Commodity information recommendation method and system

Abstract

The invention relates to a commodity information recommendation method and system. One specific implementation mode of the method comprises the steps of displaying a target commodity order page in response to the fact that a user completes payment of a target commodity order or in response to operation of the user on a target commodity order module; displaying a recommendation information module associated with the target commodity in the target commodity order page; and in response to the operation of the recommendation information module, displaying additional information related to the target commodity. According to the embodiment of the invention, the user can directly know the use knowledge, matters needing attention and other contents of the commodity and the auxiliary matched commodity after purchasing without skipping out an order page, thereby greatly facilitating the user and improving the user experience.

Description

Technical Field

[0001] This application relates to the fields of e-commerce and pharmaceutical supply chain technology, and in particular to a method and system for recommending product information. Background Technology

[0002] Currently, people can purchase various medicines and medical devices on e-commerce platforms. Due to the wide variety of medicines and medical devices, users typically need to consult online customer service or use a large-scale AI agent to inquire about the usage and precautions of the purchased medicines / medical devices. However, completing this consultation requires exiting the order page, which is quite inconvenient. Summary of the Invention

[0003] This invention integrates knowledge resources of various pharmaceuticals and medical devices (hereinafter collectively referred to as products), and stores textual and video content on the use and precautions of each product in the database. On the user's order page, the content modules and matching information corresponding to the purchased product, as well as information on matching products, are displayed according to the user's characteristics. This allows users to directly learn about the use knowledge and precautions of the product, as well as the supporting products, after purchasing without leaving the order page, which greatly facilitates users and improves the user experience.

[0004] According to one aspect of the present invention, a method for recommending product information is provided, the method comprising: displaying a target product order page in response to a user completing payment for a target product order or in response to a user's operation on a target product order module; displaying a recommendation information module associated with the target product on the target product order page; and displaying additional information related to the target product in response to an operation on the recommendation information module.

[0005] The additional information may include at least one of the following: usage knowledge of the target product, precautions for the target product, and information on other products used in conjunction with the target product.

[0006] The additional information can be carried by pre-set media content; the recommendation information module includes a preview image of the media content; in response to the operation of the recommendation information module, additional information related to the target product is displayed, including: in response to the operation of the preview image of the media content, the media content playback page is displayed, so as to display the additional information in the playback area of ​​the media content playback page.

[0007] The media content playback page may also include an associated product module; in response to the operation of the associated product module, display the details page of other products associated with the target product; or, in response to the operation of the associated product module, add other products associated with the target product to the shopping cart.

[0008] The media content may come from a media account, and the method may further include: in response to an operation on the media account identifier on the media content playback page, redirecting to the media account homepage.

[0009] The additional information is selected based on user type, which is based on user behavior and user characteristics.

[0010] The additional information is selected based on user characteristics and pharmaceutical category features.

[0011] The media content can be generated by at least one of algorithms and human intervention.

[0012] Generating the media content using algorithms may include recognizing the instruction manual using OCR and using a digital human to generate a video from the recognized text according to the algorithm.

[0013] According to one aspect of the present invention, a product information recommendation device is provided, characterized in that it includes: an order page display module, used to display a target product order page in response to a user completing payment for a target product order or in response to a user's operation on a target product order module; a recommendation information display module, used to display recommendation information modules associated with the target product on the target product order page; and an additional information display module, used to display additional information related to the target product in response to an operation on the recommendation information module.

[0014] According to one aspect of the present invention, a computer-readable storage medium is provided that stores instructions, which, when executed by a computing system, cause the computing system to perform a method, the method comprising: displaying a target product order page in response to a user completing payment for a target product order or in response to a user's operation on a target product order module; displaying a recommendation information module associated with the target product on the target product order page; and displaying additional information related to the target product in response to the recommendation information module being operated.

[0015] It should be understood that all combinations of the above concepts and other concepts discussed in more detail below are contemplated as part of the subject matter of the invention disclosed herein. Attached Figure Description

[0016] Figure 1 This is an example interface for automatically providing recommendation information after purchasing goods, according to the present invention.

[0017] Figure 2 This is another example interface according to the present invention for automatically providing recommendation information after purchasing goods.

[0018] Figure 3 This is an example interface that displays all media content of a media account simultaneously when the media content is played, according to the present invention.

[0019] Figure 4 This is an example interface for pre-configuring goods and media content according to the present invention.

[0020] Figure 5 This is an example interface for generating media content according to the present invention.

[0021] Figure 6 This is a flowchart of a method for generating media content according to the present invention.

[0022] Figure 7 This is a flowchart of a product information recommendation method according to the present invention. Detailed Implementation

[0023] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] Figure 1 This is an example interface of the product information recommendation method according to the present invention.

[0025] With the continuous development of society and changes in people's lifestyles, users can purchase medicines or medical devices on e-commerce platforms. Due to the wide variety of medicines and medical devices, users often need to understand the usage and precautions of the purchased items. Typically, users need to consult online customer service or use an AI assistant for assistance. However, completing this consultation requires exiting the order page, which is quite inconvenient.

[0026] According to the present invention, when a user purchases goods (e.g., pharmaceuticals or medical devices) on an e-commerce platform, the user can select a target product (e.g., pharmaceuticals or medical devices) according to their needs and complete the payment for the target product order. In response to the user completing the payment for the target product order, or in response to the user's operation of the target product order module, a target product order page is displayed; a recommendation information module associated with the target product is displayed on the target product order page; in response to the operation of the recommendation information module, additional information related to the target product is displayed. The additional information may include at least one of media content such as text content, image content, and video content.

[0027] As in Figure 1As shown, in response to a user completing payment for a target product order, a target product order page is displayed, showing a recommendation information module associated with the target product. In response to the recommendation information module being activated, additional information related to the target product can be displayed. This additional information may include at least one of the following: usage information for the target product, precautions for the target product, and information on other products that can be used in conjunction with the target product. Figure 1 As shown on the left, the additional information may include a preview of the "Medication Guide". When "Medication Guide" is clicked, the following will be displayed simultaneously: Figure 1 The right side shows detailed "Medication Instructions". For example... Figure 1 As shown on the right, the detailed "Medication Instructions" information may include information such as "Indications," "Dosage and Administration," "Expiration Date," "Contraindications," "Storage Conditions," and "Precautions." For example... Figure 1 As shown on the left, additional information related to the target product can be carried through pre-set media content, and the recommendation information module includes a preview image of the media content. When a user wants to watch video content, the user can click on the preview image of the video content. The video content can be a pre-recorded explanatory video or video content generated by converting text content using digital human technology.

[0028] In the example above, in response to the user completing payment for the target product order, the target product order page is displayed, showing only... Figure 1 The left side of the page. When the user clicks "Medication Guide", it will also display... Figure 1 The right side of the text can be displayed. Figure 1 The entire interface includes the left and right sides. Alternatively, it can be displayed directly in response to the user completing payment for the target product order, as needed. Figure 1 The entire interface includes the left and right sides.

[0029] The recommendation information module also allows users to view logistics, return / after-sales service, and repurchase.

[0030] Figure 2 This is another example interface for recommending product information according to the present invention.

[0031] As in Figure 2 As shown, in response to a user's action of viewing order information, a target product order page is displayed, and a recommendation information module associated with the target product is shown on the target product order page. In response to the recommendation information module being activated, additional information related to the target product can be displayed. For example... Figure 2 As shown on the left, the recommendation information module can include preview information for "medication guidance".

[0032] like Figure 2 As shown on the left, the recommendation information module may include preview images of media content such as "How to Take Vitamin B6". When a user wants to watch video content, they can click on the preview image of the video content. The video content may be a pre-recorded instructional video or video content generated by converting text content using digital human technology.

[0033] When a user clicks on the preview image for "How to take Vitamin B6", it can display... Figure 2 The media playback page on the right.

[0034] In the example above, in response to the user's action of viewing order information, the target product order page is displayed, showing only... Figure 2 The left side of the page. When the user clicks "Medication Guide", it will also display... Figure 2 The right side of the text can be displayed. Figure 2 The entire interface includes the left and right sides. Alternatively, it can be displayed directly in response to the user's action of viewing order information, as needed. Figure 2 The entire interface includes the left and right sides.

[0035] like Figure 2 As shown, the "Must-See After Purchase" module may include functions such as "View Logistics", "Return / After-Sales Service", and "Repurchase".

[0036] The media content can come from media accounts. For example... Figure 2 As indicated by the middle arrow, responding to an action on the media account identifier during media content playback can redirect to the media account's homepage. For example, as... Figure 3 As shown, all media content for that media account can be displayed.

[0037] When displaying media content, you can also showcase other products that can be used in conjunction with the target product.

[0038] The other products are recommended based on the user group type.

[0039] For example, based on user behavior and characteristics such as age, gender, medical records, health records, and historical purchase information, users can be categorized using algorithms like Native Bayes: Based on user behavior, users can be categorized as: high-frequency users, low-frequency users, first-time buyers, and repeat buyers. Based on health status: chronic disease patients, post-operative recovery users, sub-healthy individuals, and normal users.

[0040] This allows for the development of different product recommendation strategies based on user demographics. For example, the correspondence between user demographics and product types can be used to determine recommended products. For instance, frequently purchased products can be recommended to high-frequency users, low-priced products to low-frequency users, high-browsing but unordered low-priced products to first-time buyers, frequently purchased products to repeat buyers, disease-related products to patients with chronic illnesses, rehabilitation products to post-operative recovery users, health-promoting products to those in a sub-healthy state, and high-browsing but unordered products to healthy users. In practice, user demographics can be categorized differently as needed, and different product recommendation strategies can be developed based on user demographic types.

[0041] Other products can also be recommended based on user characteristics and the characteristics of pharmaceutical categories.

[0042] For example, other products can be recommended based on user characteristics such as disease information and a combination drug library including pharmaceutical category characteristics. For instance, user disease information can be obtained based on the user's purchase history and / or medical records, and drug information, drug interactions (recording the type and strength of interactions between drugs), drug-disease relationships, clinical guidelines, etc., can be obtained from the combination drug library. User characteristics can include age, gender, weight, height, medical history, allergy history, etc. Products can then be recommended based on predefined rules and a knowledge base. Machine learning models can also be used to recommend products. For example, algorithms such as logistic regression, support vector machine (SVM), decision tree, random forest, and gradient boosting tree (GBDT) can be used to determine whether a drug is suitable for a particular user. When recommending products, it can be ensured that the recommended drugs do not conflict with the patient's contraindications, avoid recommending drugs that may cause serious drug interactions, and consider the user's personal characteristics and preferences. Similarly, bundled products related to consumables can be recommended based on user characteristics.

[0043] It allows users to interact with other products displayed in the media content, such as adding them to a shopping cart or making a direct purchase.

[0044] like Figure 2 and Figure 3 As shown, to help users decide whether to add other products to their shopping cart or purchase them directly, information such as the number of products sold and the number of reviews can be displayed.

[0045] In addition, such as Figure 2 and Figure 3 As shown, when displaying media content, functions such as liking, commenting, collecting, and sharing can be implemented.

[0046] In order to display the "Must-See After Purchase" module on the target product order page at the same time as displaying the target product order page, the product (such as medicine, medical device, etc.) and media content can be pre-configured.

[0047] Figure 4 This is an example interface for pre-configuring goods and media content according to the present invention.

[0048] like Figure 4 As shown, users can enter a description of frequently asked questions using a title, upload generated videos by uploading videos, and select video covers using keyframes, etc.

[0049] In addition, such as Figure 4 As shown, source tags, categories, products, drug names, generic drug names, and complementary SKUs can be pre-configured.

[0050] In this invention, the media content can be generated by at least one of an algorithm and manual methods.

[0051] Generating the media content using algorithms may include recognizing the instruction manual using OCR and using a digital human to generate a video from the recognized text according to the algorithm. Figure 5 This is an example interface for generating media content according to the present invention. Figure 5 As shown, OCR can be used for, for example Figure 5 The user manual shown on the left undergoes text recognition to extract usage methods, precautions, and other information. Based on the algorithm, a digital human then generates a video from the extracted content. For example... Figure 5 The video shown from the side is intended to convey the message to the user in a more intuitive way.

[0052] Generating the media content manually can include having professionals film live and generate videos. These professionals can be pharmacists, purchasing agents, or similar personnel.

[0053] The generated media content can be stored in the backend system and associated with the corresponding account to better convey the product's professional information.

[0054] The following reference Figure 6 Describe how media content is generated. Figure 6 This is a flowchart of a method for generating the media content according to the present invention.

[0055] In step S610, document recognition is performed on the image to extract text from it. For example, commonly used OCR tools can be used to extract text from the image. Figure 5 The image of the instruction manual shown on the left is used for document recognition to extract the text from the image.Figure 5 In the examples, information related to contraindications, administration method, minimum single dose, indications, dosage, precautions, drug classification, adverse reactions, applicable population, and disease information can be extracted.

[0056] Optionally, to avoid incomplete accuracy of OCR recognition results, the text extracted from the image can be manually proofread and corrected.

[0057] In step S620, the extracted text is organized into a video script. For example, the extracted text can be broken down into different segments. Figure 5 In the example, information related to each aspect, such as contraindications, method of administration, minimum single dose, indications, dosage, precautions, drug classification, adverse reactions, applicable population, and disease information, can be divided into segments.

[0058] In step S630, the extracted text, broken down into segments, is converted into speech. This can be done using text-to-speech (TTS) technology or by having a human read aloud. Optionally, the digital human's actions and expressions can be designed based on the video content. For example, while reading the extracted text, the digital human can nod, smile, or perform other actions in accordance with the text content.

[0059] In step S640, a digital human video is generated using a digital human platform. The digital human platform can be any of the following: Xiaoice, Baidu Digital Human, Tencent Cloud Digital Human, Synthesia, DeepMotion, etc. After selecting a digital human platform, the programmed footsteps and generated voice can be uploaded to the platform, and a suitable digital human avatar can be chosen to generate the digital human video. Optionally, appropriate backgrounds and effects can be added based on the video content.

[0060] Optionally, the generated video can be edited and optimized. For example, video editing software can be used to edit the video to adjust the rhythm and transition effects. Furthermore, subtitles can be added to the video to facilitate user understanding, color correction can be performed to improve the video's visual effects, audio processing can be done to adjust volume, reduce noise, add background music, etc., and / or the edited video can be exported to a suitable format and resolution.

[0061] Moreover, it can be achieved through, for example Figure 4 The interface shown is used to associate the generated video with the product.

[0062] Figure 7 This is a flowchart of a product information recommendation method according to the present invention.

[0063] In step S710, in response to the user completing the payment for the target product order, or in response to the user's operation on the target product order module, the target product order page is displayed.

[0064] In step S720, a recommendation information module associated with the target product is displayed on the target product order page.

[0065] In step S730, in response to the operation of the recommendation information module, additional information related to the target product is displayed. The additional information may include at least one of the following: usage information for the target product, precautions for the target product, and information on other products that can be used in conjunction with the target product.

[0066] The additional information can be carried by pre-set media content; the recommendation information module includes a preview image of the media content; in response to the operation of the recommendation information module, additional information related to the target product is displayed, including: in response to the operation of the preview image of the media content, the media content playback page is displayed, so as to display the additional information in the playback area of ​​the media content playback page.

[0067] The media content playback page may also include an associated product module; in response to the operation of the associated product module, display the details page of other products associated with the target product; or, in response to the operation of the associated product module, add other products associated with the target product to the shopping cart.

[0068] The media content originates from a media account, and the method further includes: in response to an operation on the media account identifier on the media content playback page, redirecting to the media account homepage.

[0069] The method for automatically providing recommendation information after purchasing goods according to the present invention can be implemented on a computing system. The computing system can be any of a general-purpose server, a rack server, or a cloud server. The computing system may include: one or more processors; and a memory coupled to the one or more processors, the memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the method, including, in response to a user completing payment for a target product order or in response to a user's operation on a target product order module, displaying a target product order page, and simultaneously displaying a "Must-See After Purchase" module on the target product order page, the "Must-See After Purchase" module including additional information related to the target product.

[0070] The method for automatically providing recommendation information after purchasing goods according to the present invention can be implemented on a computer-readable storage medium storing instructions. When executed by a computing system, the instructions cause the computing system to perform the method, including, in response to a user completing payment for a target product order or in response to a user's operation on a target product order module, displaying a target product order page, and simultaneously displaying a "Must-See After Purchase" module on the target product order page, the "Must-See After Purchase" module including additional information related to the target product.

[0071] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in this disclosed technical solution all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0072] After collecting user information, we will use technical means to de-identify the data.

[0073] Although several inventive implementations have been described and illustrated herein, those skilled in the art will readily conceive of many other means and / or structures for performing functions and / or obtaining results and / or one or more advantages described herein, and each of these variations and / or improvements is considered to be within the scope of the inventive implementations described herein. Generally, those skilled in the art will readily recognize that all parameters, dimensions, materials, and configurations described herein are exemplary and that actual parameters, dimensions, materials, and / or configurations will depend on the specific application using the teachings of this invention. Those skilled in the art will recognize or be able to determine many equivalents of the specific inventive implementations described herein using only conventional experimentation. Therefore, it should be understood that the foregoing implementations are provided by way of example only, and that inventive implementations can be practiced in ways other than those specifically described and claimed within the scope of the appended claims and their equivalents. The inventive implementations of this disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. Furthermore, any combination of two or more such features, systems, articles, materials, kits, and / or methods is included within the scope of this disclosure if such features, systems, articles, materials, kits, and / or methods are not inconsistent with each other.

[0074] All definitions defined and used herein should be understood to be governed by dictionary definitions, definitions incorporated by reference in other documents, and / or the general meaning of the defined words.

[0075] Unless explicitly indicated to the contrary, the indefinite articles “a” and “an” used in this specification and claims shall be understood to mean “at least one”.

[0076] As used in this specification and claims, the phrase “and / or” should be understood to mean “any one or both” of so-called connected elements (i.e., elements that appear consecutively in some cases and separately in others). Multiple elements listed with “and / or” should be interpreted in the same way, i.e., “one or more” of so-called connected elements. Other elements may optionally be present, whether related to or unrelated to those specifically identified by the “and / or” clause. Thus, as a non-limiting example, when used in conjunction with open-ended language such as “comprising,” a reference to “A and / or B” may in one implementation refer only to A (optionally including elements other than B); in another implementation, it may refer only to B (optionally including elements other than A); in yet another implementation, it may refer to both A and B (optionally including other elements), and so on.

[0077] As used herein and in the claims, “or” should be understood to have the same meaning as “and / or” as defined above. For example, when items in a separate list are separated, “or” or “and / or” should be interpreted as inclusive, i.e., including at least one, but also including many elements or more than one element in a list of elements, as well as optional additional unlisted items. Only words that explicitly indicate the opposite, such as “only one” or “exactly one”, or “consisting of…” as used in the claims, will refer to including many elements or exactly one element in a list of elements. Generally, when an exclusive term such as “any one,” “one of,” “only one” or “exactly one” precedes it, the term “or” as used herein should be interpreted only as indicating an exclusive alternative (i.e., “one or the other, not both”). When used in the claims, “consisting substantially of…” should have its ordinary meaning as used in the field of patent law.

[0078] As used in this specification and claims, the phrase "at least one" in references to a list of one or more elements should be understood to mean at least one element selected from any one or more elements in the list of elements, but does not necessarily include at least one of every element specifically listed in the list of elements and does not exclude any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements referred to by the phrase "at least one," whether related to or unrelated to those specifically identified elements. Thus, as a non-limiting example, "at least one of A and B" (or, equivalently, "at least one of A or B," or, equivalently, "at least one of A and / or B") in one implementation may refer to at least one A, optionally including more than one A, where B is absent (and optionally including elements other than B); in another implementation may refer to at least one B, optionally including more than one B, where A is absent (and optionally including elements other than A); in yet another embodiment may refer to at least one A, optionally including more than one A, and at least one B, optionally including more than one B (and optionally including other elements), and so on.

[0079] It should also be understood that, unless expressly indicated to the contrary, in any method claimed herein that includes more than one step or action, the order of the steps or actions of the method is not necessarily limited to the order in which the steps or actions of the method are recorded.

Claims

1. A method for recommending product information, characterized in that, include: The target product order page is displayed in response to the user completing payment for the target product order or in response to the user's operation on the target product order module; The order page for the target product displays a recommendation information module associated with the target product; In response to the operation of the recommendation information module, additional information related to the target product is displayed.

2. The method according to claim 1, characterized in that, The additional information includes at least one of the following: usage knowledge of the target product, precautions for the target product, and information on other products used in conjunction with the target product.

3. The method according to claim 2, characterized in that, The additional information is carried through pre-set media content; the recommendation information module includes a preview image of the media content; In response to the operation of the recommendation information module, additional information related to the target product is displayed, including: In response to the operation of the preview image of the media content, the media content playback page is displayed to show the additional information in the playback area of ​​the media content playback page.

4. The method according to claim 3, characterized in that, The media content playback page also includes an associated product module; In response to the operation of the associated products module, the details pages of other products associated with the target product are displayed; Alternatively, in response to the operation of the associated products module, other products associated with the target product can be added to the shopping cart.

5. The method according to claim 3, characterized in that, The media content originates from a media account, and the method further includes: in response to an operation on the media account identifier on the media content playback page, redirecting to the media account homepage.

6. The method according to claim 1, characterized in that, The additional information is determined based on the user type; The additional information, determined based on user type, includes: User type is determined based on at least one of the following: age, gender, medical consultation information, user health record, and historical purchase information; and The additional information is determined by using the correspondence between user type and product type.

7. The method according to claim 1, characterized in that, The additional information is determined based on user characteristics and the characteristics of the pharmaceutical category; The additional information determined based on user characteristics and pharmaceutical category features includes: User characteristics, including the user's disease information, are obtained based on the user's purchase history and / or medical records. Based on the combined drug database, obtain at least one of the following pharmaceutical category characteristics: drug information, drug interactions, drug-disease relationship, and clinical guidelines; The additional information is determined based on predefined rules and a knowledge base that address the user characteristics and the pharmaceutical category characteristics, or by using a machine learning model based on the user characteristics and the pharmaceutical category characteristics.

8. The method according to claim 3, characterized in that, The media content is generated in the following manner: Perform file recognition on images to extract text from them; Organize the extracted text into a video script; Convert the extracted text into speech by breaking it down into fragments; as well as The media content is generated using a digital human platform.

9. A product information recommendation device, characterized in that, include: The order page display module is used to display the target product order page in response to the user completing the payment for the target product order or in response to the user's operation on the target product order module; A recommendation information display module is used to display recommendation information associated with the target product on the target product order page; The additional information display module is used to display additional information related to the target product in response to the operation of the recommendation information module.

10. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-8.

11. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-8.

Images