Product feature information determination method and device, equipment, medium and product

Abstract

The invention discloses a method, device and equipment for determining product feature information, a medium and a product, which can be applied to the field of financial science and technology, and the method comprises the following steps: determining user evaluation information of a to-be-marked product, the user evaluation information comprising at least one evaluation content; analyzing the at least one evaluation content to obtain at least one feature data, the feature data and the evaluation content being in one-to-one correspondence, and the feature data comprising at least one feature word and a feature tendency of the at least one feature word; and processing each feature word and the feature tendency of each feature word to obtain product feature information of the to-be-marked product. According to the technical scheme, the real use feedback of the user is fused into the product features, the product feature information which is high in precision and better meets the screening requirements of the user is obtained, and the user can be better assisted in product screening work.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology and can be applied to the field of financial technology. In particular, it relates to a method, device, equipment, medium and product for determining product feature information. Background Art

[0002] As the number and types of financial products increase, product management companies are developing personalized feature information for each product to differentiate and manage them. This allows users to filter preferred financial products from a wide range of products based on this personalized feature information. Currently, feature information for financial products is determined based on information such as product type, risk level, maturity limit, investment strategy, market trends, and competitiveness. For example, a comprehensive analysis of each financial product's type, risk level, maturity limit, investment strategy, market trends, and competitiveness is conducted to summarize the features of each financial product. However, different users may have significant differences in their evaluations of the same product, and the same user may have completely different experiences with two very similar products. Therefore, the product features derived from a comprehensive analysis of product type, risk level, maturity limit, investment strategy, market trends, and competitiveness have limited accuracy and applicability, and are unable to effectively assist users in efficiently and accurately screening financial products.

[0003] Therefore, designing a method for determining product feature information with high accuracy that meets user screening needs and improves users' product selection experience is one of the problems that need to be solved urgently. Summary of the Invention

[0004] The present invention provides a method, device, equipment, medium and product for determining product feature information, aiming to integrate users' real usage feedback into product features, obtain product feature information with high accuracy and more in line with users' screening needs, and better assist users in product screening.

[0005] According to one aspect of the present invention, a method for determining product feature information is provided, the method comprising:

[0006] Determining user evaluation information of the product to be marked, wherein the user evaluation information includes at least one evaluation content;

[0007] Parsing at least one evaluation content to obtain at least one feature data, wherein the feature data corresponds to the evaluation content one-to-one, and the feature data includes at least one feature word and at least one feature tendency of the feature word;

[0008] Each feature word and its characteristic tendency are processed to obtain product feature information of the product to be marked.

[0009] According to another aspect of the present invention, a device for determining product feature information is provided. The device for determining product feature information is configured to implement the method for determining product feature information in any embodiment of the present invention. The device includes:

[0010] An information determination module, configured to determine user evaluation information of the product to be marked, wherein the user evaluation information includes at least one evaluation content;

[0011] A data processing module, configured to parse at least one evaluation content to obtain at least one feature data, wherein the feature data corresponds to the evaluation content one-to-one, and the feature data includes at least one feature word and at least one feature tendency of the feature word;

[0012] The feature determination module is used to process each feature word and the feature tendency of each feature word to obtain product feature information of the product to be marked.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and a memory communicatively coupled to the at least one processor;

[0015] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the method for determining product feature information in any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for enabling a processor to implement the method for determining product feature information in any embodiment of the present invention when the computer instructions are executed.

[0017] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for determining product feature information according to any embodiment of the present invention is implemented.

[0018] The method for determining product feature information of the present invention includes: determining user evaluation information of the product to be marked, the user evaluation information including at least one evaluation content; parsing the at least one evaluation content to obtain at least one feature data, wherein the feature data and the evaluation content correspond one-to-one, and the feature data includes at least one feature word and at least one feature word characteristic tendency; processing each feature word and each feature word characteristic tendency to obtain product feature information of the product to be marked. The technical solution of the present invention will parse the evaluation information of each user on the product to be marked, determine the personalized usage experience of each user, and then synthesize the usage experience of each user to obtain the feature information of the product to be marked, integrate the user's real usage feedback into the product features, and the obtained product feature information is highly accurate and more in line with the user's screening needs, and can better assist users in product screening. It solves the problems that the product features obtained by comprehensive analysis based on product type, risk level, term limit, investment strategy, market trend and competitiveness have limited accuracy, low applicability, and cannot better assist users in efficiently and accurately screening financial products.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a flowchart of a method for determining product feature information provided by the present invention;

[0022] Figure 2 It is a flowchart of another method for determining product feature information provided by the present invention;

[0023] Figure 3 It is a structural diagram of a device for determining product characteristic information provided by the present invention;

[0024] Figure 4 It is a structural schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", "initial", "intermediate", "candidate", "alternative", "target", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Figure 1 This is a flow chart of a method for determining product feature information provided by the present invention. This embodiment is applicable to determining product feature information with high accuracy that meets user screening needs. This method can be executed by the device for determining product feature information provided by the present invention. The device can be implemented in the form of hardware and / or software. In a specific embodiment, the device can be integrated into an electronic device. The following embodiments will be described using the device integrated into an electronic device as an example. Figure 1 , the method specifically comprises the following steps:

[0028] S101: Determine user evaluation information of the product to be marked.

[0029] Products to be marked can be understood as products that need to be characterized. Products to be marked may include savings products, credit products, comprehensive products, low-liquidity products, high-liquidity products, interest products, non-interest products, fixed-income products, equity products, derivative products, etc. Different types of products have different functional tendencies. The functional tendencies and benefits of multiple products of the same type also vary to a certain extent. Therefore, different products bring different user experiences. User evaluation information can be understood as real feedback information from users who have used the products to be marked. User evaluation information includes at least one evaluation content. The evaluation content can be understood as the user's feedback text, including but not limited to the message text under the products to be marked and the background feedback information of the products to be marked.

[0030] Products to be tagged are all of the current company's financial products or untagged financial products. Tagging a company's financial products facilitates user selection of products that suit them or that interest them. For example, assuming the product to be tagged is Savings Product 1, user review information would include all messages in the message area of ​​Savings Product 1 and all private feedback messages in the backend interactive area of ​​Savings Product 1. This setup aims to capture comprehensive and authentic user feedback in order to develop product features tailored to the user experience.

[0031] In one embodiment, S101 may specifically include: obtaining user feedback information about the product to be marked within a preset time period; and classifying the user feedback information according to user identifiers to obtain at least one evaluation content.

[0032] Among them, the preset time period can be understood as a pre-set information acquisition time. The preset time period can be from the start of use of the product to be marked to the current moment to ensure the integrity of the data, or it can be a time period obtained by calculating a certain length of time from the current moment to ensure the real-time nature of the data, for example, the last x days, the last x months, etc. The preset time period of the present invention can be set according to the data volume of the product to be marked and the determination logic of the characteristic information. For example, when the data volume is greater than the preset data volume or the characteristic information is required to be as flexible as possible (i.e., in line with the user's real-time requirements), the preset time period is determined to be a time period obtained by calculating a certain length of time from the current moment. When the data volume is not greater than the preset data volume or the characteristic information is required to be as comprehensive as possible, the preset time period is determined to be from the start of use of the product to be marked to the current moment. The purpose of such a setting is to reduce the amount of data that needs to be processed as much as possible while ensuring the real-time nature and accuracy of the characteristic information, thereby improving the efficiency of determining the characteristic information.

[0033] User feedback information can be understood as feedback records left by users after using the product to be tagged, such as text left by users in the message area of ​​the product to be tagged, text sent to the backend interactive area of ​​the product to be tagged, etc. User identification can be understood as personalized characteristic information of the user, such as the user's name, number, nickname, etc., which is a unique identifier of the user and is used to distinguish between different users. The present invention divides user feedback information and organizes it according to user identification. Evaluation content can be understood as comprehensive feedback information from each user. The integration of feedback data from each user by user identification is intended to provide targeted analysis of each user's personalized evaluation.

[0034] Assuming that user 1's feedback information is text 1 and text 3, and user 2's feedback information is text 2 and text 4, there are two evaluation contents. Evaluation content 1 is user 1's feedback information, which is used to determine user 1's personalized evaluation and consists of text 1 and text 3. Evaluation content 2 is user 2's feedback information, which is used to determine user 2's personalized evaluation and consists of text 2 and text 4.

[0035] S102: Analyze at least one evaluation content to obtain at least one feature data.

[0036] There is a one-to-one correspondence between feature data and review content. Parsing at least one review content to obtain at least one feature data can be understood as parsing each review content separately to obtain the user's personalized evaluation corresponding to each review content, which is used to represent different users' attitudes towards the marked product. The feature data includes at least one feature word and at least one feature word's characteristic tendency. Feature words can be understood as keywords in the review content, such as frequently occurring words, subject words, and semantic core words, which are used to express the thinking points that the user wants to explain. The characteristic tendency of feature words can be understood as descriptive information about the feature words, which is used to express the user's thoughts on a particular thinking point.

[0037] For example, if the feature word is interest rate and the feature tendency is high, the feature data indicates that the user believes the current product is a high-interest product with a high return on investment. The advantage of this setting is that it allows for targeted analysis of each review content and obtains the personalized theme of each review content, thereby summarizing the characteristics of the product.

[0038] For any evaluation content, the evaluation content is parsed to obtain feature data, including: dividing the evaluation content according to a pre-set word segmentation rule to obtain at least two text words; determining the importance of each text word based on the first frequency of each text word appearing in the first evaluation content and the second frequency of each text word appearing in the second evaluation content; the first evaluation content is the current evaluation content, and the second evaluation content is all evaluation content in the user evaluation information except the first evaluation content; determining at least one feature word based on the importance of each text word and a pre-set feature word selection rule; determining the feature tendency of at least one feature word based on the position information of at least one feature word, the part-of-speech information of each text word and the position information.

[0039] Pre-set word segmentation rules are used to divide the review content into multiple words (i.e., text words). By counting and analyzing the text words, characteristic words and characteristic tendencies of the review content are obtained. Word segmentation rules include, but are not limited to, context-based word segmentation methods, statistical result-based word segmentation methods, and word segmentation methods based on word library string matching.

[0040] Context-based word segmentation analyzes the semantics of the review content to understand it, identifying its constituent words and segmenting them. Words have fixed combinations. The higher the probability of a particular combination and the higher the frequency of similar characters, the more likely it is a word. Statistical word segmentation methods segment based on the frequency of similar characters. Word segmentation methods based on lexicon string matching use string comparison principles to match the string corresponding to the review content against a lexicon. If a match is found with a word in the lexicon, the word is segmented, and the segmented word becomes the text word.

[0041] The first evaluation content is the evaluation content currently being parsed, the second evaluation content is all evaluation content of the product to be marked except the first evaluation content, the first frequency is the number of times or frequency that the text word to be parsed appears in the first evaluation content, and the second frequency is the number of times or frequency that the text word to be parsed appears in the second evaluation content. For example, assuming that the evaluation content of the product to be marked includes evaluation content 1, evaluation content 2, and evaluation content 3, the text word sequence after evaluation content 1 is parsed is text word 1, text word 2, text word 1, text word 3, text word 2, text word 1, text word 3, and text word 1, the text word sequence after evaluation content 2 is parsed is text word 3, text word 4, text word 4, text word 3, text word 2, text word 3, text word 4, and text word 5, and the text word sequence after evaluation content 3 is parsed is text word 1, text word 2, text word 3, text word 3, text word 3, text word 2, text word 5, and text word 4. For evaluation content 1, taking the number of times as an example, the first frequency of text word 1 is 4, and the second frequency is 1; taking the frequency as an example, the first frequency of text word 1 is 50%, and the second frequency is 6.25%.

[0042] The importance of a text word can be understood as the weight of the text word in the evaluation content, which is used to measure whether the text word can represent the user's usage experience. The more important the text word is, the larger the space it occupies in the evaluation content, the greater the probability of the user's description and mention, and the more representative the user's usage experience. The pre-set feature word selection rules can be understood as a method of filtering feature words. For example, filtering text words with an importance greater than x as feature words, filtering text words of a noun nature with an importance greater than x as feature words, filtering the top x text words in importance ranking as feature words, filtering the top x text words of a noun nature in importance ranking as feature words, etc., x is an integer greater than 1. The specific value is related to the filtering logic and is not limited here. The part-of-speech information of a text word is the type of the text word, for example, noun, verb, adjective, etc. The position information of a text word can be understood as the position of the text word in the evaluation content. The position information of a feature word is the position of the feature word in the evaluation content. The feature tendency of a feature word can be understood as the descriptive vocabulary of the feature word. A feature word can correspond to one or more feature tendencies, that is, there can be more than one descriptive vocabulary for a feature word. The purpose of this setting is to summarize the user's usage experience as comprehensively as possible.

[0043] Generally, the descriptive vocabulary of a feature word is not too far away from the feature word and has the part of speech of an adjective or noun. For example, adjectives or nouns are within five words before and after the feature word, or within ten words before and after the feature word. By combining the position information of the feature word, the part of speech information and position information of each text word, or combining the text semantics, the position information of the feature word, the part of speech information and position information of each text word, the descriptive vocabulary corresponding to the feature word can be obtained, that is, the characteristic tendency of the feature word. This search method can summarize the user's evaluation intention as much as possible and obtain a concise word combination that can express the user's main ideas.

[0044] The feature word extraction method of the present invention can be based on the term frequency-inverse document frequency (TF-IDF) logic, which aims to use the weighting technology of information retrieval and text mining to evaluate the importance of a word to a document set or one of the documents in a corpus.

[0045] Furthermore, the importance of a word is directly proportional to its frequency of appearance in the current document and inversely proportional to its frequency of appearance in other documents. For example, if a word appears more frequently in the current document and less frequently in other documents, then this word has good discriminative power and is very suitable for classification, distinguishing the differences between the current document and other documents. This word can be considered as a highly important word in the current document and can explain the characteristics of the current document and other documents.

[0046] Specifically, for any text word, the importance of the text word is determined based on the first frequency of the text word appearing in the first evaluation content and the second frequency of the text word appearing in the second evaluation content, including: when the first frequency is greater than or equal to the first quantity threshold and the second frequency is less than the second quantity threshold, the importance of the text word is determined to be the first importance; the second quantity threshold is less than the first quantity threshold; when the first frequency is greater than or equal to the first quantity threshold and the second frequency is greater than or equal to the second quantity threshold, the importance of the text word is determined to be the second importance; the second importance is lower than the first importance; when the first frequency is less than the first quantity threshold and the second frequency is greater than or equal to the second quantity threshold, the importance of the text word is determined to be the third importance; the third importance is lower than the second importance; when the first frequency is less than the first quantity threshold and the second frequency is less than the second quantity threshold, the importance of the text word is determined to be the fourth importance; the fourth importance is lower than the third importance.

[0047] Among them, the first quantity threshold can be understood as a high frequency value, which is used to evaluate whether the frequency of a word is a high frequency word. The word corresponding to a frequency greater than the first quantity threshold is a high frequency word. The second quantity threshold can be understood as a low frequency value. The word corresponding to a frequency less than the second quantity threshold is a low frequency word. The two frequencies complement each other and can be used to determine the importance of each text word. For example, the higher the frequency of appearance in the current text but the lower the frequency of appearance in other texts, the more it can reflect the characteristics of the current text and the highest importance. Conversely, the lower the frequency of appearance in the current text and the higher the frequency of appearance in other texts, the less it can reflect the characteristics of the current text and the less important it is. It is worth noting that the lower the frequency of appearance in the current text and the lower the frequency of appearance in other texts, the less it will reflect the characteristics of the current text.

[0048] The benefit of this setup is that it clarifies the method for determining the importance of text words, allowing for efficient and accurate assessment of the importance of each text word and the subsequent identification of feature words. It's worth noting that feature words are generally names. If there are many text words, lexical screening can be combined with part of speech when determining feature words. This approach can reduce the intensity of lexical screening and improve the efficiency of feature word identification.

[0049] S103: Process each feature word and its feature tendency to obtain product feature information of the product to be marked.

[0050] Among them, the product feature information of the product to be marked can be understood as the product feature introduction of the product to be marked, which integrates the comprehensive recommendation label information obtained after the usage experience of different users. Specifically, different users represent different user attributes. The present invention can also summarize the user attributes together. On the one hand, different types of products can be recommended to different users. On the other hand, users can select products that suit them based on their own attributes and the product feature information combined with user attributes. User attributes include but are not limited to age, gender, job type, work location, home location, working hours, family situation, short-term life plan, etc.

[0051] For example, assume that user A is a middle-aged woman, user B is a middle-aged man, and user C is a young woman. User A's feature data indicates that user A's evaluation of the tagged product is high risk, user B's feature data indicates that user B's evaluation of the tagged product is high interest rate, and user C's feature data indicates that user C is not interested in the tagged product. The product feature information for the tagged product is determined to be that middle-aged women believe the risk is high, middle-aged men believe the interest rate is high, and young women are not interested. The advantage of this setting is that it processes real user review information to obtain product labels that are integrated with user experience. This allows users to understand more comprehensive product feature information that is more in line with their user experience when screening products, reducing the possibility of product selection errors.

[0052] In one embodiment, S103 may specifically include: summarizing each feature word according to the category attributes of the feature word to obtain candidate features, and summarizing the feature tendencies corresponding to the candidate features to obtain description statements of the candidate features; generating product feature information based on the candidate features and the description statements of the candidate features.

[0053] Among them, the category attribute can be understood as the type of feature word. For example, words such as like, love, and don’t want to give up can be classified as favorite, and words such as shape, color, volume, and size can be classified as appearance. The purpose of summarizing the feature words to obtain candidate features is to merge feature words of the same type, reduce the number of feature words, and then reduce the amount of feature data and the number of product feature information, so as to facilitate users to intuitively view product feature information.

[0054] Candidate features can be understood as features obtained by summarizing and classifying similar features. The description of candidate features is the descriptive vocabulary or language that semantically summarizes the feature tendencies related to the candidate features. For example, assuming that the feature words include color, volume, and shape, the color characteristic tendency is good-looking, the volume characteristic tendency is suitable, and the shape characteristic tendency is satisfactory, then the candidate feature is appearance, and the description of the candidate feature is satisfactory. Assuming that the candidate features include appearance and performance, the description of appearance is satisfactory, and the description of performance is low speed, then the product feature information is satisfactory appearance but low product speed.

[0055] Furthermore, after obtaining the product feature information of the product to be marked, the present invention also includes: determining the associated feature information and the opposing feature information of the product feature information; when receiving a similar product recommendation indication sent by the user, displaying the associated feature information and the associated products corresponding to the associated feature information to the user based on the interactive interface; when receiving a completely different product recommendation indication sent by the user, displaying the opposing feature information and the opposing products corresponding to the opposing feature information to the user based on the interactive interface.

[0056] Receiving a user recommendation instruction proves that the user does not want to choose the product to be marked. The present invention can also recommend similar or highly different products to the user. When receiving a similar product recommendation instruction sent by the user, it proves that the user is slightly dissatisfied with the product to be marked and wants to choose a product that is not much different from the product to be marked. In this case, the user will be recommended related products of the product to be marked. When receiving a completely different product recommendation instruction sent by the user, it proves that the user is significantly dissatisfied with the product to be marked and wants to choose a product that is significantly different from the product to be marked. In this case, the user will be recommended products that are opposite to the product to be marked (for example, products with significantly different parameters such as interest rates and risks). The purpose of this setting is to use a decision tree to guide users step by step to find satisfactory products and enhance the user's product selection experience.

[0057] Specifically, the associated feature information can be understood as product features that are somewhat associated with the product feature information of the product to be marked, for example, product features that belong to the same savings category and have similar interest rates, risks and other parameters, which are used to guide users to understand, view and screen the associated products of the product to be marked. The opposing feature information can be understood as product features that are significantly different from the product feature information of the product to be marked, for example, product features with large interest rate differences and opposite risks, which are used to guide users to understand, view and screen comparative products of the product to be marked.

[0058] The technical solution of the above embodiment analyzes individual users' evaluation information on the products to be tagged, determines each user's personalized usage experience, and then integrates these experiences to obtain feature information of the products to be tagged. This integrates users' actual usage feedback into the product features, resulting in highly accurate product feature information that better meets user screening needs and can better assist users in product screening. This solves the problem that product features derived from a comprehensive analysis based on product type, risk level, term limit, investment strategy, market trend, and competitiveness are limited in accuracy and applicability, and are unable to better assist users in efficiently and accurately screening financial products.

[0059] Figure 2 This is a flow chart of another method for determining product feature information provided by the present invention. This embodiment provides a preferred method for determining product feature information based on the above embodiment. Specifically, Figure 2 As shown, the method includes:

[0060] S201: Obtain user feedback information on the product to be marked within a preset time period.

[0061] S202: Classify user feedback information according to the user identifier to obtain at least one evaluation content.

[0062] S203: Analyze at least one evaluation content to obtain at least one feature data.

[0063] There is a one-to-one correspondence between the feature data and the evaluation content, and the feature data includes at least one feature word and at least one feature tendency of the feature word.

[0064] S204 . Summarize the feature words according to their category attributes to obtain candidate features, and summarize the feature tendencies corresponding to the candidate features to obtain description sentences of the candidate features.

[0065] S205: Generate product feature information based on the candidate features and their descriptions.

[0066] S206: Determine the associated feature information and the opposing feature information of the product feature information.

[0067] S207. When a similar product recommendation indication is received from a user, related feature information and related products corresponding to the related feature information are displayed to the user based on the interactive interface; when a completely different product recommendation indication is received from a user, opposite feature information and opposite products corresponding to the opposite feature information are displayed to the user based on the interactive interface.

[0068] Figure 3 This is a schematic diagram of the structure of a device for determining product feature information provided by the present invention. Figure 3As shown, the device includes: an information determination module 301, a data processing module 302 and a feature determination module 303.

[0069] The information determination module 301 is used to determine user evaluation information of the product to be marked, wherein the user evaluation information includes at least one evaluation content.

[0070] The data processing module 302 is configured to parse at least one evaluation content to obtain at least one feature data, wherein the feature data corresponds to the evaluation content one-to-one and the feature data includes at least one feature word and a feature tendency of at least one feature word.

[0071] The feature determination module 303 is used to process each feature word and its feature tendency to obtain product feature information of the product to be marked.

[0072] Optionally, the information determination module 301 is specifically configured to: obtain user feedback information of the product to be marked within a preset time period; and classify the user feedback information according to user identification to obtain at least one evaluation content.

[0073] Optionally, for any evaluation content, the data processing module 302 is specifically used to: divide the evaluation content according to a pre-set word segmentation rule to obtain at least two text words; determine the importance of each text word based on the first frequency of each text word appearing in the first evaluation content and the second frequency of each text word appearing in the second evaluation content; the first evaluation content is the current evaluation content, and the second evaluation content is all evaluation content in the user evaluation information except the first evaluation content; determine at least one feature word based on the importance of each text word and a pre-set feature word selection rule; determine the feature tendency of at least one feature word based on the position information of at least one feature word, the part-of-speech information of each text word and the position information.

[0074] Optionally, for any text word, the data processing module 302 is specifically used to: when the first frequency is greater than or equal to the first quantity threshold and the second frequency is less than the second quantity threshold, determine the importance of the text word as the first importance; the second quantity threshold is less than the first quantity threshold; when the first frequency is greater than or equal to the first quantity threshold and the second frequency is greater than or equal to the second quantity threshold, determine the importance of the text word as the second importance; the second importance is lower than the first importance; when the first frequency is less than the first quantity threshold and the second frequency is greater than or equal to the second quantity threshold, determine the importance of the text word as the third importance; the third importance is lower than the second importance; when the first frequency is less than the first quantity threshold and the second frequency is less than the second quantity threshold, determine the importance of the text word as the fourth importance; the fourth importance is lower than the third importance.

[0075] Optionally, the feature determination module 303 is specifically used to: summarize the feature words according to the category attributes of the feature words to obtain candidate features, and summarize the feature tendencies corresponding to the candidate features to obtain description statements of the candidate features; generate product feature information based on the candidate features and the description statements of the candidate features.

[0076] Optionally, the feature determination module 303 is also used to: after obtaining the product feature information of the product to be marked, determine the associated feature information and the opposing feature information of the product feature information; when receiving a similar product recommendation indication sent by the user, display the associated feature information and the associated products corresponding to the associated feature information to the user based on the interactive interface; when receiving a completely different product recommendation indication sent by the user, display the opposing feature information and the opposing products corresponding to the opposing feature information to the user based on the interactive interface.

[0077] The device for determining product feature information provided in the above embodiments can execute the method for determining product feature information provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0078] Figure 4 : is a structural diagram of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0079] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (also known as random access memory, RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12 and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0080] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0081] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the method for determining product feature information.

[0082] In some embodiments, the method for determining product feature information may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining product feature information described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining product feature information in any other appropriate manner (e.g., by means of firmware).

[0083] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0085] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device or any suitable combination of the foregoing.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0087] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0088] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0089] In one embodiment, the present invention further includes a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method for determining product feature information of any embodiment of the present invention.

[0090] The computer program product may be implemented in a computer program code for performing the operations of the present invention written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​and conventional procedural programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0092] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining product feature information, characterized in that: include: Determining user evaluation information of the product to be marked, wherein the user evaluation information includes at least one evaluation content; Parsing the at least one evaluation content to obtain at least one feature data, wherein the feature data corresponds to the evaluation content in a one-to-one manner, and the feature data includes at least one feature word and a feature tendency of the at least one feature word; Each of the characteristic words and the characteristic tendency of each of the characteristic words is processed to obtain product characteristic information of the product to be marked.

2. The method according to claim 1, characterized in that Determining user evaluation information of the product to be marked includes: Obtaining user feedback information on the product to be marked within a preset time period; The user feedback information is classified according to the user identifier to obtain the at least one evaluation content.

3. The method according to claim 1, characterized in that For any evaluation content, analyze the evaluation content and obtain feature data, including: Divide the evaluation content according to a preset word segmentation rule to obtain at least two text words; Determining the importance of each text word based on a first frequency of occurrence of each text word in a first evaluation content and a second frequency of occurrence of each text word in a second evaluation content; wherein the first evaluation content is the current evaluation content, and the second evaluation content is all evaluation contents in the user evaluation information except the first evaluation content; Determining at least one feature word based on the importance of each text word and a preset feature word selection rule; Based on the position information of the at least one feature word, the part-of-speech information and the position information of each of the text words, a feature tendency of the at least one feature word is determined.

4. The method according to claim 3, characterized in that For any text word, determining the importance of the text word based on a first frequency of occurrence of the text word in a first evaluation content and a second frequency of occurrence of the text word in a second evaluation content includes: When the first frequency is greater than or equal to a first quantity threshold and the second frequency is less than a second quantity threshold, determining the importance of the text word to be a first importance; wherein the second quantity threshold is less than the first quantity threshold; When the first frequency is greater than or equal to the first quantity threshold and the second frequency is greater than or equal to the second quantity threshold, determining the importance of the text word to be a second importance; wherein the second importance is lower than the first importance; When the first frequency is less than the first quantity threshold and the second frequency is greater than or equal to the second quantity threshold, determining the importance of the text word to be a third importance; wherein the third importance is lower than the second importance; When the first frequency is less than the first quantity threshold and the second frequency is less than the second quantity threshold, the importance of the text word is determined to be a fourth importance; wherein the fourth importance is lower than the third importance.

5. The method according to claim 1, wherein The processing of each of the characteristic words and the characteristic tendency of each of the characteristic words to obtain the product characteristic information of the product to be marked includes: According to the category attributes of the feature words, the feature words are summarized to obtain candidate features, and the feature tendencies corresponding to the candidate features are summarized to obtain description sentences of the candidate features; The product feature information is generated based on the candidate features and description statements of the candidate features.

6. The method according to claim 1, characterized in that After obtaining the product feature information of the product to be marked, the method further includes: Determining associated feature information and opposing feature information of the product feature information; When receiving a similar product recommendation indication sent by a user, displaying the associated feature information and the associated products corresponding to the associated feature information to the user based on the interactive interface; When a completely different product recommendation indication sent by a user is received, the opposing feature information and the opposing product corresponding to the opposing feature information are displayed to the user based on an interactive interface.

7. A device for determining product characteristic information, characterized in that: For implementing the method for determining product feature information according to any one of claims 1 to 6, the device for determining product feature information comprises: An information determination module, configured to determine user evaluation information of the product to be marked, wherein the user evaluation information includes at least one evaluation content; a data processing module, configured to parse the at least one evaluation content to obtain at least one feature data, wherein the feature data corresponds to the evaluation content in a one-to-one manner and includes at least one feature word and a feature tendency of the at least one feature word; The feature determination module is used to process each of the feature words and the feature tendency of each of the feature words to obtain product feature information of the product to be marked.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining product feature information as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining product feature information according to any one of claims 1 to 6 when executed.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for determining product feature information according to any one of claims 1 to 6.

Images