Commodity recommendation method and system based on artificial intelligence

Abstract

The invention relates to a commodity recommendation method based on artificial intelligence, and the method comprises the steps: determining a first shopping personality of a user according to environment data, behavior data and a pre-constructed feature-personality-commodity knowledge graph, and carrying out the first shopping personality of the user from the feature-personality-commodity knowledge graph, obtaining a first recommendation strategy corresponding to the first shopping personality to perform commodity recommendation, obtaining behavior data fed back by the user based on the recommended commodity, determining a second shopping personality of the user according to the environment data, the behavior data and the feature-personality-commodity knowledge graph, and performing commodity recommendation from the feature-personality-commodity knowledge graph. And obtaining a second recommendation strategy corresponding to the second shopping personality, and recommending commodities based on the second recommendation strategy. According to the invention, the problem of low commodity recommendation efficiency is solved. Through analysis of multi-source real-time data, the shopping personality is adaptively adjusted, and the user demand is dynamically adapted to ensure that the recommended commodity always conforms to the current shopping psychology of the user, and the accuracy and efficiency of commodity recommendation are improved.

Description

Technical Field

[0001] The present application relates to the field of e-commerce, and in particular to methods, systems, electronic devices, and storage media for recommending products based on artificial intelligence. Background Art

[0002] With the explosive growth of e-commerce and digital content, users are facing the dilemma of information overload. Personalized product recommendations can reduce information overload, help users quickly find products of interest, and improve shopping satisfaction.

[0003] In related technologies, existing product recommendation systems only rely on historical data to build fixed user portraits, and are unable to dynamically adapt to users' real-time needs. In addition, a single recommendation strategy is difficult to cover users' multi-scenario needs, resulting in low recommendation efficiency.

[0004] Currently, no effective solution has been proposed to the problem of low efficiency of product recommendation in related technologies. Summary of the Invention

[0005] The embodiments of the present application provide a product recommendation method, system, electronic device, and storage medium based on artificial intelligence to at least solve the problem of low product recommendation efficiency in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a product recommendation method based on artificial intelligence, the method comprising:

[0007] Obtaining environmental data and initial user behavior data, and determining the user's first shopping personality based on the environmental data, the behavior data, and a pre-built feature-personality-product knowledge graph;

[0008] Obtaining a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and making product recommendations based on the first recommendation strategy;

[0009] Obtaining user behavior data based on product recommendation feedback, and determining the user's second shopping personality based on the environmental data, the behavior data, and the feature-personality-product knowledge graph;

[0010] A second recommendation strategy corresponding to the second shopping personality is obtained from the feature-personality-product knowledge graph, and products are recommended based on the second recommendation strategy.

[0011] In some embodiments, the feature-personality-product knowledge graph stores the personality weight of each shopping personality and the feature weights of the feature parameters under each shopping personality; the shopping personality of the user is determined based on the environmental data, the behavioral data, and the pre-constructed feature-personality-product knowledge graph, where the shopping personality includes a first shopping personality and a second shopping personality including:

[0012] extracting target feature parameters from the environmental data and the behavioral data;

[0013] Calculate the characteristic value of each shopping personality according to the characteristic weight of the target characteristic parameter under each shopping personality;

[0014] Based on the characteristic value and personality weight of each shopping personality, an evaluation value of each shopping personality is determined, and the shopping personality with the largest evaluation value is used as the shopping personality of the user.

[0015] In some embodiments, extracting target feature parameters from the environmental data and the behavioral data includes:

[0016] extracting time parameters, meteorological parameters, location parameters, and equipment type parameters from the environmental data;

[0017] Active input parameters and browsing behavior parameters are extracted from the behavior data.

[0018] In some embodiments, the method further comprises:

[0019] After the user purchases a product, adjusting the weight data in the feature-personality-product knowledge graph based on the current purchase behavior data, wherein the weight data includes personality weight and feature weight; and / or

[0020] Based on the time decay function, the weight data in the feature-personality-product knowledge graph is adjusted.

[0021] In some embodiments, the method further comprises:

[0022] According to the behavioral data of the user based on the feedback of the recommended product, the weight data of the node corresponding to the recommended product in the feature-personality-product knowledge graph is adjusted, the node includes the shopping personality and feature parameters, and the weight data includes the personality weight and the feature weight.

[0023] In some embodiments, a recommendation strategy corresponding to a shopping personality is obtained from the feature-personality-product knowledge graph, where the shopping personality includes a first shopping personality and a second shopping personality, and the recommendation strategy includes the first recommendation strategy and the second recommendation strategy including:

[0024] In the case where the shopping personality is an efficiency type, the efficiency type is matched with the feature-personality-product knowledge graph to obtain a recommendation strategy that recommends products from high to low based on sales volume and displays a parameter comparison column; or

[0025] In the case where the shopping personality is exploratory, the exploratory type is matched with the feature-personality-product knowledge graph to obtain a recommendation strategy that prioritizes new products, seasonal products, and unpopular products.

[0026] In some embodiments, the method further comprises:

[0027] The feature-personality-product knowledge graph is stored via encrypted hash values, and a different pseudonym is set for each shopping personality;

[0028] The mapping relationship between the pseudonym identifier and the user's real ID is stored in an ID mapping table.

[0029] In a second aspect, an embodiment of the present application provides an artificial intelligence-based product recommendation system, the system comprising:

[0030] A first personality analysis module is configured to obtain environmental data and initial user behavior data, and determine the user's first shopping personality based on the environmental data, the behavior data, and a pre-built feature-personality-product knowledge graph;

[0031] A first recommendation module, configured to obtain a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and make product recommendations based on the first recommendation strategy;

[0032] A second personality analysis module is used to obtain user behavior data based on recommended product feedback, and determine the user's second shopping personality based on the environmental data, the behavior data, and the feature-personality-product knowledge graph;

[0033] The second recommendation module is used to obtain a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph, and recommend products based on the second recommendation strategy.

[0034] In a third aspect, an embodiment of the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the artificial intelligence-based product recommendation method as described in the first aspect above is implemented.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence-based product recommendation method as described in the first aspect above.

[0036] Compared to related technologies, the artificial intelligence-based product recommendation method provided in the embodiment of the present application obtains environmental data and the user's initial behavioral data, determines the user's first shopping personality based on the environmental data, behavioral data, and a pre-built feature-personality-product knowledge graph, obtains a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, recommends products based on the first recommendation strategy, obtains user behavioral data based on recommended product feedback, determines the user's second shopping personality based on the environmental data, behavioral data, and the feature-personality-product knowledge graph, obtains a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph, and recommends products based on the second recommendation strategy, thereby solving the problem of low product recommendation efficiency. By analyzing multi-source real-time data, adaptively adjusting the shopping personality, and dynamically adapting to user needs, it ensures that the recommended products always meet the user's current shopping psychology, thereby improving the accuracy and efficiency of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 is a flow chart of a product recommendation method based on artificial intelligence according to an embodiment of the present application;

[0039] Figure 2 This is a structural block diagram of an artificial intelligence-based product recommendation system according to an embodiment of the present application;

[0040] Figure 3 Schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts are within the scope of protection of this application.

[0042] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0043] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0044] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0045] This embodiment provides a product recommendation method based on artificial intelligence. Figure 1 is a flow chart of a commodity recommendation method based on artificial intelligence according to an embodiment of the present application, such as Figure 1As shown, the process includes the following steps:

[0046] Step S101: Obtain environmental data and the user's initial behavior data, and determine the user's first shopping personality based on the environmental data, behavior data, and a pre-built feature-personality-product knowledge graph.

[0047] In this embodiment, environmental data includes but is not limited to time (e.g., holidays, weekdays), geographic location (e.g., office area, residential area), device type (e.g., mobile terminal, PC terminal), weather, social trends (e.g., hot search products) and inventory status; user behavior data includes but is not limited to multimodal input information (e.g., text input, voice input, image input), click frequency, page scrolling speed, and price comparison behavior.

[0048] It should be noted that the product recommendation method of this application is applied to an AI-based shopping platform. Unlike traditional shopping platforms, which include recommended products on the initial page, the initial page of this shopping platform is a dialog page. The user's initial behavioral data is usually input text, voice, or pictures on the dialog page. By extracting features from the environmental data and the initial behavioral data, the extracted features are matched with the feature-personality-product knowledge graph to confirm the user's primary shopping personality.

[0049] When recommending products based on shopping personality, the shopping platform jumps from the dialog box page to the product recommendation page. The product recommendation page includes pictures and detailed information of each recommended product. The detailed information includes but is not limited to the product name, product price, price comparison chart, and product material.

[0050] Step S102: Obtain a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and make product recommendations based on the first recommendation strategy.

[0051] The feature-personality-product knowledge graph includes mapping relationships between feature parameters and shopping personality, as well as mapping relationships between shopping personality and product recommendation strategies. Table 1 is an example table of mapping relationships between feature-personality-product knowledge graphs according to an embodiment of the present application.

[0052] Shopping personality Trigger Features Recommended Strategy Efficiency Weekday evening + clear search keywords Display sales TOP10 and parameter comparison column Exploratory Weekend + deep page browsing + cross-category jump Push unpopular group buying and user UGC content Dad type Browse Maternity & Baby Products + Men Preferred maternal and infant products

[0053] Step S103: Obtain the user's behavioral data based on the recommended product feedback, and determine the user's second shopping personality based on the environmental data, behavioral data, and feature-personality-product knowledge graph.

[0054] After recommending products based on the first recommendation strategy, the behavioral data of user feedback is obtained in real time to determine whether the user's shopping personality has changed. If so, the shopping personality is updated in real time through lightweight edge computing to ensure that the user does not perceive the switch (for example, switching from "efficiency type" to "daddy type" only requires a response delay of 300ms).

[0055] It should be noted that the first shopping personality and the second shopping personality can be the same shopping personality. That is, if the shopping personality obtained through analysis of the user's feedback behavior data is still the user's first shopping personality, product recommendations will continue to be made based on the first shopping personality.

[0056] Step S104: Obtain a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph, and recommend products based on the second recommendation strategy.

[0057] When the user's shopping personality changes, it is necessary to switch to a new shopping personality (second shopping personality) to make product recommendations.

[0058] For example, analysis shows that the user's first shopping personality is efficiency. After making product recommendations based on the efficiency personality, it is detected that the user frequently browses maternal and child products. Based on this behavior analysis, the user has transformed into a daddy personality. In this case, the current shopping personality is switched to the daddy type for product recommendations.

[0059] Through the above steps S101 to S104, environmental data and user behavior data are analyzed in real time, and the shopping personality is adaptively switched according to the analysis results to dynamically adapt to user needs, thereby improving the accuracy and efficiency of product recommendations and solving the problem of low efficiency of product recommendations.

[0060] In some embodiments, the feature-personality-product knowledge graph stores the personality weight of each shopping personality and the feature weights of the feature parameters under each shopping personality.

[0061] In step S101 and step S103, the user's shopping personality is determined based on the environmental data, behavioral data, and the pre-built feature-personality-product knowledge graph. The shopping personality includes a first shopping personality and a second shopping personality including:

[0062] Step S201: extract target feature parameters from environmental data and behavior data.

[0063] In some embodiments, step S201 includes:

[0064] Step S2011: extracting time parameters, weather parameters, location parameters, and equipment type parameters from environmental data.

[0065] Time parameters include date parameters and time parameters, and meteorological parameters include weather parameters and season parameters. Optionally, the date parameter can be used to determine whether it is a weekday or a holiday, the clock parameter can be used to determine whether it is morning, noon, or evening, the location parameter can be used to determine whether the user is in an office area or a residential area, and the device parameter can be used to determine whether the user is using a mobile device or a PC.

[0066] Step S2012: extracting active input parameters and browsing behavior parameters from the behavior data.

[0067] Active input parameters include keyword content parameters (such as product category, brand, product features) and keyword clarity parameters; browsing behavior parameters include but are not limited to click frequency, page scrolling speed, price comparison behavior, and cross-category jump paths.

[0068] Optionally, the extraction rule of the keyword clarity parameter is that if "brand + precise product name" (such as brand name + American coffee) is input, the input keyword is considered clear, and if only "product category" (such as coffee) is input, the input keyword is considered unclear.

[0069] Step S202 , calculating the feature value of each shopper personality according to the feature weight of the target feature parameter under each shopper personality.

[0070] For example, the target feature parameters include feature a, feature b, and feature c, and the initial value of each feature is set to 1. The feature parameters corresponding to Shopping Personality I include feature a, and the feature weight of feature a is 40%, so the feature value of Shopping Personality I is 0.4; the feature parameters corresponding to Shopping Personality II include features a and feature b, and the feature weight of feature a is 30% and the feature weight of feature b is 20%, so the feature value of Shopping Personality II is 0.3 + 0.2 = 0.5; the feature parameters corresponding to Shopping Personality III include feature c, and the feature weight of feature c is 60%, so the feature value of Shopping Personality III is 0.6.

[0071] Step S203: Determine the evaluation value of each shopping personality based on the characteristic value and personality weight of each shopping personality, and use the shopping personality with the largest evaluation value as the user's shopping personality.

[0072] It should be noted that the personality weight is determined based on historical behavioral data. Depending on the actual situation, the evaluation value can be the product of the feature value and the personality weight, or it can be a weighted sum.

[0073] Take the aforementioned shopping personalities I, II, and III as examples. Assume that the personality weight of Shopping Personality I is 10%, the personality weight of Shopping Personality II is 15%, and the personality weight of Shopping Personality III is 5%, and that the evaluation value = feature value * personality weight. The evaluation value of Shopping Personality I is 0.4 * 10% = 0.04, the evaluation value of Shopping Personality II is 0.5 * 15% = 0.075, and the evaluation value of Shopping Personality III is 0.6 * 5% = 0.03. Shopping Personality III has the highest evaluation value, so Shopping Personality III is selected as the user's current shopping personality.

[0074] When multiple evaluation values ​​are close, the shopping personality with the strongest scenario signal will be prioritized based on the preset signal priority. For example, if the signal priority is input signal > browsing signal > environmental signal, and the current evaluation values ​​of the efficiency and emergency personality are the same, and the AI ​​dialogue search contains the keyword "urgent need", the emergency personality will be prioritized.

[0075] This embodiment determines the characteristic value through multi-source real-time data (current environmental data and behavioral data), determines the personality weight through historical data, and obtains the evaluation value of the shopping personality based on the characteristic value and personality weight. In the process of personality analysis, multi-source real-time data and historical data are simultaneously considered to improve the accuracy of the analysis results, so that the shopping personality obtained by analysis conforms to the user's current shopping psychology, thereby improving the recommendation efficiency.

[0076] In some embodiments, a recommendation strategy corresponding to a shopping personality is obtained from a feature-personality-product knowledge graph, where the shopping personality includes a first shopping personality and a second shopping personality, and the recommendation strategy includes the first recommendation strategy and the second recommendation strategy including:

[0077] When the shopping personality is efficiency-type, the efficiency type is matched with the feature-personality-product knowledge graph to obtain a recommendation strategy that recommends products from high to low based on sales volume and displays a parameter comparison column.

[0078] When the shopping personality is exploratory, the exploratory type is matched with the feature-personality-product knowledge graph to obtain a recommendation strategy that prioritizes new products, seasonal products, and unpopular products.

[0079] The shopping personality is set according to the actual situation, including but not limited to "efficiency type", "exploration type", "parent-friendly type", "emergency type", "entertainment type" and "economic type".

[0080] In this embodiment, personality tags can also be dynamically associated with product attributes, for example, an "exploratory" personality can be associated with "new product" and "seasonal limited" tags.

[0081] A specific example of the personality switching process:

[0082] A user searches for "Starbucks coffee" during lunch break on a weekday. At the same time, high-frequency price comparison behavior is detected → the "efficiency-oriented" personality is activated → the TOP3 cost-effective products are recommended and a price comparison chart is displayed.

[0083] The same user browses "travel group buying" on the weekend. At the same time, deep browsing + cross-category jump behavior is identified → switching to the "exploration type" personality → travel products are pushed.

[0084] Behaviors such as clear keyword input, high-frequency price comparison, and in-depth browsing are identified by setting preset judgment rules.

[0085] By analyzing multi-source real-time data, the user's shopping personality is adjusted in real time to ensure that the recommended products always meet the current user's shopping psychology, thereby improving the efficiency and accuracy of personalized push.

[0086] In some embodiments, the method further comprises:

[0087] S104, after the user purchases the product, the weight data in the feature-personality-product knowledge graph is adjusted according to the current purchase behavior data, where the weight data includes personality weight and feature weight.

[0088] The personality weights and adjustment weights in the feature-personality-product knowledge graph are optimized through purchase behavior feedback. For example, if a user purchases a product after frequently comparing parameters in the efficiency-type personality state, the efficiency-type personality weight is increased. At the same time, the weight of the "parameter comparison" feature in the efficiency-type personality is increased.

[0089] S105, based on the time decay function, adjust the weight data in the feature-personality-product knowledge graph, the weight data including personality weight and feature weight.

[0090] A time decay function is introduced to reduce the weight of historical behaviors and ensure that the knowledge graph reflects the user's latest preferences. For example, items purchased a year ago should have less influence on current recommendations than items purchased more recently.

[0091] In some embodiments, the method further comprises:

[0092] S106, based on the user's behavioral data based on the recommended product feedback, adjust the weight data of the node corresponding to the recommended product in the feature-personality-product knowledge graph, the node includes the shopping personality and feature parameters, and the weight data includes the personality weight and feature weight.

[0093] Based on user feedback on recommendation results (e.g., click to view, ignore, or dislike), the relevant weight data in the knowledge graph is adjusted. Alternatively, if a user repeatedly ignores a certain category of recommended products, the weight of the personality or characteristic corresponding to that category in the knowledge graph will be reduced. For example, if a user repeatedly ignores movie recommendations, the probability of triggering the "Entertainment" personality will be reduced.

[0094] The personality weights and adjustment weights in the feature-personality-product knowledge graph are optimized through a feedback mechanism to further ensure that the recommended products are in line with the user's shopping psychology, thereby improving recommendation efficiency.

[0095] In some embodiments, the method further comprises:

[0096] The feature-personality-product knowledge graph is stored through encrypted hash values, and a different pseudonym is set for each shopping personality.

[0097] The mapping relationship between the pseudonym identifier and the user's real ID is stored in the ID mapping table.

[0098] The real ID is replaced with a pseudonymous identifier corresponding to each personality, and the mapping relationship is stored in a separate security system to protect user privacy and meet data compliance.

[0099] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0100] This embodiment also provides an artificial intelligence-based product recommendation system, which is used to implement the above-mentioned embodiments and preferred implementations. Details that have already been described will not be repeated. As used below, the terms "module," "unit," "subunit," etc. may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0101] Figure 2 This is a structural diagram of a product recommendation system based on artificial intelligence according to an embodiment of the present application. Figure 2 As shown, the system includes:

[0102] The first personality analysis module 21 is used to obtain environmental data and the user's initial behavior data, and determine the user's first shopping personality based on the environmental data, behavior data and a pre-built feature-personality-product knowledge graph.

[0103] The first recommendation module 22 is used to obtain a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and make product recommendations based on the first recommendation strategy.

[0104] The second personality analysis module 23 is used to obtain the user's behavioral data based on the recommended product feedback, and determine the user's second shopping personality based on the environmental data, behavioral data and feature-personality-product knowledge graph.

[0105] The second recommendation module 24 is used to obtain a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph and recommend products based on the second recommendation strategy.

[0106] In some embodiments, the feature-personality-product knowledge graph stores the personality weight of each shopping personality and the feature weights of the feature parameters under each shopping personality; according to the first recommendation module and the second recommendation module, the following are included:

[0107] The feature extraction module is used to extract target feature parameters from environmental data and behavioral data.

[0108] The feature value calculation module is used to calculate the feature value of each shopping personality according to the feature weight of the target feature parameter under each shopping personality.

[0109] The personality determination module is used to determine the evaluation value of each shopping personality based on the characteristic value and personality weight of each shopping personality, and take the shopping personality with the largest evaluation value as the user's shopping personality.

[0110] In some embodiments, the feature extraction module includes:

[0111] The environmental feature extraction module is used to extract time parameters, meteorological parameters, location parameters, and equipment type parameters from environmental data.

[0112] The behavior feature extraction module is used to extract active input parameters and browsing behavior parameters from the behavior data.

[0113] In some embodiments, the system further comprises:

[0114] The first feedback module is used to adjust the weight data in the feature-personality-product knowledge graph according to the current purchase behavior data after the user purchases the product. The weight data includes personality weight and feature weight.

[0115] The second feedback module is used to adjust the weight data in the feature-personality-product knowledge graph based on the time decay function.

[0116] The third feedback module is used to adjust the weight data of the node corresponding to the recommended product in the feature-personality-product knowledge graph based on the user's behavioral data based on the recommended product feedback. The node includes the shopping personality and feature parameters, and the weight data includes the personality weight and feature weight.

[0117] In some embodiments, the first recommendation module and the second recommendation module include:

[0118] The efficiency recommendation module is used to match the efficiency type with the feature-personality-product knowledge graph when the shopping personality is efficiency type, obtain the recommendation strategy of recommending products from high to low based on sales volume, and display the parameter comparison column.

[0119] The exploratory recommendation module is used to match the exploratory type with the feature-personality-product knowledge graph when the shopping personality is exploratory, and obtain a recommendation strategy that prioritizes new products, seasonal limited products, and unpopular products.

[0120] In some embodiments, the system further comprises:

[0121] The encryption module is used to store the feature-personality-product knowledge graph through encrypted hash values, set different pseudonym identifiers for each shopping personality, and store the mapping relationship between the pseudonym identifier and the user's real ID in the ID mapping table.

[0122] Through the above system, the first personality analysis module 21 obtains environmental data and the user's initial behavioral data, and determines the user's first shopping personality based on the environmental data, behavioral data, and a pre-built feature-personality-product knowledge graph. The first recommendation module 22 obtains a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph and makes product recommendations based on the first recommendation strategy. The second personality analysis module 23 obtains user behavioral data based on recommended product feedback and determines the user's second shopping personality based on the environmental data, behavioral data, and the feature-personality-product knowledge graph. The second recommendation module 24 obtains a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph and recommends products based on the second recommendation strategy, thereby solving the problem of low product recommendation efficiency. By analyzing multi-source real-time data, the shopping personality is adaptively adjusted and dynamically adapted to user needs to ensure that recommended products always meet the user's current shopping psychology, thereby improving the accuracy and efficiency of product recommendations.

[0123] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0124] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0125] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0126] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0127] S1, obtain environmental data and the user's initial behavioral data, and determine the user's first shopping personality based on the environmental data, behavioral data and the pre-built feature-personality-product knowledge graph.

[0128] S2, obtain the first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and make product recommendations based on the first recommendation strategy.

[0129] S3, obtains the user's behavioral data based on the recommended product feedback, and determines the user's second shopping personality based on the environmental data, behavioral data and feature-personality-product knowledge graph.

[0130] S4: Obtain a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph, and recommend products based on the second recommendation strategy.

[0131] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0132] In one embodiment, Figure 3 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 3 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 3 As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a product recommendation method based on artificial intelligence is implemented.

[0133] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0134] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, which can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0135] Those skilled in the art should understand that the various technical features of the above-described embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A commodity recommendation method based on artificial intelligence, characterized in that: The method comprises: Obtaining environmental data and initial user behavior data, and determining the user's first shopping personality based on the environmental data, the behavior data, and a pre-built feature-personality-product knowledge graph; Obtaining a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and making product recommendations based on the first recommendation strategy; Obtaining user behavior data based on product recommendation feedback, and determining the user's second shopping personality based on the environmental data, the behavior data, and the feature-personality-product knowledge graph; A second recommendation strategy corresponding to the second shopping personality is obtained from the feature-personality-product knowledge graph, and products are recommended based on the second recommendation strategy.

2. The method according to claim 1, characterized in that The feature-personality-product knowledge graph stores the personality weight of each shopping personality and the feature weights of the feature parameters under each shopping personality. The shopping personality of the user is determined based on the environmental data, the behavioral data, and the pre-constructed feature-personality-product knowledge graph. The shopping personality includes a first shopping personality and a second shopping personality. extracting target feature parameters from the environmental data and the behavioral data; Calculate the characteristic value of each shopping personality according to the characteristic weight of the target characteristic parameter under each shopping personality; Based on the characteristic value and personality weight of each shopping personality, an evaluation value of each shopping personality is determined, and the shopping personality with the largest evaluation value is used as the shopping personality of the user.

3. The method according to claim 2, characterized in that The extracting target feature parameters from the environmental data and the behavioral data includes: extracting time parameters, meteorological parameters, location parameters, and equipment type parameters from the environmental data; Active input parameters and browsing behavior parameters are extracted from the behavior data.

4. The method according to claim 2, characterized in that The method further comprises: After the user purchases a product, adjusting the weight data in the feature-personality-product knowledge graph based on the current purchase behavior data, wherein the weight data includes personality weight and feature weight; and / or Based on the time decay function, the weight data in the feature-personality-product knowledge graph is adjusted.

5. The method according to claim 2, characterized in that The method further comprises: According to the behavioral data of the user based on the feedback of the recommended product, the weight data of the node corresponding to the recommended product in the feature-personality-product knowledge graph is adjusted, the node includes the shopping personality and feature parameters, and the weight data includes the personality weight and the feature weight.

6. The method according to claim 1, characterized in that From the feature-personality-product knowledge graph, a recommendation strategy corresponding to the shopping personality is obtained, wherein the shopping personality includes a first shopping personality and a second shopping personality, and the recommendation strategy includes the first recommendation strategy and the second recommendation strategy including: In the case where the shopping personality is an efficiency type, the efficiency type is matched with the feature-personality-product knowledge graph to obtain a recommendation strategy that recommends products from high to low based on sales volume and displays a parameter comparison column; or In the case where the shopping personality is exploratory, the exploratory type is matched with the feature-personality-product knowledge graph to obtain a recommendation strategy that prioritizes new products, seasonal products, and unpopular products.

7. The method according to claim 1, characterized in that The method further comprises: The feature-personality-product knowledge graph is stored via encrypted hash values, and a different pseudonym is set for each shopping personality; The mapping relationship between the pseudonym identifier and the user's real ID is stored in an ID mapping table.

8. A product recommendation system based on artificial intelligence, characterized in that: The system comprises: A first personality analysis module is configured to obtain environmental data and initial user behavior data, and determine the user's first shopping personality based on the environmental data, the behavior data, and a pre-built feature-personality-product knowledge graph; A first recommendation module, configured to obtain a first recommendation strategy corresponding to the first shopping personality from the feature-personality-product knowledge graph, and make product recommendations based on the first recommendation strategy; A second personality analysis module is used to obtain user behavior data based on recommended product feedback, and determine the user's second shopping personality based on the environmental data, the behavior data, and the feature-personality-product knowledge graph; The second recommendation module is used to obtain a second recommendation strategy corresponding to the second shopping personality from the feature-personality-product knowledge graph, and recommend products based on the second recommendation strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the artificial intelligence-based product recommendation method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the artificial intelligence-based commodity recommendation method according to any one of claims 1 to 7 is implemented.

Images