Intelligent commodity recommendation method and system, computer equipment and readable storage medium

Abstract

The invention relates to an intelligent recommendation method and system for commodities, computer equipment and a readable storage medium. The method comprises the following steps: sequentially obtaining current interface browsing data browsed by a current consumption subject in a current initial browsing application; generating currently browsed main commodity information, and generating currently browsed extended commodity information according to the currently browsed main commodity information; generating associated commodity recommendation applications and main associated commodities according to the currently browsed main commodity information, pre-starting each associated commodity recommendation application, generating possible extension recommendation commodities and possible extension recommendation applications at the same time, and pre-starting the possible extension recommendation applications; a first display interface is generated in real time, and when it is detected that a current consumption subject is switched from the current initial browsing application to the possible extension recommendation application, a second display interface is generated in real time. According to the invention, extremely high commodity recommendation accuracy is realized, and the demand of consumers on commodity recommendation is met.

Description

Technical Field

[0001] The present application relates to the technical field of commodity recommendation, and in particular to a method, system, computer device and readable storage medium for intelligently recommending commodities. Background Art

[0002] Online shopping means searching for product information through the Internet, placing a shopping request through an electronic order form, and then filling in a personal checking account or credit card number. The manufacturer will ship the goods by mail order or by express delivery. For online shopping in China, the general payment method is cash on delivery and guaranteed transactions are cash on delivery.

[0003] At present, consumers often receive some product recommendations when shopping, but in fact the accuracy of product recommendations is low. For example, the invention patent with application number CN202110995570.9 discloses a shopping recommendation method, a shopping recommendation device, and an electronic device, including: obtaining a historical shopping sequence of the user to be recommended consisting of multiple historical shopping sets, clustering the information of each product included in the historical shopping sequence to obtain a clustering result, and using a pre-built coding model to process the historical shopping sequence to obtain an overall coding vector of the historical shopping sequence, so as to determine, based on the clustering result and the overall coding vector of the historical shopping sequence, the various products that the user to be recommended may purchase next time from a preset product pool, and recommend the determined products to the user to be recommended.

[0004] Although the technical solution in this invention achieves the recommendation of multiple items that the recommended user may buy next time, its recommendation relies on the data model, resulting in a large amount of data processing, which in turn leads to problems such as inaccurate product recommendations and low recommendation efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide an intelligent recommendation method, system, computer device and readable storage medium for commodities that can improve the accuracy of commodity recommendations in response to the above technical problems.

[0006] The technical solution of the present invention is as follows:

[0007] A method for intelligently recommending commodities, the method comprising:

[0008] Acquire the current interface browsing data browsed by the current consumer in the current initial browsing application; extract the current interface browsing data, generate the current browsing main commodity information after the data extraction is completed, and generate the current browsing extended commodity information according to the current browsing main commodity information; generate the related commodity recommendation application and the main related commodity according to the current browsing main commodity information, and pre-start each of the related commodity recommendation applications, and at the same time generate the possible extended recommended commodity and the possible extended recommended application according to the current browsing extended commodity information, and pre-start the possible extended recommended application; when it is detected that the current consumer switches from the current initial browsing application to the related commodity recommendation application, generate a first display interface in real time, and the first display interface is used to display the main related commodity; when it is detected that the current consumer switches from the current initial browsing application to the possible extended recommended application, generate a second display interface in real time, and the second display interface is used to display the possible extended recommended commodity.

[0009] Further, data extraction is performed on the browsing data of the current interface, and after the data extraction is completed, the main commodity information of the current browsing is generated, and the extended commodity information of the current browsing is generated according to the main commodity information of the current browsing; specifically, it includes:

[0010] Perform image extraction on the current interface browsing data and obtain current image data, and generate current first product information based on the current image data; perform text extraction on the current interface browsing data and obtain current text data, and generate current second product information based on the current text data; perform information correction on the first product information based on the second product information, and generate currently browsed main product information after information correction; generate first extended product information based on the current first product information, and generate second extended product information based on the second product information; generate currently browsed extended product information based on the first extended product information and the second extended product information.

[0011] Further, generating related product recommendation applications and main related products according to the currently browsed main product information, and pre-starting each of the related product recommendation applications, and generating possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-starting the possible extended recommended applications; specifically including:

[0012] The historical commodity purchase records of the current consumer are obtained according to the currently browsed main commodity information, wherein the historical commodity purchase records include purchased commodities, browsed applications during purchase, and actual transaction applications; the purchased commodities that match the currently browsed main commodity information are obtained according to the currently browsed main commodity information, and the purchased commodities are recorded as target commodities; the browsed applications during purchase and actual transaction applications of the target commodities are obtained, and the browsed applications during purchase and actual transaction applications are set as associated commodity recommendation applications; the associated commodity recommendation applications are pre-started, and main associated commodities are generated according to the currently browsed main commodity information at the same time; possible extended recommended commodities are generated according to the currently browsed extended commodity information, and possible extended recommended applications are generated according to the possible extended recommended commodities.

[0013] Further, when it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, a first display interface is generated in real time, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products, and then it also includes:

[0014] When it is detected that the current consumer subject switches from the associated product recommendation application to a third associated product application, obtain the product data of interest that the current consumer subject browsed on the associated product recommendation application before switching to the third associated product application; generate product index keywords based on the product data of interest; generate a third-party product recommendation index interface based on the product index keywords, and the third-party product recommendation index interface is used to be displayed when the current consumer subject switches from the associated product recommendation application to the third associated product application, and the product index keywords are displayed on the third-party product recommendation index interface; obtain the target index keywords selected by the current consumer subject from the product index keywords; index information from the third associated product application based on the target index keywords, and generate target index data, and generate a current data display interface based on the target index data, and the current data display interface is used to display the target index data.

[0015] Further, generating related product recommendation applications and main related products according to the currently browsed main product information, and pre-starting each of the related product recommendation applications, and generating possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-starting the possible extended recommended applications; and then further comprising:

[0016] Acquire the current actual browsing time of the current consumer subject in the current initial browsing application in real time; determine whether the current consumer subject corresponding to the current actual browsing time has purchase authority; if so, determine whether the current actual browsing time is greater than or equal to a preset standard non-recommended product time; if the current actual browsing time is greater than or equal to a preset standard non-recommended product time, generate a pre-start stop instruction; control the associated product recommendation application to stop pre-start according to the pre-start stop instruction, and simultaneously control the possible extended recommendation application to stop pre-start.

[0017] Furthermore, a product intelligent recommendation system includes:

[0018] The interface browsing module is used to obtain the current interface browsing data browsed by the current consumer subject in the current initial browsing application;

[0019] A data extraction module is used to extract data from the browsing data of the current interface, generate the main commodity information of the current browsing after the data extraction is completed, and generate the extended commodity information of the current browsing according to the main commodity information of the current browsing;

[0020] An application startup module, used to generate related product recommendation applications and main related products according to the currently browsed main product information, and pre-start each of the related product recommendation applications, and at the same time generate possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-start the possible extended recommended applications;

[0021] The recommendation generation module is used to generate a first display interface in real time when it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, the second display interface is used to display the possible extended recommended products.

[0022] Furthermore, the data extraction module is also used for:

[0023] Perform image extraction on the current interface browsing data and obtain current image data, and generate current first product information based on the current image data; perform text extraction on the current interface browsing data and obtain current text data, and generate current second product information based on the current text data; perform information correction on the first product information based on the second product information, and generate currently browsed main product information after information correction; generate first extended product information based on the current first product information, and generate second extended product information based on the second product information; generate currently browsed extended product information based on the first extended product information and the second extended product information.

[0024] Furthermore, the application startup module is also used for:

[0025] Acquire the historical commodity purchase record of the current consumer subject according to the currently browsed main commodity information, wherein the historical commodity purchase record includes purchased commodities, browsing applications during purchase, and actual transaction applications; acquire the purchased commodities matching the currently browsed main commodity information according to the currently browsed main commodity information, and record the purchased commodities as target commodities; acquire the browsing applications during purchase and actual transaction applications of the target commodities, and set the browsing applications during purchase and actual transaction applications as related commodity recommendation applications; pre-start the related commodity recommendation applications, and generate main related commodities according to the currently browsed main commodity information at the same time; generate possible extended recommended commodities according to the currently browsed extended commodity information, and generate possible extended recommended applications according to the possible extended recommended commodities;

[0026] The recommendation generation module is also used for:

[0027] When it is detected that the current consumer subject switches from the associated product recommendation application to a third associated product application, obtain the product data of interest that the current consumer subject browsed on the associated product recommendation application before switching to the third associated product application; generate product index keywords based on the product data of interest; generate a third-party product recommendation index interface based on the product index keywords, and the third-party product recommendation index interface is used to be displayed when the current consumer subject switches from the associated product recommendation application to the third associated product application, and the product index keywords are displayed on the third-party product recommendation index interface; obtain the target index keywords selected by the current consumer subject from the product index keywords; index information from the third associated product application based on the target index keywords, and generate target index data, and generate a current data display interface based on the target index data, and the current data display interface is used to display the target index data.

[0028] Furthermore, a computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent recommendation method for commodities when executing the computer program.

[0029] Furthermore, a computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent recommendation method for commodities.

[0030] The technical effects achieved by the present invention are as follows:

[0031] The intelligent recommendation method, system, computer device and readable storage medium of the above-mentioned goods successively obtain the current interface browsing data browsed by the current consumer subject in the current initial browsing application; extract the data of the current interface browsing data, and generate the main commodity information of the current browsing after the data extraction is completed, and generate the current browsing extended commodity information according to the main commodity information of the current browsing; generate the related commodity recommendation application and the main related commodity according to the main commodity information of the current browsing, and pre-start each of the related commodity recommendation applications, and at the same time generate the possible extended recommended commodity and the possible extended recommended application according to the current browsing extended commodity information, and pre-start the possible extended recommended application; when it is detected that the current consumer subject switches from the current initial browsing application to the related commodity recommendation application, a first display interface is generated in real time, and the first display interface is used to display the main related commodity; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommended application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended application, thereby achieving an extremely high recommendation accuracy rate for the goods, thereby satisfying the consumer's demand for goods recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a flow chart of a method for intelligently recommending commodities in one embodiment;

[0033] Figure 2 is a structural block diagram of an intelligent recommendation system for commodities in one embodiment;

[0034] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] In one embodiment, the present invention provides an application scenario, which includes a terminal, which is used to obtain current interface browsing data browsed by a current consumer subject in a current initial browsing application; extract data from the current interface browsing data, and generate current browsing main product information after the data extraction is completed, and generate current browsing extended product information based on the current browsing main product information; generate related product recommendation applications and main related products based on the current browsing main product information, and pre-start each of the related product recommendation applications, and at the same time generate possible extended recommended products and possible extended recommended applications based on the current browsing extended product information, and pre-start the possible extended recommended applications; when it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, a first display interface is generated in real time, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommended application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products.

[0037] The terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices.

[0038] In one embodiment, Figure 1 As shown, a method for intelligently recommending commodities is provided, the method comprising:

[0039] Step S100: obtaining browsing data of the current interface browsed by the current consumer subject in the current initial browsing application;

[0040] Specifically, in this step, the current consumer is the user who is currently shopping. The current initial browsing application is a specific App currently in use, including but not limited to Taobao, JD.com, and Pinduoduo. The current interface browsing data is the interface on the specific App currently in use.

[0041] Step S200: extracting data from the current interface browsing data, generating the current browsing main commodity information after the data extraction is completed, and generating the current browsing extended commodity information according to the current browsing main commodity information;

[0042] Specifically, in this step, in order to achieve accurate product recommendation in the future, the current interface browsing data is firstly extracted, and the main product information of the current browsing is generated after the data extraction is completed, and the current browsing extended product information is generated according to the main product information of the current browsing. Among them, the main product information of the current browsing is the information of the main product browsed by the current consumer. Specifically, if the current browsing interface is the browsing interface of a laptop computer, the data on the interface is the current interface browsing data, and after the data in the current interface browsing data is extracted, the main product information of the current browsing can be obtained.

[0043] Among them, the currently browsed extended product information is data of products associated with the currently browsed main product information. Through the generation of the currently browsed extended product information, subsequent more accurate recommendations of product information related to the currently browsed main product information are achieved, thereby improving the intelligence and reliability of product recommendations.

[0044] Step S300: generating related product recommendation applications and main related products according to the currently browsed main product information, and pre-starting each of the related product recommendation applications; generating possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-starting the possible extended recommended applications;

[0045] Specifically, in this step, the related product recommendation application is an application associated with the currently browsed main product information, such as Taobao and JD.com which belong to the same category of shopping apps.

[0046] The main related products are products that match the main product information currently being browsed. For example, if the main product information currently being browsed is information about computer model A, then the main related products are products that are the same or similar to computer model A.

[0047] In addition, by pre-starting each of the related product recommendation applications, the startup time is shortened when the related applications are subsequently started, the speed of product recommendation and display is increased, and the user experience is greatly improved.

[0048] The possible extended recommended products are products associated with the main associated products. Furthermore, through the generation of the possible extended recommended products, a wide range of recommendation effects of intelligent product recommendations are achieved, thereby improving the recommendation experience.

[0049] In addition, the possible extended recommended applications are applications that match the possible extended recommended commodities. For example, when the possible extended recommended commodities are food, the possible extended recommended applications are Meituan Waimai and Ele.me, etc.

[0050] In this way, by realizing the generation of the related product recommendation application, the main related products, the possible extended recommended products and the possible extended recommended applications, a wide range of intelligent recommendations, high accuracy and strong applicability are achieved, thereby improving the intelligence of product recommendations.

[0051] On the other hand, in this step, by pre-starting each of the related product recommendation applications and the possible extended recommendation application, the possible extended recommendation application and the related product recommendation application can be started efficiently and accurately when they are actually started later, thereby greatly improving the application startup speed and enhancing the user experience of intelligent product recommendations.

[0052] Step S400: When it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, a first display interface is generated in real time, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products.

[0053] Specifically, in this step, when it is detected that the current consumer switches from the current initial browsing application to the related product recommendation application, it means that the current consumer needs to consume from another application at this time, and thus it is necessary to generate a first display interface in real time, and the first display interface is used to display the main related products; in addition, when it is detected that the current consumer switches from the current initial browsing application to the possible extended recommendation application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products, thereby achieving accuracy and efficiency, and because the application has been pre-started before, this step achieves fast startup, that is, the display speed of the first display interface and the second display interface is faster than the speed after directly starting the application in the prior art, thereby achieving high-speed, efficient and high-accuracy product recommendations, greatly improving the intelligence level and recommendation effect.

[0054] Furthermore, when the associated product recommendation application and the possible extended recommendation application are actually started, the other pre-started applications are closed, thereby saving memory resources.

[0055] In one embodiment, step S200: extracting data from the current interface browsing data, generating the current browsing main commodity information after the data extraction is completed, and generating the current browsing extended commodity information according to the current browsing main commodity information; specifically includes:

[0056] Step S210: performing image extraction on the current interface browsing data and obtaining current image data, and generating current first commodity information according to the current image data;

[0057] The current image data is information contained in the image in the current interface browsing data, and is specifically obtained by performing data recognition and object recognition on the image, thereby obtaining the commodity information contained therein, and then obtaining the current first commodity information.

[0058] Step S220: extracting text from the current interface browsing data and obtaining current text data, and generating current second product information according to the current text data;

[0059] Similarly, the current text data is the product information contained in the text in the current interface browsing data, and is specifically obtained by performing data recognition, text analysis and subject extraction on the text, thereby obtaining the product information contained therein, and then obtaining the current second product information.

[0060] Step S230: Correcting the first commodity information according to the second commodity information, and generating the currently browsed main commodity information after the information correction;

[0061] Specifically, text information is more accurate in comparison, compared with the backwardness of image recognition technology in the prior art, so in order to achieve more accurate and efficient acquisition of product information, the first product information is corrected according to the second product information to achieve information intersection acquisition, and then the main product information currently being browsed is generated after the information correction.

[0062] Step S240: generating first extended product information according to the current first product information, and generating second extended product information according to the second product information;

[0063] Step S250: generating currently browsed extended product information according to the first extended product information and the second extended product information.

[0064] Next, after obtaining the current first product information and the second product information, in order to achieve strong compatibility of data acquisition, the first extended product information is generated according to the current first product information, and the second extended product information is generated according to the second product information, that is, the first extended product information and the second extended product information are mutually associated with the current first product information and the current second product information, thereby achieving strong compatibility generation of the currently browsed extended product information.

[0065] Specifically, in this embodiment, in order to achieve accurate and intelligent recommendations, in this step, image extraction is performed on the current interface browsing data to obtain the current image data, and the current first product information is generated based on the current image data; then, text extraction is performed on the current interface browsing data to obtain the current text data, and the current second product information is generated based on the current text data; then, the first product information is corrected based on the second product information, and the currently browsed main product information is generated after the information correction, and then, the first extended product information is generated based on the current first product information, and the second extended product information is generated based on the second product information; finally, the currently browsed extended product information is generated based on the first extended product information and the second extended product information, thereby achieving accurate generation of the currently browsed extended product information.

[0066] In one embodiment, step S300: generating related product recommendation applications and main related products according to the currently browsed main product information, and pre-starting each of the related product recommendation applications, and generating possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-starting the possible extended recommended applications; specifically includes:

[0067] Step S310: acquiring the historical commodity purchase records of the current consumer according to the currently browsed main commodity information, wherein the historical commodity purchase records include purchased commodities, browsed applications during purchase, and actual transaction applications;

[0068] The purchased product is a product that has been purchased. The application browsed during purchase is the data of the application browsed during the purchase of the purchased product, and the actual transaction application is the application actually used to purchase the purchased product.

[0069] Step S320: acquiring a purchased commodity matching the currently browsed main commodity information according to the currently browsed main commodity information, and recording the purchased commodity as a target commodity;

[0070] Specifically, the purchased goods matching the currently browsed main goods information are determined and obtained through the goods labels. The goods included in the currently browsed main goods information have specific labels, such as the label of a computer for electronic devices, and the label of a sesame seed cake for portable food. In addition, each of the purchased goods has a corresponding label, and then by determining whether the labels are the same, it is determined whether it is a purchased goods matching the currently browsed main goods information.

[0071] Furthermore, by making judgments based on such tags, the accuracy of judgments is improved, and the purchased goods, browsed applications during purchase, and actual transaction applications actually reflect the shopping habits of the current consumer.

[0072] Step S330: Obtain the browsing application and the actual transaction application of the target product, and set the browsing application and the actual transaction application as the associated product recommendation application;

[0073] Step S340: pre-starting the related product recommendation application, and generating main related products according to the currently browsed main product information;

[0074] Step S350: generating possible extended recommended products according to the currently browsed extended product information, and generating possible extended recommended applications according to the possible extended recommended products.

[0075] Specifically, in this embodiment, the browsing application during purchase and the actual transaction application of the target product are first obtained, and the browsing application during purchase and the actual transaction application are set as related product recommendation applications; then, the related product recommendation application is pre-started, and the main related products are generated according to the currently browsed main product information at the same time, and finally, possible extended recommended products are generated according to the currently browsed extended product information, and possible extended recommended applications are generated according to the possible extended recommended products. In this way, it is realized based on the user's usage habits, that is, by making judgments based on the usage data of the purchased products, the browsing application during purchase and the actual transaction application, thereby realizing the accuracy of generating possible extended recommended applications, and realizing the accuracy and intelligence of product recommendations.

[0076] In one embodiment, step S400: when it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, a first display interface is generated in real time, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products, and then it also includes:

[0077] Step S521: when it is detected that the current consumer subject switches from the associated product recommendation application to the third associated product application, obtaining the interested product data browsed by the current consumer subject on the associated product recommendation application before switching to the third associated product application;

[0078] The third associated product application is a non-mainstream shopping software, that is, an application such as a browser, specifically including but not limited to Sohu Browser, Google Chrome, and UC Browser.

[0079] At this time, when it is detected that the current consumer subject switches from the related product recommendation application to the third related product application, it is detected that the user switches to other applications, and then other searches for products may be required at this time.

[0080] Specifically, the product data of interest takes a computer as an example, specifically graphics card data.

[0081] Step S522: Generate commodity index keywords according to the commodity data of interest;

[0082] Step S523: generating a third-party product recommendation index interface according to the product index keyword, wherein the third-party product recommendation index interface is used to be displayed when the current consumer switches from the related product recommendation application to a third related product application, and the product index keyword is displayed on the third-party product recommendation index interface;

[0083] Specifically, the commodity index keywords include graphics card parameters, graphics card types, and graphics card prices.

[0084] Step S524: obtaining the target index keyword selected by the current consumer from the commodity index keywords;

[0085] Step S525: indexing information from the third related product application according to the target index keyword, generating target index data, and generating a current data display interface based on the target index data, wherein the current data display interface is used to display the target index data.

[0086] Furthermore, in order to achieve a more accurate search habit that meets the user's usage needs, the target index keyword selected by the current consumer from the product index keywords is obtained; then, information is indexed from the third related product application according to the target index keyword, and target index data is generated, and a current data display interface is generated based on the target index data. The current data display interface is used to display the target index data, that is, all the product index keywords are displayed first, and then the user's selection is obtained, and finally the search is started, thereby achieving an accurate environment and avoiding the user's typing search, thereby improving the user experience.

[0087] Specifically, in this embodiment, it is achieved that a third-party product recommendation index interface is generated according to the product index keywords, and the third-party product recommendation index interface is used to be displayed when the current consumer switches from the related product recommendation application to the third related product application, and the product index keywords are displayed on the third-party product recommendation index interface; then, the target index keywords selected by the current consumer from the product index keywords are obtained; then, information is indexed from the third related product application according to the target index keywords, and target index data is generated, and a current data display interface is generated based on the target index data, and the current data display interface is used to display the target index data, thereby greatly improving the user experience.

[0088] In one embodiment, step S300: generating related product recommendation applications and main related products according to the currently browsed main product information, and pre-starting each of the related product recommendation applications, and generating possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-starting the possible extended recommended applications; and then further comprising:

[0089] Step S301: obtaining in real time the current actual browsing time of the current consumer in the current initial browsing application;

[0090] Step S302: determining whether the current consumer subject corresponding to the current actual browsing time has purchase authority;

[0091] In this step, it is determined whether the user has the permission by performing password verification. On the one hand, the password verification is inserted in this step to prevent the application from crashing due to malicious browsing, and on the other hand, it prevents children from purchasing goods by mistake.

[0092] Step S303: If the judgment is yes, then determine whether the current actual browsing time is greater than or equal to the preset standard non-recommended product time;

[0093] Step S304: if it is determined that the current actual browsing time is greater than or equal to the preset standard non-recommended product time, a pre-start stop instruction is generated;

[0094] Step S305: controlling the associated product recommendation application to stop pre-starting according to the pre-start stop instruction, and controlling the possible extension recommendation application to stop pre-starting.

[0095] Specifically, in this embodiment, in order to achieve effective utilization of computing resources, when it is detected that the user does not need to switch applications or perform other intelligent recommendations for products, other pre-started applications are closed, that is, by judging whether the current actual browsing time is greater than or equal to the preset standard time for not recommending products; then, if it is judged that the current actual browsing time is greater than or equal to the preset standard time for not recommending products, a pre-start stop instruction is generated; finally, according to the pre-start stop instruction, the related product recommendation application is controlled to stop pre-starting, and the possible extended recommendation application is controlled to stop pre-starting, thereby achieving effective utilization of computing resources, lowering the threshold for effective use of carrier terminals and resource requirements, and thus meeting the needs of ordinary users.

[0096] In one embodiment, Figure 2 As shown, the present invention also provides an intelligent recommendation system for commodities, the system comprising:

[0097] The interface browsing module is used to obtain the current interface browsing data browsed by the current consumer subject in the current initial browsing application;

[0098] A data extraction module is used to extract data from the browsing data of the current interface, generate the main commodity information of the current browsing after the data extraction is completed, and generate the extended commodity information of the current browsing according to the main commodity information of the current browsing;

[0099] An application startup module, used to generate related product recommendation applications and main related products according to the currently browsed main product information, and pre-start each of the related product recommendation applications, and at the same time generate possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-start the possible extended recommended applications;

[0100] The recommendation generation module is used to generate a first display interface in real time when it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, the second display interface is used to display the possible extended recommended products.

[0101] In one embodiment, the data extraction module is further used to:

[0102] Perform image extraction on the current interface browsing data and obtain current image data, and generate current first product information based on the current image data; perform text extraction on the current interface browsing data and obtain current text data, and generate current second product information based on the current text data; perform information correction on the first product information based on the second product information, and generate currently browsed main product information after information correction; generate first extended product information based on the current first product information, and generate second extended product information based on the second product information; generate currently browsed extended product information based on the first extended product information and the second extended product information.

[0103] In one embodiment, the application startup module is further used to:

[0104] Acquire the historical commodity purchase record of the current consumer subject according to the currently browsed main commodity information, wherein the historical commodity purchase record includes purchased commodities, browsing applications during purchase, and actual transaction applications; acquire the purchased commodities matching the currently browsed main commodity information according to the currently browsed main commodity information, and record the purchased commodities as target commodities; acquire the browsing applications during purchase and actual transaction applications of the target commodities, and set the browsing applications during purchase and actual transaction applications as related commodity recommendation applications; pre-start the related commodity recommendation applications, and generate main related commodities according to the currently browsed main commodity information at the same time; generate possible extended recommended commodities according to the currently browsed extended commodity information, and generate possible extended recommended applications according to the possible extended recommended commodities;

[0105] The recommendation generation module is also used for:

[0106] When it is detected that the current consumer subject switches from the associated product recommendation application to a third associated product application, obtain the product data of interest that the current consumer subject browsed on the associated product recommendation application before switching to the third associated product application; generate product index keywords based on the product data of interest; generate a third-party product recommendation index interface based on the product index keywords, and the third-party product recommendation index interface is used to be displayed when the current consumer subject switches from the associated product recommendation application to the third associated product application, and the product index keywords are displayed on the third-party product recommendation index interface; obtain the target index keywords selected by the current consumer subject from the product index keywords; index information from the third associated product application based on the target index keywords, and generate target index data, and generate a current data display interface based on the target index data, and the current data display interface is used to display the target index data.

[0107] In one embodiment, the application startup module is also used to: obtain the current actual browsing time of the current consumer subject in the current initial browsing application in real time; determine whether the current consumer subject corresponding to the current actual browsing time has purchasing authority; if it is judged to be yes, determine whether the current actual browsing time is greater than or equal to a preset standard non-recommended product time; if it is judged that the current actual browsing time is greater than or equal to the preset standard non-recommended product time, generate a pre-start stop instruction; control the associated product recommendation application to stop pre-start according to the pre-start stop instruction, and at the same time control the possible extended recommendation application to stop pre-start.

[0108] In one embodiment, Figure 3 As shown, a computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent recommendation method for commodities when executing the computer program.

[0109] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent recommendation method for commodities.

[0110] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program 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. As an illustration and not limitation, RAM is available in many 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).

[0111] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above 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.

[0112] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for intelligently recommending commodities, characterized in that: The method comprises: Acquire the current interface browsing data browsed by the current consumer in the current initial browsing application; extract the current interface browsing data, generate the current browsing main commodity information after the data extraction is completed, and generate the current browsing extended commodity information according to the current browsing main commodity information; generate the related commodity recommendation application and the main related commodity according to the current browsing main commodity information, and pre-start each of the related commodity recommendation applications, and at the same time generate the possible extended recommended commodity and the possible extended recommended application according to the current browsing extended commodity information, and pre-start the possible extended recommended application; when it is detected that the current consumer switches from the current initial browsing application to the related commodity recommendation application, generate a first display interface in real time, and the first display interface is used to display the main related commodity; when it is detected that the current consumer switches from the current initial browsing application to the possible extended recommended application, generate a second display interface in real time, and the second display interface is used to display the possible extended recommended commodity.

2. The intelligent commodity recommendation method according to claim 1, characterized in that: Extracting data from the current interface browsing data, generating the current browsing main commodity information after the data extraction is completed, and generating the current browsing extended commodity information according to the current browsing main commodity information; specifically including: Perform image extraction on the current interface browsing data and obtain current image data, and generate current first product information based on the current image data; perform text extraction on the current interface browsing data and obtain current text data, and generate current second product information based on the current text data; perform information correction on the first product information based on the second product information, and generate currently browsed main product information after information correction; generate first extended product information based on the current first product information, and generate second extended product information based on the second product information; generate currently browsed extended product information based on the first extended product information and the second extended product information.

3. The intelligent commodity recommendation method according to claim 1, characterized in that: Generate related product recommendation applications and main related products according to the currently browsed main product information, and pre-start each of the related product recommendation applications; and generate possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-start the possible extended recommended applications; specifically including: The historical commodity purchase records of the current consumer are obtained according to the currently browsed main commodity information, wherein the historical commodity purchase records include purchased commodities, browsed applications during purchase, and actual transaction applications; the purchased commodities that match the currently browsed main commodity information are obtained according to the currently browsed main commodity information, and the purchased commodities are recorded as target commodities; the browsed applications during purchase and actual transaction applications of the target commodities are obtained, and the browsed applications during purchase and actual transaction applications are set as associated commodity recommendation applications; the associated commodity recommendation applications are pre-started, and main associated commodities are generated according to the currently browsed main commodity information at the same time; possible extended recommended commodities are generated according to the currently browsed extended commodity information, and possible extended recommended applications are generated according to the possible extended recommended commodities.

4. The intelligent commodity recommendation method according to claim 1, characterized in that: When it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, a first display interface is generated in real time, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products, and then it also includes: When it is detected that the current consumer subject switches from the associated product recommendation application to a third associated product application, obtain the product data of interest that the current consumer subject browsed on the associated product recommendation application before switching to the third associated product application; generate product index keywords based on the product data of interest; generate a third-party product recommendation index interface based on the product index keywords, and the third-party product recommendation index interface is used to be displayed when the current consumer subject switches from the associated product recommendation application to the third associated product application, and the product index keywords are displayed on the third-party product recommendation index interface; obtain the target index keywords selected by the current consumer subject from the product index keywords; index information from the third associated product application based on the target index keywords, and generate target index data, and generate a current data display interface based on the target index data, and the current data display interface is used to display the target index data.

5. The intelligent commodity recommendation method according to claim 1, characterized in that: Generate related product recommendation applications and main related products according to the currently browsed main product information, and pre-start each of the related product recommendation applications; and generate possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-start the possible extended recommended applications; and then also include: Acquire the current actual browsing time of the current consumer subject in the current initial browsing application in real time; determine whether the current consumer subject corresponding to the current actual browsing time has purchase authority; if so, determine whether the current actual browsing time is greater than or equal to a preset standard non-recommended product time; if the current actual browsing time is greater than or equal to a preset standard non-recommended product time, generate a pre-start stop instruction; control the associated product recommendation application to stop pre-start according to the pre-start stop instruction, and simultaneously control the possible extended recommendation application to stop pre-start.

6. An intelligent product recommendation system, characterized in that: The system comprises: The interface browsing module is used to obtain the current interface browsing data browsed by the current consumer subject in the current initial browsing application; A data extraction module is used to extract data from the browsing data of the current interface, generate the main commodity information of the current browsing after the data extraction is completed, and generate the extended commodity information of the current browsing according to the main commodity information of the current browsing; An application startup module, used to generate related product recommendation applications and main related products according to the currently browsed main product information, and pre-start each of the related product recommendation applications, and at the same time generate possible extended recommended products and possible extended recommended applications according to the currently browsed extended product information, and pre-start the possible extended recommended applications; The recommendation generation module is used to generate a first display interface in real time when it is detected that the current consumer subject switches from the current initial browsing application to the related product recommendation application, and the first display interface is used to display the main related products; when it is detected that the current consumer subject switches from the current initial browsing application to the possible extended recommendation application, a second display interface is generated in real time, and the second display interface is used to display the possible extended recommended products.

7. The intelligent product recommendation system according to claim 6, characterized in that: The data extraction module is also used for: Perform image extraction on the current interface browsing data and obtain current image data, and generate current first product information based on the current image data; perform text extraction on the current interface browsing data and obtain current text data, and generate current second product information based on the current text data; perform information correction on the first product information based on the second product information, and generate currently browsed main product information after information correction; generate first extended product information based on the current first product information, and generate second extended product information based on the second product information; generate currently browsed extended product information based on the first extended product information and the second extended product information.

8. The intelligent product recommendation system according to claim 6, characterized in that: The application startup module is also used for: Acquire the historical commodity purchase record of the current consumer subject according to the currently browsed main commodity information, wherein the historical commodity purchase record includes purchased commodities, browsing applications during purchase, and actual transaction applications; acquire the purchased commodities matching the currently browsed main commodity information according to the currently browsed main commodity information, and record the purchased commodities as target commodities; acquire the browsing applications during purchase and actual transaction applications of the target commodities, and set the browsing applications during purchase and actual transaction applications as related commodity recommendation applications; pre-start the related commodity recommendation applications, and generate main related commodities according to the currently browsed main commodity information at the same time; generate possible extended recommended commodities according to the currently browsed extended commodity information, and generate possible extended recommended applications according to the possible extended recommended commodities; The recommendation generation module is also used for: When it is detected that the current consumer subject switches from the associated product recommendation application to a third associated product application, obtain the product data of interest that the current consumer subject browsed on the associated product recommendation application before switching to the third associated product application; generate product index keywords based on the product data of interest; generate a third-party product recommendation index interface based on the product index keywords, and the third-party product recommendation index interface is used to be displayed when the current consumer subject switches from the associated product recommendation application to the third associated product application, and the product index keywords are displayed on the third-party product recommendation index interface; obtain the target index keywords selected by the current consumer subject from the product index keywords; index information from the third associated product application based on the target index keywords, and generate target index data, and generate a current data display interface based on the target index data, and the current data display interface is used to display the target index data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images