Information search and display method and device, computing equipment, storage medium and product

Abstract

The embodiment of the invention provides an information searching and displaying method and device, computing equipment, a storage medium and a product. Wherein the server side responds to a search request initiated by the client side based on a search keyword, executes a search operation, determines a plurality of first service objects matched with the search keyword, identifies a user search intention based on the search keyword, and generates interaction information by utilizing an artificial intelligence model in combination with the user intention and the search keyword; and sending the object prompt information of the plurality of service objects and the interaction information to a client, and displaying the object prompt information and the interaction information by the client. According to the scheme, when the search service is provided for the user, the object prompt information of the first service objects matched with the search operation is displayed, and different interaction information is generated according to different user search intentions and displayed to the user. The interaction information can be used for assisting the user in making clear search requirements, and then the service object needed by the user is accurately matched in the first service objects, so that the service conversion rate is increased.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technology, and in particular, to a method, device, computing device, storage medium, and product for information search and display. Background Art

[0002] With the development of Internet technology, many network service systems can provide service search functions for users. For example, it supports users to search based on text or voice to find the service objects required by the users.

[0003] The accuracy of the service search capabilities provided by network service systems usually depends on the accuracy of the search keywords input by users. However, in actual search scenarios, problems such as fuzzy search keyword requirements input by users and non-standard expression methods (such as dialects and colloquialisms) often occur. At this time, the searched service objects may not accurately match the user's needs, thereby affecting the subsequent service conversion rate, which urgently needs to be improved. Summary of the Invention

[0004] Embodiments of the present application provide a method, device, computing device, storage medium, and product for information search and display, so as to solve the problem that the searched service objects in the prior art cannot accurately match the user's needs and affect the service conversion rate.

[0005] Embodiments of the present application provide an information search method, which is applied to a server. The method includes receiving a search request sent by a client; the search request includes search keywords; performing a search operation to determine a plurality of first service objects that match the search keywords; identifying a user's search intention based on the search keywords; using an artificial intelligence model to generate interaction information in combination with the user's search intention and the search keywords; sending the object prompt information of the plurality of first service objects and the interaction information to the client, so that the client can display the object prompt information of the plurality of first service objects and the interaction prompt information generated based on the interaction information on the first page.

[0006] Embodiments of the present application also provide an information display method, which is applied to a client. The method includes: in response to a search operation, determining search keywords; sending a search request to the server based on the search keywords, so that the server performs a search operation to determine a plurality of first service objects that match the search keywords; identifying a user's search intention based on the search keywords, and using an artificial intelligence model to generate interaction information in combination with the user's search intention and the search keywords; receiving the object prompt information of the plurality of first service objects and the interaction prompt information sent by the server; determining interaction prompt information based on the interaction generated information; and displaying the object prompt information of the plurality of service objects and the interaction prompt information on the first page.

[0007] The embodiment of the present application further provides an information search device configured in a server, including: a first receiving module, configured to receive a search request sent by a client; the search request includes a search keyword; an object search module, configured to perform a search operation to determine a plurality of first service objects matching the search keyword; an intention recognition module, configured to recognize a user's search intention based on the search keyword; a first information generation module, configured to generate interaction information by using an artificial intelligence model in combination with the user's search intention and the search keyword; a first sending module, configured to send the object prompt information of the plurality of first service objects and the interaction information to the client, so that the client displays the object prompt information of the plurality of first service objects and the interaction prompt information generated based on the interaction information on a first page.

[0008] The embodiment of the present application further provides an information display device configured in a client, including: a keyword determination module, configured to determine a search keyword in response to a search operation; a second sending module, configured to send a search request to the server based on the search keyword, so that the server performs a search operation to determine a plurality of first service objects matching the search keyword; recognize a user's search intention based on the search keyword, and generate interaction information by using an artificial intelligence model in combination with the user's search intention and the search keyword; a second receiving module, configured to receive the object prompt information of the plurality of first service objects and the interaction prompt information sent by the server; a second information generation module, configured to determine interaction prompt information based on the interaction generated information; a display module, configured to display the object prompt information of the plurality of service objects and the interaction prompt information on a first page.

[0009] The embodiment of the present application further provides a computing device, including a processing component and a storage component; the storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the above information search method or information display method.

[0010] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processing component, it implements the above information search method or information display method.

[0011] The embodiment of the present application further provides a computer program product, including a computer program or instruction. When the computer program or instruction is executed by a processing component, it implements the above information search method or information display method.

[0012] In the embodiments of the present application, the server responds to a search request initiated by the client based on a search keyword, performs a search operation, determines multiple first service objects that match the search keyword, and at the same time, based on the search keyword, identifies the user's search intention, generates interaction information by using an artificial intelligence model in combination with the user intention and the search keyword, and sends the object prompt information of the multiple service objects and the interaction information to the client for display by the client. The solution of the embodiments of the present application, when providing a search service based on a search keyword with fuzzy requirements or non-standard expression, not only displays the object prompt information of multiple first service objects that match the search operation, but also further identifies the user's search intention corresponding to the search keyword, and generates different interaction information for different user search intentions to display to the user. It can be realized to use the interaction information to assist the user in clarifying the search requirements, and then accurately match the service object required by the user among the multiple first service objects displayed on the client side, so as to improve the service conversion rate.

[0013] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0015] Figure 1 Shows the system architecture diagram for information search and display provided by an exemplary embodiment of the present application.

[0016] Figure 2 Shows the flowchart of an information search method provided by an exemplary embodiment of the present application.

[0017] Figure 3a Shows the schematic diagram of a first page provided by an exemplary embodiment of the present application.

[0018] Figure 3b Shows the schematic diagram of another first page provided by an exemplary embodiment of the present application.

[0019] Figure 3c Shows the schematic diagram of yet another first page provided by an exemplary embodiment of the present application.

[0020] Figure 4 Shows the schematic diagram of a second page provided by an exemplary embodiment of the present application.

[0021] Figure 5 Shows the flowchart of an information display method provided by an exemplary embodiment of the present application.

[0022] Figure 6 The figure shows a schematic diagram of scenario interaction in an actual application provided by an exemplary embodiment of the present application.

[0023] Figure 7 The figure shows a schematic diagram of the structure of an information search device provided by an exemplary embodiment of the present application.

[0024] Figure 8 The figure shows a schematic diagram of the structure of an information display device provided by an exemplary embodiment of the present application.

[0025] Figure 9 The figure shows a schematic diagram of the structure of a computing device for information search and display provided by the present application. Detailed implementation manners

[0026] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0027] It should be noted that the technical solutions of the embodiments of the present application are applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register user accounts on the server through registration to obtain user identities in the network environment. The same user account can be logged in to the server through different types of clients, enabling the server to identify the same user.

[0028] The interaction operations between the server and the users can be implemented based on the user accounts. The corresponding data received or sent by the server to the users is also implemented based on the user accounts. Actually, it is the client corresponding to the user account that receives or sends the corresponding data to the server. In addition, communication between users can also be achieved through user accounts. Among them, the user can refer to an individual or an organization, such as an enterprise, etc. The present application does not make specific limitations in this regard.

[0029] It should be noted that in the case where the embodiments of the present application involve user information, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data that have been authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject. Additionally, the artificial intelligence models (including but not limited to language models or large models) involved in the present application comply with the relevant laws and standards.

[0030] In addition, it should be noted that in the case where the embodiments of the present application involve user interaction operations or trigger operations, the user interaction operations or trigger operations involved in the embodiments of the present application include but are not limited to: interaction operations in various ways such as touch operations, gesture operations, voice operations, head movement operations, eye movement operations, etc.; among them, touch operations include but are not limited to: click operations, double-click operations, long-press operations, swipe operations, pinch operations, or mouse hover operations, etc. Swipe operations include but are not limited to: straight-line swipes, curved swipes, etc.

[0031] Furthermore, it should be noted that in the case where the embodiments of the present application involve the jump between the first page and the second page, the jump methods involved in the embodiments of the present application include but are not limited to: directly jumping from the first page to the second page, first jumping from the first page to the task page and then jumping to the second page when the corresponding task operation is completed on the task page; completing the corresponding task operation on the task page includes but is not limited to: when the task page is implemented as a list display page, completing the display operations of object prompt information and interaction information on the list display page; and so on.

[0032] At present, in the actual information search scenario, it often occurs that the search keyword requirements input by users are vague and the expression methods are not standard (for example, dialects and colloquialisms), etc., resulting in the possible inability to accurately match the user's needs for the searched service objects, thereby affecting the subsequent service conversion rate. To address this technical problem, the embodiments of the present application provide a solution. The basic idea is that the server responds to a search request initiated by the client based on a search keyword, performs a search operation, determines multiple first service objects that match the search keyword, and at the same time, based on the search keyword, identifies the user's search intention, and uses an artificial intelligence model to combine the user's intention and the search keyword to generate interaction information, and sends the object prompt information of the multiple service objects and the interaction information to the client for display. The solution of the embodiments of the present application, when providing a search service based on a search keyword with vague requirements or non-standard expression methods, not only displays the object prompt information of multiple first service objects that match the search operation, but also further identifies the user's search intention corresponding to the search keyword, and generates different interaction information for different user search intentions and displays it to the user. It can be realized to use the interaction information to assist the user in clarifying the search requirements, and then accurately match the service object required by the user among the multiple first service objects displayed on the client to improve the service conversion rate.

[0033] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0034] Figure 1 FIG. shows a system architecture diagram for information search and display provided by an exemplary embodiment of the present application. The system architecture may include a client 101 and a server 102. (Or: It may include a server and multiple clients; or it may include a server, a first client, and a second client, etc.)

[0035] Among them, a connection can be established between the client 101 and the server 102 through a network. The network provides a medium for the communication link between the client 101 and the server 102. The network can include various connection types, such as wired, wireless, or fiber optic cable, etc. The client 101 can interact with the server 102 through the network to receive or send messages, etc.

[0036] Among them, the client 101 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client 101 can be deployed in an electronic device and needs to rely on the device or certain apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, etc., such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For ease of understanding, Figure 1 in Figure 1 , the user side is mainly represented by the image of the device. Various other types of applications can usually be configured in the electronic device, 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. The electronic device can refer to a device used by the user and having functions such as computing, Internet access, and communication required by the user, such as a mobile phone, a tablet computer, a personal computer, a wearable device, etc. The electronic device usually can include at least one processing component and at least one storage component. The electronic device may also include basic configurations such as a network card chip, an IO (input / output) bus, and audio-video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as a keyboard, a mouse, a stylus, a printer, etc., which are not limited in this application.

[0037] The server 102 can include servers that provide various services, such as a server that processes search requests sent by the client 101.

[0038] It should be noted that the server 102 can be implemented as a distributed server cluster composed of multiple servers, or can be implemented 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 that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms, or an intelligent cloud computing server or an intelligent cloud host with artificial intelligence technology.

[0039] It should be noted that the information search method provided in the embodiments of this application is generally executed by the server 102, and the corresponding information search device is generally set in the server 102. The information display method provided in the embodiments of this application is generally executed by the client 101, and the corresponding information display device is generally set in the client 101. It should be understood that,Figure 1 The number of clients 101 and servers 102 in the embodiment is only for illustration and any number of clients and servers may be provided according to implementation requirements.

[0040] The implementation details of the technical solution of the embodiment of the present application are described in detail below.

[0041] Figure 2 This is a flow chart of an embodiment of an information search method provided by this application. The technical solution of this embodiment can be executed by the server. Figure 2 As shown, the method may include the following steps:

[0042] S201: Receive a search request sent by a client.

[0043] The search request may be a request triggered by a client's service search page when a user has a need to search for a service object. The search request may include a search keyword. The search keyword may be information entered by the user in the search box on the search page based on their search need.

[0044] Specifically, in this embodiment, when a user needs to search for a service, they can first specify a search keyword, then enter the search keyword in the search box on the client's service search page, and trigger a search operation, for example, by clicking a search button. Upon detecting the search operation, the client generates a search request based on the user's search keyword and sends it to the server. Accordingly, the server receives the search request sent by the client.

[0045] S202: Perform a search operation to determine a plurality of first service objects that match the search keyword.

[0046] The service objects of this embodiment can be objects on the service system that users can search, query, consult, and order, and can be tangible or intangible. Specifically, in the context of an online e-commerce platform, the service objects can be services such as housekeeping, TV repair, and recruitment sold by merchants on the online e-commerce platform. The first service object can be a service object that matches the search keyword and is screened from all service objects available on the service system through a search.

[0047] Optionally, after receiving a search request, the server extracts the search keyword contained in the search request and then searches for a first object that matches the search keyword among all service objects it can provide. For example, similarity calculations can be performed between the search keyword and object information of each service object that can be provided, such as the service object name, service content of the service object, and detailed description information of the service object, to determine a preset number (e.g., the first 100) of service objects that rank highly in terms of matching degree with the search keyword as the first service objects.

[0048] S203: Identify the user's search intent based on the search keywords.

[0049] Among them, the user's search intent in this embodiment includes but is not limited to: service query intent, question consultation intent, and fuzzy word intent.

[0050] This embodiment can analyze the user's search intent by parsing the search keywords, and specifically can be identified by at least one of the following methods.

[0051] Method 1: Determine the user's search intent according to the hit degree of the search keywords in various intent determination rules. Among them, the intent determination rules corresponding to this method can include but are not limited to: circle word rules and / or inclusion word rules.

[0052] For this method, multiple circled words can be preset for different search intents. For example, for service query intent, the service categories divided by each service category can be used as the corresponding circled words. Calculate the similarity between the search keywords and the preset circled word vocabulary respectively. The higher the similarity, the higher the hit degree of the search keywords relative to the circled word vocabulary. At this time, the search intent corresponding to the circled word vocabulary with the highest hit degree can be used as the user's search intent. Similarly, multiple inclusion words can also be preset for different search intents. For example, for question consultation intent, words such as "how to do", "how to repair", "why" can be used as the corresponding inclusion words. Determine whether the search keywords contain the preset inclusion words. If so, it means that the search keywords hit the inclusion words. At this time, the search intent corresponding to the hit inclusion words can be used as the user's search intent. This embodiment can determine one or more user search intents based on one or a combination of various intent determination rules, and this is not limited.

[0053] Method 2: Use an artificial intelligence model to combine with the search keywords to identify the user's search intent.

[0054] This method can be to infer the user's intention with the help of an artificial intelligence model. Specifically, if the artificial intelligence model is an intention classification model pre-trained based on a large number of sample keywords and their corresponding sample search intentions, at this time, the search keywords input by the user can be input into the artificial intelligence model, and the artificial intelligence model can parse the search keywords to classify the user's search intention. If the artificial intelligence model is a large model, at this time, the first prompt instruction can be generated in combination with the search keywords, and then based on the generated first prompt instruction, the artificial intelligence model can be guided to parse the user's search intention corresponding to the search keywords. For example, if the search keyword is "bed", the generated first prompt instruction can be: Please judge which of the following situations the search keywords input by the user belong to. 1. The user's search intention is a question consultation type intention; 2. The user's search intention is a service query type intention; 3. The user's search intention is a fuzzy word type intention. The search keyword is "bed". Based on this first prompt instruction, the result output by the corresponding artificial intelligence model can be: 3. Fuzzy word type intention. And the corresponding explanation is given that the word "bed" is relatively general, which may be to consult various questions about the bed, belonging to the question consultation type; it may also have service requirements such as purchasing or customizing a bed, but it is difficult to clarify its specific search intention only from the word "bed", so it belongs to the fuzzy word type intention.

[0055] Method 3: Determine the user's search intention based on the similarity between each intention word in the preset word library and the search keywords.

[0056] This method can be to pre-build a self-built word library corresponding to various search intentions. For example, for the question consultation type intention, a common question library can be self-built in combination with the user's common search questions. Calculate the similarity between the search keywords and the content in the self-built word libraries corresponding to various search intentions, and use the search intention corresponding to the one or more matching contents with the highest similarity ranking in the word library as the user's search intention.

[0057] This implementation can identify the user's search intention through one or more of the above methods to improve the accuracy of user search intention recognition.

[0058] Optionally, when identifying the user's search intention, for the same search keyword, analyzing from different perspectives may identify different user search intentions. For example, if the search keyword is "home appliance repair", it may be identified as a service query intention because it hits the circled word. However, since the service scope of home appliance repair is relatively wide, when analyzed based on an artificial intelligence model, it may be identified as a fuzzy word intention. At this time, in order to determine the final user search intention, in this embodiment, priorities may be set in advance for various search intentions. For example, the priority of the fuzzy word intention is higher than that of the question consultation intention; the priority of the question consultation intention is higher than that of the service query intention. At this time, if multiple user search intentions are identified based on the search keyword, the final user search intention may be determined according to the priorities of the identified multiple user search intentions. For example, if both the fuzzy word intention and the service query intention are identified based on the search keyword, since the priority of the fuzzy word intention is higher than that of the service query intention, the final user search intention may be determined as the fuzzy word intention at this time.

[0059] S204: Use the artificial intelligence model to combine the user's search intention and the search keyword to generate interaction information.

[0060] Among them, the interaction information can be information that helps the user accurately match the required service object from the first service objects for display to the user. For example, it may include, but is not limited to: service purchase prompt information, service operation prompt information, problem solutions, and associated keywords of the search keyword, etc.

[0061] Optionally, in this embodiment, a second prompt instruction may be generated based on the user's search intention and the search keyword, and then the second prompt instruction is input into the artificial intelligence model to guide the artificial intelligence model to infer the corresponding interaction information by combining the user's search intention and the search keyword.

[0062] Optionally, the types of interactive information implemented in this embodiment can be multiple, and different types of interactive information can be generated for different user search intentions. If the user search intention is a service query intention, the artificial intelligence model is used to generate service purchase prompt information and / or service operation prompt information corresponding to the search keyword. If the search intention is a problem consultation intention, the artificial intelligence model is used to generate a solution corresponding to the search keyword. If the search intention is a fuzzy word intention, the artificial intelligence model is used to determine at least one service category divided by the service category corresponding to the search keyword, and generate at least one associated keyword corresponding to each service category. Specifically, corresponding prompt instruction templates can be pre-set for different types of user search intentions. When executing this step, the corresponding prompt instruction template can be found based on the user search intention determined in S203, and the search keyword can be filled in on the template to obtain the second prompt instruction corresponding to the user search intention, and then the second prompt instruction is input into the artificial intelligence model to guide the artificial intelligence model to generate interactive information.

[0063] For example, if the user's search intent is for problem consultation and the search keyword is "the light is not on", the second prompt instruction generated at this time can guide the artificial intelligence model to infer the operating instructions and precautions about the light not being on as the interactive information at this time. If the user's search intent is for service query intent and the search keyword is "house cleaning", the second prompt instruction generated at this time can guide the artificial intelligence model to infer the service pitfall avoidance guide and industry knowledge of house cleaning as the interactive information at this time. If the user's search intent is for fuzzy word class intent and the search keyword is "home appliance repair", the second prompt instruction generated at this time can be to guide the artificial intelligence model to split out the related keywords corresponding to the subordinate or subdivided service categories of the service category to which home appliance repair belongs, such as TV repair, air conditioner repair, washing machine repair, etc. as the interactive information at this time.

[0064] In order to more accurately determine at least one service category of the service category division corresponding to the above-mentioned search keyword, this embodiment can also be: using an artificial intelligence model to respectively determine the similarity between multiple service categories of the service category division corresponding to the search keyword and the search keyword, and determine at least one service category corresponding to the search keyword based on the similarities corresponding to multiple service categories and the indicator data of multiple service categories.

[0065] Specifically, the search keyword can be filled in the prompt instruction template corresponding to the fuzzy word class intention to obtain the second prompt instruction, and then the second prompt instruction and the multiple service categories divided by the service category corresponding to the search keyword are input into the artificial intelligence model. The second prompt instruction will guide the artificial intelligence model to calculate the similarity between each service category divided by the service category corresponding to the search keyword and the search keyword, and then combine the indicator data of multiple service categories (such as service conversion rate, etc.) to determine the evaluation values of multiple service categories. For example, the higher the similarity and the higher the service conversion rate, the higher the corresponding evaluation value. Then sort the multiple service categories from high to low according to the evaluation value, and select at least one service category with a high ranking as the at least one service category corresponding to the search keyword. Accordingly, when generating the associated keywords corresponding to at least one service category, the service category can be compressed or supplemented according to the word limit of the associated keyword (such as no more than N Chinese characters) to generate the associated keywords corresponding to at least one service category.

[0066] It should be noted that the artificial intelligence model involved in this article can be a language model (LM) or a multimodal model (MM) based on artificial intelligence, etc. The embodiments of this application do not limit the number of model parameters supported by the model, and the goal is to meet actual needs. If the number of model parameters is relatively large, the scale of the language model will be relatively large and the model performance will be relatively better. Of course, more time and resources will be consumed during the inference or training process; if the number of model parameters is relatively small, the scale of the model will be relatively small. When the performance meets the requirements, the model is more lightweight and consumes relatively less time and resources during the inference or training process. The artificial intelligence model involved in the embodiments of this application can be a deep learning model used to process and generate natural language text or multimodal data, which can be implemented based on a neural network architecture and can be pre-trained on a large amount of data. In an alternative implementation, the artificial intelligence model involved in this article can include an encoder, a decoder, a self-attention layer, and a feed-forward neural network, etc. The encoder is mainly used to convert the input data (usually in the form of a sequence) into a vector representation, and this process can capture the semantic features of the input data. The decoder is responsible for converting the intermediate representation generated by the encoder into output data (usually in the form of a sequence). The self-attention layer is a mechanism that enables the model to focus on other positions in the sequence to better encode the information at the current position; the feed-forward neural network is used to perform non-linear transformations on the output of the self-attention layer, etc., to enhance the model's expressive ability. Each part works together, enabling the model constructed based on them to perform well in various complex processing tasks, such as natural language processing, computer vision, speech recognition, machine translation, text summarization, and intelligent question answering, etc.

[0067] S205: Send the object prompt information and interaction information of multiple first service objects to the client, so that the client can display the object prompt information of multiple first service objects on the first page and display the interaction prompt information generated based on the interaction information.

[0068] It should be noted that in this embodiment, the server may directly send the object prompt information and interaction information of the multiple first service objects to the client, and the client may generate the interaction prompt information based on the interaction information, and render the object prompt information and interaction prompt information of the multiple first service objects to the first page for display. Alternatively, the server may generate the interaction prompt information based on the interaction information, and render the object prompt information and interaction prompt information of the multiple first service objects to the first page. In this case, the server may send the rendered first page to the client, and the client may directly display the received first page.

[0069] Optionally, the interactive information in this embodiment may contain a large amount of content. Displaying all of the interactive information on the first page may obscure a large area of the object prompt information of the first service object, affecting the user's ability to view the object prompt information of the searched first service object. Therefore, this embodiment may streamline the interactive information to obtain interactive prompt information, and only display the generated interactive prompt information on the first page. Specifically, the interactive prompt information may be generated by extracting the top sentences from the interactive prompt information, or by summarizing the interactive prompt information. This is not limited to this.

[0070] Optionally, in this embodiment, the method of displaying object prompt information of multiple first service objects on the first page can be based on the degree of match between the object prompt information of each first service object and the search keyword, and rendering the object prompt information of multiple first objects in the first page in order from top to bottom and from left to right in the form of a list in descending order of matching degree. The method of displaying interactive prompt information on the first page can be to add the interactive prompt information to the first page that has rendered the object prompt information in the form of a pop-up box, floating window or card, in which case the interactive prompt information will cover part of the object prompt information. It can also be to render the interactive prompt information between the object prompt information positions of any two first objects in the list. There is no limitation on this.

[0071] For example, Figure 3a What is shown is the first page generated when the search keyword is house cleaning and its corresponding user search intention is a service query intention. At this time, 301 refers to the object prompt information of multiple first objects displayed in sequence in a list format on the first page, and 302 refers to the interactive prompt information displayed in a card format on the first page, that is, the first part of the pitfall avoidance guide and knowledge (i.e., interactive information) corresponding to house cleaning is displayed. Figure 3bWhat is shown is the first page generated when the search keyword is home appliance repair and the corresponding user search intention is fuzzy word class intention. At this time, 303 refers to the object prompt information of multiple first objects displayed in sequence in a list format on the first page, and 304 refers to the interactive prompt information displayed in a card format on the first page, that is, multiple related keywords corresponding to housekeeping and cleaning. Figure 3c What is shown is the first page generated when the search keyword is "the light is not on" and the corresponding user search intention is a problem consultation intention. At this time, 305 refers to the object prompt information of multiple first objects displayed in sequence in a list format on the first page, and 306 refers to the interactive prompt information displayed in a card format on the first page, that is, the operating instructions for the light not being on.

[0072] Optionally, when the user's search intent is fuzzy word class intent, when displaying multiple related keywords on the first page, the number of related keywords can be limited, and the multiple related keywords can be displayed in separate lines based on a preset number of lines (such as two lines). To attract user attention, additional display styles can be added, such as adding a hot label before the hot word, displaying it in the form of bubbles, etc.

[0073] In an embodiment of the present application, the server responds to a search request initiated by a client based on a search keyword, performs a search operation, determines multiple first service objects that match the search keyword, and also identifies the user's search intent based on the search keyword, and uses an artificial intelligence model to combine the user's intent and the search keyword to generate interactive information, and sends the object prompt information and interactive information of the multiple service objects to the client for display by the client. When providing search services to users based on search keywords with vague requirements or non-standard expressions, the solution of an embodiment of the present application not only displays the object prompt information of multiple first service objects that match the search operation, but also further identifies the user's search intent corresponding to the search keyword, and generates different interactive information for different user search intentions and displays it to the user. It can be achieved by using interactive information to assist users in clarifying their search needs, and then accurately matching the service objects they need among the multiple first service objects displayed on the client, so as to improve the service conversion rate.

[0074] In some embodiments, after the client displays the object prompt information of multiple first service objects and the interaction prompt information on the first page, if the user is interested in the displayed interaction prompt information, the user can be supported to trigger the interaction prompt information on the first page. At this time, the client will generate a corresponding operation request for the trigger operation of the interaction prompt information. Specifically, if the interaction prompt information displayed on the first page is generated based on the service purchase prompt information and / or service operation prompt information corresponding to the service query type intention, or is generated based on the solution corresponding to the question consultation type intention, at this time, the operation detected by the client for this interaction prompt information is the first trigger operation. Correspondingly, the operation request corresponding to the generated interaction prompt information is the first operation request. If the interaction prompt information displayed on the first page is generated based on the associated keywords corresponding to the fuzzy word type intention, at this time, the operation detected by the client for this interaction prompt information is the second trigger operation. Correspondingly, the operation request corresponding to the generated interaction prompt information is the second operation request. Next, these two situations will be introduced separately.

[0075] Situation 1: Receive the second operation request sent by the client for the interaction prompt information; the second operation request is generated by the client in response to the selection operation for at least one associated keyword. In response to the second operation request, determine the selected target associated keyword; based on the target associated keyword, re - execute the search operation to determine multiple second service objects that match the target associated keyword. Send the object prompt information of the multiple second service objects to the client, so that the client can update the first page to display the object prompt information of the multiple second service objects on the first page.

[0076] Specifically, since the second operation request is the operation of the user selecting any associated keyword in the interaction prompt information through the client, the client can send the second operation request to the server based on the associated keyword selected by the user. At this time, after receiving this second operation request, the server can use the associated keyword selected by the user as the target associated keyword, and then, based on the target associated keyword, in a similar manner to S202, search for multiple second service objects that match the target associated keyword and send them to the client, so that the client can replace the object prompt information of the multiple first objects currently displayed on the first page with the object prompt information of the multiple second service objects.

[0077] Optionally, after obtaining the target associated keyword in this embodiment, the server can also use the target associated keyword as the user's new search keyword and return to execute S202 and its subsequent operations.

[0078] Case 2: Receive a first operation request for interactive prompt information sent by the client; in response to the first operation request, filter at least one recommended object from multiple first service objects; send object prompt information of the at least one recommended object to the client, so that the client jumps from the first page to the second page, and displays the interactive information and the object prompt information of the at least one recommended object on the second page.

[0079] Specifically, the first operation request is an operation in which the user clicks on the interactive prompt information in the first page through the client. When the client sends the first operation request to the server, it means that the user is interested in the interactive prompt information displayed on the first page and wants to further view all the contents of the interactive information. At this time, in order to better assist the user in finding the required service object. This embodiment can further filter out at least one recommended object from multiple first service objects. Since the interactive information has been sent to the client, only the object prompt information of the at least one recommended object may be sent to the client at this time. After receiving the object prompt information of at least one recommended object, the client may render all the interactive information and the object prompt information of at least one recommended object to the second page, and then jump from the first page to the second page, and display the interactive information and the object prompt information of at least one recommended object through the second page.

[0080] For example, Figure 4 Shows the user clicking Figure 3a After asking the assistant, the client jumps to the second page. Among them, 401 refers to the interactive information displayed on the second page, that is, the pitfall avoidance guide and knowledge corresponding to the cleaning; 402 refers to the recommended objects displayed on the second page. Figure 4 The second page shown displays two recommended objects.

[0081] In some embodiments, the accuracy of the recommended object determination directly affects the conversion rate of subsequent services. Therefore, to improve the accuracy of the recommended object determination, the method of screening recommended objects from multiple first service objects in this embodiment may include: in response to the first operation request, determining the similarity between the object prompt information of the multiple first service objects and the search keyword, and determining the service distance between the service locations of the multiple first service objects and the user's location; and screening at least one recommended object from the multiple first service objects based on the similarity and service distance corresponding to the multiple first service objects.

[0082] The service location of the first service object may be the location of the service provider of the first service, and the user location may be the location where the user of the client initiating the search request wants to receive the service, for example, the user's current location or a location specified by the user.

[0083] Specifically, an implementation of this embodiment may be as follows: in response to a first operation request, based on the object prompt information, service locations, search keywords, and user location of multiple first service objects, a third prompt instruction is generated. Using this third prompt instruction, the artificial intelligence model is guided to infer the similarity between the object prompt information of multiple first service objects and the search keywords respectively, determine the service distance between the service locations of multiple first service objects and the user location, and based on the determined similarity and service distance corresponding to each of the multiple first service objects, sort the multiple first service objects, and select at least one service object with a higher ranking from the multiple first service objects as the recommended object.

[0084] Another implementation of this embodiment may be: in response to a first operation request, calculate the similarity between the object prompt information of multiple first service objects and the search keywords respectively, and determine the similarity scores of the multiple first service objects; for example, the higher the similarity, the higher the similarity score. Then calculate the service distance between the service locations of multiple first service objects and the user location respectively, and determine the distance scores of the multiple first service objects; for example, the closer the service distance, the higher the distance score. Furthermore, fuse (such as summing or weighted summing, etc.) the similarity scores and distance scores of each first service object to obtain the recommendation scores of each first service object, and use at least one service object with a higher ranking of the recommendation scores as the recommended object.

[0085] In some embodiments, when determining the service distance between the service locations of multiple first service objects and the user location, it may first be determined whether the search location sent by the user has been received. If the search location sent by the client has been received, use the search location as the user location, and determine the service distance between the service locations of multiple first service objects and the user location; if the search location sent by the client has not been received, obtain the user location, and determine the service distance between the service locations of multiple first service objects and the user location. Among them, obtaining the user location may further include: obtaining the positioning information sent by the client as the user location; or using the location corresponding to the Internet Protocol address of the client as the user location.

[0086] Specifically, when the user fills in the search keywords to trigger the search operation, in order to ensure the accuracy of the search results, the client will provide a search location selection item on the search page for the user to select. For example, the user is prompted to select the city or business district where the service is searched. If the user makes a selection in the search location selection item, the client will send the search location (i.e., the city or business district) selected by the user and the search keywords to the server for searching for the first service object.

[0087] Correspondingly, if the server has received the search location sent by the client, it can directly use this search location as the user location and determine the service distances between the service locations of multiple first service objects and the user location. If it has not received the search location sent by the client, it can further determine whether the user of this client has authorized the location information. If authorized, it obtains the location information of the client as the user location, and then determines the service distances between the service locations of multiple first service objects and the user location. If the location information has not been authorized, it can parse the regional location corresponding to the Internet Protocol (IP) address of the client as the user location corresponding to the client, and then determine the service distances between the service locations of multiple first service objects and the user location. This embodiment determines the user location corresponding to the client from multiple aspects based on the search area selected by the user, the location information authorized by the user, and the regional location corresponding to the client's IP address, improving the accuracy of user location determination and thus ensuring the accuracy of recommended object screening.

[0088] In some embodiments, when the user views the service object prompt information displayed on the first page or the second object through the client, if interested in a certain service object and wants to further consult the service provider about service-related information (such as service price or service content), the user can click on the consultation component in the service object prompt information, such as Figures 3a - 3c the phone consultation button in any of the service object prompt information in, to trigger a consultation operation. When the client detects the triggered consultation operation by the user, it sends a consultation request to the server based on the object identifier of the service object it wants to consult. The server responds to the received consultation request and establishes a communication connection between the client and the service provider so that the user can conduct further consultation and communication with the service provider through the client.

[0089] At this time, to prevent a series of bad phenomena such as the service provider arbitrarily raising prices and the lack of transparency in service content and service fees from occurring frequently, the server in this embodiment can also perform the following steps:

[0090] Step 1: Receive the consultation request sent by the client for any service object on the first page; the consultation request includes the object identifier of the service object.

[0091] Among them, the consultation request can be a request triggered by the user when they want to consult the provider of a certain service object for more relevant information about the service object (such as price or service content, etc.). This consultation request can be a phone consultation request or an online voice or text chat consultation request. The consultation request includes the object identifier.

[0092] In this embodiment, when a user views a service object through a client, if there is a need to consult about the service object, the user can trigger a consultation operation based on the consultation service operation component on the list display page or the detail display page. After the client detects the consultation operation triggered by the user, a consultation request will be generated based on the service object corresponding to the consultation operation, such as the object identifier of the service object, and the generated consultation request will be sent to the server. Correspondingly, the server will receive the consultation request sent by the client.

[0093] Step 2: Determine the service type of the service object corresponding to the object identifier.

[0094] Among them, the service type can be obtained by classifying various services provided by the system according to factors such as service nature, characteristics, and functions. There are multiple service objects corresponding to each service type. For example, when the service type is cleaning, the corresponding service objects can include: daily cleaning, deep cleaning, cleaning the range hood, and cleaning the glass, etc.

[0095] Optionally, the server will, in response to the received consultation request, obtain the object identifier included in the consultation request, and then determine the service type of the service object corresponding to the object identifier based on the mapping relationship between the object identifier and the service type. It is also possible to infer the service type of the corresponding service object through an artificial intelligence model combined with the object identifier. It can also be determined by other means, which is not limited herein.

[0096] Since the consultation request in this embodiment is a request triggered by the user wanting to communicate with the provider of the service object, after the server receives the consultation request and determines the object identifier, it will also determine the service provider corresponding to the object identifier, and establish a communication connection between the client and the service provider, so that the user can conduct further consultation and communication with the service provider through the client. For example, it can be to call the service provider's phone number through the terminal where the client is located, so that the user can communicate with the service provider by phone. It can also be to provide an interactive page for the user to communicate with the provider by voice or text through this interactive page.

[0097] Step 3: Generate an artificial intelligence prompt instruction for obtaining service-related information corresponding to the service type;

[0098] Among them, the service-related information is used as reference information to compare with the service price and / or service content of the service object. The artificial intelligence prompt instruction is an instruction that can guide the artificial intelligence model to perform reasoning operations. For example, it can be a promt instruction. The artificial intelligence prompt instruction is used for the artificial intelligence model to infer the service-related information corresponding to the service type.

[0099] This embodiment may generate an artificial intelligence prompt instruction for obtaining the service price and / or service content corresponding to the service type. Specifically, it may select at least one comparison item from the service price and service content for comparison of service-related information, or it may analyze the consultation dialogue between the client and the provider and use the client's consultation information (such as at least one comparison item in the service price and service content) for comparison of service-related information.

[0100] When generating an AI prompt, the AI prompt can be generated based on the service type and in conjunction with a prompt model. For example, the AI prompt can be generated by adding the service type corresponding to the object identifier to the prompt template. Alternatively, the AI prompt can be generated based on the service type and comparison items corresponding to the service-related information, in conjunction with the prompt template. For example, the AI prompt can be generated by adding the service type corresponding to the object identifier and comparison items corresponding to the service-related information to the prompt template.

[0101] Optionally, after the server generates the artificial intelligence prompt instruction, if a callable artificial intelligence model is deployed on the server side, the server can directly input the artificial intelligence prompt instruction into its callable artificial intelligence model to use the artificial intelligence model to infer the service-related information corresponding to the service type, and directly send the service-related information to the client for the client to display the service-related information.

[0102] If no callable artificial intelligence model is deployed on the server side, the server can generate service comparison prompt information based on the artificial intelligence prompt instruction, and send the service comparison prompt information to the client, so that the client can display the service comparison prompt information on the first page, receive the instruction acquisition request sent by the client, and send the artificial intelligence prompt instruction to the client. The artificial intelligence prompt instruction is used to input into the artificial intelligence model to use the artificial intelligence model to infer service-related information corresponding to the service type.

[0103] The service comparison prompt information may be a prompt information for prompting the user to obtain an artificial intelligence prompt instruction. For example, it may be "Hi customer, click to copy the instruction to go to the artificial intelligence model, check the market price of [land reclamation and cleaning] in seconds, and easily avoid scams. Click to copy the price comparison instruction."

[0104] The first page can be the page on the client displaying service comparison prompt information. Optionally, the first page can be a newly generated page for displaying service comparison prompt information. It can also be the client's currently displayed page. For example, if the client triggers a consultation operation based on a list display page, the first page at this time can be the list display page. If the client triggers a consultation operation based on a detail display page, the first page at this time can be the detail display page.

[0105] Among them, the instruction acquisition request is generated by the client in response to the information acquisition operation triggered by the service comparison prompt information, and is used to request the acquisition of the artificial intelligence prompt instruction generated by S203. At this time, the information acquisition operation can be clicking on the position of the service comparison prompt information on the first page, or clicking on the corresponding icon at the service comparison prompt information in the first page.

[0106] Specifically, the server can pre-set a prompt template. At the corresponding position of the service type in the prompt template, fill in the service type corresponding to the object identifier, and then link the generated artificial intelligence prompt instruction to obtain the service comparison prompt information. Then it is sent to the client. If the first page is a newly generated page, at this time the client will render the received service comparison prompt information into a new page (i.e., the first page), and then jump from the current page to the first page to display the service comparison prompt information. If the first page is the current page, at this time the client can directly add the service comparison prompt information on the current page in the form of a floating window, a pop-up window, a card, etc., and display the first page after adding the service comparison prompt information by refreshing the first page. The user clicks on the corresponding position of the service comparison prompt information in the first page through the client, thereby triggering the information acquisition operation. The client will respond to this information acquisition operation, generate an instruction acquisition request, and send the generated instruction acquisition request to the server. Correspondingly, the server will receive and respond to this instruction acquisition request, and send the artificial intelligence prompt instruction to the client.

[0107] After the client receives the artificial intelligence instruction, if there is a callable artificial intelligence model locally on the client, at this time the client can call the artificial intelligence model, infer the service-related information corresponding to the service type based on the artificial intelligence prompt instruction, and then jump from the first page to the second page, and display the service-related information in the second page. Specifically, it can directly call the artificial intelligence model, input the received artificial intelligence instruction into the artificial intelligence model, run the artificial intelligence model to infer the service-related information corresponding to the service type, and then render the service-related information into the second page, and then jump from the first page to the second page, and display the service-related information corresponding to the inferred service type in the second page.

[0108] If there is no callable artificial intelligence model on the client side locally, the client will save the artificial intelligence prompt instruction to the local clipboard at this time; the artificial intelligence instruction is used to be pasted from the clipboard to the target position in response to the acquisition operation. Specifically, the received artificial intelligence prompt instruction can be saved in the local clipboard of the client for the user to paste the artificial intelligence instruction from the clipboard into a third-party application with an artificial intelligence model. The artificial intelligence model in the third-party application infers the service-related information corresponding to the service type based on the pasted artificial intelligence instruction, and then displays the service-related information corresponding to the inferred service type through the display page of the third-party application.

[0109] After receiving the consultation request containing the object identifier sent by the client in this embodiment, the server determines the service type of the service object corresponding to the object identifier, generates an artificial intelligence prompt instruction for the service-related information corresponding to the service type, and then generates service comparison prompt information corresponding to the artificial intelligence prompt instruction, and sends it to the client, and the client displays the service comparison prompt information on the first page. After receiving the instruction acquisition request sent by the client based on the service comparison prompt information, the artificial intelligence prompt instruction is sent to the client again. The artificial intelligence prompt instruction is used to be input into the artificial intelligence model to infer the service-related information corresponding to the service type. In the process of the user consulting the service-related information of the service object through the client in the solution of this application embodiment, the server interacts with the client to display the service comparison prompt information for the user to independently select whether to view the specific service-related information. If needed, then use the artificial intelligence model to infer the corresponding service-related information based on the artificial intelligence prompt instruction for the user to compare with the service-related information of the consulted service object, such as service price and / or service content, to avoid losses caused to the user due to the chaos of the market order, thereby improving the credibility of the network service system.

[0110] In some embodiments, in order to further improve the accuracy of the model in inferring service-related information. When generating the artificial intelligence prompt instruction for obtaining the service-related information corresponding to the service type in this embodiment, it can be to determine the user location corresponding to the client; according to the service type of the service object and the user location, generate the artificial intelligence prompt instruction for the service-related information corresponding to the service type.

[0111] Optionally, when determining the user location corresponding to the client in this embodiment, it can be to first determine whether a search location sent by the user is received. If the search location sent by the client has been received, the search location is used as the user location corresponding to the client; if the search location sent by the client has not been received, the location information of the client or the location corresponding to the Internet protocol address of the client is used as the user location corresponding to the client.

[0112] Specifically, when a user fills in a search keyword to trigger a search operation, to ensure the accuracy of search results, the client will provide a search location selection option on the search page for the user to choose. For example, the user is prompted to select the city or business district where the search service is located. If the user makes a selection in the search location selection option, the client will use the location selected by the user (i.e., the city or business district) as the user's search location and send it to the server together with the search keyword for searching for service objects. Correspondingly, when the server determines the user location corresponding to the client, if it has received the search location sent by the client, it can directly use this search location as the user location corresponding to the client. If it has not received the search location sent by the client, it can further determine whether the user of this client has authorized the location information. If authorized, it obtains the location information of the client as the user location corresponding to the client. If the location information has not been authorized, it can parse the regional location corresponding to the Internet Protocol (IP) address of the client as the user location corresponding to the client.

[0113] This embodiment determines the user location corresponding to the client from multiple aspects based on the search area selected by the user, the location information authorized by the user, and the regional location corresponding to the client's IP address, improving the accuracy of user location determination and thus ensuring the accuracy of the subsequent generated service-related information.

[0114] Optionally, after the server determines the user location corresponding to the client, it can generate an artificial intelligence prompt instruction according to the service type and the user location, in combination with the prompt instruction model. For example, it can add the service type corresponding to the object identifier and the user location to the prompt instruction template to obtain the artificial intelligence prompt instruction. It can also generate an artificial intelligence prompt instruction according to the service type, the comparison item corresponding to the service-related information, and the determined user location, in combination with the prompt instruction template. For example, adding the service type corresponding to the object identifier, the comparison item corresponding to the service-related information, and the user location to the prompt instruction template can obtain the artificial intelligence prompt instruction.

[0115] In some embodiments, during the process of searching for services, the user may frequently trigger consultation requests through the client. To avoid frequently displaying service comparison prompt information to the user and affecting the user experience. In this embodiment, when generating the artificial intelligence prompt instruction for obtaining the service-related information corresponding to the service type, a further judgment can be made first. If the service object meets the prompt requirements, an artificial intelligence prompt instruction for obtaining the service-related information corresponding to the service type is generated.

[0116] Specifically, the methods for determining that the service object meets the prompt requirements in this embodiment may include:

[0117] Method 1: The consultation request is the first consultation request sent by the client for the service object. For this method, the server can determine whether it has ever received a consultation request containing the object identifier. If not, it is determined that the service object meets the prompt requirements.

[0118] Method 2: The consultation request is the first consultation request sent by the client for the search result page where the service object is located. At this time, the first page is the search result page. It should be noted that the search result page at this time can be the object list display page where the service object is located. The object list display page is used to display the object information of multiple service objects determined based on the search keywords, and the object identifier included in the consultation request in this embodiment belongs to the identifier of one of the multiple service objects found. For this method, the server can first determine the search result page corresponding to the object identifier, and then further determine whether the received consultation request at this time is the first consultation request triggered through the search result page. If so, it is determined that the service object meets the prompt requirements.

[0119] It should be noted that after determining that the service object meets the prompt requirements, the method of generating the artificial intelligence prompt instruction is similar to the method introduced in the foregoing embodiments and will not be elaborated here.

[0120] Then, the generated service comparison prompt information is sent to the client so that the client can display the service comparison prompt information in the first page in the form of a floating layer, a prompt pop-up window, a card, etc. The user clicks on the corresponding position of the service comparison prompt information in the first page through the client, thereby triggering an information acquisition operation. The client will respond to this information acquisition operation, generate an instruction acquisition request, and send the generated instruction acquisition request to the server. The server will then send the artificial intelligence prompt instruction to the client. At this time, if there is a callable artificial intelligence model on the client side, the artificial intelligence model can be directly called, and the received artificial intelligence instruction is input into the artificial intelligence model to run the artificial intelligence model to infer the service-related information corresponding to the service type, and then jump from the first page to the third page, and display the service-related information corresponding to the inferred service type in the third page. If there is no callable artificial intelligence model on the client side, at this time, the client can save the received artificial intelligence prompt instruction locally on the client side for the user to paste the artificial intelligence instruction into a third-party application program with an artificial intelligence model. The artificial intelligence model in the third-party application program infers the service-related information corresponding to the service type based on the pasted artificial intelligence instruction, and then displays the service-related information corresponding to the inferred service type through the display page of the third-party application program.

[0121] During the process that the user consults the service-related information of the service object through the client to the provider, the server interacts with the client to display service comparison prompt information to the user for the user to independently select whether to view the specific service-related information. If needed, then use the artificial intelligence model to infer the corresponding service-related information based on the artificial intelligence prompt instruction for the user to compare with the service-related information of the consulted service object, such as service price and / or service content, to avoid losses caused to the user due to the chaos of the market order, thereby improving the credibility of the network service system.

[0122] Figure 5 It is a flowchart of an information display method provided for an exemplary embodiment of the present application. The technical solution of this embodiment can be executed by the client, and the client can be a client in an online service system that provides services such as searching, consulting, and placing orders for service objects. The method may include the following steps:

[0123] S501: In response to a search operation, determine a search keyword.

[0124] S502: Send a search request to the server based on the search keyword so that the server performs a search operation to determine multiple first service objects that match the search keyword; based on the search keyword, identify the user's search intention, and use the artificial intelligence model to combine the user's search intention and the search keyword to generate interaction information.

[0125] S503: Receive the object prompt information and interaction prompt information of multiple first service objects sent by the server.

[0126] S504: Determine the interaction prompt information based on the interaction generation information.

[0127] S505: Display the object prompt information of multiple service objects and the interaction prompt information on the first page.

[0128] In some embodiments, the client detects a first trigger operation for the interaction prompt information, generates a first operation request for the interaction prompt information; sends the first operation request to the server; receives the object prompt information of at least one recommended object fed back by the server in response to the first operation request; wherein, the at least one recommended object is screened from the multiple first service objects; jumps from the first page to the second page, and displays the interaction information and the object prompt information of at least one recommended object on the second page.

[0129] In some embodiments, the client may also, in response to a consultation operation for a service object, obtain the object identifier of the service object; based on the object identifier of the service object, send a consultation request to the server, so that the server determines the service type of the service object corresponding to the object identifier, generates an artificial intelligence prompt instruction for obtaining service-related information corresponding to the service type, and generates service comparison prompt information based on the artificial intelligence prompt instruction; receive the service comparison prompt information sent by the server; display the service comparison prompt information on a first page to prompt the user to obtain the artificial intelligence prompt instruction; in response to an information acquisition operation triggered by the service comparison prompt information, send an instruction acquisition request to the server; receive the artificial intelligence prompt instruction sent by the server in response to the instruction acquisition request, and the artificial intelligence prompt instruction is used to be input into an artificial intelligence model to infer and obtain service-related information corresponding to the service type by using the artificial intelligence model.

[0130] In some embodiments, if there is no callable artificial intelligence model deployed locally on the client, after the client receives the artificial intelligence prompt instruction sent by the server in response to the instruction acquisition request, it further includes: saving the artificial intelligence prompt instruction to the local clipboard; the artificial intelligence instruction is used to be pasted from the clipboard to a target location in response to an acquisition operation. An artificial intelligence model is deployed at the target location, so the artificial intelligence instruction can be used to guide the artificial intelligence model to infer and display service-related information corresponding to the service type at the target location.

[0131] In some embodiments, if there is a callable artificial intelligence model deployed locally on the client, after the client receives the artificial intelligence prompt instruction sent by the server in response to the instruction acquisition request, it further includes: calling the artificial intelligence model to infer and obtain service-related information corresponding to the service type based on the artificial intelligence prompt instruction; jumping from the first page to the second page and displaying the service-related information on the second page.

[0132] In some embodiments, since the service-related information in this embodiment is used as reference information for comparing service comparison prompt information with the service price and / or service content of the service object. To avoid the situation of invalidly prompting the user, for example, not getting through to the consultation phone with the service provider and directly exiting to select other service objects to initiate a consultation request, etc. When the client in this embodiment displays the service comparison prompt information on the first page, it can be that if it is detected that the time interval from the current moment to the trigger moment of the consultation operation exceeds the first time threshold, the service comparison prompt information is displayed on the first page. Specifically, the client can start timing after receiving the consultation operation for the service object, and after reaching the first time threshold (such as 8 seconds) and receiving the service comparison prompt information sent by the server, it executes the operation of displaying the service comparison prompt information on the first page. Among them, the setting of the first time threshold can be determined by combining the waiting times of a large number of users to establish calls with the provider, in order to display the service comparison information only when the user successfully talks with the provider.

[0133] In some embodiments, the display of the service comparison prompt information on the first page in this embodiment includes: generating a prompt pop-up window containing the service comparison prompt information; and displaying the prompt pop-up window on the first page. Specifically, after the server generates the prompt pop-up window containing the service comparison prompt information, it can add the prompt pop-up window at a preset position (such as the middle of the page) on the first page, and the user can adjust the display position of the prompt pop-up window according to the need.

[0134] Correspondingly, at this time, in order to avoid causing consultation interference to the user by continuously displaying the service comparison prompt information for a long time. This embodiment can also, after displaying the prompt pop-up window on the first page, detect in real time whether the closing requirement is met, and if so, cancel the display of the prompt pop-up window on the first page. Optionally, it can be that if no selection operation for the service comparison prompt information is detected within the second time threshold, or a closing operation of the prompt pop-up window is detected, the display of the prompt pop-up window on the first page is cancelled. Specifically, one implementable way can be: after displaying the prompt pop-up window on the first page, start timing, and if the second time threshold (such as 5 seconds) is reached and the user has not triggered a selection operation for the service comparison prompt information, it can be determined at this time that the user has no need to view the service-related information, and at this time, the display of the prompt pop-up window on the first page can be cancelled. Another implementable way can be that when a closing operation of the prompt pop-up window by the user is detected, for example, clicking the close button on the prompt pop-up window, it indicates that the user has no need to view the service-related information, and at this time, the display of the prompt pop-up window on the first page can be cancelled. It is also possible to start the judgment of the above two methods simultaneously, and if one of them is met, it can be determined that the user has no need to view the service-related information, and at this time, the display of the prompt pop-up window on the first page can be cancelled.

[0135] It should be noted that the process and beneficial effects of the client in this embodiment implementing the above information display method have been introduced in the above embodiments and will not be elaborated here.

[0136] In a practical application, the technical solution of the embodiment of the present application can be applied to an online service trading scenario. The service provider is the merchant providing the service, the service object is the service provided by the merchant, and the user is the consumer. The merchant can search for and display services for the user with the help of the network service system. Taking the online service trading scenario as an example, the technical solution of the embodiment of the present application will be introduced below.

[0137] As Figure 6 shown, the user can input a search keyword through the service search page provided by the client, click the search button to trigger a search operation. The client responds to the search operation, determines the search keyword, and sends a search request to the server based on the search keyword. The server receives the search request sent by the client (step 601), performs a search operation to determine a plurality of first service objects that match the search keyword, and identifies the user's search intention based on the search keyword by means of circle word / included word rules recognition, model recognition, self-built thesaurus recognition, etc. (steps 602 - 603). The identified user search intention may include: service query type intention under standard requirements, problem consultation type requirements under standard requirements, fuzzy word type intention under general requirements, and non-the above intentions (steps 604 - step 607).

[0138] For service query type intentions, the server will use an artificial intelligence model to generate a service selection guide corresponding to the search keyword, and send the service selection guide and the object prompt information of the plurality of first service objects to the client for the client to display the plurality of object prompt information and the service selection guide card on the first page, that is, the list page (step 608). At this time, if the user triggers the service selection guide card, the client will interact with the server to obtain the recommended objects screened by the server, and then jump from the first page to the second page (i.e., the landing page entered after the user clicks), and display the service selection guide and the object prompt information of the recommended objects on the landing page (step 612).

[0139] For fuzzy word type requirements, the server will use an artificial intelligence model to generate a refined search term guidance card corresponding to the search keyword, and send the refined search term guidance card and the object prompt information of the plurality of first service objects to the client for the client to display the plurality of object prompt information and the refined search term guidance card on the first page, that is, the list page (step 609). At this time, if the user triggers the refined search term guidance card, the client will send a new search request to the server (step 613). At this time, the server will return to perform the operation of 601 again.

[0140] For question consultation intents, the server will use an artificial intelligence model to generate common sense popular science knowledge corresponding to the search keywords, and send the common sense popular science knowledge and the object prompt information of multiple first service objects to the client for the client to display the multiple object prompt information and common sense popular science cards on the first page, that is, the list page (step 610). At this time, if the user triggers the common sense popular science card, the client will interact with the server to obtain the recommended objects screened by the server, and then jump from the first page to the second page (i.e., the landing page entered after the user clicks), and display the common sense popular science knowledge and the object prompt information of the recommended objects on the landing page (step 614).

[0141] For non - the above - mentioned intents, the server will send the object prompt information of multiple first service objects to the client for the client to display the multiple object prompt information on the first page, that is, the list page, and at this time, the AI search card is not displayed (step 611).

[0142] The detailed implementation manners and beneficial effects of each step in the method of this embodiment have been described in detail in the foregoing embodiments, and will not be elaborated herein.

[0143] It should be noted that in some of the processes described in the above embodiments and the accompanying drawings, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The operation numbers such as 202 and 203 are only used to distinguish different operations, and the 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 such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0144] In addition to providing method embodiments, the embodiments of the present application also provide an information search device. The process of the information search device provided by the embodiments of the present application will be described below.

[0145] Figure 7A structural schematic diagram of an information search device provided for an exemplary embodiment of the present application. The device is configured on a server side and includes: a first receiving module 701, configured to receive a search request sent by a client; the search request includes a search keyword; an object search module 702, configured to perform a search operation to determine a plurality of first service objects that match the search keyword; an intention recognition module 703, configured to recognize a user's search intention based on the search keyword; a first information generation module 704, configured to generate interaction information by using an artificial intelligence model in combination with the user's search intention and the search keyword; a first sending module 705, configured to send object prompt information of the plurality of first service objects and the interaction information to the client, so that the client can display the object prompt information of the plurality of first service objects and display interaction prompt information generated based on the interaction information on a first page.

[0146] In an alternative embodiment, the first receiving module 701 is further configured to receive a first operation request sent by the client for the interaction prompt information; an object screening module, configured to, in response to the first operation request, screen at least one recommended object from the plurality of first service objects; the first sending module 705 is further configured to send object prompt information of the at least one recommended object to the client, so that the client can jump from the first page to a second page and display the interaction information and the object prompt information of the at least one recommended object on the second page.

[0147] In an alternative embodiment, the object screening module is configured to, in response to the first operation request, determine the similarity between the object prompt information of the plurality of first service objects and the search keyword respectively, and determine the service distance between the service locations of the plurality of first service objects and the user location; and screen at least one recommended object from the plurality of first service objects according to the similarity and service distance respectively corresponding to the plurality of first service objects.

[0148] In an alternative embodiment, when the object screening module determines the service distance between the service locations of the plurality of first service objects and the user location, it is specifically configured to: if the search location sent by the client has been received, use the search location as the user location and determine the service distance between the service locations of the plurality of first service objects and the user location; if the search location sent by the client has not been received, obtain the user location and determine the service distance between the service locations of the plurality of first service objects and the user location.

[0149] In an optional embodiment, when obtaining the user location, the object screening module is specifically configured to obtain the positioning information sent by the client as the user location; or use the location corresponding to the Internet Protocol address of the client as the user location.

[0150] In an optional embodiment, the interaction information includes at least one associated keyword; the first receiving module 701 is further configured to receive a second operation request for the interaction prompt information sent by the client; the second operation request is generated by the client in response to a selection operation for the at least one associated keyword; the object search module 702 is further configured to, in response to the second operation request, determine the selected target associated keyword; re-execute a search operation based on the target associated keyword to determine a plurality of second service objects matching the target associated keyword; the first sending module 705 is further configured to send the object prompt information of the plurality of second service objects to the client, so that the client updates the first page to display the object prompt information of the plurality of second service objects on the first page.

[0151] In an optional embodiment, the intent recognition module 703 is further configured to perform at least one of the following: determine the user search intent according to the hit degree of the search keyword in various intent determination rules; use the artificial intelligence model in combination with the search keyword to identify the user search intent; determine the user search intent based on the similarity between each intent word in the preset word library and the search keyword.

[0152] In an optional embodiment, if the intent recognition module 703 identifies multiple user search intents based on the search keyword, it is further configured to determine the final user search intent according to the priorities of the identified multiple user search intents.

[0153] In an optional embodiment, if the user search intent is a service query type intent, the first information generation module 704 is based on using an artificial intelligence model to generate service purchase prompt information and / or service operation prompt information corresponding to the search keyword; if the search intent is a problem consultation type intent, use the artificial intelligence model to generate a solution corresponding to the search keyword; if the search intent is a fuzzy word type intent, use the artificial intelligence model to determine at least one service category for the service category division corresponding to the search keyword, and generate an associated keyword corresponding to each of the at least one service category.

[0154] In an alternative embodiment, when the first information generation module 704 executes to determine at least one service category corresponding to the service category division of the search keyword by using an artificial intelligence model, it is specifically configured to use the artificial intelligence model to respectively determine the similarity between multiple service categories corresponding to the service category division of the search keyword and the search keyword, and determine at least one service category corresponding to the search keyword according to the similarities corresponding to the multiple service categories and the index data of the multiple service categories.

[0155] In an alternative embodiment, the first receiving module 701 is further configured to receive a consultation request sent by the client for any service object in the first page; the consultation request includes the object identifier of the service object; the service type determination module is configured to determine the service type of the service object corresponding to the object identifier; the prompt instruction generation module is configured to generate an artificial intelligence prompt instruction for obtaining service-related information corresponding to the service type; the artificial intelligence prompt instruction is used for the artificial intelligence model to infer the service-related information corresponding to the service type.

[0156] Figure 7 The information search device described above can execute Figure 2 the information search method described in the foregoing embodiments, and its implementation principle and technical effects will not be elaborated further. For the information search device in the above embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0157] In addition to providing method embodiments, the embodiments of the present application also provide an information display device. The process of the information display device provided by the embodiments of the present application will be described below.

[0158] Figure 8 FIG. is a schematic structural diagram of an information display device provided for an exemplary embodiment of the present application. The device is configured in a client and includes: a keyword determination module 801, configured to determine a search keyword in response to a search operation; a second sending module 802, configured to send a search request to a server based on the search keyword, so that the server performs a search operation to determine multiple first service objects matching the search keyword; based on the search keyword, identify the user's search intention, and generate interaction information by using an artificial intelligence model in combination with the user's search intention and the search keyword; a second receiving module 803, configured to receive the object prompt information and the interaction prompt information of the multiple first service objects sent by the server; a second information generation module 804, configured to determine the interaction prompt information based on the interaction generation information; a display module 805, configured to display the object prompt information of the multiple service objects and the interaction prompt information on a first page.

[0159] In an optional embodiment, the apparatus further includes: a request generation module, configured to detect a first trigger operation for the interaction prompt information and generate a first operation request for the interaction prompt information; the second sending module 802 is further configured to send the first operation request to the server; the second receiving module 803 is further configured to receive object prompt information of at least one recommended object fed back by the server in response to the first operation request; wherein, the at least one recommended object is screened from the multiple first service objects; the display module 805 is further configured to jump from the first page to a second page and display the interaction information and the object prompt information of at least one recommended object on the second page.

[0160] Figure 8 The information display device described above can execute Figure 5 The information display method described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated further. For the information display device in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0161] Figure 9 FIG. is a schematic structural diagram of an embodiment of a computing device provided by the present application. As Figure 9 shown, in practice, the computing device may include: a storage component 901 and a processing component 902.

[0162] The storage component 901 is configured to store computer programs and can be configured to store various other data to support operations on the computing device. Examples of such data include instructions for any application program or method for operating on the computing device, data structures, contact data, phone book data, messages, pictures, videos, etc.

[0163] The processing component 902 is coupled to the storage component 901 and is configured to execute the computer programs in the storage component 901 to implement the information search method as Figure 2 shown, or to implement the information display method as Figure 5 shown.

[0164] Further, as Figure 9 shown, the computing device may further include: other components such as a communication component 903, a display component 904, a power supply component 905, an audio component 906, etc. Figure 9 Only some components are schematically shown, and it does not mean that the computing device only includes Figure 9 the components shown. Additionally, Figure 9The components within the dashed-line box are optional components, rather than mandatory components, and are specifically determined by the product form of the specific computing device. The computing device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT (Internet of Things) device, or can also be a server device such as a conventional server, a cloud server, or a server array. If the computing device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, etc., it may include Figure 9 the components within the dashed-line box; if the computing device of this embodiment is implemented as a server device such as a conventional server, a cloud server, or a server array, it may not include Figure 9 the components within the dashed-line box.

[0165] The above processing component includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can 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 for executing the above method.

[0166] The above 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, a magnetic disk, or an optical disk.

[0167] The above communication component is configured to facilitate communication between the device where the communication component is located and other devices in a wired or wireless manner. The device where the communication component is located can access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.

[0168] The above display component may include a screen, and the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation.

[0169] The above power supply component supplies power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.

[0170] The above audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signals can be further stored in the memory or transmitted via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals.

[0171] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to be able to implement the steps in the above method embodiments. Among them, the computer-readable storage medium can be implemented by a volatile or non-volatile or a combination thereof, and can be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, Phase-change Random Access Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), flash memory or other memory technologies, Compact Disc Read-Only Memory (CD-ROM), Digital Video Disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium

[0172] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the processor is enabled to implement each step in the above method embodiments. It should be understood that each process or a combination of multiple processes in the above method flow can be implemented by the computer program or instructions. In addition, these computer programs or instructions can be applied to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices, so that the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices can be used as devices to implement the corresponding functions in the above method embodiments.

[0173] 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 foregoing method embodiments, and will not be elaborated herein.

[0174] It should also be noted that the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity, or device including the element.

[0175] Finally, it should be noted that the above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An information search method, characterized in that, Applied to the server side, including: Receiving a search request sent by a client; the search request includes a search keyword; Performing a search operation to determine a plurality of first service objects that match the search keyword; Identifying the user's search intent based on the search keyword; Using an artificial intelligence model to generate interaction information in combination with the user's search intent and the search keyword; Sending the object prompt information of the plurality of first service objects and the interaction information to the client, so that the client can display the object prompt information of the plurality of first service objects and the interaction prompt information generated based on the interaction information on the first page.

2. The method according to claim 1, wherein It also includes: Receiving a first operation request sent by the client for the interaction prompt information; In response to the first operation request, screening at least one recommended object from the plurality of first service objects; Sending the object prompt information of the at least one recommended object to the client, so that the client can jump from the first page to the second page and display the interaction information and the object prompt information of the at least one recommended object on the second page.

3. The method according to claim 2, characterized in that, The screening of at least one recommended object from the plurality of first service objects in response to the first operation request includes: In response to the first operation request, determining the similarity between the object prompt information of the plurality of first service objects and the search keyword respectively, and determining the service distance between the service locations of the plurality of first service objects relative to the user location; Screening at least one recommended object from the plurality of first service objects according to the similarity and service distance corresponding to the plurality of first service objects respectively.

4. The method according to claim 3, characterized in that, The determining of the service distance between the service locations of the plurality of first service objects relative to the user location includes: If the search location sent by the client has been received, using the search location as the user location and determining the service distance between the service locations of the plurality of first service objects relative to the user location; If the search location sent by the client has not been received, obtaining the user location and determining the service distance between the service locations of the plurality of first service objects relative to the user location.

5. The method according to claim 4, wherein The obtaining of the user location includes: Obtaining the positioning information sent by the client as the user location; or, Using the location corresponding to the Internet Protocol address of the client as the user location.

6. The method according to claim 1, wherein The interaction information includes at least one associated keyword; the method also includes: Receiving a second operation request sent by the client for the interaction prompt information; the second operation request is generated by the client in response to a selection operation for the at least one associated keyword; In response to the second operation request, determining the selected target associated keyword; Based on the target associated keyword, re-performing a search operation to determine a plurality of second service objects that match the target associated keyword; Sending the object prompt information of the plurality of second service objects to the client, so that the client can update the first page to display the object prompt information of the plurality of second service objects on the first page.

7. The method according to claim 1, characterized in that, Based on the search keywords, identifying the user's search intent includes at least one of the following: Determining the user's search intent according to the hit degree of the search keywords in various intent determination rules; Using the artificial intelligence model in combination with the search keywords to identify the user's search intent; Determining the user's search intent based on the similarity between each intent word in the preset word library and the search keywords.

8. The method according to claim 7, wherein It also includes: If multiple user search intents are identified based on the search keywords, determining the final user search intent according to the priorities of the identified multiple user search intents.

9. The method according to claim 1, characterized in that, Using the artificial intelligence model in combination with the user's search intent and the search keywords to generate interaction information includes: If the user's search intent is a service query type intent, using the artificial intelligence model to generate service purchase prompt information and / or service operation prompt information corresponding to the search keywords; If the search intent is a question consultation type intent, using the artificial intelligence model to generate a solution corresponding to the search keywords; If the search intent is a fuzzy word type intent, using the artificial intelligence model to determine at least one service category for the service category division corresponding to the search keywords, and generating associated keywords corresponding to each of the at least one service category.

10. The method according to claim 9, wherein Using the artificial intelligence model to determine at least one service category for the service category division corresponding to the search keywords includes: Using the artificial intelligence model to respectively determine the similarity between multiple service categories for the service category division corresponding to the search keywords and the search keywords, and determining at least one service category corresponding to the search keywords according to the similarities corresponding to the multiple service categories and the index data of the multiple service categories.

11. The method according to claim 1, characterized in that, It also includes: Receiving a consultation request sent by the client for any service object in the first page; The consultation request includes the object identifier of the service object; Determining the service type of the service object corresponding to the object identifier; Generating an artificial intelligence prompt instruction for obtaining service-related information corresponding to the service type; the artificial intelligence prompt instruction is used for the artificial intelligence model to infer the service-related information corresponding to the service type.

12. An information display method, characterized in that, Applied to the client, it includes: In response to a search operation, determining the search keywords; Sending a search request to the server based on the search keywords, so that the server performs a search operation to determine multiple first service objects matching the search keywords; based on the search keywords, identifying the user's search intent, and using the artificial intelligence model in combination with the user's search intent and the search keywords to generate interaction information; Receiving the object prompt information of the multiple first service objects and the interaction prompt information sent by the server; Determining the interaction prompt information based on the interaction generation information; Displaying the object prompt information of the multiple service objects and the interaction prompt information on the first page.

13. The method according to claim 12, wherein It also includes: Detecting a first trigger operation on the interaction prompt information, and generating a first operation request for the interaction prompt information; Sending the first operation request to the server; Receive the object prompt information of at least one recommended object feedback by the server in response to the first operation request; wherein, the at least one recommended object is screened from the multiple first service objects; Jump from the first page to the second page, and display the interaction information and the object prompt information of at least one recommended object on the second page.

14. An information search device, characterized in that, Configured on the server, including: A first receiving module, configured to receive a search request sent by the client; the search request includes a search keyword; An object search module, configured to perform a search operation to determine multiple first service objects that match the search keyword; An intention recognition module, configured to recognize the user's search intention based on the search keyword; A first information generation module, configured to use an artificial intelligence model to combine the user's search intention and the search keyword to generate interaction information; A first sending module, configured to send the object prompt information of the multiple first service objects and the interaction information to the client, so that the client displays the object prompt information of the multiple first service objects and the interaction prompt information generated based on the interaction information on the first page.

15. An information display device, characterized in that, Configured on the client, including: A keyword determination module, configured to determine a search keyword in response to a search operation; A second sending module, configured to send a search request to the server based on the search keyword, so that the server performs a search operation to determine multiple first service objects that match the search keyword; recognize the user's search intention based on the search keyword, and use an artificial intelligence model to combine the user's search intention and the search keyword to generate interaction information; A second receiving module, configured to receive the object prompt information of the multiple first service objects and the interaction prompt information sent by the server; A second information generation module, configured to determine interaction prompt information based on the interaction generation information; A display module, configured to display the object prompt information of the multiple service objects and the interaction prompt information on the first page.

16. A computing device, characterized in that, Includes a processing component and a storage component; The storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the information search method as described in any one of claims 1-11, or the information display method as described in claim 12 or 13.

17. A computer-readable storage medium, characterized in that, Stored thereon is a computer program, which when executed by the processing component, implements the information search method as described in any one of claims 1-11, or the information display method as described in claim 12 or 13.

18. A computer program product, characterized in that, Includes a computer program or instruction, which when executed by the processing component, implements the information search method as described in any one of claims 1-11, or the information display method as described in claim 12 or 13.

Images