Resource display method and device, electronic equipment and storage medium

Abstract

The invention provides a resource display method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the field of large models and generative models. The specific implementation scheme is as follows: in response to a received query request, determining at least one piece of to-be-clarified information associated with at least part of nodes in a target node queue according to the query request; outputting the at least one piece of to-be-clarified information so as to obtain at least one piece of clarified information for the at least one piece of to-be-clarified information, the clarified information representing the attribute or demand of the object; based on the large model, according to the at least one piece of clarified information, determining a target resource from the plurality of candidate resources; and displaying the target resource.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more particularly to the fields of large models and generative models. More specifically, the present disclosure provides a resource display method, apparatus, electronic device, storage medium, and computer program product. Background Art

[0002] Users sometimes need to select target resources that meet their own needs and actual situations from multiple resources. For example, select a travel destination from multiple cities, or select a college to apply for from multiple institutions when choosing a school. Summary of the Invention

[0003] The present disclosure provides a resource display method, apparatus, electronic device, storage medium, and computer program product.

[0004] According to one aspect of the present disclosure, there is provided a resource display method, including: in response to receiving a query request, determining, according to the query request, at least one piece of information to be clarified associated with at least some of the nodes in the target node queue; outputting the at least one piece of information to be clarified so as to obtain at least one piece of clarified information for the at least one piece of information to be clarified, the clarified information representing the attributes or requirements of an object; based on a large model, determining a target resource from multiple candidate resources according to the at least one piece of clarified information; and displaying the target resource.

[0005] According to another aspect of the present disclosure, there is provided a resource display apparatus, including: a first determination module, an output module, a second determination module, and a display module. The first determination module is configured to, in response to receiving a query request, determine, according to the query request, at least one piece of information to be clarified associated with at least some of the nodes in the target node queue. The output module is configured to output the at least one piece of information to be clarified so as to obtain at least one piece of clarified information for the at least one piece of information to be clarified, the clarified information representing the attributes or requirements of an object. The second determination module is configured to, based on a large model, determine a target resource from multiple candidate resources according to the at least one piece of clarified information. The display module is configured to display the target resource.

[0006] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method provided by the present disclosure.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a computer program product including a computer program which, when executed by a processor, implements the method provided by the present disclosure.

[0009] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understandable through the following description. Description of the Drawings

[0010] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0011] Figure 1 is a schematic diagram of the application scenario of the resource display method and device according to an embodiment of the present disclosure;

[0012] Figure 2 is a schematic flowchart of the resource display method according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of the configuration node, clarification point, and clarification item according to an embodiment of the present disclosure;

[0014] Figure 4 is a schematic diagram of the front-end display configuration node, clarification point, and clarification item according to an embodiment of the present disclosure.

[0015] Figure 5 is a schematic diagram of the configuration node dependency relationship according to an embodiment of the present disclosure;

[0016] Figure 6 is a schematic diagram of the directed acyclic graph according to an embodiment of the present disclosure;

[0017] Figure 7 is a schematic diagram of the node queue according to an embodiment of the present disclosure;

[0018] Figures 8A to 8F is a schematic diagram of the front-end page of the recommended colleges and universities according to an embodiment of the present disclosure;

[0019] Figures 9A to 9E is a schematic diagram of the front-end page according to an embodiment of the present disclosure;

[0020] Figure 10 is a schematic structural block diagram of the resource display device according to an embodiment of the present disclosure; and

[0021] Figure 11 is a structural block diagram of the electronic device for implementing the resource display method according to an embodiment of the present disclosure. Detailed Embodiments

[0022] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0024] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0025] Sometimes users need to select target resources that meet their needs and actual conditions from multiple resources. Taking the user school selection scenario as an example, candidates can search for schools on relevant enrollment information websites based on screening conditions such as the location of the school, the category of the competent department, and the characteristics of the school, and choose a major that suits them based on the school's website announcement, enrollment brochure, major introduction and other information. However, due to the large number of schools and majors, it is difficult for candidates to find their intended schools and majors. In addition, the information on the score lines and admission rules of various colleges and universities is complicated, making it difficult for candidates to determine whether they meet the requirements. When there are multiple choices, it is difficult for users to determine the priority, and they need to rely on online information or the help of teachers to determine which choice is more suitable for them. In addition, there are many screening items, and candidates do not know from which dimensions to measure whether they meet the requirements of a certain college.

[0026] The disclosed embodiments aim to provide a resource display method, which can recommend target resources that meet the needs and personal circumstances to users, so that users can find the required target resources accurately and quickly.

[0027] In addition, users have various query requirements, for example, some users want to query schools, and some users want to query travel destinations. If software code is developed independently for each application scenario to implement the recommendation function, the development cost will be too high.

[0028] The method provided in this embodiment can first construct a target node queue. During the process of determining the target resources, nodes are screened from the target node queue, and the user is asked about the to-be-clarified information associated with the nodes, so as to collect the clarified information, and then resource recommendation is carried out. In this way, for different application scenarios, some data (such as nodes, to-be-clarified information, etc.) can be reused. Developers mainly configure the corresponding relationships between different scenarios and nodes, as well as the association relationships between nodes and to-be-clarified information, and then the function of information recommendation can be realized in different application scenarios, thus improving the development efficiency.

[0029] The resource display method provided in this embodiment can be applied to recommendation scenarios, such as recommending colleges and universities to examinees, recommending tourist destinations to tourists, recommending books, movies, etc. to users.

[0030] The technical solutions provided by the present disclosure will be elaborated in detail below in conjunction with the accompanying drawings and specific embodiments.

[0031] Figure 1 It is a schematic diagram of the application scenario of the resource display method and device according to the embodiment of the present disclosure.

[0032] It should be noted that Figure 1 The example shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0033] As Figure 1 shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0034] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0035] The server 105 may be a server providing various services, such as a background management server (only an example) that supports the websites browsed by users using the terminal devices 101, 102, 103. The background management server can analyze and process data such as user requests received, and feedback the processing results (such as the filtered target resources obtained according to the user request and the recommended reasons for the generated target resources, etc.) to the terminal devices.

[0036] It should be noted that the resource display method provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the resource display device provided by the embodiments of the present disclosure can generally be set in the server 105. The resource display method provided by the embodiments of the present disclosure can also be executed by the terminal devices 101, 102, and 103. Correspondingly, the resource display device provided by the embodiments of the present disclosure can also be set in the terminal devices 101, 102, and 103.

[0037] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in

[0038] Figure 2 is a schematic flowchart of the resource display method according to the embodiments of the present disclosure.

[0039] As Figure 2 shown, the resource display method 200 may include operation S210 to operation S240.

[0040] In operation S210, in response to receiving a query request, at least one piece of information to be clarified associated with at least some nodes in the target node queue is determined according to the query request.

[0041] For example, the object can be a user. The object performs operations such as selection and input on the front end. For example, when the user clicks options such as "start school selection" and "next step", the front end can send a query request to the back end, which can be a server or an electronic device such as a mobile phone or a computer.

[0042] For example, the corresponding relationship between the type of the query request and the nodes can be pre-query. For example, querying the nodes 1, 2, and 3 corresponding to the institution, and querying the nodes 3, 4, and 5 corresponding to the travel destination. The association relationship between the nodes and the information to be clarified can be pre-configured. The information to be clarified can include clarification points and clarification items. For example, the clarification point is "What is your undergraduate institution?", and the clarification items are point options or drop-down options that require the user to perform operation confirmation. For example, the clarification items include "Peking University", "Tsinghua University", etc. After the user views the information to be clarified through the front-end page, the user can clarify it by selection or input (Clarify).

[0043] It should be noted that for a query requirement of the user, multiple pieces of information to be clarified may be required to be clarified by the user. Multiple pieces of information to be clarified can be output to the front end at one time, and the user is allowed to reply at one time. It can also be in sequence, outputting a single piece of information to be clarified to the front end one by one, and after obtaining the corresponding clarified information, outputting the next piece of information to be clarified to the front end.

[0044] It should be noted that during the process of determining the target resource, the user needs to reply to the information to be clarified. If the information to be clarified involves the user's personal information, the user is aware of and consents to the acquisition and use of the information in the user's reply, and all of them comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0045] In operation S220, at least one piece of information to be clarified is output to obtain at least one piece of clarified information for at least one piece of information to be clarified, and the clarified information represents the attributes or requirements of the object.

[0046] For example, the backend can output the information to be clarified to the frontend. The information to be clarified can include clarification points and can also include clarification items. The user can perform a selection operation through the frontend to select one or more clarification items, and then the value of the clarification item selected by the user can be used as the clarified information. In other examples, the information to be clarified may not include clarification items, and the user can perform an input operation through the frontend, and then the information input by the user can be used as the clarified information.

[0047] For example, the clarified information can represent the attributes of the user. For example, the clarified information is the user's undergraduate institution, undergraduate grades, etc. The clarified information can also represent the user's needs. For example, the clarified information is that the user's personal intention for the institution and the region where the travel destination is located is Beijing.

[0048] In operation S230, based on the large model, according to at least one piece of clarified information, the target resource is determined from multiple candidate resources.

[0049] For example, the clarified information, the relevant information of the candidate resources, and the pre-configured prompt information template can be combined to obtain the prompt information (prompt), and then the prompt information is input into the large model, and the large model is used to select the target resource. The prompt information template can guide the large model to select the target resource that meets the user's needs and personal circumstances based on the clarified information and the relevant information of the candidate resources. The large model can be a generative model, and the structure of the large model is not limited in this embodiment.

[0050] In operation S240, the target resource is displayed.

[0051] For example, the backend outputs the target resource to the frontend, and then the target resource is displayed to the user through the frontend.

[0052] The technical solution provided by the embodiments of the present disclosure can recommend target resources that meet the needs and personal circumstances to users, enabling users to accurately and quickly find the target resources they need. In addition, during the process of determining the target resources, nodes are screened from the target node queue, and users are asked for the to-be-clarified information associated with the nodes, so as to collect the clarified information, and then resource recommendation is carried out. In this way, for different application scenarios, some data (such as nodes, to-be-clarified information, etc.) can be reused, and developers mainly configure the corresponding relationships between different scenarios and nodes, as well as the association relationships between nodes and to-be-clarified information, so as to implement the function of information recommendation in different application scenarios, thereby improving the development efficiency.

[0053] Figure 3 It is a schematic diagram of nodes, clarification points, and clarification items according to the embodiments of the present disclosure.

[0054] As Figure 3 shown, in this embodiment, nodes 301 in the directed acyclic graph can be pre-configured. The nodes 301 represent to-be-clarified information, each node 301 is associated with one or more clarification points 302, and each clarification point 302 is associated with one or more specific clarification items 303. The nodes 301 in the directed acyclic graph, the clarification points 302 in the to-be-clarified information, and the clarification items 303 in the to-be-clarified information can be configured. For example, during the actual configuration process, for the nodes 301 in the directed acyclic graph, fields such as node identifier, node name, type, step order, and associated clarification point list can be configured. For the clarification points 302, fields such as clarification point identifier, clarification point name, whether it is a single-choice item, and associated clarification item list can be configured. For the clarification items 303, fields such as clarification item identifier, clarification item name, and whether it is default selected can be configured.

[0055] Figure 4 It is a schematic diagram of configuring nodes, clarification points, and clarification items for front-end display according to the embodiments of the present disclosure.

[0056] For example, as Figure 4 shown, in this page 401, "2 / 4" is the step order of the node in the directed acyclic graph, and this node is used to ask about the user's learning situation. "Professional level", "English level", and "Mathematical level" are clarification points, and "Top 20%", "Top 40%", "Top 60%", and "Others" are the clarification items of the clarification point "Professional level".

[0057] Figure 5 It is a schematic diagram of configuring node dependency relationships according to the embodiments of the present disclosure.

[0058] As Figure 5As shown, in this embodiment, the directed acyclic graph includes multiple nodes, and the dependency relationships of each node can be configured in the form of a table. For example, the node number 501, node name 502, and the number of the preceding dependent node 503 are configured. It should be noted that the directed acyclic graph can have only one root node or can include multiple root nodes without dependency relationships.

[0059] For example, Figure 5 Taking

[0060] Figure 6 as an example, nodes node_0 to node_5 are configured. Among them, node node_0 is the root node, node node_1 depends on node node_0, node node_2 is the root node, node node_3 depends on node node_0, node node_4 depends on node node_1, and node node_5 depends on node node_2.

[0061] As Figure 6 shown, in this embodiment, for the directed acyclic graph DAG, the nodes that satisfy the dependency relationship are connected by edges. Figure 6 The directed acyclic graph DAG of

[0062] Figure 7 includes nodes node_0 to node_5. Among them, the edge between node node_0 and node node_1 indicates that node node_1 depends on node node_0, and other dependency relationships are similar.

[0063] As Figure 7 shown, in this embodiment, the directed acyclic graph is maintained in the configuration in advance. Since there are dependency relationships between each node, that is, only after the operation of the first node is completed can the operation of the second node be carried out. Therefore, by performing a topological sort on this directed acyclic graph, a reasonable input order can be obtained, ensuring the dependency of the front and back nodes, and finally obtaining a node queue including multiple nodes. It should be noted that the topological sort is mainly sorted according to the out-degree and in-degree of the nodes, and the implementation means of the topological sort in this embodiment are not limited. For example, the arrangement order of each node in the node queue is node node_0, node node_2, node node_1, node node_3, node node_5, and node node_4.

[0064] In addition, during the actual execution of the processing logic of each node in the node queue, pruning operations can be performed on the nodes in the node queue. It can be determined whether a node satisfies the pruning condition according to the pruning expression. If the pruning condition is satisfied, the node is skipped and the execution continues in order.

[0065] For example, after the processing logic of node node_1 is executed, it can be determined whether node node_3 meets the pruning condition. If it meets, node node_3 can be skipped, and then it can be determined whether node node_5 meets the pruning condition, and so on.

[0066] According to another embodiment of the present disclosure, the process of determining the information to be clarified may include: in response to receiving a query request, for the current node selected from the target node queue, determine whether to execute the processing logic of the current node according to whether the processing logic of the current node has been executed and whether the current node meets the pruning condition. If not, update the subsequent node in the target node queue to the current node, and return the operation of determining whether to execute the current node until a predetermined termination condition is met. If so, determine the configuration information associated with the current node as the information to be clarified and output it to obtain the clarified information.

[0067] For example, the processing logic of each node is pre-configured, and the processing logics of different nodes can be the same or different. For example, a processing logic can be to read the pre-configured information to be clarified, assemble the information to be clarified into a predetermined format, and then return it to the front end. For example, for node 1 and node 2, if the answer to the information to be clarified associated with node 1 (i.e., the clarified information) has been obtained and the answer to the information to be clarified associated with node 1 has not been obtained, it can be considered that the processing logic of node 1 has been executed and the processing logic of node 2 has not been executed.

[0068] For example, pruning expressions can be pre-configured. The pruning expressions can include one or more conditional operators. The conditional operators can be the smallest computing units with business logic judgment capabilities. Each conditional operator can be combined into a Boolean expression through logical operations. The logical operations can include AND, OR, and NOT. For example, each conditional operator corresponds to a sub-result indicating whether the current node meets the conditional operator. The sub-result is a Boolean value and can include "yes" and "no". In addition, by performing logical operations on the sub-results of each conditional operator, the output result of the pruning expression can be obtained. The output result includes "yes" and "no". It can be determined that the current node meets the pruning condition when the output result of the pruning expression is "yes", indicating that the node needs to be skipped and the processing logic of the node is not executed. It can be determined that the current node does not meet the pruning condition when the output result of the pruning expression is "no".

[0069] For example, it can be determined to execute the processing logic of the current node when the current node does not meet the pruning condition and the processing logic of the current node has not been executed. It can be determined not to execute the processing logic of the current node when the current node meets the pruning condition or the processing logic of the current node has been executed.

[0070] It can be understood that in this embodiment, it is determined whether the current node meets the pruning condition, and it is also determined whether the processing logic of the current node has been executed. This embodiment does not limit the execution order of the above two judgment steps.

[0071] In this embodiment, by pre-configuring the processing logic and pruning expressions of the nodes, it is possible to dynamically determine whether to execute the processing logic of a certain node according to business requirements. When a node meets the pruning condition or its processing logic has been executed, the node is skipped to reduce redundant calculations; otherwise, the processing logic of the node is executed to obtain the information to be clarified and output. In this way, the processing flow can be flexibly adjusted according to the real-time business status (such as the existence or non-existence of the clarified information), thereby improving the response speed and resource utilization rate of the system. In addition, through the flexible combination of various conditional operators in the pruning expression, different business scenarios can be adapted, enhancing the scalability and adaptability of the system.

[0072] According to another embodiment of the present disclosure, the process of determining the information to be clarified may further include: in response to receiving a query request and the query request includes a type field, determining a target node queue from multiple candidate node queues according to the type field, where the candidate node queues are obtained by performing a topological sort on a directed acyclic graph, and the directed acyclic graph is related to the type field.

[0073] For example, according to business requirements, multiple directed acyclic graphs can be pre-configured. Each directed acyclic graph can correspond to a type of business scenario. For example, one business scenario is school choice. A directed acyclic graph DAG_1 can be configured for this business scenario. The directed acyclic graph DAG_1 includes multiple nodes, and two nodes with a dependency relationship can be connected by an edge. Performing a topological sort on the directed acyclic graph DAG_1 can obtain a node queue. It is also possible to configure the value of the type field to be 1 and establish an association relationship between the directed acyclic graph, the node queue, and the type field.

[0074] For example, if the user clicks "start school choice" on the front end, the back end detects that the value of the type field in the query request is 1. Then, the back end can determine the node queue associated with the type field as the target node queue.

[0075] In this embodiment, according to the type field in the query request, the target node queue is dynamically determined from multiple pre-configured candidate node queues, so that the corresponding processing flow can be quickly selected and executed for different business scenarios. In addition, by pre-configuring the association relationship between the directed acyclic graph and the type field, it can be applied to multiple business scenarios and meet the requirements of different scenarios.

[0076] According to another embodiment of the present disclosure, during the process of determining the information to be clarified, the following operations may further be included: in response to receiving a query request and the query request includes an answer, add the answer to the clarified information, then store the clarified information in a predetermined storage area, and next, trigger an operation of determining whether to execute the processing logic of the current node.

[0077] In this embodiment, after obtaining the user's answer, the answer can be stored first, and then it is determined whether the processing logic of the current node has been executed. On the one hand, this way can record the answer provided by the user in a timely and effective manner for subsequent input data provided to the large model. On the other hand, it can be determined whether the processing logic of the current node has been executed based on the data in the predetermined storage area, thereby simplifying the judgment logic.

[0078] According to another embodiment of the present disclosure, after receiving a query request and the query request includes an answer, relevant reference information can be retrieved from the database according to the answer, and then the reference information is added to the clarified information. For example, the business scenario is school selection. After asking the user for undergraduate school information, the user makes a selection operation and triggers a query request. The answer in the query request is "Tsinghua University", and the reference information may include the introduction, ranking, and major disciplines of the school. In this way, during the process of the large model processing the clarified information to determine the target resource, the reference information can provide a reference for the inference of the large model, thereby improving the accuracy and rationality of the target recommended resource.

[0079] According to another embodiment of the present disclosure, after receiving a query request, the current node can be determined first, and then it can be determined whether the processing logic of the current node is executed according to whether the clarified information for the current node has been stored in the predetermined storage area. For example, if the clarified information for the current node has been stored in the predetermined storage area, it is determined that the processing logic of the current node has been executed, and then the node can be skipped and the next node is updated as the current node. Otherwise, it is considered that the processing logic of the current node has not been executed, so the processing logic of the current node is executed.

[0080] In this embodiment, after receiving a query request, by checking whether the clarified information of the current node has been stored in the predetermined storage area, it is determined whether to execute the processing logic of the node. In this way, the node to be executed can be quickly determined by simply reading the predetermined storage area.

[0081] According to another embodiment of the present disclosure, the predetermined termination condition includes: the current node selected from the node queue is a predetermined termination node. For example, a directed acyclic graph can be topologically sorted to obtain an initial node queue. Then, a predetermined start node can be set at the beginning of the initial node queue, and a predetermined termination node can be set at the end of the initial node queue. In this way, when the selected current node is the predetermined termination node, it can be determined that the predetermined termination condition is satisfied, and at this time, the system can stop asking the user for information to be clarified.

[0082] In this embodiment, when the processing flow reaches the predetermined termination node, the system automatically stops asking the user for information to be clarified, which can ensure the logical integrity and sequentiality of the processing flow.

[0083] According to another embodiment of the present disclosure, in the process of determining the target resource, based on a large model, according to at least one clarified information, the target resource can be determined from multiple candidate resources, and a recommendation reason for the target resource can be generated, and then the recommendation reason can be displayed. In this embodiment, by displaying the recommendation reason, the user can better understand the recommendation basis and improve the user experience.

[0084] According to another embodiment of the present disclosure, after the target resource is displayed, if a view operation on the target resource is detected, the attributes of the target resource are also obtained from the database, and then the attributes of the target resource are displayed. For example, by presenting the recommended colleges and universities to the user through the front end, after the user clicks on a college or university, the user can query the attributes such as the major information, examination subjects, research directions, etc. of the college or university, and then display these attributes to help the user more comprehensively understand the resource details, and further assist the user in making a more accurate choice and improving the user experience.

[0085] It can be understood that the type of the query request, the content of the information to be clarified, and the attributes of the target resource can be configured according to business requirements, and the recommended scenarios in this embodiment are not limited.

[0086] For example, one recommended scenario is to recommend colleges and universities. Correspondingly, the query request represents that the query type is to query colleges and universities. At least one of the at least one information to be clarified includes at least one of the following: the historical college information of the object, the attributes of the object, and the intention information of the object. In addition, the attributes of the target resource include at least one of the following: the major information of the college, the examination subjects, the research directions, and the application details.

[0087] For example, one recommended scenario is to recommend tourist destinations. Correspondingly, the query request represents that the query type is to query tourist destinations. Correspondingly, at least one of the at least one information to be clarified includes at least one of the following: the number of tourist days, the budget, the intended landscape type, the intended region, etc. In addition, the attributes of the target resource include at least one of the following: the temperature range, the popular scenic spots, the traffic conditions, the special local foods, etc.

[0088] Figures 8A to 8FIt is a schematic diagram of the front-end page of recommended universities according to an embodiment of the present disclosure.

[0089] In this embodiment, taking recommended universities as an example, this embodiment will be described.

[0090] Information such as the location, competent department, university characteristics, professional settings, admission rules, past years' admission scores, and scientific research conditions of multiple schools can be pre-entered into the database.

[0091] As Figure 8A shown, when the user enters "start choosing a university" in the conversation to trigger the university selection process, the user input content and interaction terms can be displayed through page Page_1.

[0092] As Figure 8B shown, after triggering the university selection process, the user's undergraduate university information can be actively asked through page Page_2 to assist the user in choosing a university.

[0093] As Figure 8C shown, after the user clarifies their undergraduate university and triggers the secondary clarification, information such as the user's current professional level, English level, and math level can be asked through page Page_3.

[0094] As Figure 8D shown, after the user clarifies their learning situation and triggers the tertiary clarification, information such as the user's type, intended major, and intended university level can be asked through page Page_4.

[0095] As Figure 8E shown, after the user clarifies their intention information and triggers the quaternary clarification, the user's intended region can be asked through page Page_5.

[0096] Figure 8F shown, after the user clarifies their intended region, based on the user's provided answers and the school and major information pre-stored in the database, combined with the large model, recommended schools and reasons for recommendation can be provided, and then can be displayed through page Page_6.

[0097] In addition, the user can view the recommended schools, majors, etc., and then view the details of the majors, exam subjects, research directions, etc. of the school. These information can be retrieved from the database or generated by the large model. In addition, if the user is not satisfied with the recommended results, they can also re-clarify or enrich their information or wishes, etc., and then re-search for school and major information that better suits them.

[0098] In this embodiment, the user input answer is obtained by gradually passing the information to be clarified in the form of a dialogue, and the existing information is filtered based on the clarified information provided by the user, and then the recommended target object and the reason for recommendation are output to the user.

[0099] According to another embodiment of the present disclosure, the data interaction process between the front end and the back end is described. For example, after the back end receives a query request from the front end, if the query request includes a type field, the back end can determine the target node queue from multiple candidate node queues according to the type field. If the query request does not include an answer, the back end may not store the clarified information and needs to determine the current node to be executed and obtain the clarified information through the processing logic. If the query request includes an answer, the back end can store the clarified information and then determine the current node to be executed and obtain the clarified information through the processing logic. The processing logic for determining the current node to be executed and obtaining the clarified information may include: for the current node selected from the target node queue, determine whether to execute the processing logic of the current node according to whether the processing logic of the current node has been executed and whether the current node meets the pruning condition. If it is determined not to execute the processing logic of the current node, the subsequent node in the target node queue is updated to the current node, and the operation of determining whether to execute the current node is returned until a predetermined termination condition is met. If it is determined to execute the processing logic of the current node, the configuration information associated with the current node is determined as the information to be clarified and output for display through the front end, so as to obtain the clarified information.

[0100] For example, taking the recommendation of colleges and universities as an example, the data interaction process between the front end and the back end is described.

[0101] First, the user clicks "Start School Selection", and the front end sends a query request to the back end. The query request includes a type field, and the value of the type field corresponds to "Start School Selection". After the back end receives the query request, the back end determines the target node queue from multiple candidate node queues according to the value of the type field. Since the query request does not include the answer to the previous question of the object at this time, the back end does not need to store the answer or the stored answer is empty. In addition, the back end traverses the nodes in the target node queue in order to determine the node to be executed. For example, the back end selects the first node from the target node queue in order as the current node, and then determines whether to execute the processing logic of the first node according to whether the processing logic of the first node has been executed and whether the first node meets the pruning condition. If so, according to the pre-configured information, obtain the configuration information associated with the first node. The configuration information may include a clarification point and a clarification item. The clarification point is, for example, the undergraduate school information of the questioned object. Then, the back end takes the clarification point and the clarification item as the information to be clarified and outputs them to the front end, so that the front end can display the clarification point and the clarification item for the user to select. If not, update the second node in the target node queue as the current node, and then re-determine whether to execute the processing logic of the second node, and so on.

[0102] Taking the execution of the processing logic of the first node in the previous operation as an example, next, the user can see the clarification point and the clarification item of the first node on the front end, and can perform operations such as selection and input to clarify the undergraduate school information of himself and click "Next". Then, the front end sends another query request to the back end. The query request includes an answer, that is, the undergraduate school selected by the user. After the back end receives the query request, it first stores the clarified information. For example, it stores the answer as the clarified information in a predetermined storage area. In addition, it can also retrieve reference information from the database according to the answer. The reference information is, for example, the relevant introduction of the undergraduate school selected by the user. Then, it stores the reference information as the clarified information in a predetermined storage area. After storing the clarified information, the back end traverses the nodes in the target node queue in order to determine the node to be executed. For example, the back end selects the first node from the target node queue as the current node. Since the first node has been executed at this time, skip the first node and update the second node as the current node, and re-determine whether to execute the second node. If so, obtain the configuration information associated with the second node. The configuration information may include a clarification point and a clarification item. The clarification point is, for example, the undergraduate grades of the questioned object. Then, the back end takes the clarification point and the clarification item as the information to be clarified and outputs them to the front end, so that the front end can display the clarification point and the clarification item for the user to select or input. If not, update the third node in the target node queue as the current node, and then re-determine whether to execute the processing logic of the third node, and so on.

[0103] Taking the processing logic of the second node in the previous round of operation as an example, next, the user can see the clarification points and items of the second node on the front end and can perform operations such as selection and input to clarify their undergraduate grades. For example, clarify the three clarification points of professional level, English level, and math level. After the user clicks "Next", the front end sends another query request to the back end. This query request includes the answers, that is, the undergraduate study situation selected by the user. After the back end receives the query request, it first stores the clarified information, and then traverses the nodes in the target node queue in sequence to determine the node to be executed, and then outputs the information to be clarified to the user again, such as asking about the user type, intended major, intended school level, etc. The data processing process is similar to the above process and will not be elaborated here.

[0104] Next, the user can see the clarification points and items of the third node on the front end and can perform operations such as selection and input. For example, clarify the three clarification points of type, intended major, and intended school level. After the user clicks "Next", the front end sends another query request to the back end. This query request includes the answers, that is, the clarification items selected and input by the user. After the back end receives the query request, it first stores the clarified information, and then traverses the nodes in the target node queue in sequence to determine the node to be executed, and then outputs the information to be clarified to the user again, such as asking about the user's intention for the city. The data processing process is similar to the above process and will not be elaborated here.

[0105] Next, the user can see the clarification points and items of the fourth node on the front end and can perform operations such as selection and input. For example, clarify the intended region. If the clarification point is not a required item, the user can also choose not to clarify. After the user clicks "Next", the front end sends another query request to the back end. This query request includes the answers, that is, the clarification items selected or input by the user. If the user has not made a clarification, the user's answer is empty. After the back end receives the query request, it first stores the clarified information, and then traverses the nodes in the target node queue in sequence to determine the node to be executed. If the traversal reaches the termination node at this time, the user can be stopped from being asked.

[0106] It can be seen that every time the user operates on the front-end page, such as selecting "Start school selection" or clarifying relevant information and clicking "Next", the front end will send a query request to the back end. After the back end receives the query request, it can determine the target node queue, store the clarified information, and traverse the target node queue in sequence to determine the current node to be executed.

[0107] Through the above processing process, multiple questions can be asked to the user, such as asking for the user's undergraduate institution information, professional level, English level, math level, type, intended major, intended institution, intended region, etc. After meeting the predetermined termination conditions, the answers of the user to each question can be obtained, thus obtaining multiple clarified information items.

[0108] Next, based on the large model, at least one clarified information item can be used to determine a target resource from multiple candidate resources, and then the target resource can be displayed.

[0109] Figures 9A to 9E It is a schematic diagram of the front-end page according to an embodiment of the present disclosure.

[0110] As Figure 9A shown, the user can be asked questions through page 901. The form submission button, form item name, clarification items (radio, checkbox, cascading selection, input box, etc.) can be configured according to actual needs.

[0111] For example, as Figure 9B shown, the direction of the form items can be adjusted from the horizontal page Page_1 as Figure 9A shown to the vertical page 902 as Figure 9B shown.

[0112] As Figure 9C shown, it can be configured whether the front-end page is disabled. If the user clicks the pause button, the clarification page can be disabled. For example, the color of page 903 is lighter at this time.

[0113] As Figure 9D shown, verification fields can be configured. Through this field, it can be determined whether the required items are filled. If not filled, the "Next" button cannot be selected, and the user can also be prompted through page 904 to fill in the required items.

[0114] As Figure 9E shown, after the user selects an option, the option can be displayed through page 905.

[0115] In addition, callback logic can be configured. After the user inputs or selects clarification items at the front end and confirms the next step, the user's speech content can be generated based on the clarification items. The generated template is "My {form item name} is {displayed selected value}". For example, if the clarification item selected by the user for the clarification point "Undergraduate institution" is "Beijing XX University", then "My undergraduate institution is Beijing XX University" can be displayed at the front end through the page. In addition, the clarification items input by the user multiple times can also be displayed, and then institutions can be recommended to the user.

[0116] Figure 10 It is a schematic structural block diagram of a resource display device according to an embodiment of the present disclosure.

[0117] As Figure 10 shown, the resource display device 1000 may include a first determination module 1010, an output module 1020, a second determination module 1030, and a display module 1040.

[0118] The first determination module 1010 is configured to, in response to receiving a query request, determine, according to the query request, at least one piece of information to be clarified associated with at least some of the nodes in the target node queue.

[0119] The output module 1020 is configured to output at least one piece of information to be clarified, so as to obtain at least one piece of clarified information for the at least one piece of information to be clarified, where the clarified information characterizes the attributes or requirements of an object.

[0120] The second determination module 1030 is configured to determine a target resource from multiple candidate resources based on a large model according to the at least one piece of clarified information.

[0121] The display module 1040 is configured to display the target resource.

[0122] According to another embodiment of the present disclosure, the first determination module includes: a first sub-module, a second sub-module, and a third sub-module. The first sub-module is configured to, in response to receiving a query request, for the current node selected from the target node queue, determine whether to execute the processing logic of the current node according to whether the processing logic of the current node has been executed and whether the current node meets the pruning condition. The second sub-module is configured to, when it is determined not to execute the processing logic of the current node, update the subsequent node in the target node queue to the current node, and return the operation of determining whether to execute the processing logic of the current node until a predetermined termination condition is met. The third sub-module is configured to, when it is determined to execute the processing logic of the current node, determine the configuration information associated with the current node as the information to be clarified and output it, so as to obtain the clarified information.

[0123] According to another embodiment of the present disclosure, the first determination module further includes: a fourth sub-module, configured to, in response to receiving a query request and the query request includes a type field, determine a target node queue from multiple candidate node queues according to the type field; where the candidate node queue is obtained by performing a topological sort on a directed acyclic graph, and the directed acyclic graph is related to the type field.

[0124] According to another embodiment of the present disclosure, the first determination module further includes: a fifth sub-module, a sixth sub-module, and a seventh sub-module. The fifth sub-module is configured to, in response to receiving a query request and the query request includes an answer, add the answer to the clarified information. The sixth sub-module is configured to store the clarified information in a predetermined storage area. The seventh sub-module is configured to trigger the operation of determining whether to execute the processing logic of the current node.

[0125] According to another embodiment of the present disclosure, the first determination module further includes: an eighth sub-module and a ninth sub-module. The eighth sub-module is configured to retrieve reference information related to the answer from the database according to the answer. The ninth sub-module is configured to add the reference information to the clarified information.

[0126] According to another embodiment of the present disclosure, the first determination module further includes: a tenth sub-module and an eleventh sub-module. The tenth sub-module is configured to determine that the processing logic of the current node has been executed in response to determining that the clarified information for the current node has been stored in the predetermined storage area. The eleventh sub-module is configured to determine that the processing logic of the current node has not been executed in response to determining that the clarified information for the current node has not been stored in the predetermined storage area.

[0127] According to another embodiment of the present disclosure, the predetermined termination condition includes: the current node selected from the node queue is a predetermined termination node.

[0128] According to another embodiment of the present disclosure, it further includes: a generation module and a reason display module. The generation module is configured to generate a recommendation reason for the target resource based on the large model according to at least one piece of clarified information. The reason display module is configured to display the recommendation reason.

[0129] According to another embodiment of the present disclosure, it further includes: an acquisition module and an attribute display module. The acquisition module is configured to acquire the attributes of the target resource from the database in response to detecting a viewing operation on the target resource. The attribute display module is configured to display the attributes of the target resource.

[0130] According to another embodiment of the present disclosure, the query request represents that the query type is to query institutions of higher learning; at least one piece of information to be clarified includes at least one of the following: the historical institution information of the object, the attributes of the object, the intention information of the object; and the attributes of the target resource include at least one of the following: the professional information of the institution, the examination subjects, the research directions, the application details.

[0131] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above resource display method.

[0132] According to an embodiment of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the above resource display method.

[0133] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, including a computer program that implements the above resource display method when executed by a processor.

[0134] Figure 11 It is a block diagram of an electronic device for implementing the resource display method according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0135] As Figure 11 shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0136] A plurality of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a magnetic disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0137] The computing unit 1101 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 executes the various methods and processes described above, such as the resource display method. For example, in some embodiments, the resource display method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the resource display method described above can be executed. Alternatively, in other embodiments, the computing unit 1101 can be configured to execute the resource display method by any other suitable means (e.g., by means of firmware).

[0138] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0140] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0142] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0143] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of the client and the server is generated by computer programs running on the respective computers and having a client-server relationship to each other.

[0144] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0145] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A resource display method, comprising: In response to receiving a query request, determining, according to the query request, at least one piece of information to be clarified associated with at least some nodes in a target node queue; Outputting the at least one piece of information to be clarified, so as to obtain at least one piece of clarified information for the at least one piece of information to be clarified, where the clarified information represents the attributes or requirements of an object; Based on a large model, determining a target resource from multiple candidate resources according to the at least one piece of clarified information; And Displaying the target resource.

2. The method according to claim 1, wherein The determining, in response to receiving a query request, at least one piece of information to be clarified associated with at least some nodes in a target node queue according to the query request includes: In response to receiving the query request, for a current node selected from the target node queue, determining whether to execute the processing logic of the current node according to whether the processing logic of the current node has been executed and whether the current node meets the pruning condition; In the case of determining not to execute the processing logic of the current node, updating a subsequent node in the target node queue to the current node, and returning the operation of determining whether to execute the processing logic of the current node until a predetermined termination condition is met; and In the case of determining to execute the processing logic of the current node, determining the configuration information associated with the current node as the information to be clarified and outputting it, so as to obtain the clarified information.

3. The method according to claim 2, wherein The determining, in response to receiving a query request, at least one piece of information to be clarified associated with at least some nodes in a target node queue according to the query request further includes: In response to receiving the query request and the query request includes a type field, determining the target node queue from multiple candidate node queues according to the type field; Wherein, the candidate node queue is obtained by performing a topological sort on a directed acyclic graph, and the directed acyclic graph is related to the type field.

4. The method according to claim 2, wherein The determining, in response to receiving a query request, at least one piece of information to be clarified associated with at least some nodes in a target node queue according to the query request further includes: In response to receiving the query request and the query request includes an answer, adding the answer to the clarified information; Storing the clarified information in a predetermined storage area; and Triggering an operation of determining whether to execute the processing logic of the current node.

5. The method according to claim 4, wherein, The determining, in response to receiving a query request, at least one piece of information to be clarified associated with at least some nodes in a target node queue according to the query request further includes: Retrieving reference information related to the answer from a database according to the answer; and Adding the reference information to the clarified information.

6. The method according to claim 2, wherein, The determining, in response to receiving a query request, at least one piece of information to be clarified associated with at least some nodes in a target node queue according to the query request further includes: In response to determining that the predetermined storage area has stored the clarified information for the current node, determining that the processing logic of the current node has been executed; and In response to determining that the clarified information for the current node is not stored in the predetermined storage area, it is determined that the processing logic of the current node has not been executed.

7. The method according to claim 2, wherein, The predetermined termination condition includes: the current node selected from the node queue is a predetermined termination node.

8. The method according to claim 1, further comprising: Based on the large model, generating a recommendation reason for the target resource according to the at least one clarified information; and Displaying the recommendation reason.

9. The method according to any one of claims 1 to 8, further comprising: In response to detecting a viewing operation on the target resource, obtaining the attributes of the target resource from a database; and Displaying the attributes of the target resource.

10. The method according to claim 9, wherein The query request represents that the query type is to query an institution; The at least one information to be clarified includes at least one of the following: the historical institution information of the object, the attributes of the object, the intention information of the object; and The attributes of the target resource include at least one of the following: the major information of the institution, the examination subjects, the research direction, the application details.

11. A resource display device, comprising: A first determination module, configured to, in response to receiving a query request, determine at least one information to be clarified associated with at least some nodes in a target node queue according to the query request; An output module, configured to output the at least one information to be clarified, so as to obtain at least one clarified information for the at least one information to be clarified, where the clarified information represents the attributes or requirements of an object; A second determination module, configured to determine a target resource from multiple candidate resources based on a large model according to the at least one clarified information; and A display module, configured to display the target resource.

12. An electronic device, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 10.

14. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images