a positive evaluation of the optimized product, the second tag represents a negative evaluation, and the third tag represents a neutral evaluation.

[0070] Specifically, semantic analysis is performed on the candidate text. Based on the semantics represented by multiple words in the candidate text and the context analysis of the candidate text, the evaluation type represented by the candidate text is determined. If the evaluation type is positive, the evaluation label of the candidate text is determined as the first label. If the evaluation type is negative, the evaluation label of the candidate text is determined as the second label. If the evaluation type is neutral, the evaluation label of the candidate text is determined as the third label.

[0071] This method obtains user rating tags, which helps to deeply explore user needs for the product. Then, in the subsequent optimization process, it can target the product needs with high negative ratings and improve the product optimization effect.

[0072] S206. For any one of the multiple candidate texts, based on the preset requirement parameters, identify and analyze the candidate text to obtain the corresponding requirement content.

[0073] The requirement parameters include functional parameters, behavioral parameters, and state parameters. Based on the preset requirement parameters, candidate texts are identified and analyzed to obtain the specific content corresponding to each requirement parameter. Based on the specific content corresponding to multiple requirement parameters, product requirements corresponding to the candidate texts are constructed.

[0074] Understandably, the above functional parameters are used to indicate the function name, module name, or component name, the behavioral parameters are used to indicate the user's required behavior, and the status parameters include: the current status of the functional parameters, and the user's required status for the functional parameters.

[0075] For example, functional parameters could be: payment function, repayment function; behavioral parameters could be: hope, suggestion, and satisfaction; and status parameters could be: automatic contact recognition, faster loading.

[0076] This method obtains the requirement content corresponding to each candidate text through standardized requirement parameters, which improves the efficiency of obtaining product requirements and yields product requirements with unified structure and standards, thereby improving the quality of the obtained product requirements.

[0077] S207. Generate product requirements based on the requirements corresponding to functional parameters, behavioral parameters, and state parameters.

[0078] After obtaining the corresponding requirements for functional parameters, behavioral parameters, and state parameters, product requirements are generated based on these requirements. For example, if the functional parameter is "insurance business," the behavioral parameter is "desire," and the state parameter is "the process shouldn't be too cumbersome," then the resulting product requirement is: Users hope that the process for handling insurance business won't be too cumbersome.

[0079] S208. Identify the demand characteristics corresponding to the product demand; based on the demand characteristics, determine the demand type corresponding to the product demand.

[0080] The requirements include: the object of the requirement and the action of the requirement. These verbs include, but are not limited to: function request words, experience words, fault words, and preference words. Examples of function request words are: "add"; examples of experience words are: "too slow" and "optimize"; examples of fault words are: "crashes" and "unusable"; and examples of preference words are: "accustomed to" and "not used to". This application does not restrict the setting of requirement verbs.

[0081] Specifically, keywords are extracted from product requirements to obtain corresponding requirement objects and actions. These requirement objects and actions are then combined into requirement features. Based on a pre-defined mapping relationship, the requirement type corresponding to this requirement feature is determined. The pre-defined mapping relationship includes the correspondence between requirement features and requirement types.

[0082] Optionally, the requirement types include, but are not limited to: new feature additions, feature optimizations, usage obstacles, and user habits. For example, if the requirement feature is: "We want to add a ventilation function," then based on a preset mapping relationship, the requirement type corresponding to this requirement feature is a new feature addition.

[0083] For example, standard requirement features corresponding to each requirement type are pre-stored. In the process of determining the requirement type corresponding to the product requirement, the priority of the requirement type is pre-set. For example, the first priority is the use obstacle category, the second priority is the function optimization category, the third priority is the user habit category, and the fourth priority is the new function category.

[0084] According to this priority, the requirement characteristics corresponding to the product requirement are compared with the standard requirement characteristics corresponding to the use barrier category. The standard requirement characteristics consist of a preset verb and a preset object. If the above requirement characteristics meet at least one standard requirement characteristic corresponding to the use barrier category, the requirement type corresponding to the product requirement is determined to be the use barrier category.

[0085] Understandably, if a requirement's characteristics do not match the standard requirement characteristics corresponding to the "Usability Obstacles" category, the requirement characteristics are matched against the standard requirement characteristics corresponding to the "Function Optimization" category based on a preset priority to determine whether the corresponding product requirement belongs to the "Function Optimization" category. This process continues until the requirement type corresponding to the product requirement is determined.

[0086] S209. Determine the scores corresponding to the multiple scoring factors for each type of demand.

[0087] The rating factors include, but are not limited to: feedback frequency factors, user weight factors, evaluation factors, and functional criticality factors. Each rating factor corresponds to a preset rating calculation rule, and the rating of the corresponding rating factor is determined according to the rating calculation rule.

[0088] Optionally, in this embodiment, the scores corresponding to the feedback frequency factor, user weight factor, evaluation factor, and functional key factor are determined according to the following methods:

[0089] Optionally, a method for determining the first score corresponding to the feedback frequency factor for each demand type is provided herein. The method includes: for any product demand among multiple product demands, determining multiple word units corresponding to the product demand; determining the word frequency weight corresponding to each word unit; generating a first feature corresponding to the product demand based on the multiple word units and the word frequency weight corresponding to each word unit; determining the similarity between the multiple product demands based on the first features corresponding to the multiple product demands; and clustering the multiple product demands based on the multiple similarities to obtain the first score of the feedback frequency factor corresponding to each demand type.

[0090] The word frequency weight is determined based on the frequency of occurrence of the word unit in the product requirements and the feedback frequency of the word unit in all product requirements. For example, the first product requirement is segmented into functional word units, behavioral word units, and status word units according to functional parameters, behavioral parameters, and status parameters. The frequency of occurrence of each word unit in the first product requirement and the feedback frequency of each word unit in all product requirements are determined. Based on the feedback frequency, the inverse document frequency of the word unit is determined. The word frequency weight corresponding to the first product requirement is then the product of the occurrence frequency and the inverse document frequency.

[0091] The word frequency weights are normalized, and based on the normalized weight values ​​and the first product requirement, a corresponding first feature is generated. This first feature can be, for example, [functional parameter = a, behavioral parameter = b, state parameter = c], where a, b, and c are the word frequency weights of the functional parameter, behavioral parameter, and state parameter, respectively.

[0092] After obtaining the first features corresponding to multiple product requirements, the similarity between the multiple first features is calculated. Based on the similarity, the multiple product requirements are clustered, and the number of product requirements belonging to the same requirement type is determined, that is, the total frequency of feedback of the same requirement type.

[0093] Optionally, if the total frequency of multiple demand types is the same, the first score mentioned above is determined as the preset score. The preset score can be, for example, 0. This application does not limit the specific value of the preset score.

[0094] Optionally, from the total frequency of multiple demand types, determine the minimum and maximum total frequencies. If the maximum total frequency is not equal to the minimum total frequency, then determine the first score corresponding to each demand type based on the following formula:

[0095] First score = (Total frequency of current demand type - Minimum total frequency) / (Maximum total frequency - Minimum total frequency).

[0096] Optionally, a method is provided here to determine the first score corresponding to the user weight factor for each demand type. The method includes: for any demand type among multiple demand types, determining the user attributes of the users corresponding to each product demand in the demand type; and determining the second score corresponding to the user weight factor based on the feedback weights corresponding to the multiple user attributes and the number of users corresponding to the demand type.

[0097] For example, the second score is determined according to the following formula:

[0098] Second rating = Sum of multiple feedback weights / Number of users.

[0099] Optionally, a method for determining the third score corresponding to the evaluation factors of each demand type is provided here. The method includes: each evaluation label corresponds to a different evaluation weight; for any demand type among multiple demand types, based on the evaluation labels corresponding to multiple product demands in that demand type, multiple evaluation weights corresponding to that demand type are determined; and the multiple evaluation weights are statistically and normally processed to obtain the third score corresponding to the above demand type.

[0100] Optionally, a method is provided here to determine the fourth score corresponding to the functional critical factors of each demand type. The method includes: each functional parameter has a different critical weight; for any demand type among multiple demand types, the critical weight corresponding to the functional parameter in each product demand of that demand type is determined; and based on the multiple critical weights, the fourth score corresponding to that demand type is determined.

[0101] The critical weights can be determined based on the frequency of use of the function and the risk level, and this application does not impose any restrictions on this.

[0102] It should be noted that, in this embodiment of the application, there is no restriction on the calculation order of the scores corresponding to the feedback frequency factor, user weight factor, evaluation factor, and functional key factor.

[0103] S210. Based on multiple scores, determine the priority score corresponding to the requirement type.

[0104] For any one of the multiple demand types, the priority score corresponding to that demand type is determined based on the scores corresponding to the multiple rating factors of that demand type.

[0105] Optionally, the priority score corresponding to the requirement type can be calculated based on the following formula:

[0106]

[0107] in, The first score corresponding to the feedback frequency factor. The second score corresponding to the user weight factor. The third score corresponding to the evaluation factor. This is the fourth score corresponding to the key functional factor. , , , These are the weight parameters corresponding to the feedback frequency factor, user weight factor, evaluation factor, and functional key factor, respectively.

[0108] Understandably, the weight parameters corresponding to the above-mentioned feedback frequency factor, user weight factor, evaluation factor, and functional criticality factor are set based on the optimization requirements of the product, and this application does not impose any restrictions on them.

[0109] S211. Based on the priority score, determine the priority label corresponding to the requirement type, and sort the multiple requirement types by priority to obtain the priority sequence.

[0110] The priority label indicates the priority level, and a corresponding score range is pre-set for each priority label. Specifically, the score range to which the priority score belongs for each requirement type is determined, and the corresponding priority label is determined based on this score range.

[0111] For example, the first score range corresponding to the first label is [0.85, 1], the second score range corresponding to the second label is [0.60, 0.84], and the third score range corresponding to the third label is [0.00, 0.59]. The priority level corresponding to the first label is high, the priority level corresponding to the second label is medium, and the priority level corresponding to the third label is low.

[0112] S212. Based on multiple product requirements, priority sequences, and the requirement type, priority score, priority label, and evaluation label corresponding to each product requirement, generate a product requirement report.

[0113] According to the preset output format, multiple product requirements, priority sequences, and the requirement type, priority score, priority tag, and evaluation tag corresponding to each product requirement are formatted in a unified manner. Based on the product type of the product to be optimized, the product requirement report template corresponding to that product type is called. Then, based on the unified format of multiple product requirements, priority sequences, and the requirement type, priority score, priority tag, and evaluation tag corresponding to each product requirement, the above product requirement report template is populated and updated to obtain the product requirement report of the product to be optimized.

[0114] S213. Based on the product requirement report, optimize the product to be optimized.

[0115] Analyze the product requirement report to obtain the optimization plan for the product to be optimized, and then optimize the product based on the optimization plan.

[0116] The product optimization method provided in this embodiment acquires multi-source text data corresponding to the product to be optimized, performs text analysis on the multi-source text data to obtain multiple first text units, and then determines second text units from the multiple first text units based on preset sentence patterns, and determines candidate texts including at least one preset keyword from the multiple second text units. This method obtains candidate texts with unified structure and unified screening criteria through preset sentence patterns and multiple preset keywords, which helps to improve the efficiency of product requirement identification and the quality of generated product requirements.

[0117] For any one of the multiple candidate texts, text analysis is performed to obtain the corresponding evaluation tag. This evaluation tag is used to indicate the type of evaluation the user gives to the product to be optimized. Combining this evaluation tag with the determination of the optimization plan for the product to be optimized is beneficial to improving the optimization effect of the product to be optimized.

[0118] Furthermore, for any candidate text among multiple candidate texts, based on preset requirement parameters, the candidate text is identified and analyzed to obtain the corresponding requirement content. Then, based on the requirement content corresponding to functional parameters, behavioral parameters, and state parameters, product requirements are generated. This method improves the efficiency and accuracy of product requirement identification through requirement parameters, and generates product requirements with a unified structure and standard based on standardized requirement parameters, thus improving the quality of the obtained product requirements.

[0119] Furthermore, this method identifies the demand characteristics corresponding to product requirements, determines the corresponding demand type based on these characteristics, and identifies the scores corresponding to multiple scoring factors for each demand type. Then, based on these scores, it determines the priority score for each demand type. Finally, based on the priority score, it determines the priority label for each demand type and sorts the multiple demand types by priority to obtain a priority sequence. This method statistically analyzes the demand types to which product requirements belong and comprehensively and accurately determines the priority score for each demand type based on multiple scoring factors, which helps staff to quickly and accurately analyze and develop optimization solutions. In addition, based on the priority label corresponding to each demand type, it efficiently and accurately locates key demand types, thereby enabling targeted optimization of the product and improving optimization effectiveness.

[0120] After obtaining the requirement type, priority score, priority tag, and evaluation tag corresponding to each product requirement, a product requirement report is generated based on multiple product requirements, priority sequences, and the requirement type, priority score, priority tag, and evaluation tag corresponding to each product requirement. Based on the product requirement report, the product to be optimized is optimized, resulting in a complete product requirement report. This provides quantitative standards for product optimization, which is conducive to formulating accurate and feasible optimization plans, thereby improving the optimization effect of the product to be optimized.

[0121] Figure 3 A schematic diagram of the product optimization device provided in this application is shown below. Figure 3 As shown, the product optimization device 30 provided in this embodiment includes:

[0122] Module 301 is used to acquire multi-source text data corresponding to the product to be optimized.

[0123] The determination module 302 is used to determine multiple candidate texts corresponding to multi-source text data according to preset rules. The preset rules include: preset sentence patterns and preset keywords.

[0124] Analysis module 303 is used to perform semantic analysis on any one of the multiple candidate texts to obtain the corresponding product requirements.

[0125] Product optimization module 304 is used to prioritize multiple product requirements and optimize the products to be optimized based on the prioritized product requirements.

[0126] In one possible implementation, the analysis module 303 is also used to perform text analysis on multi-source text data to obtain multiple first text units, each of which carries a sentence pattern identifier.

[0127] The determining module 302 is further configured to determine a second text unit from a plurality of first text units based on a preset sentence pattern, the second text unit carrying a first sentence pattern identifier;

[0128] The determining module 302 is also used to determine candidate texts from a plurality of second text units that include at least one preset keyword.

[0129] In one possible implementation, the above-mentioned apparatus further includes: a generation module 305;

[0130] The analysis module 303 is also used to identify and analyze candidate texts based on preset requirement parameters to obtain the corresponding requirement content. The requirement parameters include: functional parameters, behavioral parameters and state parameters.

[0131] The generation module 305 is used to generate product requirements based on the requirements corresponding to functional parameters, behavioral parameters, and state parameters.

[0132] In one possible implementation, the above-mentioned device further includes: an identification module 306;

[0133] The identification module 306 is used to identify the requirement characteristics corresponding to the product requirements;

[0134] The determination module 302 is also used to determine the type of requirement corresponding to the product requirement based on the requirement characteristics.

[0135] In one possible implementation, the above-mentioned device further includes: a sorting module 307;

[0136] The determination module 302 is also used to determine the scores corresponding to multiple scoring factors of the demand type;

[0137] The determination module 302 is also used to determine the priority score corresponding to the requirement type based on multiple scores;

[0138] Module 302 is also used to determine the priority label corresponding to the requirement type based on the priority score;

[0139] The sorting module 307 is used to sort multiple requirement types by priority to obtain a priority sequence.

[0140] In one possible implementation, the above-mentioned device further includes: a clustering module 308;

[0141] The determination module 302 is also used to determine multiple word units corresponding to any one of the multiple product requirements;

[0142] The determination module 302 is also used to determine the word frequency weight corresponding to each word unit. The word frequency weight is determined based on the frequency of occurrence of the word unit in product requirements and the feedback frequency of the word unit in all product requirements.

[0143] The generation module 305 is also used to generate the first feature corresponding to the product requirement based on multiple word units and the word frequency weight corresponding to each word unit;

[0144] The determination module 302 is also used to determine the similarity between multiple product requirements based on the first features corresponding to the multiple product requirements respectively;

[0145] Clustering module 308 is used to cluster multiple product requirements based on multiple similarities to obtain the first score of the feedback frequency factor corresponding to each of the multiple requirement types.

[0146] In one possible implementation, the determining module 302 is further configured to determine the user attributes of the user corresponding to each product requirement in the requirement type for any one of the multiple requirement types.

[0147] The determination module 302 is also used to determine the second score corresponding to the user weight factor based on the feedback weights corresponding to multiple user attributes and the number of users corresponding to the demand type.

[0148] In one possible implementation, the analysis module 303 is also used to perform text analysis on any one of the multiple candidate texts to obtain the corresponding evaluation label.

[0149] In one possible implementation, the generation module 305 is also used to generate a product requirement report based on multiple product requirements, a priority sequence, and the requirement type, priority score, priority label, and evaluation label corresponding to each product requirement.

[0150] The product optimization device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0151] Product optimization module 304 is specifically used to optimize products based on product requirement reports.

[0152] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0153] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0154] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0155] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0156] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0157] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0158] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0159] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0160] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0161] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0162] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0163] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0164] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0165] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0166] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0167] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0168] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0169] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0170] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or in the form of software program modules.

[0171] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0172] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0173] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0174] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0175] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A product optimization method, characterized in that, include: Obtain multi-source text data corresponding to the product to be optimized, and determine multiple candidate texts corresponding to the multi-source text data according to preset rules, the preset rules including: preset sentence patterns and preset keywords; For any one of the multiple candidate texts, perform semantic analysis on the candidate text to obtain the corresponding product requirements; Multiple product requirements are prioritized, and the product to be optimized is optimized based on the prioritized product requirements.

2. The method according to claim 1, characterized in that, The step of determining multiple candidate texts corresponding to the multi-source text data according to preset rules includes: Text analysis is performed on the multi-source text data to obtain multiple first text units, each of which carries a sentence structure identifier. Based on the preset sentence pattern, a second text unit is determined from a plurality of first text units, the second text unit carrying a first sentence pattern identifier; Candidate texts containing at least one preset keyword are determined from a plurality of second text units.

3. The method according to claim 1, characterized in that, The step of performing semantic analysis on the candidate text to obtain the corresponding product requirements includes: Based on preset requirement parameters, the candidate text is identified and analyzed to obtain the corresponding requirement content. The requirement parameters include: functional parameters, behavioral parameters, and state parameters. Product requirements are generated based on the requirements corresponding to the functional parameters, behavioral parameters, and state parameters, respectively.

4. The method according to any one of claims 1-3, characterized in that, After performing semantic analysis on the candidate text to obtain the corresponding product requirements, the method further includes: Identify the demand characteristics corresponding to the product requirements; Based on the aforementioned demand characteristics, determine the demand type corresponding to the product demand.

5. The method according to claim 4, characterized in that, The prioritization process for multiple product requirements includes: Determine the scores corresponding to the multiple scoring factors for the aforementioned demand type; Based on the multiple scores, the priority score corresponding to the demand type is determined; Based on the priority score, the priority label corresponding to the requirement type is determined, and the priority sorting process is performed on multiple requirement types to obtain a priority sequence.

6. The method according to claim 5, characterized in that, The scoring factors include: a feedback frequency factor, and the scores corresponding to the multiple scoring factors for determining the demand type include: For any one of the multiple product requirements, determine multiple word units corresponding to that product requirement; Determine the word frequency weight corresponding to each word unit, the word frequency weight being determined based on the frequency of occurrence of the word unit in the product demand and the feedback frequency of the word unit in all product demands; Based on the multiple word units and the word frequency weight corresponding to each word unit, a first feature corresponding to the product requirement is generated; Based on the first features corresponding to the multiple product requirements, the similarity between the multiple product requirements is determined. Based on the multiple similarities, the multiple product requirements are clustered to obtain the first score of the feedback frequency factor corresponding to each of the multiple requirement types.

7. The method according to claim 6, characterized in that, The rating factors also include: a user weight factor, wherein the ratings corresponding to the multiple rating factors for determining the demand type include: For any one of the multiple demand types, determine the user attributes of the user corresponding to each product demand in the demand type; The second score corresponding to the user weight factor is determined based on the feedback weights corresponding to the various user attributes and the number of users corresponding to the demand type.

8. The method according to claim 7, characterized in that, After determining multiple candidate texts corresponding to the multi-source text data according to preset rules, the method further includes: For any one of the multiple candidate texts, perform text analysis on the candidate text to obtain the corresponding evaluation tag.

9. The method according to claim 8, characterized in that, The method further includes: Based on the multiple product requirements, the priority sequence, and the requirement type, priority score, priority tag, and evaluation tag corresponding to each product requirement, a product requirement report is generated. The optimization of the product to be optimized based on the sorted product requirements includes: Based on the product requirement report, the product to be optimized is optimized.

10. A product optimization device, characterized in that, include: The acquisition module is used to acquire multi-source text data corresponding to the product to be optimized. The determination module is used to determine multiple candidate texts corresponding to the multi-source text data according to preset rules, the preset rules including: preset sentence patterns and preset keywords; The analysis module is used to perform semantic analysis on any one of the multiple candidate texts to obtain the corresponding product requirements. The product optimization module is used to prioritize multiple product requirements and optimize the products to be optimized based on the prioritized product requirements.

11. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 9.

Images