Information recommendation method, display method, data processing method, computing device and computer storage medium

Abstract

The embodiment of the invention provides an information recommendation method, an information display method, a data processing method, computing equipment, a computer storage medium and a computer program product. The information recommendation method comprises the following steps: in response to an object viewing request, determining a target object; determining at least one piece of evaluation information of the target object; wherein the at least one piece of evaluation information is extracted from at least one piece of evaluation data of the target object; providing an object display page; and providing at least one piece of target evaluation information in the at least one piece of evaluation information in the object display page. According to the technical scheme provided by the embodiment of the invention, the information accuracy and effectiveness are improved, and the user interaction experience is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular to an information recommendation method, an information display method, a data processing method, a computing device, a computer storage medium, and a computer program product. Background Art

[0002] In some online systems that provide objects for users to perform interactive behaviors such as purchase, users can learn about the objects by browsing the object detail information in the object detail page provided by the online system. The object detail information is usually provided by the object provider. Users can choose to collect the object, add the object to the shopping cart, or directly purchase the object in the object detail page. In addition, the online system can also provide some object recommendation pages to display multiple objects in a list format.

[0003] In these object display pages such as object collection pages, shopping cart pages or object recommendation pages, some key information extracted or generated from the object details information can be displayed as object prompt information to make recommendations to users. In these object display pages, users can further perform interactive behaviors such as purchasing or entering the indexed object details page. However, the object prompt information displayed in these object display pages is often not enough to motivate users to perform interactive behaviors. Therefore, how to provide more accurate and effective information to improve the user interaction experience becomes a technical problem that needs to be solved. Summary of the invention

[0004] Embodiments of the present application provide an information recommendation method, an information display method, a data processing method, a computing device, a computer storage medium, and a computer program product.

[0005] In a first aspect, an embodiment of the present application provides an information recommendation method, comprising:

[0006] In response to a shopping cart viewing request, determining a target object corresponding to the shopping cart;

[0007] Determining at least one evaluation information of the target object; the at least one evaluation information is extracted from at least one evaluation data of the target object;

[0008] Provide a shopping cart page;

[0009] In the shopping cart page, at least one target evaluation information among the at least one evaluation information is provided.

[0010] In a second aspect, an information display method is provided in an embodiment of the present application, comprising:

[0011] In response to the shopping cart viewing operation, a shopping cart viewing request is sent to the server;

[0012] Display the shopping cart page in the user interface;

[0013] The object prompt information of the target object and at least one target evaluation information corresponding to the target object are displayed on the shopping cart page; the at least one target evaluation information is determined from at least one evaluation information of the target object; and the at least one evaluation information is extracted from at least one evaluation data of the target object.

[0014] In a third aspect, an embodiment of the present application provides a data processing method, including:

[0015] extracting at least one evaluation information from at least one evaluation data of the target object using the data extraction model;

[0016] storing the at least one evaluation information corresponding to the target object;

[0017] Among them, the at least one evaluation information is used to display at least one target evaluation information among the at least one evaluation information in the shopping cart page when the target object responds to any user request to add to the shopping cart and a shopping cart viewing request triggered by the user is detected.

[0018] In a fourth aspect, an embodiment of the present application provides an information recommendation method, comprising:

[0019] In response to the object viewing request, determining a target object;

[0020] Determine at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object;

[0021] Provide object display page;

[0022] At least one target evaluation information among the at least one evaluation information is provided in the object display page.

[0023] In a fifth aspect, an embodiment of the present application provides an information recommendation device, including:

[0024] A first object determination unit, configured to determine a target object corresponding to the shopping cart in response to a shopping cart viewing request;

[0025] A first evaluation information determining unit, configured to determine at least one evaluation information of the target object; the at least one evaluation information is extracted from at least one evaluation data of the target object;

[0026] A first page providing unit, used for providing a shopping cart page;

[0027] The first display unit is used to provide at least one target evaluation information among the at least one evaluation information in the shopping cart page.

[0028] In a sixth aspect, an embodiment of the present application provides an information display device, including:

[0029] A first request sending unit, configured to send a shopping cart viewing request to a server in response to a shopping cart viewing operation;

[0030] A second page display unit, used to display a shopping cart page in the user interface;

[0031] The third page display unit is used to display object prompt information of the target object and at least one target evaluation information corresponding to the target object on the shopping cart page; the at least one target evaluation information is determined from at least one evaluation information of the target object; and the at least one evaluation information is extracted from at least one evaluation data of the target object.

[0032] In a seventh aspect, an embodiment of the present application provides a data processing device, including:

[0033] A first evaluation information extraction unit, configured to extract at least one evaluation information from at least one evaluation data of a target object using a data extraction model;

[0034] A first evaluation information storage unit, configured to store the at least one evaluation information corresponding to the target object;

[0035] Among them, the at least one evaluation information is used to display at least one target evaluation information among the at least one evaluation information in the shopping cart page when the target object responds to any user request to add to the shopping cart and a shopping cart viewing request triggered by the user is detected.

[0036] In an eighth aspect, an embodiment of the present application provides an information recommendation device, including:

[0037] A second object determination unit, configured to determine a target object in response to an object viewing request;

[0038] A second evaluation information determination unit, configured to determine at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object;

[0039] A second page providing unit, used for providing an object display page;

[0040] The fourth page display unit is used to provide at least one target evaluation information among the at least one evaluation information in the object display page.

[0041] In a seventh aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component;

[0042] The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the information recommendation method provided in the embodiment of the present application, or to implement the information display method provided in the embodiment of the present application, or to implement the data processing method provided in the embodiment of the present application, or to implement the information recommendation method provided in the embodiment of the present application.

[0043] In an eighth aspect, a computer storage medium is provided in an embodiment of the present application, storing a computer program, and when the computer program is executed by a computer, it implements the information recommendation method provided in the embodiment of the present application, or implements the information display method provided in the embodiment of the present application, or implements the data processing method provided in the embodiment of the present application, or implements the information recommendation method provided in the embodiment of the present application.

[0044] In the ninth aspect, a computer program product is provided in an embodiment of the present application, and the computer program product includes a computer program code. When the computer program code is executed by a computer, the information recommendation method provided in the embodiment of the present application is implemented, or the information display method provided in the embodiment of the present application is implemented, or the data processing method provided in the embodiment of the present application is implemented, or the information recommendation method provided in the embodiment of the present application is implemented.

[0045] In an embodiment of the present application, by adopting the following technical solutions: determining a target object in response to an object viewing request; determining at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object; providing an object display page; and providing at least one target evaluation information in the at least one evaluation information in the object display page. After extracting at least one evaluation information from at least one evaluation data of the target object, at least one evaluation information can be provided in the object display page of the target object to assist the user in making a purchasing decision. In this way, in addition to obtaining introductory information of the target object itself from the object display page, the user can also obtain evaluation information of the target object from other users, thereby improving the accuracy and effectiveness of the information and improving the user interaction experience.

[0046] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A system architecture diagram is shown in which the technical solution of an embodiment of the present application can be applied;

[0049] Figure 2 A flowchart of an embodiment of an information recommendation method provided by the present application is shown;

[0050] Figure 3 A schematic diagram showing an information recommendation method provided by an embodiment of the present application is shown;

[0051] Figure 4 A flowchart of an embodiment of an information recommendation method provided by the present application;

[0052] Figure 5 A flowchart of an embodiment of a data processing method provided by the present application;

[0053] Figure 6 A flowchart of an information display method provided in an embodiment of the present application;

[0054] Figure 7 A signaling flow chart applicable to an information recommendation system provided in an embodiment of the present application is shown;

[0055] Figure 8 A schematic diagram showing a display of a user interface in an actual application of an embodiment of the present application is shown;

[0056] Fig. 9 A schematic diagram of a server in one embodiment of the present application is shown;

[0057] Fig.10 An architectural design diagram applicable to an information recommendation method in one embodiment of the present application is shown;

[0058] Fig.11 A block diagram of an information recommendation device provided by an embodiment of the present application;

[0059] Fig.12 A block diagram of an information display device provided in one embodiment of the present application;

[0060] Fig.13 A block diagram of a data processing device provided for one embodiment of the present application;

[0061] Fig.14 A block diagram of an information recommendation device provided by an embodiment of the present application;

[0062] Fig.15 A block diagram of a computing device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0064] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0065] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0066] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register a user account in the server through registration to obtain a user identity in the network environment.

[0067] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0068] Figure 1A system architecture diagram in which the technical solution of an embodiment of the present application can be applied is shown, and the system architecture may include a user end 101 and a server end 102. The user end 101 is user-oriented, and allows the user to perform interactive operations such as object search, object collection, object addition to shopping cart, and object purchase.

[0069] The user terminal 101 and the server terminal 102 are connected via a network. The network provides a medium for a communication link between the user terminal 101 and the server terminal 102. The network may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0070] The client 101 can interact with the server 102 through the network to receive or send messages, etc.

[0071] The user terminal 101 may be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The user terminal 101 may be deployed in an electronic device and may rely on the device to run or some apps in the device to run, etc. For example, the electronic device may have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. For ease of understanding, Figure 1 In the text, the user end is mainly represented by the device image. Various other types of applications can usually be configured in electronic devices, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0072] The server 102 may include servers that provide various services, such as a server for background training that provides support for the model used on the user terminal 101, or a server that processes interactive information sent by the user terminal.

[0073] It should be noted that the server 102 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0074] It should be noted that the information recommendation method provided in the embodiments of the present application is generally executed by the server 102, and the corresponding information recommendation device is generally set in the server 102. However, in other embodiments of the present application, the user terminal 101 may also have similar functions to the server 102, so as to execute the information display method and data processing method provided in the embodiments of the present application.

[0075] It should be understood that Figure 1 The number of the user terminals and the server terminals in the figure is only for illustration. Any number of the user terminals and the server terminals may be provided according to the implementation requirements.

[0076] The implementation details of the technical solution of the embodiment of the present application are elaborated in detail below.

[0077] Figure 2 A flowchart of an embodiment of an information recommendation method provided by the present application is shown. The technical solution of this embodiment is executed by the server. The method may include the following steps:

[0078] 201: In response to an object viewing request, determine a target object.

[0079] 202: Determine at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object.

[0080] 203: Provide an object display page.

[0081] 204: providing at least one target evaluation information in the at least one evaluation information in the object display page.

[0082] Among them, the server can determine the target object through an object viewing request.

[0083] In one implementation, the object viewing request may be triggered based on page prompt information for an object display page, and the object display page may be an object list for displaying recommendation information of multiple objects, such as an object collection page, a shopping cart page, an object recommendation page, or a search result page. The target object may refer to any object corresponding to the object list page. Taking the shopping cart page as an example, a navigation control that can trigger the entry into the shopping cart page is often provided in the homepage of the user terminal. By triggering the navigation control, the user terminal detects the trigger operation, and thus may generate an object viewing request.

[0084] Of course, in another implementation, as described above, the object list page can display recommendation information corresponding to multiple objects, and each recommendation information can be indexed to the object details page of the corresponding object. Therefore, the object viewing request can also be triggered based on the recommendation information for the target object, and the object display page can refer to the object details page. The target object can be any object corresponding to the object list page.

[0085] In actual applications, for example, when the object is a tangible product, after the user purchases the object, the object provider will send the product corresponding to the purchased object to the user. The user can evaluate the actual situation of the product received, so as to publish the evaluation data for the object in the online system or other social media platforms. The evaluation data may include images, videos and / or texts to share the use experience, advantages and disadvantages of the object. In the process of implementing this application, the inventor found that the evaluation data includes some more accurate information, which can effectively help users understand the nature and characteristics of the object, and plays a vital role in the user's interactive behavior such as purchase. In actual applications, the object details page usually provides evaluation data viewing prompt information, and the user can trigger the evaluation viewing request to enter the evaluation data page. The evaluation data page will display the evaluation data for the same object published by different users in the online system. It can be seen from the evaluation data viewing process that the link to the evaluation data page is long, especially in the object list page. If you want to view the evaluation data of an object, you need to first enter the object details page from the object list page, and then enter the evaluation data page from the object details page. At the same time, an object may correspond to a lot of evaluation data, and the user needs to filter them one by one to obtain the desired purpose information. In view of the role of evaluation data and the characteristics of mixed information in the evaluation data, the inventor proposed the technical solution of the present application, which can extract evaluation information from at least one evaluation data of the target object and provide the evaluation information in the object display page, which can help users understand the target object with the help of the evaluation data when viewing the object display page, thereby improving the accuracy and effectiveness of the information in the object display page. The evaluation data is extracted and only the extracted evaluation information is provided to help users screen information, etc., which helps users quickly obtain useful information and further ensures the accuracy of the information, thereby helping to improve the object conversion rate and enhance the user interaction experience.

[0086] The at least one evaluation data may include all evaluation data corresponding to the target object, and of course, may also be the evaluation data selected most recently from all the evaluation data or screened out after data cleaning.

[0087] The target object's evaluation data may be obtained, for example, from an online system on the target object's evaluation data page; in addition, the target object's evaluation data may also be obtained from relevant topic discussions on social media platforms, or from professional evaluation websites, etc.

[0088] At least one evaluation information may include evaluation information that is valuable to the target object in at least one evaluation data. For example, the extracted at least one evaluation information may be a user's positive evaluation of the target object; or, at least one evaluation information may be evaluation information related to the industry attributes of the industry to which the target object belongs. For example, the industry to which the target object belongs is clothing, and the industry attributes may include, for example, style attributes, fabric material attributes, size specification attributes, seasonal attributes, etc., so that at least one evaluation information may be evaluation information for any one or more of the style attributes, fabric material attributes, size specification attributes, and seasonal attributes; for another example, the industry to which the target object belongs may be electronic products, and the industry attributes of electronic products may include functional performance attributes, hardware composition attributes, software system attributes, etc., so that at least one evaluation information may be evaluation information for any one or more of the functional performance attributes, hardware composition attributes, and software system attributes.

[0089] In the embodiments of the present application, the evaluation data may be the user's feelings written casually after purchasing the product or experiencing the service. The form is relatively free and the length varies. For example, on an e-commerce platform, the evaluation of an electronic product may be written like this: "I recently bought this smart sweeping robot. When I first used it, I was really excited. I felt that I could finally free my hands and didn't have to sweep the floor myself. Its appearance design is quite fashionable. It is a simple and modern style. It doesn't look out of place in any corner of the house. The operation is also very simple. It can be easily controlled through the mobile phone APP. It is very convenient to set the cleaning mode and schedule cleaning. And it cleans quite cleanly, taking care of every corner, and sucking in hair and dust. However, its battery life is a bit disappointing. After being fully charged, it may run out of power halfway through cleaning a larger room, and it needs to be recharged to continue the cleaning task. Also, it makes a lot of noise when working, especially in a quiet environment. It feels quite noisy. But overall, it still brings a lot of convenience to my daily cleaning."

[0090] If the above evaluation data is directly displayed to users, it may not be able to effectively convey the characteristics of the target object and the user's main feelings about the target object.

[0091] Therefore, in a possible implementation of the present application, at least one evaluation information may be obtained after extracting key information from at least one evaluation data, so that the at least one evaluation information can concisely and accurately reflect the characteristics of the target object and the user evaluation.

[0092] For example, after extracting key information from the above evaluation data, we can obtain evaluation information: "The smart sweeping robot has a fashionable appearance design and a simple and modern style", or: "The smart sweeping robot can be easily controlled through a mobile phone application, and it is convenient to set the cleaning mode and other operations."

[0093] Among them, the object display page can be used to display basic object information, media information, etc. of the target object. The basic object information can include, for example, the name, model, appearance color, price, etc. of the target object, and the media information can include pictures and videos of the target object.

[0094] In one possible implementation, the object display page can be implemented as a product details page of an e-commerce platform, a brand flagship store page, a recommended product page, a shopping cart page, a search result display page, etc.

[0095] In an embodiment of the present application, at least one evaluation information may be displayed in a larger font and eye-catching color at the top of the object display page or in other prominent positions, so that the user can see the key information as soon as the object display page is opened.

[0096] In an embodiment of the present application, by adopting the following technical solutions: determining a target object in response to an object viewing request; determining at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object; providing an object display page; and providing at least one target evaluation information in the at least one evaluation information in the object display page. After extracting at least one evaluation information from at least one evaluation data of the target object, at least one evaluation information can be provided in the object display page of the target object to assist the user in making a purchasing decision. In this way, in addition to obtaining introductory information of the target object itself from the object display page, the user can also obtain evaluation information of the target object from other users, thereby improving the accuracy and effectiveness of the information and improving the user interaction experience.

[0097] In some embodiments, in the object display page, providing at least one target evaluation information in at least one evaluation information may be specifically implemented as follows:

[0098] Detect whether at least one evaluation information meets the first risk control condition; determine at least one candidate evaluation information according to the risk control detection result; and provide at least one target evaluation information among the at least one candidate evaluation information in the object display page.

[0099] The first risk control condition may be a standard set to ensure that the evaluation information displayed on the object display page meets certain risk control requirements. For example, multiple keywords or sentence mode restrictions may be set in the standard, such as the sentence mode that generalizes and denigrates other subjects cannot appear.

[0100] In an embodiment of the present application, at least one evaluation information can be matched with a first risk control condition. If the content set in the first risk control condition appears in the evaluation information, the risk control detection result of the evaluation information can be determined to not meet the first risk control condition; otherwise, the risk control detection result of the evaluation information is determined to meet the first risk control condition.

[0101] After the risk control result is determined, the evaluation information that meets the first risk control condition can be determined as candidate evaluation information.

[0102] In some embodiments, detecting whether at least one evaluation information meets the risk control condition may be specifically implemented as follows:

[0103] Query the stored data to see whether there is any risk control detection result corresponding to any evaluation information; if so, obtain the risk control detection result; if not, check whether the evaluation information meets the risk control conditions, and store the risk control detection result corresponding to the evaluation information.

[0104] Among them, the stored data can record the risk control detection results after the evaluation information is pre-tested, so that when it is necessary to determine whether the same evaluation information meets the first risk control condition in the future, the risk control detection results can be quickly queried to improve the risk control detection efficiency.

[0105] Since a series of risk control detection results have been recorded in the storage data, when it is necessary to detect whether at least one evaluation information meets the first risk control condition, a query operation can be first performed in the storage data to try to match whether the risk control detection result of the evaluation information has been stored in the storage data. If a risk control detection result corresponding to the evaluation information to be detected is found in the storage data, this means that the evaluation information has been previously subjected to risk control detection, and whether it meets the first risk control condition has been clearly recorded in the storage data, then the existing risk control detection result can be directly obtained. When no risk control detection result corresponding to the current evaluation information is found in the storage data, the first risk control condition can be used to perform a risk control detection process on the evaluation information to generate a risk control detection result, and then the newly generated risk control detection result can be stored in the storage data, so that when the same evaluation information is encountered again, the corresponding detection result can be directly queried from the storage data to avoid repeated detection.

[0106] In some embodiments, detecting whether at least one evaluation information meets the risk control condition may be specifically implemented as follows:

[0107] Combined with at least one risk control keyword corresponding to the user attribute information, detect whether any evaluation information hits any risk control keyword.

[0108] Among them, user attribute information may include, for example, the user's age, gender, region, consumption level, historical purchasing behavior, browsing habits, etc. The user attribute information can be used to draw a general portrait of the user, and then determine the user's consumption preferences, risk tolerance, etc.

[0109] At least one risk control keyword can be pre-generated based on user attribute information. For example, for young consumer groups, when purchasing electronic products, risk control keywords may include "excessive entertainment" and "addiction to games"; for users with higher consumption levels, when purchasing luxury goods, risk control keywords may include "concerns about counterfeiting and inferior products" and "concerns about after-sales guarantee", reflecting their high requirements for product quality and services and possible concerns.

[0110] After determining at least one risk control keyword, the evaluation information that needs to be tested for risk control may be matched and tested one by one with the at least one risk control keyword determined in combination with the user attribute information.

[0111] Among them, when detecting whether any evaluation information hits any risk control keyword, precise matching or fuzzy matching can be used. Taking young users buying electronic products as an example, risk control keywords can include "excessive entertainment" and "addiction to games". Based on this, when matching the evaluation information, if precise matching is used, it will only be judged as a hit when the two complete words "excessive entertainment" or "addiction to games" appear in the evaluation information; if fuzzy matching is used, then as long as words with similar meanings to "excessive entertainment" or "addiction to games" appear (such as "addiction to it" can be regarded as similar to "addiction to games"), it will be judged as a hit.

[0112] In some embodiments, determining at least one evaluation information of the target object may be specifically implemented as follows:

[0113] At least one evaluation information of the target object is queried from the stored data.

[0114] In some embodiments, the evaluation information is obtained as follows:

[0115] At least one evaluation phrase is extracted from at least one evaluation data of the target object; evaluation information containing the target keyword is screened from the at least one evaluation phrase; and the extracted evaluation information is stored corresponding to the target object.

[0116] In an embodiment of the present application, at least one evaluation information of the target object may be queried from the stored data according to a unique identifier of the target object, wherein the unique identifier may include an object number, a product code, and the like.

[0117] The evaluation phrase may include a phrase or a short sentence that can summarize the core content of the evaluation data.

[0118] In a possible implementation of the present application, the target keywords may include keywords related to the industry attributes of the target object industry.

[0119] After extracting at least one evaluation phrase, each evaluation phrase may be compared with the target keyword one by one to filter out evaluation information containing the target keyword.

[0120] By storing the extracted evaluation information in correspondence with the target, when the evaluation information of the target object needs to be obtained in the future, the corresponding evaluation information can be directly queried from the stored data without the need to perform the information extraction and screening process again, thereby improving the query efficiency.

[0121] In some embodiments, the method may further include:

[0122] Generate a scheduling instruction at a predetermined time interval; determine at least one incremental evaluation data generated within a predetermined time corresponding to the target object in response to the scheduling instruction; extract at least one incremental evaluation phrase from the at least one incremental evaluation data;

[0123] The evaluation information containing the target keyword is filtered out from at least one incremental evaluation phrase; and the extracted evaluation information is stored corresponding to the target object.

[0124] In the embodiments of the present application, by generating a scheduling instruction at a predetermined interval, the incremental evaluation data of the target object can be regularly collected to ensure timely acquisition of the latest feedback from users on the target object. For example, in the scenario of an e-commerce platform, if the predetermined time is set to one day, a scheduling instruction will be generated every day to process the latest evaluation of the target object on the e-commerce platform; if it is for some products with relatively low update frequency, such as large industrial equipment, the predetermined time may be set to one week or even one month.

[0125] In some embodiments, extracting at least one evaluation phrase from at least one evaluation data of the target object may be specifically implemented as follows:

[0126] At least one evaluation phrase is extracted from at least one evaluation data of the target object using a data extraction model.

[0127] The data extraction model can be used to extract valuable evaluation phrases from at least one evaluation data of the target object. The data extraction model can learn and analyze a large amount of text data to understand the semantics and structure of the text, thereby accurately extracting evaluation phrases that meet the requirements.

[0128] In some embodiments, the data extraction model is a large model; the above-mentioned use of the data extraction model to extract at least one evaluation phrase from at least one evaluation data of the target object can be specifically implemented as follows:

[0129] generating first prompt information based on at least one evaluation data of the target object;

[0130] The first prompt information is input into the data extraction model to obtain at least one evaluation phrase generated by the data extraction model.

[0131] Among them, the large model can refer to a machine learning model with a large number of parameters and complex structure, which can process massive data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc. It is an AI (Artificial Intelligence, artificial intelligence) model. Among them, the large model can be implemented by a large language model (Large Language Model, LLM) or a multimodal large model (Multimodal Large Model, MLM), etc., for example, GPT-3 (Generative Pre-Trained Transformer-3, the third generation of generative pre-training model), GPT-4 (Generative Pre-Trained Transforme-4, the fourth generation of generative pre-training model), BERT (Bidirectional Encoder Representation from Transformers, a bidirectional encoder model based on Transformers), Turing NLG (Turing Natural language Generation, Turing Natural Language Generation) and the like. This application does not limit this. This type of large model can perform well in various natural language processing tasks, such as text generation, text translation, question-answering systems, etc. Of course, in addition to large language models, there are many other types of large models.

[0132] In the embodiments of the present application, when the large model is used to extract evaluation information, the large model can better understand the semantic associations between words in the evaluation data based on the knowledge obtained by its pre-training, and then accurately determine which phrases or short sentences can be extracted as valuable evaluation phrases. For example, in the face of evaluation data such as "the appearance design of this mobile phone is very fashionable and the metal texture is very strong", the large model, with its ability to understand language, can identify phrases such as "fashionable appearance design" and "strong metal texture" that are semantically consistent and can summarize the core content of the evaluation as evaluation phrases for extraction.

[0133] Among them, the first prompt information (Prompt) is a form of input used to prompt or guide the large model to give an expected output. The prompt information is a natural language input, similar to a command or instruction, to let the large model know what it needs to do. In an embodiment of the present application, the first prompt information can be used for the data extraction model to better understand the content that needs to be processed, that is, the key information contained in at least one evaluation data of the target object, so as to more accurately extract the evaluation phrase. It is equivalent to providing the data extraction model with a clear task guide and a summary of the relevant text content, helping the model to focus on specific evaluation data and dig out valuable phrases from it.

[0134] In a possible implementation of the present application, in order to guide the data extraction model to extract evaluation phrases that match the industry to which the target object belongs from the evaluation data of the target object, the industry information of the target object may be included in the first prompt information.

[0135] The first prompt information is a natural language input, similar to a command or instruction, to let the data extraction model know what it needs to do. In the embodiment of the present application, in order to facilitate the generation of the first prompt information, a prompt template can be pre-configured, and the industry information and evaluation data of the target object can be added to the prompt template, so that the corresponding first prompt information can be generated.

[0136] Among them, the prompt template usually contains the following parts:

[0137] Industry information of the target object: presented in an easy-to-understand format, such as the example of "home appliance industry" provided in the above embodiment.

[0138] Evaluation data: evaluation text about the target object to be processed. For example, the evaluation text is: "This air purifier has high purification efficiency and low noise."

[0139] Furthermore, after the first prompt information is input into the data extraction model, the data extraction model learns how to convert natural language evaluation text into evaluation phrases, and then generates one or more target evaluation phrases based on the provided first prompt information, and these evaluation phrases can reflect the characteristics of the target object in the industry to which it belongs.

[0140] For example, the first prompt information can be: assume that you are an industry evaluation and analysis expert. The following is a user evaluation of air purifiers in the home appliance industry. The evaluation content is: "This air purifier has a high purification efficiency and low noise." From the above evaluation content, summarize the evaluation phrases containing industry vocabulary, and only return 5 or less phrases related to the product attributes of the air purifier industry. If no summary can be made, return "" directly without returning other content. Based on this, the data extraction model can generate the following target evaluation phrases: "high purification efficiency" and "low noise".

[0141] In some embodiments, the data extraction model is trained as follows:

[0142] Obtain training sample data for the training data extraction model, the training sample data including evaluation sample data and industry knowledge data; and use the training sample data to train the data extraction model.

[0143] The evaluation sample data may include manually labeled evaluation sample data including industry attributes, evaluation sample data excluding industry attributes, and negative evaluation sample data, wherein the negative evaluation sample data can be used to enable the data extraction model to screen out such negative evaluation information when performing phrase extraction.

[0144] Industry knowledge data may include industry attribute keywords, industry attribute value samples, etc. Among them, industry attribute keywords may include words that can represent the core characteristics of a certain industry. For example, in the electronics industry, industry attribute keywords may include chips, screens, batteries, communications, etc.; in the clothing industry, industry attribute keywords may include fabrics, styles, sizes, tailoring, styles, etc. Industry attribute value samples may include specific values, instances, or forms of expression corresponding to industry attribute keywords, which can intuitively show the specific situation of industry attributes in practice. By providing industry attribute value samples, the data extraction model can better understand the specific meaning represented by industry attribute keywords and their performance in different situations, so as to more accurately extract evaluation information from evaluation data. For example, for the industry attribute keyword "chip" in the electronics industry, its industry attribute value samples may include specific chip models; in the clothing industry, for the keyword "fabric", industry attribute value samples may include specific fabric types such as "pure cotton fabric", "polyester fiber fabric", and "silk fabric". Some industry attribute value examples are presented in the form of specific numerical values. For example, in the electronics industry, for the industry attribute keyword "battery capacity", the industry attribute value examples may be "3000mAh", "5000mAh" and other specific capacity values; in the construction industry, the industry attribute value examples corresponding to the industry attribute keyword "building height" may be "100 meters", "200 meters" and other specific height values. At the same time, there may also be a range of values. For example, in the automobile industry, the industry attribute value examples of the industry attribute keyword "car fuel consumption" may be "6 liters to 8 liters per 100 kilometers".

[0145] By using industry knowledge data to fine-tune the data extraction model, the fine-tuned data extraction model can be better adapted to the key concerns of the industry to which it belongs, thereby improving the accuracy of the data extraction model in extracting evaluation phrases in a specific industry.

[0146] In some embodiments, training the data extraction model using the training sample data may be specifically implemented as follows:

[0147] A low-rank adaptation module is added to the data extraction model; the pre-trained parameters of the data extraction model are frozen, and the data extraction model is fine-tuned using the training sample data to obtain the incremental parameters corresponding to the low-rank adaptation module; the incremental parameters are merged with the pre-trained parameters of the pre-trained large language model to obtain the data extraction model.

[0148] In an embodiment of the present application, a low-rank adaptation (Lora) module can be a technical means for fine-tuning a model to adapt to specific tasks or data characteristics without significantly changing the overall architecture of the original data extraction model. Its core idea is to capture information related to a specific task by introducing additional trainable parameters (i.e., incremental parameters), while keeping most of the pre-trained parameters of the original model fixed, so as to better adapt to the specific task scenario to be processed on the basis of utilizing the powerful generalization ability of the pre-trained model. For example, when the data extraction model needs to extract specific evaluation phrases related to the industry from the evaluation text of the target object, the Lora module can help the model to learn patterns and features related to the evaluation characteristics of the industry in a targeted manner based on the industry knowledge data, evaluation sample data, etc. in the training sample data, without causing significant interference to the pre-training results of the model in other aspects.

[0149] Among them, the pre-training parameters may include parameters learned by the data extraction model through large-scale pre-training. These pre-training parameters have been trained on a large amount of text data and have strong generalization capabilities, which can help the model understand and process various natural language tasks.

[0150] Freezing the pre-trained parameters allows you to preserve them during industrial fine-tuning of the data extraction model.

[0151] In an embodiment of the present application, in the process of fine-tuning the data extraction model for industry, only the incremental parameters in the Lora module are trainable, while other pre-trained parameters remain frozen. During fine-tuning, the training sample data can be sequentially input into the data extraction model according to the input format required by the model. The data extraction model processes the input data according to its internal calculation logic and algorithm, combined with the parameter adjustment mechanism of the Lora module, and calculates the value of the loss function by comparing it with the real target output (such as the accurately extracted evaluation phrase). Then, according to the value of the loss function, the parameters of the Lora module are updated using an optimization algorithm (such as a stochastic gradient descent algorithm, etc.), so that the model output gradually approaches the real target output. After multiple iterations of fine-tuning, the incremental parameters of the Lora module can be continuously updated and optimized, and finally the incremental parameters corresponding to the stable low-rank adaptation module are obtained. These incremental parameters are based on retaining the advantages of the original model pre-training parameters, and are specifically designed for the task characteristics reflected by the current training sample data (such as extracting the target object industry-related evaluation phrases) and learn additional information. They can help the model capture task-related features and patterns more accurately when processing similar tasks, thereby improving the performance of the model.

[0152] In an embodiment of the present application, the fusion of the incremental parameters and the pre-trained parameters can be achieved by weighted summation, matrix splicing and other operations on the incremental parameters and the pre-trained parameters. For example, assuming that the incremental parameter is △w, △w can be composed of matrices A and B, and the pre-trained parameter can be W. During fusion, a weighted summation can be performed according to a certain weight ratio (such as α and β, and α+β=1) to obtain a new parameter combination W'=αW+β△w, and then this new parameter combination is updated to the data extraction model to replace the original pre-trained parameters, thereby obtaining a complete fused data extraction model. Alternatively, the matrix splicing method is adopted to splice the matrix corresponding to the incremental parameter and the matrix corresponding to the pre-trained parameter according to certain rules to form a new parameter matrix, which is then applied to the data extraction model to complete the fusion operation. For example, the new parameter combination W'=W+A·B.

[0153] In some embodiments, obtaining training sample data may be specifically implemented as follows:

[0154] Obtaining first evaluation sample data;

[0155] Inputting the first evaluation sample data set into the data generation model to obtain second evaluation sample data generated by the data generation model;

[0156] The first evaluation sample data and the second evaluation sample data are respectively used as training sample data.

[0157] In an embodiment of the present application, the data generation model can be implemented as a large model. By inputting the first evaluation sample data into the data generation model, the language generation ability of the data generation model can be utilized to expand and transform the input evaluation sample data according to the semantic relationships, common expression patterns and language knowledge learned by the first evaluation sample data, so as to generate some new evaluation sample data that are semantically related to the first evaluation sample data but may be expressed differently.

[0158] By using the first evaluation sample data and the second evaluation sample data generated by the data generation model as training sample data to train the data extraction model, the diversity of training samples can be significantly enriched, and the accuracy and generalization ability of the data extraction model in extracting target object evaluation information can be improved.

[0159] In some embodiments, in the object display page, providing at least one target evaluation information in at least one candidate evaluation information may be specifically implemented as follows:

[0160] Determine the priority information corresponding to at least one candidate evaluation information respectively; determine at least one target evaluation information according to the priority information; and provide at least one target evaluation information in the object display page.

[0161] In an embodiment of the present application, after obtaining at least one candidate evaluation information, in order to be able to more specifically display evaluation information that is more valuable to the user, priority information can be determined for the obtained candidate evaluation information. Priority information can be used to distinguish the degree of influence of different evaluation information on user purchase decisions, thereby ensuring that the target evaluation information determined according to the priority information can meet user needs. For example, for the candidate evaluation information of a smartphone, some candidate evaluation information may involve core functions such as photo effects, some candidate evaluation information may be about appearance design, and some candidate evaluation information is about battery life and other aspects. By determining the priority, it can be clear which aspects of the evaluation information are more important to the user, and key information can be displayed preferentially in a limited display space.

[0162] In one possible implementation of the present application, a higher priority can be given to candidate evaluation information related to the industry to which the target object belongs. For example, for a laptop computer, the relevant information about its industry may include processor performance, memory capacity, graphics processing capabilities, etc. If the candidate evaluation information mentions "the processor performance of this laptop computer is super strong and it can run large software without any pressure", it can be given a higher priority because it directly involves the relevant industry.

[0163] The priority setting of different candidate evaluation information can be set in a targeted manner according to the specific situation, and the embodiments of the present application do not specifically limit this.

[0164] After determining the priority information of at least one candidate evaluation information respectively, at least one target evaluation information can be selected in descending order.

[0165] In some embodiments, the information recommendation method further includes:

[0166] In response to an adding operation on the target object, adding the target object to the candidate list;

[0167] Performing a risk control test on at least one evaluation information using the first risk control condition to obtain a risk control test result;

[0168] The risk control detection results are stored in the storage data.

[0169] The candidate list can be implemented as a shopping cart on an e-commerce platform, for example. The shopping cart can be a virtual space for users to temporarily store the goods they want to buy (i.e., the target object). Users can add the goods they are interested in to the shopping cart while browsing various goods, so as to facilitate subsequent operations such as unified settlement and payment, comparison of different goods, and adjustment of purchase quantity. Through the object adding operation, the target object can be added to the shopping cart.

[0170] In an embodiment of the present application, after determining that the user has added the target object to the candidate list, it can be confirmed that the user may subsequently view the detailed information of the target object. Therefore, after determining that the user has added the target object to the candidate list, risk control detection can be performed on at least one evaluation information of the target object in advance, and the risk control detection result can be stored in the storage data, so that when the user requests to view the target object, the risk control detection result of the target object can be directly queried from the storage data, thereby improving processing efficiency.

[0171] In some embodiments, the information recommendation method further includes:

[0172] Obtain a second risk control condition for updating the first risk control condition; use the second risk control condition to re-perform risk control detection on at least one evaluation information stored in the stored data to obtain an updated risk control detection result; and update the stored data using the updated risk control detection result corresponding to at least one evaluation information.

[0173] In an embodiment of the present application, risk control conditions often change according to industry development, market changes, legal and regulatory risks, etc. Therefore, a risk control instruction can be generated at a predetermined interval, and in response to the risk control instruction, a risk control check can be performed on at least one evaluation information stored in the stored data using the current second risk control condition to obtain an updated risk control check result.

[0174] By using the latest risk control conditions to perform risk control checks on evaluation information at scheduled intervals, we can continuously adapt to industry development and regulatory changes and ensure that the evaluation information displayed to users meets the latest risk control requirements.

[0175] In some embodiments, after extracting at least one evaluation phrase from at least one evaluation data of the target object, the information recommendation method further includes:

[0176] The at least one evaluation phrase is stored offline.

[0177] In some embodiments, before filtering the evaluation information containing the target keyword from the at least one evaluation phrase, the method further includes:

[0178] At least one evaluation phrase is obtained from the offline storage data.

[0179] Among them, by storing at least one evaluation phrase in an offline database, at least one evaluation phrase can be stored locally or in a specific offline storage device to prevent data loss caused by unexpected situations such as network failures.

[0180] In some embodiments, storing the extracted evaluation information corresponding to the target object may be specifically implemented as follows:

[0181] The extracted evaluation information is stored in real time corresponding to the target object.

[0182] In the embodiment of the present application, the real-time database can always be closely connected to the running system, and can instantly reflect the latest data changes in the system. For the storage of evaluation information, this means that once new evaluation information is extracted and corresponds to the target object, it can be quickly stored in the real-time database so that the evaluation information can be queried in real time later.

[0183] For ease of understanding, in combination with the information recommendation method performed by the server in each of the above embodiments, Figure 3 As shown, in an actual application, the server may design operations to implement information recommendation, for example, including:

[0184] Data labeling and amplification are performed 301 to generate fine-tuned data suitable for a specific industry. Then, the data extraction model is fine-tuned 302 using the fine-tuned data to meet the needs of the specific industry.

[0185] In order to extract evaluation information in batches, first prompt information for extracting data 303 can also be constructed, and model parameters can be set to extract evaluation information 304, while controlling the divergence and return quantity of the data extraction model. The extracted evaluation information can be stored in an offline database 305.

[0186] The system can also regularly schedule the execution of incremental data extraction tasks 306 to extract incremental evaluation data generated in the recent period of time. The extracted data will be keyword filtered 307 to ensure that the evaluation information displayed to the user meets the user's needs.

[0187] The evaluation information filtered by keywords can be stored in the real-time database 308. After the user triggers the object viewing request, the evaluation information corresponding to the target object can be queried from the real-time database 309. At the same time, the evaluation information can also be combined with the user attribute information to perform risk control verification 310 to identify potential risks.

[0188] In order to optimize query performance, the risk control detection results may be cached 311. The system may also schedule risk control tasks 312 on a regular basis, and update the risk control cache using the second risk control detection condition to ensure the timeliness of risk control information.

[0189] Finally, the evaluation information that has passed the risk control detection may be converted to a view layer so that the target evaluation information is displayed in the object display page 313 .

[0190] Figure 4 This is a flowchart of an embodiment of an information recommendation method provided by the present application. The technical solution of this embodiment is executed by the server. The method may include the following steps:

[0191] 401: In response to the shopping cart viewing request, determine the target object corresponding to the shopping cart.

[0192] 402: Determine at least one evaluation information of the target object; the at least one evaluation information is extracted from at least one evaluation data of the target object.

[0193] 403: Serving the shopping cart page.

[0194] 404: On the shopping cart page, provide at least one target evaluation information among the at least one evaluation information.

[0195] In some embodiments, in the shopping cart page, providing at least one target evaluation information in at least one evaluation information may be specifically implemented as follows:

[0196] Detecting whether at least one evaluation information meets the first risk control condition;

[0197] Determine at least one candidate evaluation information according to the risk control detection result;

[0198] In the shopping cart page, at least one target evaluation information among at least one candidate evaluation information is provided.

[0199] In some embodiments, detecting whether at least one evaluation information meets the risk control condition may be specifically implemented as follows:

[0200] Query the stored data to see whether there is any risk control detection result corresponding to the evaluation information;

[0201] If yes, obtain the risk control detection result; if no, check whether the evaluation information meets the risk control conditions, and store the risk control detection result corresponding to the evaluation information.

[0202] In some embodiments, detecting whether at least one evaluation information meets the risk control condition may be specifically implemented as follows:

[0203] Combined with at least one risk control keyword corresponding to the user attribute information, detect whether any evaluation information hits any risk control keyword.

[0204] In some embodiments, determining at least one evaluation information of the target object may be specifically implemented as follows:

[0205] Querying at least one evaluation information of the target object from the stored data;

[0206] The evaluation information is obtained as follows:

[0207] extracting at least one evaluation phrase from at least one evaluation data of the target object;

[0208] Filtering review information containing a target keyword from at least one review phrase;

[0209] The extracted evaluation information is stored corresponding to the target object.

[0210] In some embodiments, the method further comprises:

[0211] Generate a scheduling instruction at every predetermined time interval;

[0212] In response to the scheduling instruction, determining at least one incremental evaluation data generated within a predetermined time corresponding to the target object;

[0213] extracting at least one incremental evaluation phrase from at least one incremental evaluation data;

[0214] Filtering evaluation information containing a target keyword from at least one incremental evaluation phrase;

[0215] The extracted evaluation information is stored corresponding to the target object.

[0216] In some embodiments, extracting at least one evaluation phrase from at least one evaluation data of the target object may be specifically implemented as follows:

[0217] At least one evaluation phrase is extracted from at least one evaluation data of the target object using a data extraction model.

[0218] In some embodiments, the data extraction model is a large model.

[0219] In some embodiments, extracting at least one evaluation phrase from at least one evaluation data of the target object using the data extraction model may be specifically implemented as follows:

[0220] generating first prompt information based on at least one evaluation data of the target object;

[0221] The first prompt information is input into the data extraction model to obtain at least one evaluation phrase generated by the data extraction model.

[0222] In some embodiments, the data extraction model is trained as follows:

[0223] Obtaining training sample data, the training sample data includes evaluation sample data and industry knowledge data;

[0224] The data extraction model is trained using the training sample data.

[0225] In some embodiments, obtaining training sample data may be specifically implemented as follows:

[0226] Obtaining first evaluation sample data;

[0227] Inputting the first evaluation sample data into the data generation model to obtain second evaluation sample data generated by the data generation model;

[0228] The first evaluation sample data and the second evaluation sample data are respectively used as training sample data.

[0229] In some embodiments, in the shopping cart page, providing at least one target evaluation information among at least one candidate evaluation information may be specifically implemented as follows:

[0230] Determine priority information corresponding to at least one piece of candidate evaluation information respectively;

[0231] determining at least one target evaluation information according to the priority information;

[0232] On the shopping cart page, provide at least one target evaluation information.

[0233] In some embodiments, the method further comprises:

[0234] In response to the add-to-cart request for the target object, adding the target object to the shopping cart;

[0235] Performing a risk control test on at least one evaluation information using the first risk control condition to obtain a risk control test result;

[0236] The risk control detection results are stored in the storage data.

[0237] In some embodiments, the method further comprises:

[0238] Obtaining a second risk control condition for updating the first risk control condition;

[0239] Re-performing a risk control test on at least one evaluation information stored in the storage data using the second risk control condition to obtain an updated risk control test result;

[0240] The stored data is updated using the updated risk control detection results respectively corresponding to the at least one evaluation information.

[0241] In some embodiments, after extracting at least one evaluation phrase from at least one evaluation data of the target object, the method further includes:

[0242] storing at least one evaluation phrase offline;

[0243] In some embodiments, before filtering the evaluation information containing the target keyword from the at least one evaluation phrase, the method further includes:

[0244] Obtaining at least one evaluation phrase from offline storage data;

[0245] Storing the extracted evaluation information corresponding to the target object includes:

[0246] The extracted evaluation information is stored in real time corresponding to the target object.

[0247] In some embodiments, training the data extraction model using the training sample data may be specifically implemented as follows:

[0248] Add a low-rank adaptation module to the data extraction model;

[0249] Freeze the pre-trained parameters of the data extraction model, and use the training sample data to fine-tune the data extraction model to obtain the incremental parameters corresponding to the low-rank adaptation module;

[0250] The incremental parameters are fused with the pre-trained parameters of the pre-trained large language model to obtain a data extraction model.

[0251] Figure 4 The implementation process of the information recommendation method shown can refer to Figure 2 The information recommendation method shown will not be described in detail here.

[0252] Figure 5 This is a flow chart of an embodiment of a data processing method provided by the present application. The technical solution of this embodiment is executed by a user end. The method may include the following steps:

[0253] 501: Extract at least one evaluation information from at least one evaluation data of a target object using a data extraction model.

[0254] 502: at least one evaluation information is stored corresponding to the target object; wherein the at least one evaluation information is used to display at least one target evaluation information in the at least one evaluation information on the shopping cart page when the target object responds to any user request to add the target object to the shopping cart and detects a shopping cart viewing request triggered by the user.

[0255] Figure 5 In the data processing method shown, the process of obtaining target evaluation information can refer to Figure 2 or Figure 4 The information recommendation method shown will not be described in detail here.

[0256] Figure 6 This is a flow chart of an information display method provided in an embodiment of the present application. The technical solution of this embodiment is executed by a user end. The method may include the following steps:

[0257] 601: In response to the shopping cart viewing operation, a shopping cart viewing request is sent to the server.

[0258] 602: Displaying a shopping cart page in the user interface.

[0259] 603: Displaying object prompt information of the target object and at least one target evaluation information corresponding to the target object on the shopping cart page; the at least one target evaluation information is determined from at least one evaluation information of the target object; and the at least one evaluation information is extracted from at least one evaluation data of the target object.

[0260] Figure 6 In the information display method shown, the process of obtaining the target evaluation information can refer to Figure 2 or Figure 4 The information recommendation method shown will not be described in detail here.

[0261] An embodiment of the present application also provides an information recommendation system, which may include:

[0262] The user end is used to send a shopping cart viewing request to the server end in response to a shopping cart viewing operation triggered by the user; obtain a user interface and at least one target evaluation information sent by the server end, display a shopping cart page in the user interface, and display object prompt information of the target object and at least one target evaluation information corresponding to the target object on the shopping cart page;

[0263] The server is used to respond to a shopping cart viewing request sent by a user terminal, determine a target object corresponding to the shopping cart, determine at least one evaluation information of the target object, and extract at least one evaluation information from at least one evaluation data of the target object; provide a shopping cart page to the user terminal, and at least one target evaluation information determined from the at least one evaluation information.

[0264] Figure 7 A signaling flow chart applicable to an information recommendation system provided in an embodiment of the present application is shown.

[0265] like Figure 7 As shown, user 703 can trigger a shopping cart viewing operation 7031 through user terminal 701, and user terminal 701 can send a shopping cart viewing request 7011 to server terminal 702 in response to shopping cart viewing operation 7031. Server terminal 702 can determine the target object corresponding to the shopping cart in response to shopping cart viewing request 7011, and then query at least one evaluation information 7021 pre-stored in the real-time database. After querying and obtaining at least one evaluation information, at least one evaluation information can be filtered 7022 using keywords, and the query result, i.e., target evaluation information 7023, is returned. Through operation 7024, a constructed shopping cart page 7025 and target evaluation information determined from at least one evaluation information are sent to user terminal 701, so that user terminal 701 can display the shopping cart page.

[0266] After determining at least one evaluation information, the server 702 may first determine whether the cache stores the risk control detection result 7026 of at least one evaluation information; if the cache has pre-stored the risk control detection result of at least one evaluation information, the risk control detection result 7027 may be returned, and at least one target evaluation information may be determined based on the risk control detection result. If the risk control detection result of at least one evaluation information is not found in the cache, the risk control detection 7028 may be triggered, and the risk control detection 7029 may be performed on the at least one evaluation information in combination with at least one risk control keyword corresponding to the user attribute information of the user 701 to generate a risk control detection result, and the risk control detection result is stored in the storage data 7020, and then at least one target evaluation information is determined based on the risk control detection result.

[0267] For ease of understanding, Figure 8 A display schematic diagram of a user interface in an actual application of an embodiment of the present application is shown.

[0268] like Figure 8 As shown, a shopping cart page 801 may be displayed in the user interface, and object prompt information 802 of the target object may be displayed in the shopping cart page 801, wherein the object prompt information 802 may include, for example, the model, appearance color, price, etc. of the target object. In addition, the shopping cart page 801 may also display target evaluation information 803 corresponding to the target object. In the embodiment of the present application, the target evaluation information may be, for example, "the purification effect is significant".

[0269] In an actual application, the server can be divided into multiple modules to perform different operations. In a possible implementation, Fig. 9 As shown in , the server 900 may include, for example, a view construction module 901, an evaluation information query module 902, a risk control scheduling module 903, a risk control verification module 904, a risk control result cache module 905, etc. Figure 7The signaling flow chart shown shows the operations performed by each module, which may include: the view construction module 901 receives a shopping cart viewing request, and then the evaluation information query module 902 can query at least one evaluation information of the target object requested by the shopping cart viewing request from the storage data. The risk control verification module 904 can determine whether the risk control detection result corresponding to at least one evaluation information has been stored in the cache. If the risk control detection result of at least one evaluation information has been pre-stored in the cache, at least one target evaluation information can be determined based on the risk control detection result. If the risk control detection result of at least one evaluation information is not queried in the cache, the risk control scheduling module 903 can trigger the risk control scheduling operation, and perform risk control detection on at least one evaluation information in combination with at least one risk control keyword corresponding to the user attribute information of the user to generate a risk control detection result, and then the risk control result cache module 905 can store the generated risk control detection result in the cache.

[0270] The server may further include a priority processing module, which may configure respective priority information for multiple evaluation information, so that the evaluation information query module 902 may determine target evaluation information from multiple evaluation information according to the priority information.

[0271] The multi-terminal adaptation module can adapt the shopping cart interface page generated by the attempt construction module 901 according to the type of the user terminal. For example, the shopping cart page can be converted into a page suitable for PC display, or the shopping cart page can be converted into a page suitable for mobile terminal display.

[0272] In addition, it can also include a data labeling module and a model training module. The data labeling module can label the training sample data and input the labeled training sample data into the model training module. The model training module can use the training sample data to fine-tune the data extraction model.

[0273] The data cleaning module can filter invalid evaluations and negative evaluations from the acquired evaluation data, so that target evaluation information can be extracted from the filtered evaluation data.

[0274] The server may also include a prompt word construction module, a keyword filtering module, an evaluation extraction module and an evaluation storage module, so as to provide a first prompt message through the prompt word construction module. The first prompt message may include evaluation data extracted by the evaluation extraction module. The evaluation data may be obtained by filtering multiple evaluation data using the keyword filtering module. Furthermore, the evaluation storage module may store the evaluation information extracted from the evaluation data.

[0275] In addition, an incremental scheduling module, an incremental data extraction module, and an offline storage module may be included, so that the incremental scheduling module generates a scheduling instruction at a predetermined time, so that the incremental data extraction module obtains the incremental evaluation data generated by the target object. The offline storage module can store the incremental evaluation information extracted from the incremental evaluation data offline.

[0276] based on Fig. 9 The server shown can implement Fig.10 The architecture design diagram shown shows the system architecture of the information recommendation method provided in the embodiment of the present application.

[0277] like Fig.10 As shown, the system architecture diagram may include a display layer 1001, and the display layer 1001 can be performed by different types of user terminals, such as a mobile terminal or a PC (Personal Computer).

[0278] The service layer 1002 can be used to implement the evaluation transmission service and the risk control service. The evaluation transmission service can be understood as querying the target evaluation information of the target object from the pre-stored storage data and displaying the target evaluation information on the shopping cart page, so as to provide the shopping cart page to the display layer 1001 for display; the risk control service can perform risk control detection on the evaluation information. Fig. 9 The view building module, evaluation information query module, priority processing module, multi-terminal matching module, etc. shown in the figure can be realized; the risk control service can be used Fig. 9 It is implemented by the risk control scheduling module, risk control verification module, and risk control result caching module shown.

[0279] The data and algorithm layer 1003 can be used to implement data cleaning services, model fine-tuning services, and evaluation extraction services. Among them, the data cleaning service can be used Fig. 9 The data cleaning module shown is used to filter out invalid and negative evaluations in the evaluation data. The model fine-tuning service can use Fig. 9 The data labeling module and model training module shown are implemented; the evaluation extraction module can be used Fig. 9 The prompt word construction module, keyword filtering module, evaluation extraction module and evaluation storage module are shown to implement it.

[0280] Fig.11 A block diagram of an information recommendation device provided by an embodiment of the present application, such as Fig.11 As shown, the information recommendation device may include:

[0281] A first object determining unit 1101 is configured to determine a target object corresponding to the shopping cart in response to a shopping cart viewing request;

[0282] A first evaluation information determining unit 1102 is used to determine at least one evaluation information of a target object; the at least one evaluation information is extracted from at least one evaluation data of the target object;

[0283] The first page providing unit 1103 is used to provide a shopping cart page;

[0284] The first display unit 1104 is used to provide at least one target evaluation information among the at least one evaluation information in the shopping cart page.

[0285] In some embodiments, the first display unit 1104 may include:

[0286] A first detection subunit, used to detect whether at least one evaluation information meets a first risk control condition;

[0287] A candidate evaluation information determination subunit, used to determine at least one candidate evaluation information according to the risk control detection result;

[0288] The information providing subunit is used to provide at least one target evaluation information among at least one candidate evaluation information in the shopping cart page.

[0289] In some embodiments, the first detection subunit is specifically used for:

[0290] Query the stored data to see whether there is any risk control detection result corresponding to the evaluation information;

[0291] If yes, obtain the risk control detection result; if no, check whether the evaluation information meets the risk control conditions, and store the risk control detection result corresponding to the evaluation information.

[0292] In some embodiments, the first detection subunit is specifically used for:

[0293] Combined with at least one risk control keyword corresponding to the user attribute information, detect whether any evaluation information hits any risk control keyword.

[0294] In some embodiments, the first evaluation information determining unit 1102 further includes:

[0295] A storage query subunit, used to query at least one evaluation information of a target object from the stored data;

[0296] In some embodiments, the evaluation information is obtained using an evaluation acquisition unit, and the evaluation acquisition unit may include:

[0297] A phrase extraction unit, configured to extract at least one evaluation phrase from at least one evaluation data of a target object;

[0298] an information screening unit, configured to screen evaluation information containing a target keyword from at least one evaluation phrase;

[0299] The corresponding storage unit is used to store the extracted evaluation information corresponding to the target object.

[0300] In some embodiments, the device further comprises:

[0301] A scheduling generation unit, used for generating a scheduling instruction at predetermined intervals;

[0302] An incremental data determination unit, configured to determine, in response to the scheduling instruction, at least one incremental evaluation data corresponding to the target object generated within a predetermined time;

[0303] An incremental phrase extraction unit, configured to extract at least one incremental evaluation phrase from at least one incremental evaluation data;

[0304] An incremental screening unit, configured to screen evaluation information containing a target keyword from at least one incremental evaluation phrase;

[0305] The incremental storage unit is used to store the extracted evaluation information corresponding to the target object.

[0306] In some embodiments, the phrase extraction unit includes:

[0307] a phrase extraction subunit, configured to extract at least one evaluation phrase from at least one evaluation data of a target object using a data extraction model;

[0308] In some embodiments, the data extraction model is a large model.

[0309] In some embodiments, the phrase extraction subunit is specifically used to:

[0310] generating first prompt information based on at least one evaluation data of the target object;

[0311] The first prompt information is input into the data extraction model to obtain at least one evaluation phrase generated by the data extraction model.

[0312] In some embodiments, the data extraction model is obtained by training using a model training unit, and the model training unit is specifically used to:

[0313] Obtaining training sample data, the training sample data includes evaluation sample data and industry knowledge data;

[0314] The data extraction model is trained using the training sample data.

[0315] In some embodiments, the training sample data is obtained by a sample generation unit, and the sample generation unit is specifically used to:

[0316] Obtaining first evaluation sample data;

[0317] Inputting the first evaluation sample data into the data generation model to obtain second evaluation sample data generated by the data generation model;

[0318] The first evaluation sample data and the second evaluation sample data are respectively used as training sample data.

[0319] In some embodiments, the first display unit 1104 is specifically used for:

[0320] Determine priority information corresponding to at least one piece of candidate evaluation information respectively;

[0321] determining at least one target evaluation information according to the priority information;

[0322] On the shopping cart page, provide at least one target evaluation information.

[0323] In some embodiments, the device may further include:

[0324] an object adding unit, configured to add the target object to the shopping cart in response to a purchase request for the target object;

[0325] a risk control unit, configured to perform a risk control detection on at least one evaluation information using the first risk control condition to obtain a risk control detection result;

[0326] The risk control storage unit is used to store the risk control detection results in the storage data.

[0327] In some embodiments, the device further comprises:

[0328] A risk control updating unit, configured to obtain a second risk control condition for updating the first risk control condition;

[0329] An updating risk control detection unit is used to re-perform risk control detection on at least one evaluation information stored in the storage data using the second risk control condition to obtain an updated risk control detection result;

[0330] The risk control storage unit is updated to update the stored data using the updated risk control detection results corresponding to at least one evaluation information.

[0331] In some embodiments, after extracting at least one evaluation phrase from at least one evaluation data of the target object, the apparatus further comprises:

[0332] An offline storage unit, used for storing at least one evaluation phrase offline;

[0333] In some embodiments, before filtering the evaluation information containing the target keyword from the at least one evaluation phrase, the device further includes:

[0334] An offline acquisition unit, used to acquire at least one evaluation phrase from offline storage data;

[0335] In some embodiments, the corresponding storage unit includes:

[0336] The real-time storage subunit is used to store the extracted evaluation information corresponding to the target object in real time.

[0337] In some embodiments, the model training unit is specifically used to:

[0338] Add a low-rank adaptation module to the data extraction model;

[0339] Freeze the pre-trained parameters of the data extraction model, and use the training sample data to fine-tune the data extraction model to obtain the incremental parameters corresponding to the low-rank adaptation module;

[0340] The incremental parameters are fused with the pre-trained parameters of the pre-trained large language model to obtain a data extraction model.

[0341] Fig.11 The information recommendation device can perform Figure 4 The implementation principle and technical effect of the information recommendation method in the embodiment shown are not described in detail. The specific way in which each unit and subunit performs operations in the information recommendation device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0342] Fig.12 A block diagram of an information display device provided by an embodiment of the present application, such as Fig.12 As shown, the information display device may include:

[0343] The first request sending unit 1201 is used to send a shopping cart viewing request to the server in response to the shopping cart viewing operation;

[0344] The second page display unit 1202 is used to display a shopping cart page in the user interface;

[0345] The third page display unit 1203 is used to display the object prompt information of the target object and at least one target evaluation information corresponding to the target object on the shopping cart page; the at least one target evaluation information is determined from at least one evaluation information of the target object; and the at least one evaluation information is extracted from at least one evaluation data of the target object.

[0346] Fig.12 The information display device can perform Figure 6 The implementation principle and technical effect of the information display method in the illustrated embodiment will not be described in detail. The specific manner in which each unit performs operations in the information display device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0347] Fig.13 A block diagram of a data processing device provided in one embodiment of the present application, such as Fig.13 As shown, the data processing device may include:

[0348] A first evaluation information extraction unit 1301 is used to extract at least one evaluation information from at least one evaluation data of a target object by using a data extraction model;

[0349] A first evaluation information storage unit 1302, used to store at least one evaluation information corresponding to a target object;

[0350] Among them, at least one evaluation information is used to display at least one target evaluation information in the at least one evaluation information on the shopping cart page when the target object is added to the shopping cart in response to any user request and a shopping cart viewing request triggered by the user is detected.

[0351] Fig.13 The data processing device can execute Figure 5 The implementation principle and technical effect of the data processing method in the embodiment shown are not described in detail. The specific way in which each unit performs operations in the data processing device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0352] Fig.14 A block diagram of an information recommendation device provided by an embodiment of the present application, such as Fig.14 As shown, the information recommendation device may include:

[0353] The second object determining unit 1401 is used to determine a target object in response to an object viewing request;

[0354] A second evaluation information determining unit 1402 is used to determine at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object;

[0355] The second page providing unit 1403 is used to provide an object display page;

[0356] The fourth page display unit 1404 is used to provide at least one target evaluation information in the at least one evaluation information in the object display page.

[0357] Fig.14 The information recommendation device can perform Figure 2 The implementation principle and technical effect of the information recommendation method in the illustrated embodiment will not be described in detail. The specific manner in which each unit performs operations in the information recommendation device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0358] In a possible design, the information recommendation device, data processing device, and information display device provided in the embodiments of the present application can be implemented as a computing device, such as Fig.15 As shown, the computing device may include a storage component 1501 and a processing component 1502;

[0359] The storage component 1501 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 1502 to implement the information recommendation method, data processing method, and information display method provided in the embodiments of the present application.

[0360] Of course, the computing device may also include other components, such as input / output interfaces, communication components, etc. The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.

[0361] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0362] When the computing device is a physical device, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device.

[0363] The embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a computer, the information recommendation method, data processing method, and information display method provided in the embodiment of the present application can be implemented.

[0364] The embodiment of the present application also provides a computer program product, including a computer program. When the computer program is executed by a computer, it can implement the information recommendation method, data processing method, and information display method provided in the embodiment of the present application.

[0365] The processing components in the above corresponding embodiments may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing components may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0366] The storage component is configured to store various types of data to support operations in the device. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0367] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0368] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0369] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0370] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An information recommendation method, characterized in that: include: In response to a shopping cart viewing request, determining a target object corresponding to the shopping cart; Determining at least one evaluation information of the target object; The at least one evaluation information is extracted from at least one evaluation data of the target object; Provide a shopping cart page; In the shopping cart page, at least one target evaluation information among the at least one evaluation information is provided.

2. The method according to claim 1, characterized in that: The providing, in the shopping cart page, at least one target evaluation information in the at least one evaluation information comprises: Detecting whether the at least one evaluation information meets the first risk control condition; Determine at least one candidate evaluation information according to the risk control detection result; In the shopping cart page, at least one target evaluation information among the at least one candidate evaluation information is provided.

3. The method according to claim 2, characterized in that The detecting whether the at least one evaluation information meets the first risk control condition includes: Query the stored data to see whether there is any risk control detection result corresponding to the evaluation information; If so, obtain the risk control detection result; if not, detect whether the evaluation information meets the first risk control condition, and store the risk control detection result corresponding to the evaluation information.

4. The method according to claim 2, characterized in that: The detecting whether the at least one evaluation information meets the first risk control condition includes: Combined with at least one risk control keyword corresponding to the user attribute information, detect whether any evaluation information hits any risk control keyword.

5. The method according to claim 1, characterized in that Determining at least one evaluation information of the target object includes: Querying at least one evaluation information of the target object from the stored data; The evaluation information is obtained as follows: extracting at least one evaluation phrase from at least one evaluation data of the target object; Filtering evaluation information containing a target keyword from the at least one evaluation phrase; The extracted evaluation information is stored corresponding to the target object.

6. The method according to claim 5, characterized in that: Also includes: Generate a scheduling instruction at every predetermined time interval; In response to the scheduling instruction, determining at least one incremental evaluation data corresponding to the target object generated within the predetermined time; extracting at least one incremental evaluation phrase from the at least one incremental evaluation data; Filtering evaluation information containing a target keyword from the at least one incremental evaluation phrase; The extracted evaluation information is stored corresponding to the target object.

7. The method according to claim 5, characterized in that The extracting at least one evaluation phrase from at least one evaluation data of the target object comprises: extracting at least one evaluation phrase from at least one evaluation data of the target object using a data extraction model; The data extraction model is a large model; Extracting at least one evaluation phrase from at least one evaluation data of the target object using a data extraction model includes: generating first prompt information based on at least one evaluation data of the target object; The first prompt information is input into the data extraction model to obtain at least one evaluation phrase generated by the data extraction model.

8. The method according to claim 7, characterized in that The data extraction model is trained in the following manner: Acquire training sample data, wherein the training sample data includes evaluation sample data and industry knowledge data; The data extraction model is trained using the training sample data.

9. The method according to claim 8, characterized in that Obtaining training sample data includes: Obtaining first evaluation sample data; Inputting the first evaluation sample data into a data generation model to obtain second evaluation sample data generated by the data generation model; The first evaluation sample data and the second evaluation sample data are respectively used as the training sample data.

10. The method according to claim 2, characterized in that The providing, in the shopping cart page, at least one target evaluation information among the at least one candidate evaluation information comprises: respectively determining priority information corresponding to the at least one candidate evaluation information; Determining the at least one target evaluation information according to the priority information; In the shopping cart page, the at least one target evaluation information is provided.

11. The method according to claim 3, characterized in that Also includes: In response to an add-to-cart request for the target object, adding the target object to the shopping cart; Performing a risk control test on the at least one evaluation information using the first risk control condition to obtain a risk control test result; The risk control detection result is stored in the storage data.

12. The method according to claim 11, characterized in that The method further comprises: Acquire a second risk control condition for updating the first risk control condition; Re-performing a risk control test on at least one evaluation information stored in the stored data using the second risk control condition to obtain an updated risk control test result; The stored data is updated using the updated risk control detection results respectively corresponding to the at least one evaluation information.

13. The method according to claim 5, characterized in that After extracting at least one evaluation phrase from at least one evaluation data of the target object, the method further includes: storing the at least one evaluation phrase offline; Before filtering the evaluation information containing the target keyword from the at least one evaluation phrase, the method further includes: Acquiring the at least one evaluation phrase from offline storage data; The step of storing the extracted evaluation information corresponding to the target object includes: The extracted evaluation information is stored in real time corresponding to the target object.

14. The method according to claim 8, characterized in that The training of the data extraction model using the training sample data includes: Adding a low-rank adaptation module to the data extraction model; Freeze the pre-trained parameters of the data extraction model, and fine-tune the data extraction model using the training sample data to obtain incremental parameters corresponding to the low-rank adaptation module; The incremental parameters are merged with the pre-trained parameters of the pre-trained large language model to obtain the data extraction model.

15. An information display method, characterized in that: include: In response to the shopping cart viewing operation, a shopping cart viewing request is sent to the server; Display the shopping cart page in the user interface; Displaying object prompt information of a target object and at least one target evaluation information corresponding to the target object on the shopping cart page; The at least one target evaluation information is determined from at least one evaluation information of the target object; The at least one evaluation information is extracted from at least one evaluation data of the target object.

16. A data processing method, characterized in that: include: extracting at least one evaluation information from at least one evaluation data of the target object using the data extraction model; storing the at least one evaluation information corresponding to the target object; Among them, the at least one evaluation information is used to display at least one target evaluation information among the at least one evaluation information in the shopping cart page when the target object responds to any user request to add to the shopping cart and a shopping cart viewing request triggered by the user is detected.

17. An information recommendation method, characterized in that: include: In response to the object viewing request, determining a target object; Determine at least one evaluation information of the target object; wherein the at least one evaluation information is extracted from at least one evaluation data of the target object; Provide object display page; At least one target evaluation information among the at least one evaluation information is provided in the object display page.

18. A computing device, characterized in that including a processing component and a storage component; The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the information recommendation method as described in any one of claims 1 to 14, or to implement the information display method as shown in claim 15, or to implement the data processing method as described in claim 16, or to implement the information recommendation method as described in claim 17.

19. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, it implements the information recommendation method as described in any one of claims 1 to 14, or implements the information display method as shown in claim 15, or implements the data processing method as described in claim 16, or implements the information recommendation method as described in claim 17.

20. A computer program product, characterized in that The computer program product includes computer program code, and when the computer program code is executed by a computer, it implements the information recommendation method as described in any one of claims 1 to 14, or implements the information display method as shown in claim 15, or implements the data processing method as described in claim 16, or implements the information recommendation method as described in claim 17.

Images