An AI-based shopping guide method and device for e-commerce products

Abstract

An embodiment of the present invention discloses an e-commerce product shopping guide method and device based on artificial intelligence, including: in response to a user's search instruction, obtaining a search timestamp, keywords, and user information included in the search instruction, obtaining the user's historical order information based on the account information, screening target historical orders matching the keywords from the historical order information, calculating the score of each historical order in the target historical orders respectively, selecting the orders ranked in the top N in terms of score as reference orders, generating product information matching the user according to the user's historical portrait and keywords, generating recommended products based on the product information and the reference orders, and sending a recommended purchase page generated from the recommended products to the user; the embodiment automatically matches products suitable for the user by combining the user's current purchase needs and the user's historical portrait, and starting from the user's purchase preferences in combination with historical orders for recommendation, and can accurately recommend products that better meet the user's personalized needs.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and particularly relates to a method and device for guiding the purchase of e-commerce products based on artificial intelligence. Background Art

[0002] At present, generally speaking, the e-commerce industry is still advancing steadily. With the continuous improvement of Internet technology, major e-commerce service providers are committed to providing more professional services to platform users, reducing the costs required in the transaction process to the greatest extent, and increasing users' desire to purchase. The development model of e-commerce has put forward many new requirements for enterprises, such as the accuracy of product recommendations, the timeliness of delivery, the quality assurance of products, the convenience of returns and exchanges, and many other new requirements.

[0003] Among them, the most prominent problem is product selection, and the product recommendations on its platform will affect users' product selection. How to accurately display personalized recommendations on the platform to users and make appropriate product recommendations to users is an essential part of e-commerce shopping guidance. Summary of the Invention

[0004] In view of the above defects, embodiments of the present invention disclose a method and device for guiding the purchase of e-commerce products based on artificial intelligence, which provide personalized and accurate shopping guidance recommendations for different users.

[0005] A first aspect of an embodiment of the present invention discloses a method for guiding the purchase of e-commerce products based on artificial intelligence, including:

[0006] In response to a user's search instruction, obtain the search timestamp, keyword, and user information included in the search instruction, where the user information includes account information and at least one user historical portrait; the user historical portrait includes facial features, body information, age information, and gender;

[0007] Obtain the user's historical order information based on the account information, and screen the target historical orders that match the keyword from the historical order information according to the keyword;

[0008] Calculate the score of each historical order in the target historical orders respectively, and select the orders with the top N scores as reference orders; where N is a natural number and N is not equal to 0;

[0009] Generate product information that matches the user based on the user historical portrait and the keyword, generate recommended products based on the product information and the reference orders, and send the recommended purchase page of the recommended products to the user.

[0010] As an optional implementation manner, in the first aspect of an embodiment of the present invention, screening the target historical orders that match the keyword from the historical order information according to the keyword includes:

[0011] Delete historical order information with a shopping time exceeding a preset time threshold from the historical order information to obtain historical order information within the target period;

[0012] Obtain the product category of the keyword, and based on the product category, exclude orders in the historical order information within the target period that do not match the product category to obtain the preliminary selected historical orders;

[0013] Match the product usage time according to the search timestamp, and match the target historical orders from the preliminary selected historical orders based on the product usage time.

[0014] As an optional implementation manner, in the first aspect of the embodiments of the present invention, calculate the scores of each historical order in the target historical orders respectively, including:

[0015] Obtain all the purchasing stores in the target historical orders, and count the first purchase times of each purchasing store;

[0016] Obtain all the purchased categories in the target historical orders, and count the second purchase times of each purchased category;

[0017] Assign corresponding score values to different numbers of first purchase times and second purchase times respectively;

[0018] Obtain the first purchase times corresponding to the purchasing stores in each historical order, and calculate the sum of the score values corresponding to the first purchase times and the second purchase times respectively according to the purchased categories in each historical order to obtain the score of this historical order.

[0019] As an optional implementation manner, in the first aspect of the embodiments of the present invention, generate product information matching the user according to the user historical portrait and the keyword, including:

[0020] Select the matching user historical portrait from at least one user historical portrait according to the keyword;

[0021] Obtain the matching user historical portrait, generate a three-dimensional simulated human image, load all products of the same category matching the keyword into the three-dimensional simulated human image, and calculate the image score value after each product is loaded into the three-dimensional simulated human image;

[0022] Select the product with the highest image score value as the target product, and obtain the subdivision words of the target product.

[0023] As an optional implementation manner, in the first aspect of the embodiments of the present invention, generate a recommended purchase page for the recommended products and send it to the user, including:

[0024] Extract the main images and keywords of each recommended product, obtain the purchase links of the recommended products, and embed the keywords into the extracted main images;

[0025] Generate a new purchase identification image with the keywords embedded in the main image and the purchase link;

[0026] Select a background template from the preset background library, randomly arrange the new purchase identification images of all recommended products into the background template to generate a recommended purchase page, and send the purchase page to the user.

[0027] As an alternative implementation, in the first aspect of the embodiments of the present invention, generating a recommended purchase page for the recommended products and sending it to the user includes:

[0028] Retain the search page of the user's search keywords and create a new purchase page;

[0029] Randomly sort all recommended products and add them to the purchase page, and display the purchase page to the user.

[0030] As an alternative implementation, in the first aspect of the embodiments of the present invention, it further includes:

[0031] Receive the operation instruction of the user to agree or reject the recommended purchase page;

[0032] When the user rejects the recommended purchase page, close the purchase page, and generate a user shopping preference score based on the historical order information and historical portrait information;

[0033] Sort the products on the search page according to the user shopping preference score from high to low.

[0034] The second aspect of the embodiments of the present invention discloses an e-commerce product shopping guide device based on artificial intelligence, including:

[0035] Instruction response module: used to respond to the user's search instruction, obtain the search timestamp, keyword, and user information included in the search instruction, where the user information includes account information and at least one user historical portrait; the user historical portrait includes facial features, body information, age information, and gender;

[0036] Information collection module: used to obtain the user's historical order information based on the account information, and screen the target historical orders that match the keyword from the historical order information according to the keyword;

[0037] Score calculation module: used to calculate the score of each historical order in the target historical orders respectively, and select the orders with the top N scores as reference orders; where N is a natural number and N is not equal to 0;

[0038] Product recommendation module: used to generate product information matching the user based on the user's historical portrait and keywords, generate recommended products based on the product information and reference orders, and generate a recommended purchase page for the recommended products and send it to the user.

[0039] As an alternative implementation, in the second aspect of the embodiments of the present invention, screening target historical orders matching the keyword from the historical order information according to the keyword includes:

[0040] Deleting historical orders in the historical order information whose shopping time exceeds a preset time threshold to obtain historical order information within a target period;

[0041] Obtaining the product category of the keyword, and excluding orders in the historical order information within the target period that do not match the product category based on the product category to obtain preliminary selected historical orders;

[0042] Matching the product usage time according to the search timestamp, and matching the target historical order from the preliminary selected historical orders based on the product usage time.

[0043] As an alternative implementation, in the second aspect of the embodiments of the present invention, calculating the score of each historical order in the target historical orders respectively includes:

[0044] Obtaining all the purchasing stores in the target historical orders, and counting the first purchase times of each purchasing store;

[0045] Obtaining all the purchased categories in the target historical orders, and counting the second purchase times of each purchased category;

[0046] Giving score values corresponding to different numbers of first purchase times and second purchase times respectively;

[0047] Obtaining the first purchase times corresponding to the purchasing store in each historical order, and calculating the sum of the score values corresponding to the first purchase times and the second purchase times respectively according to the second purchase times corresponding to the purchased category in each historical order to obtain the score of this historical order.

[0048] As an alternative implementation, in the second aspect of the embodiments of the present invention, generating product information matching the user based on the user's historical portrait and keywords includes:

[0049] Selecting a matching user historical portrait from at least one user historical portrait according to the keyword;

[0050] Obtaining the matching user historical portrait, generating a three-dimensional simulated human image, loading all products of the same category matching the keyword into the three-dimensional simulated human image, and calculating the image score value after each product is loaded into the three-dimensional simulated human image;

[0051] Select the product with the highest image score as the target product, and obtain the subdivision words of the target product.

[0052] As an optional implementation manner, in the second aspect of the embodiments of the present invention, sending a recommended purchase page of the recommended products to the user includes:

[0053] Extract the main image and keywords of each recommended product, obtain the purchase link of the recommended product, and embed the keywords into the extracted main image;

[0054] Generate a new purchase identification image with the main image embedded with keywords and the purchase link;

[0055] Select a background template from a preset background library, randomly arrange the new purchase identification images of all recommended products into the background template to generate a recommended purchase page, and send the purchase page to the user.

[0056] As an optional implementation manner, in the second aspect of the embodiments of the present invention, sending a recommended purchase page of the recommended products to the user includes:

[0057] Retain the search page of the user's search keywords and create a new purchase page;

[0058] Randomly sort all recommended products and add them to the purchase page, and display the purchase page to the user.

[0059] As an optional implementation manner, in the second aspect of the embodiments of the present invention, it further includes:

[0060] Receive an operation instruction for the user to agree or reject the recommended purchase page;

[0061] When the user rejects the recommended purchase page, close the purchase page, and generate a user shopping preference score according to the historical order information and historical portrait information;

[0062] Sort the products on the search page according to the user shopping preference score from high to low.

[0063] The third aspect of the embodiments of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method for guiding the purchase of e-commerce products based on artificial intelligence disclosed in the first aspect of the embodiments of the present invention.

[0064] The fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute the method for guiding the purchase of e-commerce products based on artificial intelligence disclosed in the first aspect of the embodiments of the present invention.

[0065] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0066] The e-commerce product shopping guide method based on artificial intelligence disclosed in the embodiments of the present invention includes responding to a user's search instruction, obtaining the search timestamp, keyword, and user information included in the search instruction, obtaining the user's historical order information based on the account information, screening target historical orders matching the keyword from the historical order information, calculating the score of each historical order in the target historical orders respectively, selecting the top N orders with the highest scores as reference orders, generating product information matching the user according to the user's historical portrait and keyword, generating recommended products based on the product information and reference orders, and sending the recommended product generation recommended purchase page to the user; The embodiment automatically matches products suitable for the user by combining the user's current purchase needs and the user's historical portrait, and recommends starting from the user's purchase preferences in combination with historical orders, and can accurately recommend products that better meet the user's personalized needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0068] Figure 1 is a schematic flow chart of a method for guiding the purchase of e-commerce products based on artificial intelligence disclosed in the embodiments of the present invention;

[0069] Figure 2 is a schematic structural diagram of a device for guiding the purchase of e-commerce products based on artificial intelligence provided by the embodiments of the present invention;

[0070] Figure 3 is a schematic structural diagram of an electronic device provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0072] It should be noted that the terms "first", "second", "third", "fourth", etc. in the description and claims of the present invention are used to distinguish different objects, rather than to describe a specific order. The terms "including" and "having" in the embodiments of the present invention and any variations thereof are intended to cover non-exclusive inclusion. Exemplarily, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0073] The embodiments of the present invention disclose an e-commerce product shopping guide method, device, electronic device and storage medium based on artificial intelligence. The e-commerce product shopping guide method disclosed in the embodiments includes: in response to a user's search instruction, obtaining the search timestamp, keyword and user information included in the search instruction, obtaining the user's historical order information based on the account information, screening target historical orders matching the keyword from the historical order information, calculating the score of each historical order in the target historical orders respectively, selecting the top N orders with the highest scores as reference orders, generating product information matching the user according to the user's historical portrait and the keyword, generating recommended products based on the product information and the reference orders, and sending the recommended product generation recommended purchase page to the user; The embodiments can automatically match products suitable for users by combining the user's current purchase needs and the user's historical portrait, and start recommending from the user's purchase preferences in combination with historical orders, so as to accurately recommend products that better meet the user's personalized needs.

[0074] Embodiment 1

[0075] Please refer to Figure 1 , Figure 1 is a schematic flowchart of an e-commerce product shopping guide method based on artificial intelligence disclosed in the embodiments of the present invention. Among them, the execution subject of the method described in the embodiments of the present invention is an execution subject composed of software or / and hardware. The execution subject can receive relevant information through wired or / and wireless means and can send certain instructions. Of course, it can also have certain processing functions and storage functions. The execution subject can control multiple devices, such as remote physical servers or cloud servers and related software, or can also be a local host or server and related software that performs related operations on devices placed somewhere. In some scenarios, multiple storage devices can also be controlled. The storage devices can be placed in the same place or different places as the devices. As Figure 1 shown, the e-commerce product shopping guide method based on artificial intelligence includes the following steps:

[0076] 101. In response to a user's search instruction, obtain the search timestamp, keyword and user information included in the search instruction.

[0077] In the embodiment, the user information includes account information and at least one user historical portrait; the user historical portrait includes facial features, body information, age information, and gender. Usually, a user logs in to their account on a certain shopping platform to shop, which may be to purchase items they need or to purchase items with strong user attributes for others, such as clothes. Therefore, one account information may correspond to multiple user historical portraits. The user historical portrait in the embodiment refers to the portrait information input manually by the user before this shopping or generated based on the shopping preferences on the basis of manual input. For example, the facial features of the user can be input manually by the user in the form of photos or by the user inputting words describing the features.

[0078] 102. Obtain the historical order information of the user based on the account information, and screen the target historical orders that match the keyword from the historical order information according to the keyword.

[0079] In this step, to screen and obtain the target historical orders from the historical order information, specifically, delete the historical orders in the historical order information whose shopping time exceeds the preset time threshold to obtain the historical order information within the target period; obtain the product category of the keyword, and based on the product category, eliminate the orders in the historical order information within the target period that do not match the product category to obtain the preliminary selected historical orders. Match the product usage time according to the search timestamp, and match the target historical orders from the preliminary selected historical orders based on the product usage time.

[0080] In the above, for example, the preset time threshold is also defined according to the target period. For example, the target period is 3 months, that is, only select the historical orders within the past three months starting from the current time. This can better meet the user's recent shopping preferences.

[0081] 103. Calculate the scores of each historical order in the target historical orders respectively, and select the orders with the top N scores as the reference orders; where N is a natural number and N is not equal to 0.

[0082] In this step, obtain all the purchased stores in the target historical orders and count the first purchase times of each purchased store; obtain all the purchased categories in the target historical orders and count the second purchase times of each purchased category; assign corresponding score values to different numbers of the first purchase times and the second purchase times respectively; obtain the first purchase times corresponding to the purchased store in each historical order, and calculate the sum of the score values corresponding to the first purchase times and the second purchase times respectively according to the second purchase times corresponding to the purchased category in each historical order to obtain the score of this historical order.

[0083] Exemplarily, in the user's target historical orders, the purchased categories include clothing, office supplies, and kitchen supplies. The number of purchases of clothing, office supplies, and kitchen supplies all belong to the first purchase count. Further taking clothing as an example, the total number of stores where the user purchased clothing is Store A, Store B, and Store C. And Store A was purchased 3 times, Store B was purchased 1 time, and Store C was purchased 2 times. Then the purchase counts of these stores are the second purchase count. It is preset that, for example, purchasing 1 time from the same store corresponds to an x1 score value, purchasing 2 times corresponds to an x2 score value, purchasing 3 times corresponds to an x3 score value... The first purchase count is the same way, and x1, x2, and x3 all refer to specific numerical values.

[0084] 104. Generate product information matching the user based on the user's historical portrait and keywords, generate recommended products based on the product information and reference orders, and generate a recommended purchase page for the recommended products and send it to the user.

[0085] In this step, select a matching user historical portrait from at least one user historical portrait according to the keywords; obtain the matching user historical portrait, generate a three-dimensional simulated human image, load all products of the same category matching the keywords into the three-dimensional simulated human image, and calculate the image score value after each product is loaded into the three-dimensional simulated human image; select the product with the highest image score value as the target product, and obtain the sub-words of the target product.

[0086] The three-dimensional simulated human image is a three-dimensional human model generated based on the user's historical portrait and conforming to the image of the user's historical portrait. For example, if the user's height is 160 cm and the waist circumference is 60 cm in the user's historical portrait, the drawn three-dimensional human model also has a corresponding ratio of 160 cm in height and 60 cm in waist circumference. For example, when the user selects clothes, bags, etc., it can be considered according to the user's overall image. And calculating the image score value can be based on preset specifications. For example, where should the lower edge of a fitted top reach on the body, and within the range, this item gets full marks, and exceeding the range by how much will correspond to a deduction of how many points.

[0087] Further, generating a recommended purchase page for the recommended products and sending it to the user includes: extracting the main image and keywords of each recommended product, and obtaining the purchase link of the recommended product, embedding the keywords into the extracted main image; generating a new purchase identification image with the embedded keywords and the purchase link; selecting a background template from a preset background library, arranging the new purchase identification images of all recommended products randomly in the background template to generate a recommended purchase page, and sending the purchase page to the user.

[0088] In another example, it can also be to retain the search page of the user's search keywords and create a new purchase page; randomly sort all recommended products and add them to the purchase page, and display the purchase page to the user.

[0089] In this embodiment, the user can also reject the shopping recommendation and continue to search according to their uncertain or new preferences. Then, an operation instruction for the user to agree or reject the recommended purchase page is received. When the user rejects the recommended purchase page, the purchase page is closed, and a user shopping preference score is generated based on the historical order information and historical portrait information. The products on the search page are sorted according to the user shopping preference score from high to low.

[0090] Embodiment Two

[0091] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of an e-commerce product shopping guide device based on artificial intelligence disclosed in an embodiment of the present invention. As Figure 2 shown, the e-commerce product shopping guide device based on artificial intelligence may include: an instruction response module 201, an information collection module 202, a score calculation module 203, and a product recommendation module 204. Among them, the instruction response module 201: is configured to respond to a search instruction of a user, and obtain a search timestamp, a keyword, and user information included in the search instruction. The user information includes account information and at least one user historical portrait; the user historical portrait includes facial features, body information, age information, and gender; the information collection module 202: is configured to obtain historical order information of the user based on the account information, and screen target historical orders matching the keyword from the historical order information according to the keyword; the score calculation module 203: is configured to calculate the score of each historical order in the target historical orders respectively, and select the top N orders with the highest scores as reference orders; where N is a natural number and N is not equal to 0; the product recommendation module 204: is configured to generate product information matching the user based on the user historical portrait and the keyword, generate recommended products based on the product information and the reference orders, and send the recommended products to generate a recommended purchase page to the user.

[0092] In the information collection module 202, screening the target historical orders matching the keyword from the historical order information includes: deleting the historical orders in the historical order information whose shopping time exceeds a preset time threshold to obtain the historical order information within the target period; obtaining the product category of the keyword, and excluding the orders in the historical order information within the target period that do not match the product category based on the product category to obtain the preliminary selected historical orders; matching the product usage time according to the search timestamp, and matching the target historical orders from the preliminary selected historical orders based on the product usage time.

[0093] In the scoring calculation module 203, the scores of each historical order in the target historical order are calculated respectively, including: obtaining all the purchased stores in the target historical order and counting the first purchase times of each purchased store; obtaining all the purchased categories in the target historical order and counting the second purchase times of each purchased category; respectively assigning score values corresponding to different numbers of first purchase times and second purchase times; obtaining the first purchase times corresponding to the purchased stores in each historical order, and calculating the sum of the score values corresponding to the first purchase times and the second purchase times respectively according to the second purchase times corresponding to the purchased categories in each historical order to obtain the score of this historical order.

[0094] In the product recommendation module 204, product information matching the user is generated according to the user historical portrait and keywords, including: selecting the matching user historical portrait from at least one user historical portrait according to the keywords; obtaining the matching user historical portrait, generating a three-dimensional simulated human image, loading all the products of the same category matching the keywords into the three-dimensional simulated human image, and calculating the image score value after each product is loaded into the three-dimensional simulated human image; selecting the product with the highest image score value as the target product and obtaining the sub-words of this target product.

[0095] In the product recommendation module 204, the recommended products are generated into a recommended purchase page and sent to the user. Exemplarily, it can include extracting the main picture and keywords of each recommended product, obtaining the purchase link of the recommended product, and embedding the keywords into the extracted main picture; generating a new purchase recognition picture with the main picture embedded with keywords and the purchase link; selecting a background template from the preset background library, arranging the new purchase recognition pictures of all the recommended products randomly in the background template to generate a recommended purchase page, and sending the purchase page to the user. In another example, it can also include retaining the search page of the user's search keywords and creating a new purchase page; randomly sorting all the recommended products and adding them to the purchase page, and displaying the purchase page to the user.

[0096] The embodiment can also include a rejection processing module, which is used to receive the operation instruction of the user to agree or reject the recommended purchase page; when the user rejects the recommended purchase page, close the purchase page, and generate a user shopping preference score value according to the historical order information and historical portrait information; sort the products on the search page according to the level of the user shopping preference score value.

[0097] Embodiment III

[0098] Please refer to Figure 3 , Figure 3It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. The electronic device can be a computer, a server, etc. Of course, in certain cases, it can also be an intelligent device such as a mobile phone, a tablet computer, and a monitoring terminal, as well as an image acquisition device with processing functions. As Figure 3 shown, the electronic device may include:

[0099] A memory 301 storing executable program code;

[0100] A processor 302 coupled to the memory 301;

[0101] Wherein, the processor 302 calls the executable program code stored in the memory 301 and executes some or all of the steps in the e-commerce product shopping guide method based on artificial intelligence in the first embodiment.

[0102] An embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute some or all of the steps in the e-commerce product shopping guide method based on artificial intelligence in the first embodiment.

[0103] An embodiment of the present invention also discloses a computer program product, wherein when the computer program product runs on a computer, it enables the computer to execute some or all of the steps in the e-commerce product shopping guide method based on artificial intelligence in the first embodiment.

[0104] An embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, it enables the computer to execute some or all of the steps in the e-commerce product shopping guide method based on artificial intelligence in the first embodiment.

[0105] In various embodiments of the present invention, it should be understood that the magnitude of the serial numbers of the various processes does not necessarily mean the inevitable sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0106] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, in each embodiment of the present invention, the various functional units may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0108] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several requests for causing a computer device (which can be a personal computer, a server, or a network device, etc., specifically, the processor in the computer device) to execute some or all of the steps of the methods described in the various embodiments of the present invention.

[0109] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0110] Those of ordinary skill in the art can understand that some or all of the steps in the various methods of the embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically-erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium that can be used to carry or store data.

[0111] The above has introduced in detail the e-commerce product shopping guide method, device, electronic device and storage medium based on artificial intelligence disclosed in the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An e-commerce product shopping guide method based on artificial intelligence, characterized in that: include: In response to a user's search instruction, obtaining a search timestamp, a keyword, and user information contained in the search instruction, wherein the user information includes account information and at least one user history portrait; the user history portrait includes facial features, body shape information, age information, and gender; Obtain the user's historical order information based on the account information, and delete the historical orders whose shopping time exceeds the preset time threshold in the historical order information to obtain the historical order information within the target period; obtain the product category of the keyword, and based on the product category, remove the orders that do not match the product category in the historical order information within the target period to obtain the preliminary historical orders; Match product usage time according to the search timestamp, and match target historical orders from the preliminary historical orders based on the product usage time; Get all the purchase stores in the target's historical orders, and count the number of first purchases in each purchase store; Obtain all purchase categories in the target historical orders, and count the number of second purchases for each purchase category; assign rating values ​​corresponding to different numbers of first purchases and second purchases; Obtain the first purchase number corresponding to the purchase store in each historical order, and the second purchase number corresponding to the purchase category in each historical order, calculate the sum of the score values ​​corresponding to the first purchase number and the second purchase number respectively to obtain the score of the historical order, and select the orders with the top N scores as reference orders; where N is a natural number, and N is not equal to 0; Generate user-matched product information based on user history portraits and keywords, generate recommended products based on the product information and reference orders, extract the main image and keywords of each recommended product, obtain the purchase link of the recommended product, embed the keywords into the extracted main image; generate a new purchase identification image with the main image and purchase link embedded with keywords; Select a background template from a preset background library, arbitrarily arrange the new purchase identification images of all recommended products into the background template to generate a recommended purchase page, and send the purchase page to the user, or retain the search page of the user's search keyword and create a new purchase page; Adding all recommended products to the purchase page in random order, and displaying the purchase page to the user; Receive an operation instruction from the user to agree or reject the recommended purchase page; When the user rejects the recommended purchase page, the purchase page is closed, and a user shopping preference score is generated according to the historical order information and historical portrait information; According to the user shopping preference score, the products on the search page are sorted according to the user shopping preference score.

2. An e-commerce product shopping guide device based on artificial intelligence, characterized in that: include: Instruction response module: used to respond to the user's search instruction and obtain the search timestamp, keywords and user information contained in the search instruction, wherein the user information includes account information and at least one user history portrait; the user history portrait includes facial features, body shape information, age information and gender; Information collection module: used to obtain the user's historical order information based on the account information, and filter the target historical orders matching the keywords from the historical order information according to the keywords; Rating calculation module: used to obtain all the purchase stores in the target's historical orders and count the number of first purchases in each purchase store; Obtain all purchase categories in the target historical orders, and count the number of second purchases for each purchase category; assign rating values ​​corresponding to different numbers of first purchases and second purchases; Obtain the first purchase number corresponding to the purchase store in each historical order, and the second purchase number corresponding to the purchase category in each historical order, calculate the sum of the score values ​​corresponding to the first purchase number and the second purchase number respectively to obtain the score of the historical order, and select the orders with the top N scores as reference orders; where N is a natural number, and N is not equal to 0; Product recommendation module: used to generate user-matched product information based on user history portraits and keywords, generate recommended products based on the product information and reference orders, extract the main image and keywords of each recommended product, obtain the purchase link of the recommended product, embed the keywords into the extracted main image; generate a new purchase identification image with the main image and purchase link embedded with keywords; Select a background template from a preset background library, arbitrarily arrange the new purchase identification images of all recommended products into the background template to generate a recommended purchase page, and send the purchase page to the user, or retain the search page of the user's search keyword and create a new purchase page; Adding all recommended products to the purchase page in random order, and displaying the purchase page to the user; A rejection processing module is used to receive an operation instruction from a user to agree or reject the recommended purchase page; when the user rejects the recommended purchase page, the purchase page is closed, and a user shopping preference score is generated based on the historical order information and historical portrait information; and the products on the search page are sorted according to the user shopping preference score.

3. An electronic device, characterized in that: include: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based e-commerce product shopping guide method described in claim 1.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the artificial intelligence-based e-commerce product shopping guide method of claim 1.

Images