CN110597962A - Search result display method, device, medium and electronic equipment - Google Patents

Abstract

The present disclosure provides an artificial intelligence-based search result display method, device, medium and electronic equipment. The method in the embodiment of the present disclosure includes: receiving a search request, and determining an index keyword according to the search request; retrieving the target brand subject in the brand database according to the index keyword, and obtaining the brand subject of the target brand subject Attribute information; determine the application subject and information dissemination subject associated with the target brand subject, and obtain the program subject link information corresponding to the application subject and the communication subject link information corresponding to the information dissemination subject; according to The brand body attribute information, the program body link information and the communication body link information generate a search result display page. The method can improve the search accuracy and search efficiency, and at the same time can provide users with a richer and more intuitive display effect of media-rich brand information.

Description

Search result display method, device, medium and electronic equipment

technical field

The present disclosure relates to the technical field of artificial intelligence, in particular, to an artificial intelligence-based search result display method, an artificial intelligence-based search result display device, a computer-readable medium, and an electronic device.

Background technique

With the development of computer and network technology, brand promotion through the Internet and providing products and services to users through the Internet have gradually become the routine choice of the main body of the brand. On this basis, many network platforms that can provide brand promotion channels and product and service sales channels for brand subjects have also been derived. For example, users can find the official accounts or mini programs of various brands through the functional interface provided by the WeChat platform, so as to obtain the products or services provided by the brand subject.

However, due to the complexity of brand network resources and the diversity of brand service forms, when users search for related brands, products, services, etc. through the network platform, the search results are usually mixed with a lot of noise information. Only through identification and layer upon layer of screening can the accurate brand subject be found. Moreover, even if an accurate brand subject is found, it is still necessary to jump to a specific product purchase page or service page through multiple layers of network pages or application page jumps. Therefore, how to improve brand search accuracy and search efficiency is an urgent problem to be solved.

It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the application, and therefore may include information that does not constitute prior art known to those of ordinary skill in the art.

Contents of the invention

The purpose of the present disclosure is to provide an artificial intelligence-based search result display method, an artificial intelligence-based search result display device, a computer-readable medium, and an electronic device, thereby at least to a certain extent overcoming the brand Technical problems such as poor search accuracy and low search efficiency.

Other features and advantages of the present disclosure will become apparent from the following detailed description, or in part, be learned by practice of the present disclosure.

According to an aspect of an embodiment of the present disclosure, there is provided a method for displaying search results based on artificial intelligence, the method includes: receiving a search request, and determining index keywords according to the search request; Retrieve the target brand subject, and obtain the brand subject attribute information of the target brand subject; determine the application subject and information dissemination subject associated with the target brand subject, and obtain the program subject link corresponding to the application subject Information and communication subject link information corresponding to the information dissemination subject; generate a search result display page according to the brand subject attribute information, the program subject link information, and the communication subject link information.

According to an aspect of an embodiment of the present disclosure, there is provided an artificial intelligence-based search result display device, which includes: a keyword determination module configured to receive a search request, and determine index keywords according to the search request; attribute information The obtaining module is configured to retrieve the target brand body in the brand database according to the index keywords, and obtain the brand body attribute information of the target brand body; the link information obtaining module is configured to determine the target brand body and the target brand body Associated application subject and information dissemination subject, and obtain the link information of the program subject corresponding to the application subject and the link information of the dissemination subject corresponding to the information dissemination subject; the display page generation module is configured to The attribute information of the brand subject, the link information of the program subject and the link information of the communication subject generate a search result display page.

In some embodiments of the present disclosure, based on the above technical solutions, the keyword determination module includes: a search information acquisition module configured to acquire the search information carried in the search request; a semantic recognition module configured to Semantic identification of the search information to obtain basic keywords in the search information; the keyword expansion module is configured to obtain extended keywords related to the basic keywords, and combine the basic keywords and the extended The keywords are determined as index keywords.

In some embodiments of the present disclosure, based on the above technical solutions, the attribute information acquisition module includes: a candidate brand retrieval module configured to retrieve multiple candidate brand subjects in the brand database according to the index keywords; recommendation information The acquisition module is configured to determine the information dissemination subject associated with the candidate brand subject, and acquire brand recommendation information corresponding to the information dissemination subject; the target brand determination module is configured to select the target brand according to the brand recommendation information One or more candidate brand subjects serve as target brand subjects.

In some embodiments of the present disclosure, based on the above technical solution, the attribute information acquisition module includes: a candidate brand retrieval module configured to retrieve multiple candidate brand subjects in the brand database according to the index keywords; information dissemination The subject determination module is configured to determine the information dissemination subject associated with the candidate brand subject, and obtains the exposure rate, the number of associated users and the category information of the information dissemination subject; the recommendation coefficient determination module is configured to The exposure rate, the number of associated users and the category information determine the brand recommendation coefficient of the information dissemination subject; the target brand determination module is configured to sort the multiple candidate brand subjects according to the brand recommendation coefficient, and according to the sorted The candidate brand subject determines the target brand subject.

In some embodiments of the present disclosure, based on the above technical solutions, the index keywords include brand subject index keywords and application program index keywords; the attribute information acquisition module includes: a brand recall module configured to utilize the The brand subject index keyword searches the brand subject's brand recall keyword in the brand database; the candidate brand determination module is configured to determine the brand subject whose brand recall keyword matches the brand subject index keyword as a candidate brand subject, and determine a candidate application subject associated with the candidate brand subject; a program recall module configured to use the application index keywords to retrieve the application recall keywords of the candidate application subject in the brand database The brand matching module is configured to determine the candidate application subject that matches the application recall keyword and the application index keyword as the target application subject, and associate the target application subject with the The candidate brand subject is determined as the target brand subject.

In some embodiments of the present disclosure, based on the above technical solution, the device further includes: a target service item determination module configured to determine the target service item provided by the target application subject according to the application recall keyword , and acquire the service item link information corresponding to the target service item; the display page generation module is configured to combine the information of the brand subject attribute information, the program subject link information, and the communication subject link information Link information of the above service items to generate a search result display page.

In some embodiments of the present disclosure, based on the above technical solution, the device further includes: a recommended service item determination module configured to determine the recommended service item provided by the application program main body, and obtain the recommended service item corresponding to the recommended service item Item service item link information; the display page generation module is configured to generate search results according to the brand subject attribute information, the program subject link information and the communication subject link information, combined with the service item link information Display the page.

According to an aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for displaying search results based on artificial intelligence as in the above technical solution is implemented.

According to an aspect of an embodiment of the present disclosure, there is provided an electronic device, the electronic device includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the The above executable instructions are used to execute the artificial intelligence-based search result display method in the above technical solution.

In the technical solution provided by the embodiments of the present disclosure, by establishing an association relationship between a brand subject and multiple brand association objects, relevant information can be integrated and displayed in brand information search, and while improving search accuracy and search efficiency, it can provide Users are provided with richer and more intuitive media-rich brand information display effects, enabling users to obtain products and services provided by brand subjects more quickly and accurately. In addition, by displaying a variety of related information together, the interference of noise information on the target brand subject can be avoided, and users can also intuitively distinguish between regular brands and counterfeit brands from multiple dimensions such as brand introductions, small programs, and official accounts.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure. Apparently, the drawings in the following description are only some embodiments of the present disclosure, and those skilled in the art can obtain other drawings according to these drawings without creative efforts. In the attached picture:

Fig. 1 shows a schematic diagram of an exemplary system architecture applying the technical solution of the present disclosure.

Fig. 2 schematically shows a flow chart of the steps of the method for displaying search results based on artificial intelligence in some embodiments of the present disclosure.

Fig. 3 schematically shows a flow chart of steps for determining index keywords in some embodiments of the present disclosure.

Fig. 4 schematically shows a flow chart of steps for retrieving a target brand subject based on brand recommendation information in some embodiments of the present disclosure.

Fig. 5 schematically shows a flow chart of steps for retrieving a target brand subject based on brand recommendation coefficients in some embodiments of the present disclosure.

Fig. 6 schematically shows a flow chart of steps for retrieving a brand subject based on various keywords in some embodiments of the present disclosure.

FIG. 7 schematically shows a framework diagram of a brand retrieval system established by a social platform server based on materials uploaded by merchants.

Fig. 8 schematically shows an interactive interface for displaying search results to a user on a mobile terminal.

Fig. 9 schematically shows a data sharing system for storing data related to a brand subject in some embodiments of the present disclosure.

Fig. 10 schematically shows the composition structure of the blockchain in some embodiments of the present disclosure.

Fig. 11 schematically shows the process of generating a block by a blockchain in some embodiments of the present disclosure.

Fig. 12 schematically shows a composition block diagram of an apparatus for displaying search results based on artificial intelligence in some embodiments of the present disclosure.

FIG. 13 shows a schematic structural diagram of a computer system suitable for implementing electronic devices according to embodiments of the present disclosure.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, means, steps, etc. may be employed. In other instances, well-known methods, apparatus, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

The block diagrams shown in the drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices entity.

The flow charts shown in the drawings are only exemplary illustrations, and do not necessarily include all contents and operations/steps, nor must they be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be combined or partly combined, so the actual order of execution may be changed according to the actual situation.

In the related technologies disclosed in this disclosure, the brand subject will use a self-developed network platform or a third-party network platform to carry out activities such as brand promotion or product sales. For example, a brand entity can build its own official website or online store, or open social accounts, applications, online stores, etc. on third-party online platforms such as WeChat, Weibo, Taobao, and JD.com. Taking the WeChat platform as an example, brand entities can operate and maintain public accounts or mini programs for publicizing or providing products and services. However, the search for Official Accounts or Mini Programs is generally based on the names and descriptions of relevant subjects, so the search results are quite complicated and contain various noise information. Moreover, the simple name and description usually cannot accurately explain the core functions of the official account or the mini program itself. In this way, when users search for application services, Official Accounts or Mini Programs that are more relevant to the search terms will not be exposed, and thus users will not be able to quickly and accurately find the products or services they need. In addition, in terms of display form, the search results of Official Accounts or Mini Programs cannot provide users with simple and direct services. Users need to perform multiple jumps within Official Accounts or Mini Programs to obtain specific products or services.

Based on the problems in the above solutions, the present disclosure provides an artificial intelligence-based search result display method, an artificial intelligence-based search result display device, a computer-readable medium, and an electronic device that can provide accurate recall and direct service functions.

Fig. 1 shows a schematic diagram of an exemplary system architecture applying the technical solution of the present disclosure.

As shown in FIG. 1 , the system architecture 100 may include a client 110 , a network 120 and a server 130 . The client 110 may include various terminal devices such as smart phones, tablet computers, notebook computers, and desktop computers. The server 130 may include various server devices such as a web server, an application server, and a database server. The network 120 may be a communication medium capable of providing various connection types of a communication link between the client 110 and the server 130 , such as a wired communication link, a wireless communication link, and the like.

According to implementation requirements, the system architecture in the embodiments of the present disclosure may have any number of clients, networks and servers. For example, the server 130 may be a server group composed of multiple server devices. In addition, the method for displaying search results based on artificial intelligence in the embodiment of the present disclosure may be applied to the client 110 or the server 130, which is not specifically limited in the present disclosure.

For example, when the method for displaying search results based on artificial intelligence provided by the embodiments of the present disclosure is applied to the server 130, the user can fill in the search information related to the brand, product or service in the search interface of the client 110, The client 110 generates a corresponding search request according to the search information, and sends the search request to the server 130 through the network 120 . In response to the received search request, the server 130 can perform semantic analysis on the information carried in the search request to obtain corresponding index keywords, and then use the index keywords to determine the target brand subject and the application program subject and The information dissemination subject finally generates a search result display page according to the attribute information of the brand subject, the link information of the program subject and the link information of the dissemination subject. The server 130 returns the page data of the search result display page to the client 110 through the network 120, and the client 110 renders the page data and presents it on the display interface.

In some optional implementation manners, an AI processing function module based on artificial intelligence (Artificial Intelligence, AI) can also be set on the server 130, and technologies such as voice technology, natural language processing, and machine learning can be used to obtain index keywords and determine targets. Brand subject and other method steps.

Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.

Artificial intelligence technology is a comprehensive subject that involves a wide range of fields, including both hardware-level technology and software-level technology. Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics. Artificial intelligence software technology mainly includes several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.

The key technologies of speech technology (Speech Technology, ST) include automatic speech recognition technology (ASR), speech synthesis technology (TTS) and voiceprint recognition technology. Enabling computers to hear, see, speak, and feel is the development direction of human-computer interaction in the future, and voice will become one of the most promising ways of human-computer interaction in the future.

Natural Language Processing (NLP) is an important direction in the field of computer science and artificial intelligence. It studies various theories and methods that can realize effective communication between humans and computers using natural language. Natural language processing is a science that combines linguistics, computer science, and mathematics. Therefore, research in this field will involve natural language, that is, the language that people use every day, so it is closely related to the study of linguistics. Natural language processing technologies usually include text processing, semantic understanding, machine translation, robot question answering, knowledge graph and other technologies.

Machine Learning (ML) is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. Specializes in the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its application pervades all fields of artificial intelligence. Machine learning and deep learning usually include techniques such as artificial neural network, belief network, reinforcement learning, transfer learning, inductive learning, and teaching learning.

The artificial intelligence-based search result display method, artificial intelligence-based search result display device, computer-readable medium, and electronic device provided in the present disclosure will be described in detail below in conjunction with specific embodiments.

Fig. 2 schematically shows a flow chart of the steps of the method for displaying search results based on artificial intelligence in some embodiments of the present disclosure. As shown in Figure 2, the method may mainly include the following steps:

Step S210. Receive a search request, and determine index keywords according to the search request.

According to the user's search requirements, a search request may be generated through a client program or a web page. After receiving the search request, the client device or the server device can determine the corresponding index keywords. Index keywords may be keywords related to content such as brand names, product names, and service information. In addition, the index keywords can be the keywords directly input by the user when generating the search request or the keywords obtained by analyzing and extracting the information input by the user, or they can be automatically generated by the user by clicking or selecting the label or option provided by the search interface in the search interface. Generated keywords. For example, the index keywords may be "express delivery", "China Mobile", "McDonald's" and so on.

Step S220. Search the brand database according to the index keywords to obtain the target brand subject, and obtain the brand subject attribute information of the target brand subject.

In order to improve the accuracy of brand information search, the embodiment of the present disclosure can pre-configure and maintain a brand database, which is used to store the introduction information of various brand subjects and the network acquisition interface of various products or services related to the brand subject . Each brand entity can configure and manage its own related materials and associated information, such as product lists, product purchase links, service lists, service information, WeChat public accounts, WeChat applets, etc. The brand database can uniformly maintain the retrieval elements of each brand subject, and compare the retrieval elements of each brand subject according to the index keywords obtained in step S210, and the brand subject that is successfully compared is regarded as the target brand subject. For the retrieved target brand subject, this step will also obtain its brand subject attribute information. The attribute information of the brand body may mainly include one or more of the name of the brand body, the logo of the brand body, the introduction of the brand body, and the brand certification logo. The name of the brand subject can be the common name or nickname of the brand subject, such as "China Mobile", "10086", "China Mobile 10086" and so on. The main body logo of the brand can be the brand's trademark, LOGO and other identifying information. The introduction of the main body of the brand can be descriptive text related to the service, product and other content of the main body of the brand. The brand certification mark can be the certification mark information of the nature or attribute of the brand subject. For example, it can analyze the public account connected to the brand search based on information such as exposure rate, number of fans, and categories, and provide information for the brand subject that meets specific requirements. Provide a certification mark such as "Official".

Step S230. Determine the application subject and the information dissemination subject associated with the target brand subject, and acquire the program subject link information corresponding to the application program subject and the communication subject link information corresponding to the information dissemination subject.

For the target brand subject determined in step S220, this step may determine one or more brand related objects associated with the target brand subject according to the relationship between each brand subject and various related objects. Brand-associated objects may at least include information dissemination subjects for disseminating brand information and application program subjects for providing brand services, and may also include product collections or service item collections provided by brand subjects. The brand subject can manage and maintain a product collection for display in search results. For example, a mobile phone brand can form a product collection with the latest mobile phone products on the market. The associated object display information corresponding to the product collection may include the name, model, image, price, purchase link, etc. of each product in the product collection. The information dissemination subject can be a network information dissemination interface or channel for disseminating brand information. For example, the subject of information dissemination may be a public broadcasting subject such as an official website, a Weibo account, or a group broadcasting subject such as a WeChat public account or an Alipay Life account. Using the link information of the communication subject can directly jump to the information dissemination page provided by the information dissemination subject, for example, it can jump to the official account page corresponding to the target brand subject. The application program can be a program client or a WeChat applet for providing brand services, etc. Using the application program link information can directly open the corresponding application program body, for example, can open the program client or applet provided by the target brand body.

Step S240. Generate a search result display page according to the attribute information of the brand body, the link information of the program body, and the link information of the communication body.

Based on the target brand subject determined in step S220, a search result display page composed of one or more search items may be generated, and each search item corresponds to a target brand subject. Moreover, the display content in each search item may include at least three parts, namely, brand body attribute information related to the target brand body, program body link information, and communication body link information.

In the artificial intelligence-based search result display method provided by the embodiments of the present disclosure, relevant information can be integrated in brand information search by establishing an association relationship for multiple brand-associated objects such as the brand subject, the application program subject, and the information dissemination subject. Display, while improving search accuracy and search efficiency, it can provide users with richer and more intuitive media-rich brand information display effects, enabling users to more quickly and accurately obtain products and services provided by brand entities. In addition, by displaying a variety of related information together, the interference of noise information on the target brand subject can be avoided, and users can also intuitively distinguish between regular brands and counterfeit brands from multiple dimensions such as brand introductions, small programs, and official accounts.

Fig. 3 schematically shows a flow chart of steps for determining index keywords in some embodiments of the present disclosure. As shown in FIG. 3 , on the basis of the above embodiments, determining the index keywords according to the search request in step S210 may include the following steps:

Step S310. Obtain the search information carried in the search request.

The user can input search information on the client device by means of voice, text, or gesture interaction, and then the client sends a search request generated based on the search information to the server, or the server actively obtains the search request from the client. After parsing the search request, the server can obtain the search information carried therein, and the search information can be expressed as a single character, a word composed of one or more characters, or a sentence composed of multiple words. For example, the user uses the voice function to input the information "I want to send a courier" on the client terminal, and the search request carrying the information is sent to the server, and the server analyzes and obtains it.

Step S320. Perform semantic recognition on the search information to obtain basic keywords in the search information.

Useless information can be stripped through semantic recognition of search information, so as to obtain basic keywords related to user intentions. The semantic recognition performed in this step can specifically adopt the method of named entity recognition, for example, a regular expression can be used to perform regular matching detection on the search information, or a word search tree (Trie) can be used to perform word matching detection on the search information, or Named entity recognition can be performed on search information using pre-trained machine learning models. One or more basic keywords can be obtained by semantic recognition of search information, and the number of basic keywords depends on the information content and specific semantics of search information.

Step S330. Obtain extended keywords related to the basic keyword, and determine the basic keyword and the extended keyword as index keywords.

In the embodiment of the present disclosure, a corresponding keyword library can be configured in the brand database. When basic keywords are obtained from search information, search can be performed in the keyword library to obtain extended keywords with the same or similar semantics as the basic keywords. For example, if the basic keyword is "express delivery", then the acquired extended keywords may include "parcel", "mail", "delivery", "running errands" and so on. In some optional implementation manners, this step may also use a pre-trained machine learning model to expand the basic keywords. Determining the basic keywords and extended keywords together as index keywords can greatly increase the recall rate of the brand subject and increase the probability of hitting the user's search needs.

In addition to the recall rate of the brand subject, the retrieval accuracy rate of the brand subject is also an important factor affecting the search results. In order to improve the retrieval accuracy rate of the brand subject, this disclosure can provide the target brand subject based on brand recommendation information or brand recommendation coefficient. Retrieval method.

Fig. 4 schematically shows a flow chart of steps for retrieving a target brand subject based on brand recommendation information in some embodiments of the present disclosure. As shown in Figure 4, on the basis of the above embodiments, the retrieval of the target brand subject in the brand database according to the index keywords in step S220 may include the following steps:

Step S410. Search the brand database according to the index keywords to obtain a plurality of candidate brand subjects.

The index keywords may be keywords related to the brand name, or may be keywords related to the product name, service item, or service field of the brand provided by the brand. Using index keywords as retrieval elements can generally retrieve multiple candidate brand entities in the brand database. Most of these candidate brand entities are brand entities with similar names, the same service fields, or other relevant characteristics.

Step S420. Determine the information dissemination subject associated with the candidate brand subject, and acquire brand recommendation information corresponding to the information dissemination subject.

For each candidate brand subject retrieved in step S410, this step may respectively determine the information dissemination subject associated with each candidate brand subject, for example, may separately determine the official account associated with each candidate brand subject. For each information dissemination subject, corresponding brand recommendation information can be pre-configured in the brand database. For example, according to the account subject information of the official account, all official accounts can be divided into two types: official official account and unofficial official account. type. Among them, the official official account has a high degree of recommendation, while the non-official official account has a relatively low degree of recommendation.

Step S430. Select one or more candidate brand subjects as target brand subjects according to brand recommendation information.

According to the brand recommendation information corresponding to the information dissemination subject, the retrieved multiple candidate brand subjects can be screened, and one or more candidate brand subjects with high recommendation degree can be selected as the target brand subject.

Information dissemination entities such as official accounts generally need to submit certification materials to the official account operation platform when they go online. Using the authentication results of official accounts as brand recommendation information can give priority to presenting candidate brand entities that have passed the official certification as target brand entities to users.

Fig. 5 schematically shows a flow chart of steps for retrieving a target brand subject based on brand recommendation coefficients in some embodiments of the present disclosure. As shown in Figure 5, on the basis of the above embodiments, the retrieval of the target brand subject in the brand database according to the index keywords in step S220 may include the following steps:

Step S510. Search the brand database according to the index keywords to obtain multiple candidate brand subjects.

The method of retrieving the candidate brand subject is similar to the previous embodiment, and will not be repeated here.

Step S520. Determine the information dissemination subject associated with the candidate brand subject, and obtain the exposure rate, number of associated users and category information of the information dissemination subject.

Still taking the official account as an example, after determining the official account associated with each candidate brand entity, this step can obtain the exposure rate, number of associated users, and category information of each official account. Among them, the exposure rate refers to the number of times the official account is displayed per unit time, the number of associated users can be, for example, the number of followers of the official account, and the category information can include different types of official accounts such as subscription accounts, service accounts, or corporate WeChat.

Step S530. Determine the brand recommendation coefficient of the information dissemination subject according to the exposure rate, the number of associated users, and the category information.

The brand recommendation coefficient of the information dissemination subject can be determined by analyzing the exposure rate, the number of associated users, and the category information. For example, the three types of information can be quantitatively characterized, and then weighted according to different weights to obtain the brand recommendation of the information dissemination subject. coefficient.

Step S540. Rank the multiple candidate brand entities according to the brand recommendation coefficients, and determine the target brand entity according to the sorted candidate brand entities.

According to the size of the brand recommendation coefficient, multiple candidate brand entities can be sorted, and then the target brand entity can be determined according to the ranking results. Several candidate brand entities greater than a certain threshold are determined as target brand entities.

In some embodiments of the present disclosure, the index keywords used for brand subject search may further include brand subject index keywords and application program index keywords. When there are multiple index keywords determined according to the search request, the embodiments of the present disclosure can identify their types, and determine some of the index keywords as brand subject index keywords, while other index keywords except the brand subject index keywords The index key is then determined as the application index key. Fig. 6 schematically shows a flow chart of steps for retrieving a brand subject based on various keywords in some embodiments of the present disclosure. As shown in Figure 6, on the basis of the above embodiments, the retrieval of the target brand subject in the brand database according to the index keywords in step S220 may include the following steps:

Step S610. Use the brand subject index keywords to search the brand database for brand recall keywords of the brand subject.

In the brand subject database, corresponding brand recall keywords can be configured for each brand subject to retrieve and recall them. Brand recall keywords can be keywords related to the name, products, services and other content of the brand subject. In this step, firstly, search and compare the brand subject index keywords with the brand recall keywords corresponding to each brand subject in the brand database to determine whether the brand subject index keywords can be successfully matched with the brand recall keywords.

Step S620. Determine the brand subject whose brand recall keyword matches the brand subject index keyword as a candidate brand subject, and determine a candidate application program subject associated with the candidate brand subject.

When a brand recall keyword can be successfully matched with the brand subject index keywords, the brand subject corresponding to the brand recall keyword can be determined as a candidate brand subject. At the same time, in this step, the candidate application subject associated with the candidate brand subject can be determined according to the pre-configured association relationship.

Step S630. Using the application program index keywords to search the brand database for the application program recall keywords of the candidate application program subject.

In order to improve the recall accuracy of the brand subject, for the application subject associated with the brand subject, an application recall keyword can be configured for it in the brand database. In this step, search and compare the application index keywords with the application recall keywords corresponding to each candidate application subject to determine whether the application index keywords can be successfully matched with the application recall keywords. In some optional implementation manners, brand recall keywords may overlap with application program recall keywords, for example, certain keywords may serve as brand recall keywords and application program recall keywords at the same time.

Step S640. Determine the candidate application subject whose application recall keyword matches the application index keyword as the target application subject, and determine the candidate brand subject associated with the target application subject as the target brand subject.

If a certain application recall keyword can successfully match the application index keyword, then the candidate application subject corresponding to the application recall keyword can be determined as the target application subject. Accordingly, a candidate brand entity associated with the target application entity may be determined as the target brand entity.

For example, when two indexed keywords are identified from a search query, one of the keywords may be identified as a brand indexed keyword related to the brand subject's brand subject name, while the other keyword is identified as related to the application The principal's associated application index key. For example, if a user enters two keywords "Huawei" and "mobile phone" at the same time, then the search keyword "Huawei" can be used as a brand index keyword. The application index keywords can be searched and compared to determine that the application subject associated with the brand subject "Huawei" is the "Huawei Mall+" applet. The two search keywords hit the associated brand subject and application subject at the same time, so the corresponding brand subject can be recalled, and then the brand information search results related to the display information of the brand subject and the display information of the associated object can be generated. On the contrary, if the two search keywords cannot hit the associated brand subject and application subject at the same time, it can be considered that there is no corresponding brand subject in the brand database, so as to avoid providing users with wrong or inaccurate search results.

On the basis of using the brand index keywords and application program index keywords to retrieve the target brand subject, the embodiments of the present disclosure can also determine the target service items provided by the target application program subject according to the successfully matched application program recall keywords, and at the same time obtain the corresponding Service item link information of the target service item. For example, when the target brand subject is "China Mobile", the target application subject associated with it is the "China Mobile 10086+" applet, based on the application recall keyword "phone bill", it can be determined that the corresponding target service items include "phone bill" "Enquiry", "Telephone charge" and other service items related to the keyword "phone charge" provided by the Mini Program. For a determined target service item, when generating a search result display page, the service item link information corresponding to the target service item may be displayed while displaying brand subject attribute information, program subject link information, and communication subject link information. Use the service item link information to jump to the corresponding mini program service page, so that users can directly obtain the service item they want to use.

In addition, when the index keywords only include brand index keywords, the embodiment of the present disclosure may obtain the recommended service items provided by the application subject after determining the application subject associated with the target brand subject, and obtain the corresponding The service item link information of the recommended service item. For example, when the target brand subject is "China Mobile", the target application subject associated with it is the "China Mobile 10086+" mini-program, and the recommended service items provided by the mini-program may include "traffic query", "recharge payment" Wait for the priority recommended service items provided by the Mini Program. For a determined recommended service item, when generating a search result display page, the service item link information corresponding to the recommended service item may be displayed while displaying brand subject attribute information, program subject link information, and communication subject link information. The embodiments of the present disclosure can intelligently determine the recommended service items according to the user's usage habits or the historical usage records of the main body of the application program, so as to improve the convenience for the user to use the related service items.

The application of the search result display method based on artificial intelligence in the embodiment of the present disclosure on both sides of the social platform server and the mobile terminal will be described below.

FIG. 7 schematically shows a framework diagram of a brand retrieval system established by a social platform server based on materials uploaded by merchants. As shown in Figure 7, merchants 710 can upload materials related to their own brands to the social platform server 720, which can specifically include brand introduction information and information about official accounts, mini programs or other related objects associated with the brand subject, so as to achieve Enrich the effect of brand display content. The social platform server 720 can establish a brand database 730 including at least a keyword library 731 and an associated material library 732 according to related materials and associated information uploaded by merchants 710 . Among them, the keyword library 731 stores recall keywords corresponding to the brand subject, and the associated material library 732 stores information of public accounts, mini programs or other related objects associated with the brand subject. Based on the brand database 730, a brand retrieval system 740 can be established to search and match users' search needs, so as to provide users with search results including attribute information and related information of brand subjects.

Fig. 8 schematically shows an interactive interface for displaying search results to a user on a mobile terminal. As shown in Figure 8, when a user needs to inquire about brand information, check the content published by the official account, or use the goods or services provided by the mini program, he can first log in to the social platform on the mobile terminal. In the interactive interface 810 of the social platform, various function entrances such as "circle of friends", "scan", "search", etc. are provided.

The user can enter the search page 820 by clicking "Search" or by sending a voice command. A search box 821 is provided in the search page 820, and the user can input search information in text form or voice form through the search box 821. According to the search information, a search request can be generated on the mobile terminal, and the search request can be sent to the social platform server through network communication.

The social platform server can determine the index keywords after analyzing the received search request, and then use the brand retrieval system to search and match in the brand database, and the search results will be returned to the mobile terminal.

After rendering the relevant data, the mobile terminal may generate a search result display page 830 . Multiple search items corresponding to different brand subjects can be simultaneously displayed on the search result display page 830 . Each search item includes two display parts: a brand body display area 831 and an associated object display area 832 .

The brand body display area 831 is used to display the brand body attribute information of the brand body, for example, it may include the brand body name, brand body logo, brand body introduction, brand certification logo and so on.

The associated object display area 832 may further include a service item display area 8321 , an application program main display area 8322 and an information dissemination main display area 8323 . The service item display area 8321 is used to display the product list or service list associated with the target brand subject, mainly the service items provided by the application program subject; the application program subject display area 8322 can be used to display the application associated with the brand subject The program, for example, can display the program jump entry corresponding to the program client jump link or the applet jump link; the information dissemination subject display area 8323 can be used to display the public broadcast subject or group broadcast subject associated with the brand subject , for example, the page jump entry corresponding to the jump link of the official account or the jump link of the official website can be displayed.

When the user clicks on the brand body display area 831 in a certain search item, the user can enter a detailed display page for the corresponding brand body. When the user clicks on a certain display object in the related object display area 832 , it may jump to a display page of other related content such as the corresponding official account, mini-program, or service items provided by the mini-program.

In some embodiments of the present disclosure, blockchain technology can be used to share and store various data such as brand subject information and brand associated object information in the brand database. Fig. 9 schematically shows a data sharing system for storing data related to a brand subject in some embodiments of the present disclosure. As shown in Figure 9, a data sharing system 900 refers to a system for sharing data between nodes, the data sharing system may include a plurality of nodes 910, and the plurality of nodes 910 may refer to each client in the data sharing system end. Each node 910 may receive input information during normal operation, and maintain shared data in the data sharing system based on the received input information. In order to ensure information intercommunication in the data sharing system, there may be an information connection between each node in the data sharing system, and information transmission may be performed between nodes through the above information connection. For example, when any node in the data sharing system receives input information, other nodes in the data sharing system will obtain the input information according to the consensus algorithm, and store the input information as data in the shared data, so that the data in the data sharing system The data stored on all nodes are consistent.

For each node in the data sharing system, there is a node ID corresponding to it, and each node in the data sharing system can store the node IDs of other nodes in the data sharing system, so that later, according to the node IDs of other nodes, Broadcast the generated blocks to other nodes in the data sharing system. Each node can maintain a node ID list as shown in the following table, and store the node name and node ID in the node ID list. Wherein, the node identifier may be an IP (Internet Protocol, a protocol for interconnecting networks) address and any other information that can be used to identify the node. Table 1 only uses the IP address as an example for illustration.

node name Node ID node 1 117.114.151.174 node 2 117.116.189.145 … … Node N 119.123.789.258

Every node in the data sharing system stores an identical blockchain. The block chain is composed of multiple blocks, and Fig. 10 schematically shows the composition structure of the block chain in some embodiments of the present disclosure. As shown in Figure 10, the blockchain is composed of multiple blocks. The genesis block includes a block header and a block body. The block header stores the input information feature value, version number, timestamp and difficulty value. The input information is stored; the next block of the founding block takes the founding block as the parent block, and the next block also includes the block header and the block body. The block header stores the input information characteristic value of the current block, the parent block The block header characteristic value, version number, timestamp and difficulty value of the block, and so on, so that the block data stored in each block in the blockchain is associated with the block data stored in the parent block, The security of the input information in the block is guaranteed.

Fig. 11 schematically shows the process of generating a block by a blockchain in some embodiments of the present disclosure. As shown in Figure 11, when the node where the blockchain is located receives the input information, it verifies the input information. After the verification is completed, the input information is stored in the memory pool, and the hash key used to record the input information is updated. Afterwards, update the update timestamp to the time when the input information is received, try different random numbers, and perform eigenvalue calculations multiple times, so that the calculated eigenvalues can satisfy the following formula:

SHA256(SHA256(version+prev_hash+merkle_root+ntime+nbits+x))<TARGET

Among them, SHA256 is the eigenvalue algorithm used to calculate the eigenvalue; version (version number) is the version information of the relevant block protocol in the blockchain; prev_hash is the block header eigenvalue of the parent block of the current block; merkle_root is the input information ntime is the update time of the update timestamp; nbits is the current difficulty, which is a fixed value for a period of time, and will be determined again after a fixed period of time; x is a random number; TARGET is the threshold of the feature value, the feature The value threshold can be determined according to nbits.

In this way, when the random number satisfying the above formula is calculated, the information can be stored correspondingly, the block header and block body are generated, and the current block is obtained. Subsequently, according to the node identification of other nodes in the data sharing system, the node where the blockchain is located sends the newly generated blocks to other nodes in the data sharing system where it is located, and the other nodes verify the newly generated blocks , and add the newly generated block to its stored blockchain after verification is completed.

It should be noted that although the various steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in that particular order, or that all illustrated steps must be performed to achieve the desired the result of. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and/or one step may be decomposed into multiple steps for execution, etc.

The device embodiments of the present disclosure are introduced below, which can be used to implement the method for displaying search results based on artificial intelligence in the foregoing embodiments of the present disclosure. For the details not disclosed in the disclosed device embodiments, please refer to the above-mentioned embodiments of the method for displaying search results based on artificial intelligence in the present disclosure.

Fig. 12 schematically shows a composition block diagram of an apparatus for displaying search results based on artificial intelligence in some embodiments of the present disclosure. As shown in FIG. 12 , the search result display device 1200 may mainly include: a keyword determination module 1210 configured to receive a search request and determine an index keyword according to the search request; an attribute information acquisition module 1220 configured to Retrieve the target brand subject in the brand database, and obtain the brand subject attribute information of the target brand subject; the link information acquisition module 1230 is configured to determine the application program subject and information dissemination subject associated with the target brand subject, and obtain the corresponding The program subject link information of the application program subject and the communication subject link information corresponding to the information dissemination subject; the display page generation module 1240 is configured to generate a search result display page according to the brand subject attribute information, the program subject link information and the communication subject link information.

In some embodiments of the present disclosure, based on the above embodiments, the keyword determination module includes: a search information acquisition module configured to acquire the search information carried in the search request; a semantic identification module configured to perform semantic identification on the search information to obtain the basic keywords in the search information; the keyword expansion module is configured to obtain extended keywords related to the basic keywords, and determine the basic keywords and the extended keywords as index keywords.

In some embodiments of the present disclosure, based on the above embodiments, the attribute information acquisition module includes: a candidate brand retrieval module configured to retrieve multiple candidate brand subjects in the brand database according to index keywords; a recommendation information acquisition module is configured Configured to determine the information dissemination subject associated with the candidate brand subject, and obtain brand recommendation information corresponding to the information dissemination subject; the target brand determination module is configured to select one or more candidate brand subjects as the target brand according to the brand recommendation information main body.

In some embodiments of the present disclosure, based on the above embodiments, the attribute information acquisition module includes: a candidate brand retrieval module configured to retrieve multiple candidate brand subjects in the brand database according to index keywords; an information dissemination subject determination module, It is configured to determine the information dissemination subject associated with the candidate brand subject, and obtain the exposure rate, the number of associated users and category information of the information dissemination subject; the recommendation coefficient determination module is configured to determine according to the exposure rate, the number of associated users and category information The brand recommendation coefficient of the information dissemination subject; the target brand determination module configured to sort a plurality of candidate brand subjects according to the brand recommendation coefficient, and determine the target brand subject according to the sorted candidate brand subjects.

In some embodiments of the present disclosure, based on the above embodiments, the index keywords include brand subject index keywords and application program index keywords; the attribute information acquisition module includes: a brand recall module configured to use the brand subject index keywords in The brand recall keyword of the brand subject is retrieved from the brand database; the candidate brand determination module is configured to determine the brand subject whose brand recall keyword matches the brand subject index keyword as a candidate brand subject, and determine the brand subject associated with the candidate brand subject the candidate application subject; the program recall module configured to use the application index keyword to retrieve the application recall keyword of the candidate application subject in the brand database; the brand matching module configured to match the application recall keyword with the application The candidate application subject matching the program index keywords is determined as the target application subject, and the candidate brand subject associated with the target application subject is determined as the target brand subject.

In some embodiments of the present disclosure, based on the above embodiments, the search result display device further includes: a target service item determination module configured to determine the target service item provided by the target application subject according to the application recall keyword, and obtain Corresponding to the service item link information of the target service item; the display page generating module is configured to generate a search result display page according to the brand subject attribute information, the program subject link information and the dissemination subject link information, combined with the service item link information.

In some embodiments of the present disclosure, based on the above embodiments, the device for displaying search results further includes: a recommended service item determination module configured to determine the recommended service item provided by the application program main body, and obtain the service corresponding to the recommended service item item link information; the display page generating module is configured to generate a search result display page according to the brand subject attribute information, the program subject link information and the dissemination subject link information, combined with the service item link information.

FIG. 13 shows a schematic structural diagram of a computer system suitable for implementing electronic devices according to embodiments of the present disclosure.

It should be noted that the computer system 1300 of the electronic device shown in FIG. 13 is only an example, and should not limit the functions and application scope of the embodiments of the present disclosure.

As shown in FIG. 13 , a computer system 1300 includes a central processing unit (Central Processing Unit, CPU) 1301, which can be stored in a program in a read-only memory (Read-Only Memory, ROM) 1302 or loaded from a storage part 1308 to a random Various appropriate actions and processes are executed by accessing programs in the memory (Random Access Memory, RAM) 1303 . In the RAM 1303, various programs and data necessary for system operation are also stored. The CPU 1301 , ROM 1302 , and RAM 1303 are connected to each other via a bus 1304 . An input/output (Input/Output, I/O) interface 1305 is also connected to the bus 1304 .

The following components are connected to the I/O interface 1305: an input section 1306 including a keyboard, a mouse, etc.; an output section 1307 including a cathode ray tube (Cathode Ray Tube, CRT), a liquid crystal display (Liquid Crystal Display, LCD), etc., and a speaker ; a storage section 1308 including a hard disk or the like; and a communication section 1309 including a network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1309 performs communication processing via a network such as the Internet. A drive 1310 is also connected to the I/O interface 1305 as needed. A removable medium 1311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 1310 as necessary so that a computer program read therefrom is installed into the storage section 1308 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described in the respective method flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 1309 and/or installed from removable media 1311 . When the computer program is executed by a central processing unit (CPU) 1301, various functions defined in the system of the present application are performed.

It should be noted that the computer-readable medium shown in the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash memory, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable The combination. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that includes one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a A combination of dedicated hardware and computer instructions.

It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. Actually, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided to be embodied by a plurality of modules or units.

Through the description of the above implementations, those skilled in the art can easily understand that the example implementations described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of software products, and the software products can be stored in a non-volatile storage medium (which can be CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to make a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) execute the method according to the embodiments of the present disclosure.

Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure .

It should be understood that the present disclosure is not limited to the precise constructions which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (10)

1. A method for displaying search results based on artificial intelligence, comprising: receiving a search request, and determining index keywords according to the search request; Retrieving the target brand subject in the brand database according to the index keywords, and obtaining the brand subject attribute information of the target brand subject; determining the application subject and the information dissemination subject associated with the target brand subject, and obtaining the link information of the program subject corresponding to the application subject and the link information of the dissemination subject corresponding to the information dissemination subject; A search result display page is generated according to the brand body attribute information, the program body link information, and the communication body link information. 2. The method for displaying search results based on artificial intelligence according to claim 1, wherein said determining index keywords according to said search request comprises: Obtain the search information carried in the search request; performing semantic recognition on the search information to obtain basic keywords in the search information; Acquiring extended keywords related to the basic keywords, and determining the basic keywords and the extended keywords as index keywords. 3. The method for displaying search results based on artificial intelligence according to claim 1, wherein the retrieval of the target brand subject in the brand database according to the index keyword comprises: searching the brand subject according to the index keyword A number of candidate brand entities are retrieved from the database; determining an information dissemination subject associated with the candidate brand subject, and obtaining brand recommendation information corresponding to the information dissemination subject; One or more candidate brand subjects are selected as target brand subjects according to the brand recommendation information. 4. The method for displaying search results based on artificial intelligence according to claim 1, wherein the retrieval of the target brand subject in the brand database according to the index keywords includes: Retrieving multiple candidate brand subjects in the brand database according to the index keywords; Determine the information dissemination subject associated with the candidate brand subject, and obtain the exposure rate, number of associated users and category information of the information dissemination subject; determining the brand recommendation coefficient of the information dissemination subject according to the exposure rate, the number of associated users and category information; The plurality of candidate brand subjects are sorted according to the brand recommendation coefficients, and a target brand subject is determined according to the sorted candidate brand subjects. 5. The method for displaying search results based on artificial intelligence according to claim 1, wherein the index keywords include brand subject index keywords and application program index keywords; The target brand subjects retrieved from the database include: Retrieving the brand recall keywords of the brand subject in the brand database by using the brand subject index keywords; determining a brand entity whose brand recall keyword matches the brand entity index keyword as a candidate brand entity, and determining a candidate application program entity associated with the candidate brand entity; Retrieving the application program recall keywords of the candidate application program subject in the brand database by using the application program index keywords; determining a candidate application subject whose application recall keyword matches the application index keyword as a target application subject, and determining a candidate brand subject associated with the target application subject as a target brand subject . 6. The method for displaying search results based on artificial intelligence according to claim 5, characterized in that, The method further includes: determining a target service item provided by the target application program subject according to the application program recall keyword, and acquiring service item link information corresponding to the target service item; The generation of a search result display page according to the attribute information of the brand subject, the link information of the program subject and the link information of the communication subject includes: According to the attribute information of the brand subject, the link information of the program subject and the link information of the dissemination subject, combined with the link information of the service item, a search result display page is generated. 7. The method for displaying search results based on artificial intelligence according to claim 1, characterized in that the method further comprises: determining the recommended service items provided by the application program main body, and obtaining the recommended service items corresponding to the recommended service items The link information of the service item; The generation of a search result display page according to the attribute information of the brand subject, the link information of the program subject and the link information of the communication subject includes: According to the attribute information of the brand subject, the link information of the program subject and the link information of the dissemination subject, combined with the link information of the service item, a search result display page is generated. 8. A search result display device based on artificial intelligence, characterized in that it comprises: A keyword determining module configured to receive a search request, and determine an index keyword according to the search request; The attribute information acquisition module is configured to retrieve the target brand subject in the brand database according to the index keywords, and acquire the brand subject attribute information of the target brand subject; The link information acquisition module is configured to determine the application program subject and the information dissemination subject associated with the target brand subject, and acquire the link information of the program subject corresponding to the application program subject and the dissemination information corresponding to the information dissemination subject subject link information; The display page generation module is configured to generate a search result display page according to the brand subject attribute information, the program subject link information and the communication subject link information. 9. A computer-readable medium on which a computer program is stored, wherein when the computer program is executed by a processor, the method for displaying search results based on artificial intelligence according to any one of claims 1 to 7 is realized . 10. An electronic device, characterized in that it comprises: processor; and a memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the method for displaying search results based on artificial intelligence according to any one of claims 1 to 7 by executing the executable instructions.