Processing method for demand related to map interest point, electronic equipment and storage medium

Abstract

The invention provides a processing method and device for demands related to map interest points, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence such as generative large language models, agents and retrieval enhancement generation. The method comprises the steps of obtaining a dynamic demand related to a map interest point, wherein the dynamic demand needs to be combined with real-time information related to the map interest point for demand processing; issuing a demand parameter corresponding to the dynamic demand to a target agent with a corresponding demand processing capability, wherein the target agent is pre-constructed based on an agent technology combined with map interest point related services and a retrieval enhancement generation technology; controlling the target intelligent body to check real-time information associated with the map interest point to obtain supplementary information; and controlling the target agent to output a demand processing result corresponding to the supplementary information and the demand parameter as input information.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, specifically to the field of artificial intelligence technology such as generative large language models, intelligent agents, retrieval enhancement generation, and more particularly to a method, device, electronic device, computer-readable storage medium, and computer program product for processing requirements related to map points of interest. Background Art

[0002] Large language models (LLM, Large Language Model, which is essentially a generative model, also known as a generative large language model), such as ChatGPT (Chat Generative Pre-trained Transformer, a chatbot program developed by OpenAI), can generate human-like fluent responses for many downstream tasks (such as task-oriented dialogues and question answering).

[0003] However, how to make map applications better meet users' timeliness requirements related to a certain point of interest (POI) on a map (also called dynamic requirements, that is, requirements that require dynamic determination of results in combination with real-time information) is a key issue that technical personnel in this field urgently need to solve. For example, "How long does it take to drive from Company A to City B before work next Monday?" "My flight is at 10 o'clock tomorrow morning. When should I leave home so that I won't be late?" Such requirements not only require the combination of real-time information but also require a full understanding of semantics. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing requirements related to map points of interest.

[0005] In a first aspect, an embodiment of the present disclosure proposes a method for processing demands related to map points of interest, including: obtaining dynamic demands related to map points of interest; wherein the dynamic demands are demands that need to be processed in combination with real-time information associated with the map points of interest; sending demand parameters corresponding to the dynamic demands to a target intelligent agent with corresponding demand processing capabilities; wherein the target intelligent agent is pre-constructed based on intelligent agent technology that combines map point of interest related services and retrieval enhancement generation technology; controlling the target intelligent agent to retrieve real-time information associated with the map points of interest to obtain supplementary information; and controlling the target intelligent agent to output a demand processing result corresponding to the supplementary information and demand parameters as input information.

[0006] In a second aspect, an embodiment of the present disclosure proposes a processing device for demands related to map points of interest, comprising: a dynamic demand acquisition unit, configured to acquire dynamic demands related to map points of interest; wherein the dynamic demands are demands that need to be processed in combination with real-time information associated with the map points of interest; a demand parameter sending unit, configured to send demand parameters corresponding to the dynamic demands to a target intelligent agent with corresponding demand processing capabilities; wherein the target intelligent agent is pre-constructed based on intelligent agent technology that combines map point of interest related services and retrieval enhancement generation technology; a real-time information retrieval unit, configured to control the target intelligent agent to retrieve real-time information associated with the map points of interest to obtain supplementary information; and a demand processing result output unit, configured to control the target intelligent agent to output a demand processing result corresponding to the supplementary information and demand parameters as input information.

[0007] In a third aspect, an embodiment of the present disclosure provides 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 implement the processing method related to map points of interest as described in the first aspect when executing.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement the processing method related to map interest points as described in the first aspect when executed.

[0009] In a fifth aspect, an embodiment of the present disclosure provides a computer program product including a computer program, which, when executed by a processor, can implement the steps of the method for processing requirements related to map points of interest as described in the first aspect.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0012] Figure 1 is an exemplary system architecture in which the present disclosure may be applied;

[0013] Figure 2 A flowchart of a method for processing requirements related to map points of interest provided in an embodiment of the present disclosure;

[0014] Figure 3 A schematic diagram of enumerating various target intelligent agents provided in the embodiments of the present disclosure;

[0015] Figure 4 A flowchart of another method for processing requirements related to map points of interest provided by an embodiment of the present disclosure;

[0016] Figure 5 A flowchart of a method for sending task parameters of respective subtasks to corresponding target intelligent agents provided by an embodiment of the present disclosure;

[0017] Figure 6 A flowchart of another method for sending task parameters of respective subtasks to corresponding target intelligent agents provided by an embodiment of the present disclosure;

[0018] Figure 7 A flowchart of a method for retrieving supplementary information for each target agent according to task parameters provided in an embodiment of the present disclosure;

[0019] Figure 8 A structural block diagram of a device for processing requirements related to map points of interest provided in an embodiment of the present disclosure;

[0020] Fig. 9 A schematic diagram of the structure of an electronic device suitable for executing a processing method related to map points of interest provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] 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 clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments may be combined with each other without conflict.

[0022] 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.

[0023] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the method, apparatus, electronic device, and computer-readable storage medium for processing requirements related to map points of interest of the present disclosure can be applied.

[0024] like Figure 1As shown, the system architecture 100 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, wireless communication links or optical fiber cables, etc.

[0025] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 and server 105 can be installed with various applications for realizing information communication between the two, such as map applications, online shopping applications, instant messaging applications, etc.

[0026] Terminal devices 101, 102, 103 and server 105 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc.; when terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above, which can be implemented as multiple software or software modules, or as a single software or software module, and no specific limitation is made here. When server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server; when the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, and no specific limitation is made here.

[0027] The server 105 can provide various services through various built-in applications. Taking a map application that can process dynamic demands related to map points of interest initiated by users as an example, the server 105 can achieve the following effects when running the map application: first, dynamic demands related to map points of interest transmitted by users through terminal devices 101, 102, and 103 are received through network 104, and the dynamic demands are demands that need to be processed in combination with real-time information associated with the map points of interest; then, the demand parameters corresponding to the dynamic demands are sent to a target intelligent agent with corresponding demand processing capabilities, and the target intelligent agent is pre-built based on intelligent agent technology that combines map point of interest related services and retrieval enhancement generation technology; next, the target intelligent agent is controlled to retrieve real-time information associated with the map point of interest to obtain supplementary information; finally, the target intelligent agent is controlled to output a demand processing result corresponding to the supplementary information and the demand parameters as input information.

[0028] Furthermore, the server 105 may also return the demand processing result to the terminal devices 101 , 102 , 103 via the network 104 , so that the terminal devices 101 , 102 , 103 present the received demand processing result to the user.

[0029] It should be noted that, in addition to being temporarily obtained from the terminal devices 101, 102, 103 through the network 104, the dynamic requirements related to the map points of interest can also be pre-stored locally in the server 105 in various ways. Therefore, when the server 105 detects that these data have been stored locally (for example, starting to process the dynamic requirements to be processed before), it can choose to directly obtain these data locally. In this case, the exemplary system architecture 100 may also not include the terminal devices 101, 102, 103 and the network 104.

[0030] The processing methods for the requirements related to the map points of interest provided in the subsequent embodiments of the present disclosure are generally executed by the server 105 with strong computing power and more computing resources. Accordingly, the processing device for the requirements related to the map points of interest is generally also set in the server 105. However, it should also be pointed out that when the terminal devices 101, 102, and 103 also have computing power and computing resources that meet the requirements, the terminal devices 101, 102, and 103 can also complete the above-mentioned various operations that are handed over to the server 105 through the map application installed thereon, and then output the same result as the server 105. Especially in the case where there are multiple terminal devices with different computing capabilities at the same time, but the map application determines that the terminal device where it is located has strong computing power and more remaining computing resources, it can let the terminal device perform the above-mentioned operations, thereby appropriately reducing the computing pressure of the server 105. Accordingly, the processing device for the requirements related to the map points of interest can also be set in the terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104.

[0031] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0032] Please refer to Figure 2 , Figure 2 A flowchart of a method for processing requirements related to map points of interest provided by an embodiment of the present disclosure, wherein process 200 includes the following steps:

[0033] Step 201: Obtain dynamic requirements related to map points of interest;

[0034] This step is intended to be performed by the execution subject of the processing method related to the map interest point requirements (such as Figure 1 The server 105 or the map application installed and running on the terminal devices 101, 102, 103 shown in the figure obtains the dynamic demand related to the map interest points initiated by the user to the map application. The dynamic demand refers to the demand that can only be processed based on the real-time change information related to the map interest points required by a certain demand scenario at a specific time point. That is, this type of demand cannot be accurately processed only by static and fixed map knowledge or map information, but will be affected by various dynamic factors such as time, environment, external conditions, etc. In the application scenarios of maps and navigation, dynamic demands often require real-time or near real-time feedback and processing. The dynamic demand can be a problem, demand or expectation described by the user in various forms of natural language.

[0035] For example, if a user asks the question "How long does it take to drive from Company A to City B next Monday?", in addition to solving the basic problem of route planning, it is also necessary to consider a variety of dynamic factors, such as real-time road conditions, weather, traffic control, road restrictions, congestion, etc. These factors will change with changes in time, location and other conditions.

[0036] Among them, the dynamic demand related to map points of interest refers to the actual demand expressed by the user that contains at least one vague or definite map point of interest (such as a company, city, tourist attraction, etc.). The map point of interest may be used as a retrieval and positioning object, or as a starting point or end point in a navigation parameter or a path planning parameter.

[0037] At the same time, the processing of dynamic demand is not just a simple calculation of time and place, but it is necessary to infer demand based on real-time traffic conditions, weather, holidays, etc. For example, traffic conditions in a specific time period (such as road closures, construction, etc.) and road condition forecast data related to that time period (such as congestion, accidents, license plate restrictions, etc.) are all real-time data.

[0038] Taking the dynamic demand of "the time from Company A to City B next Monday" as an example, it not only involves the geographical location and preset path of the starting point and the end point, but also requires dynamic evaluation based on the traffic data of the future time (such as next Monday). The acquisition of this real-time data can include but is not limited to:

[0039] 1) Traffic flow data: including real-time road conditions and congestion predictions;

[0040] 2) Traffic control information: such as license plate restrictions, road closures, construction sections, etc.;

[0041] 3) Weather influence: the influence of rain, snow and other weather on road traffic;

[0042] 4) Other emergencies: temporary events that may occur due to traffic accidents, road accidents, etc.

[0043] An implementation method including but not limited to may be:

[0044] First, the above-mentioned execution entity obtains any demand related to the map point of interest; then, when the above-mentioned execution entity recognizes that the arbitrary demand contains preset keywords that represent the need to process the demand in combination with real-time information associated with the map point of interest (for example, specific time description information expressed in the form of "next Monday" or "tomorrow", and prediction-related description information expressed in the form of "estimated time", etc.), the above-mentioned execution entity can determine the obtained arbitrary demand as the dynamic demand.

[0045] Step 202: Sending the demand parameters corresponding to the dynamic demand to the target agent with the corresponding demand processing capability;

[0046] Based on step 201, this step aims to send the demand parameters corresponding to the dynamic demand to the target agent with the corresponding demand processing capability by the above-mentioned execution subject. The target agent is pre-built based on the agent technology combining the map interest point related service and the retrieval-augmented generation (RAG) technology. Specifically, the target agent may include at least one of the following (see Figure 3 Schematic diagram shown):

[0047] A retrieval and positioning agent corresponding to the retrieval and positioning service of map points of interest; a path planning agent corresponding to the path planning service between different map points of interest; a navigation agent corresponding to the navigation service between different map points of interest; and an association recommendation agent corresponding to the association recommendation service of map points of interest.

[0048] The agent pre-built in this step is based on the various services or functions provided by the map application for map points of interest. It not only uses agent technology to make it more powerful in semantic understanding and complex problem handling, but also combines RAG technology to improve the accuracy and knowledge richness of the generative large language model used in forming the agent when processing information, especially to enable it to obtain real-time information from the outside to solve dynamic needs. The core idea of ​​RAG technology is to obtain information related to user queries (in this disclosure, the user initiates dynamic needs related to map points of interest) through an external retrieval system, and combine this information with other capabilities of the generative large language model to generate more context-aware and knowledge-rich answers.

[0049] The technical principle of RAG includes two main steps:

[0050] Retrieval: When receiving a user's query or input, the agent built with RAG technology can first retrieve information related to the input content (such as map points of interest) from an external document database, knowledge base or search engine through a retriever (usually a semantic search-based tool such as inverted index or neural network retrieval);

[0051] Generation phase: The retrieved relevant information will be input into the generative large language model (such as the GPT series, BERT, etc.) together with the user's original input as context. This information will serve as supplementary information for the generative large language model to gain more background knowledge when understanding the original input, enabling it to generate more well-founded, informative, and accurate text content as answers.

[0052] Step 203: Control the target agent to retrieve real-time information associated with the map point of interest to obtain supplementary information;

[0053] This step is to control the target agent to retrieve the real-time information associated with the map points of interest by the execution subject to obtain supplementary information, which corresponds to the retrieval stage of the agent combined with RAG technology when processing dynamic needs.

[0054] Step 204: Control the target agent to output a demand processing result corresponding to the supplementary information and demand parameters as input information.

[0055] Based on step 203, this step aims to control the target agent to output the demand processing result corresponding to the supplementary information and demand parameters as input information by the execution subject, which corresponds to the generation stage of the agent combined with RAG technology when processing dynamic demand.

[0056] The method for processing demands related to map points of interest provided in the embodiments of the present disclosure is for dynamic demands initiated by users that need to be processed in combination with real-time information associated with the map points of interest. By pre-constructing an intelligent agent based on intelligent agent technology that combines map point of interest related services and retrieval enhancement generation technology, the demand parameters corresponding to the dynamic demands are sent to a target intelligent agent with corresponding demand processing capabilities, so that the target intelligent agent can obtain the real-time information associated with the map point of interest as supplementary information by retrieval, and finally the target intelligent agent outputs a demand processing result that corresponds to the supplementary information and the demand parameters as input information and is more in line with the actual needs of the user.

[0057] Considering that the dynamic requirements that users may express to map applications are complex requirements that are difficult to fully handle through a single step operation, please refer to Figure 4 , Figure 4A flowchart of another method for processing requirements related to map points of interest provided by an embodiment of the present disclosure, wherein process 400 includes the following steps:

[0058] Step 401: Obtain dynamic requirements related to map points of interest;

[0059] This step is consistent with step 201 in process 200 and will not be described again here.

[0060] Step 402: using a preset generative large language model, split the dynamic requirement into at least two subtasks;

[0061] This step aims to enable the above-mentioned execution subject to use the pre-trained generative large language model to decompose the dynamic demand into tasks to obtain at least two subtasks, that is, the completion of all subtasks means the completion of the processing of the actual dynamic demand.

[0062] In the process of splitting the user's dynamic needs into multiple sub-tasks, the generative large language model often needs to first fully understand the semantics to obtain the expected processing intention, and then split the tasks according to the expected processing intention and the preset problem processing logic to obtain sub-tasks corresponding to each processing step.

[0063] An implementation method including but not limited to may be:

[0064] Using a generative large language model, dynamic requirements are split into at least two subtasks in a thought chain mode.

[0065] Among them, the generative large language model is a large-scale natural language processing model trained by deep learning technology. This type of model can generate corresponding outputs based on the input text, and is usually used for tasks such as dialogue generation, automatic text writing, and translation. The generative large language model can process requirements by understanding and generating text, and generate appropriate responses based on the context. In this embodiment, it is used to implement task decomposition of complex user requirements.

[0066] Among them, the Chain of Thought (COT) model refers to breaking down complex problems into a series of thinking steps with a logical order. This method is often used to solve tasks that require multiple reasoning steps. The generative large language model breaks down dynamic requirements into multiple subtasks through the "Chain of Thought Model" and reasons through the logical order of each subtask. For example, when dealing with a problem, you may first conduct a preliminary analysis, then derive the necessary information, and finally draw conclusions or perform specific operations. These steps form a chain, and each subtask is the reasoning result of the previous task. Through this model, complex problems can be simplified into a series of manageable small tasks, so that they can be solved step by step.

[0067] Step 403: Determine the target agent corresponding to each subtask;

[0068] On the basis of step 402, this step aims to determine the target agent corresponding to each subtask by the above-mentioned execution subject. Specifically, the process of assigning each subtask to a matching target agent can also be performed through the generative large language model, that is, it is necessary to pre-register each constructed agent in the generative large language model, and make it determine the matching target agent for each split subtask based on the pre-learned correspondence between different subtasks and different agents. Of course, in addition to being performed by the map application or the generative large language model controlled by the map application, the above operation can also be performed by another agent dedicated to subtask matching. No specific limitation is made here, as long as it can achieve the determination of a matching target agent for each subtask.

[0069] Step 404: Send the task parameters corresponding to each subtask to the corresponding target agent;

[0070] On the basis of step 403, this step aims to send the task parameters corresponding to each subtask to the corresponding target agent by the execution subject. The task parameters include the task information required by the target agent to process the corresponding subtask. For example, if there is a subtask to determine the planned travel route between A and B, the task parameters should at least include the POI information of A as the starting point and the POI information of B as the destination, as well as the selected restriction parameters including possible travel time, travel mode and travel preference.

[0071] Among them, the task parameters of each subtask can also come from the task description information generated by the generative large language model for each subtask. When determining the target intelligent agent matching each subtask, the matching target intelligent agent can also be determined based on the task description information corresponding to each subtask.

[0072] Step 405: Control the target agent to retrieve real-time information associated with the map point of interest to obtain supplementary information;

[0073] Step 406: Control the target agent to output a demand processing result corresponding to the supplementary information and demand parameters as input information.

[0074] The above steps 405-406 are similar to Figure 2 Steps 203-204 shown are consistent, and for the same contents, please refer to the corresponding parts of the previous embodiment, which will not be repeated here.

[0075] Compared to Figure 2The embodiment shown in this embodiment is Figure 4 The implementation provided uses a generative large language model to split the dynamic demand into multiple subtasks through steps 4021 and 403, and determines the target agent corresponding to each subtask, so as to facilitate sending the task parameters of each subtask to the corresponding target agent. The processing capability of complex dynamic demands is improved, and the user's dynamic demands can be better processed with the help of the collaboration between different target agents corresponding to different subtasks, so as to obtain a demand processing result that is more in line with user expectations and more reasonable.

[0076] In order to deepen the understanding of how to determine the matching target agent for each subtask and how to send the task parameters to the corresponding target agent, we also disclose Figure 5 and Figure 6 Two different implementations are provided, Figure 5 The illustrated process 500 includes the following steps:

[0077] Step 501: Obtain task description information generated by the generative large language model for each subtask;

[0078] Step 502: extracting the target function name from the task description information corresponding to each subtask;

[0079] This step aims to extract the target function name from the task description information corresponding to each subtask by the above-mentioned execution subject, that is, the task description information at least includes the function name and task parameters of the function that can process the subtask.

[0080] For example, if the subtask is a path planning task, then the function name recorded in the corresponding task description information may be: path planning function.

[0081] Step 503: According to the preset function registration table, a registered agent with the same target function name is determined as the target agent corresponding to the corresponding subtask;

[0082] The function registration table records the correspondence between different function names and different registered agents, and the pre-built agents with different function names will be pre-registered in the execution subject to form the function registration table. This step aims to determine the registered agent with the same target function name as the target agent corresponding to the corresponding subtask by the execution subject according to the correspondence recorded in the function registration table.

[0083] Step 504: Send the task parameters corresponding to each subtask to the corresponding target agent.

[0084] The purpose of this step is for the above-mentioned subject to send the task parameters extracted from the task description information corresponding to each subtask to the corresponding target intelligent agent.

[0085] Figure 6 The process 600 shown includes the following steps:

[0086] Step 601: Obtain task description information generated by the generative large language model for each subtask;

[0087] Step 602: extracting the target function name from the task description information corresponding to each subtask;

[0088] Step 601 - Step 602 are consistent with step 501 - Step 502 and will not be repeated here.

[0089] Step 603: Determine the target routing address corresponding to the target function name according to the preset function routing registration table;

[0090] The function routing registry records the correspondence between different function names and different routing addresses, and different routing addresses are used to call different registered agents. Pre-built agents with different function names will be registered in advance in the above-mentioned execution subject, thereby forming the function routing registry.

[0091] This step is intended for the above-mentioned execution subject to determine the target routing address corresponding to the target function name according to the corresponding relationship recorded in the function routing registration table.

[0092] Step 604: Determine the registered agent that can be called through the target routing address as the target agent corresponding to the corresponding subtask;

[0093] On the basis of step 603, this step aims to determine the registered agent that can be called through the target routing address as the target agent corresponding to the corresponding subtask by the above-mentioned execution subject.

[0094] Step 605: extracting corresponding task parameters from the task description information corresponding to each subtask;

[0095] Step 606: The extracted task parameters are transmitted to the corresponding target agents through the corresponding target routing addresses.

[0096] In step 605-step 606, the above-mentioned execution subject transfers the task parameters extracted from the task description information to the corresponding target intelligent agent through the target routing address, thereby sending the task parameters to the target intelligent agent.

[0097] exist Figure 4On the basis of the solution provided by the illustrated embodiment, since the complex dynamic requirements are split into multiple subtasks with the help of a generative large language model, process 203 will also be adaptively changed to: the above-mentioned execution subject controls each target intelligent agent to retrieve real-time information on the map points of interest contained in the received task parameters, and obtains the retrieval results, and the supplementary information includes the retrieval results.

[0098] To deepen your understanding of how the target agent retrieves real-time information about the map points of interest contained in the task parameters, please refer to Figure 7 , Figure 7 A flowchart of a method for retrieving supplementary information for each target agent according to task parameters provided in an embodiment of the present disclosure is intended to control each target agent to perform the following retrieval steps as shown in process 700:

[0099] Step 701: extracting map points of interest from received task parameters;

[0100] Step 702: calling a preset search tool to search for a search statement constructed with the map interest points as search keywords, and obtaining a real-time search result returned by the preset search tool;

[0101] Among them, the preset detection tool may include: at least one of: a preset search engine, a preset geographic knowledge graph, a preset road administration information source, and a preset lane-level road database.

[0102] Among them, a map point of interest refers to a specific geographical location or object on the map that is of interest to the user, such as a restaurant, a store, a scenic spot, a hospital, etc. Using it as a search keyword means using it as a keyword or search item, which may be a name, classification, description or other identification information related to the location. The constructed search statement can be a complete search statement or query string using the relevant information of the map point of interest. This statement can be a search request for a specific field. For example, the search statement may be "find nearby restaurants" or "query medical facilities in the area".

[0103] The construction of the search statement depends on the input points of interest and may be combined with specific geographic locations, time or other filtering conditions. The key to this step is to dynamically generate queries based on the points of interest data, rather than static queries, and can be combined with historical interaction data between the user and the map application or the user's real-time profile or preferences.

[0104] Step 703: Generate supplementary prompt words according to the real-time search results.

[0105] Based on step 702, this step aims to generate supplementary prompt words by the execution subject according to the real-time search results. The supplementary prompt words can form more comprehensive input information together with the original dynamic requirement expression or the task parameters of the current subtask, so that the target agent can output a more accurate answer to the input information.

[0106] Based on how to control the target agents to retrieve the supplementary information respectively given in the previous embodiment, the demand processing result matching the dynamic demand can also be obtained in the following manner:

[0107] The target intelligent agent corresponding to the last subtask is controlled by the above-mentioned execution subject to output the demand processing result corresponding to the input information together with the corresponding supplementary information and task parameters.

[0108] Among them, the last subtask is the subtask that is executed last in the execution sequence of each subtask. The execution sequence is determined according to the execution dependency relationship between each subtask (the execution dependency relationship is usually reflected by splitting the subtasks in a chain of thought), and the task parameters of the subtask executed later are determined based on the subtask processing results of the subtask executed earlier. That is, the input information of the target agent of the last subtask has collected the output results of the target agent of the previous subtask, so the output result of the target agent of the last subtask can be used as the demand processing result of the dynamic demand.

[0109] To deepen understanding, the present disclosure also provides a specific implementation solution in combination with a specific application scenario:

[0110] Assuming that the dynamic demand passed in by the user is specifically to determine the actual time taken to travel from the first map point of interest to the second map point of interest within a preset time period, the generative large language model can be first used to split the dynamic demand into sequentially executed retrieval and positioning subtasks, path planning subtasks, and navigation subtasks in a thought chain manner.

[0111] Among them, the retrieval and positioning subtask is used to locate the actual geographical locations of the first map point of interest and the second map point of interest, the path planning subtask is used to determine the travel route according to the actual geographical locations of the first map point of interest and the second map point of interest, and the navigation subtask is used to determine the actual time consumed to travel along the travel route during a preset time period.

[0112] After the retrieval and positioning subtask is sent to the retrieval and positioning agent, the retrieval and positioning agent can be controlled to retrieve the first real-time information associated with the names of the first map point of interest and the second map point of interest to obtain the first supplementary information;

[0113] After the path planning subtask is sent to the path planning agent, the path planning agent can be controlled to retrieve the second real-time information associated with each actual road section covered by the travel route and the preset time period to obtain the second supplementary information;

[0114] After the navigation subtask is sent to the navigation agent, the navigation agent can be controlled to retrieve third real-time information associated with travel routes using different means of transportation during a preset time period to obtain third supplementary information.

[0115] Finally, the navigation agent is controlled to output the predicted time corresponding to the third supplementary information and the corresponding task parameters as input information.

[0116] Among them, the task parameters sent to the navigation agent are determined based on the task parameters of the navigation subtask and the subtask processing results of the path planning subtask, the subtask processing results of the path planning subtask are determined based on the task parameters of the path planning subtask, the second supplementary information and the subtask processing results of the retrieval and positioning subtask, and the subtask processing results of the retrieval and positioning subtask are determined based on the task parameters of the retrieval and positioning subtask and the first supplementary information.

[0117] Still taking "How long does it take to drive from Company A to City B next Monday" as an example, the execution subject of this embodiment can first split it into POI retrieval tasks and assign it to the retrieval and positioning agent to obtain the geographical location information of the user's starting point (Company A) and the end point (City B);

[0118] Then, the split path planning task is assigned to the path planning agent. After receiving the geographical location information of Company A and City B from the retrieval and positioning agent, the path planning agent searches for multiple alternative travel routes and sections between the two locations, and optimizes them based on the real-time traffic information, weather information, and license plate restriction information in the future (next Monday), to obtain the optimal travel route with the least congestion possible.

[0119] Finally, the split navigation tasks will be further assigned to the navigation agent. The navigation agent will obtain the preferred travel route from the path planning agent, provide navigation information combined with the selected travel tools, and extract the estimated travel time from the navigation information and feed it back to the user.

[0120] Further references Figure 8 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for processing requirements related to map points of interest. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0121] like Figure 8As shown, the processing device 800 for map interest point related requirements of this embodiment may include: a dynamic requirement acquisition unit 801, a requirement parameter delivery unit 802, a real-time information retrieval unit 803, and a requirement processing result output unit 804. The dynamic requirement acquisition unit 801 is configured to acquire dynamic requirements related to map interest points; wherein the dynamic requirements are requirements that need to be processed in combination with real-time information associated with map interest points; the requirement parameter delivery unit 802 is configured to deliver the requirement parameters corresponding to the dynamic requirements to a target agent with corresponding requirement processing capabilities; wherein the target agent is pre-built based on the agent technology that combines map interest point related services and retrieval enhancement generation technology; the real-time information retrieval unit 803 is configured to control the target agent to retrieve the real-time information associated with the map interest points to obtain supplementary information; the requirement processing result output unit 804 is configured to control the target agent to output the requirement processing result corresponding to the supplementary information and the requirement parameters as input information.

[0122] In this embodiment, in the processing device 800 for processing requirements related to map points of interest: the specific processing of the dynamic requirement acquisition unit 801, the requirement parameter issuing unit 802, the real-time information retrieval unit 803, and the requirement processing result output unit 804 and the technical effects thereof can be referred to respectively. Figure 2 The relevant descriptions of steps 201 - 204 in the corresponding embodiment are not repeated here.

[0123] In some optional implementations of this embodiment, the dynamic demand acquisition unit 801 may be further configured to:

[0124] Get any requirements related to map points of interest;

[0125] In response to any demand containing a preset keyword representing a need to process the demand in combination with real-time information associated with a map point of interest, the acquired any demand is determined to be a dynamic demand.

[0126] In some optional implementations of this embodiment, the target agent includes at least one of the following:

[0127] A retrieval and positioning agent corresponding to the retrieval and positioning service of the map point of interest;

[0128] A path planning agent corresponding to the path planning service between different map points of interest;

[0129] A navigation agent corresponding to navigation services between different map points of interest;

[0130] An associated recommendation agent corresponding to the associated recommendation service for map points of interest.

[0131] In some optional implementations of this embodiment, the processing device 800 for requirements related to map points of interest may further include:

[0132] A demand splitting unit is configured to split the dynamic demand into at least two subtasks using a preset generative large language model;

[0133] A matching agent determination unit, configured to determine a target agent corresponding to each subtask;

[0134] Correspondingly, the demand parameter delivery 802 may include:

[0135] The task parameter sending subunit is configured to send the task parameters corresponding to each subtask to the corresponding target intelligent agent.

[0136] In some optional implementations of this embodiment, the demand splitting unit may include:

[0137] The thought chain mode splitting sub-unit is configured to utilize a generative large language model to split the dynamic requirement into at least two sub-tasks in a thought chain mode.

[0138] In some optional implementations of this embodiment, the thought chain pattern splitting sub-unit may be further configured as follows:

[0139] In response to the dynamic demand for determining the actual time consumed to travel from a first map point of interest to a second map point of interest within a preset time period, a generative large language model is used to split the dynamic demand into a retrieval and positioning subtask, a path planning subtask, and a navigation subtask that are executed sequentially in a thought chain manner; wherein the retrieval and positioning subtask is used to locate the actual geographical locations of the first map point of interest and the second map point of interest, the path planning subtask is used to determine a travel route based on the actual geographical locations of the first map point of interest and the second map point of interest, and the navigation subtask is used to determine the actual time consumed to travel along the travel route within the preset time period.

[0140] In some optional implementations of this embodiment, the matching agent determination unit may include:

[0141] The task description information acquisition subunit is configured to acquire the task description information generated by the generative large language model for each subtask;

[0142] The matching agent determination subunit is configured to determine the target agent corresponding to the corresponding subtask based on the task description information corresponding to each subtask.

[0143] In some optional implementations of this embodiment, the matching agent determination subunit may include:

[0144] A function name extraction module is configured to extract a target function name from task description information corresponding to each subtask;

[0145] The agent matching module is configured to determine the registered agent with the same target function name as the target agent corresponding to the corresponding subtask based on a preset function registration table; wherein the function registration table records the correspondence between different function names and different registered agents.

[0146] In some optional implementations of this embodiment, the agent matching module may be further configured to:

[0147] In response to the function registration table being a function routing registration table, determining a target routing address corresponding to the target function name according to the function routing registration table; wherein the function routing registration table records the correspondence between different function names and different routing addresses, and different routing addresses are used to call different registered agents;

[0148] The registered intelligent agent that can be called through the target routing address is determined as the target intelligent agent corresponding to the corresponding subtask.

[0149] In some optional implementations of this embodiment, the task parameter sending subunit may be further configured as follows:

[0150] Extracting corresponding task parameters from the task description information corresponding to each subtask;

[0151] The extracted task parameters are transmitted to the corresponding target agent through the corresponding target routing address.

[0152] In some optional implementations of this embodiment, the real-time information retrieval unit 803 may include:

[0153] The real-time information retrieval subunit is configured to control each target intelligent agent to retrieve the real-time information of the map interest points contained in the received task parameters to obtain the retrieval results; wherein the supplementary information includes the retrieval results.

[0154] In some optional implementations of this embodiment, the real-time information retrieval subunit may be further configured to:

[0155] For each target agent, the target agent is controlled to perform the following retrieval steps:

[0156] Extracting map points of interest from received task parameters;

[0157] Calling a preset search tool to search for a search statement constructed by using the map interest points as search keywords, and obtaining a real-time search result returned by the preset search tool;

[0158] Supplementary prompt words are generated according to the real-time search results; wherein the supplementary information includes the supplementary prompt words.

[0159] In some optional implementations of this embodiment, the preset search tool includes any of the following:

[0160] Preset search engine, preset geographic knowledge graph, preset road administration information source, preset lane-level road database.

[0161] In some optional implementations of this embodiment, the demand processing result output unit 804 may be further configured to:

[0162] Control the target intelligent agent corresponding to the last subtask to output the demand processing result corresponding to the corresponding supplementary information and task parameters as input information; wherein, the last subtask is the subtask that is executed last in the execution sequence of each subtask, the execution sequence is determined according to the execution dependency relationship between the subtasks, and the task parameters of the subtask executed later are determined based on the subtask processing results of the subtask executed earlier.

[0163] In some optional implementations of this embodiment, the real-time information retrieval unit 803 may include being further configured to:

[0164] In response to the retrieval positioning subtask being sent to the retrieval positioning agent, controlling the retrieval positioning agent to retrieve first real-time information associated with the names of the first map point of interest and the second map point of interest to obtain first supplementary information;

[0165] In response to the path planning subtask being sent to the path planning agent, controlling the path planning agent to retrieve second real-time information associated with each actual road section covered by the travel route and the preset time period to obtain second supplementary information;

[0166] In response to the navigation subtask being sent to the navigation agent, the navigation agent is controlled to retrieve third real-time information associated with traveling along the travel route using different transportation tools during a preset time period to obtain third supplementary information.

[0167] In some optional implementations of this embodiment, the demand processing result output unit 804 may be further configured to:

[0168] Control the navigation agent to output the predicted time corresponding to the input information using the third supplementary information and corresponding task parameters; wherein the task parameters sent to the navigation agent are determined based on the task parameters of the navigation subtask and the subtask processing results of the path planning subtask, the subtask processing results of the path planning subtask are determined based on the task parameters of the path planning subtask, the second supplementary information and the subtask processing results of the retrieval and positioning subtask, and the subtask processing results of the retrieval and positioning subtask are determined based on the task parameters of the retrieval and positioning subtask and the first supplementary information.

[0169] This embodiment exists as an apparatus embodiment corresponding to the above-mentioned method embodiment. The apparatus for processing demands related to map points of interest provided by this embodiment is for dynamic demands initiated by users that need to be processed in combination with real-time information associated with the map points of interest. An intelligent agent is pre-constructed based on intelligent agent technology that combines map point of interest related services and retrieval enhancement generation technology. The demand parameters corresponding to the dynamic demands are sent to a target intelligent agent with corresponding demand processing capabilities, so that the target intelligent agent can first obtain the real-time information associated with the map point of interest as supplementary information by retrieval, and finally enable the target intelligent agent to output demand processing results that are more in line with the actual needs of the user and correspond to the supplementary information and demand parameters as input information.

[0170] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: 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 implement the processing method for requirements related to map points of interest described in any of the above embodiments when executing.

[0171] According to an embodiment of the present disclosure, the present disclosure further provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the processing method related to map interest points described in any of the above embodiments when executed.

[0172] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, which, when executed by a processor, can implement the method for processing requirements related to map points of interest described in any of the above embodiments.

[0173] Fig. 9A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, 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 required herein.

[0174] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0175] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0176] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 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, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as a processing method for requirements related to map points of interest. For example, in some embodiments, the processing method for requirements related to map points of interest may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the processing method for requirements related to map points of interest described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured in any other appropriate manner (eg, by means of firmware) to execute a processing method for requirements related to map points of interest.

[0177] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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 special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0179] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0180] 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types 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 input, voice input, or tactile input).

[0181] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may 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.

[0182] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0183] According to the technical solution of the embodiment of the present disclosure, for the dynamic demand initiated by the user that needs to be processed in combination with the real-time information associated with the map point of interest, the intelligent agent constructed in advance based on the intelligent agent technology combined with the retrieval enhancement generation technology for the map point of interest related services can send the demand parameters corresponding to the dynamic demand to the target intelligent agent with the corresponding demand processing capability, so that the target intelligent agent can first obtain the real-time information associated with the map point of interest as supplementary information by retrieval, and then the target intelligent agent can output the demand processing result that corresponds to the supplementary information and the demand parameters as input information and better meets the actual needs of the user.

[0184] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0185] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for processing requirements related to map points of interest, comprising: Acquire dynamic demands related to the map point of interest; wherein the dynamic demands are demands that need to be processed in combination with real-time information associated with the map point of interest; Sending the demand parameters corresponding to the dynamic demand to a target intelligent agent with corresponding demand processing capability; wherein the target intelligent agent is pre-built based on intelligent agent technology combining map interest point related services and retrieval enhancement generation technology; Controlling the target agent to retrieve real-time information associated with the map point of interest to obtain supplementary information; The target agent is controlled to output a demand processing result corresponding to the supplementary information and the demand parameter as input information.

2. The method according to claim 1, wherein: The obtaining of dynamic requirements related to the map points of interest includes: Get any requirements related to map points of interest; In response to the arbitrary demand containing a preset keyword indicating that demand processing needs to be performed in combination with the real-time information associated with the map point of interest, the acquired arbitrary demand is determined to be the dynamic demand.

3. The method according to claim 1 or 2, wherein: The target agent includes at least one of the following: A retrieval and positioning agent corresponding to the retrieval and positioning service of the map point of interest; A path planning agent corresponding to the path planning service between different map points of interest; A navigation agent corresponding to navigation services between different map points of interest; An associated recommendation agent corresponding to the associated recommendation service for map points of interest.

4. The method according to claim 3, further comprising: Using a preset generative large language model, split the dynamic requirement into at least two subtasks; Determining a target agent corresponding to each of the subtasks; Correspondingly, the step of sending the demand parameters corresponding to the dynamic demand to the target agent having the corresponding demand processing capability includes: The task parameters corresponding to each of the subtasks are sent to the corresponding target agent.

5. The method according to claim 4, wherein: The method uses a preset generative large language model to split the dynamic demand into at least two subtasks, including: The generative large language model is used to split the dynamic demand into at least two subtasks in a thought chain mode.

6. The method according to claim 5, wherein: The utilizing of the generative large language model to split the dynamic requirement into at least two subtasks in a thought chain mode includes: In response to the dynamic demand for determining the actual time consumed to travel from a first map point of interest to a second map point of interest within a preset time period, the generative large language model is used to split the dynamic demand into a retrieval and positioning subtask, a path planning subtask, and a navigation subtask that are executed sequentially in accordance with the thought chain method; wherein the retrieval and positioning subtask is used to locate the actual geographical locations of the first map point of interest and the second map point of interest, the path planning subtask is used to determine a travel route based on the actual geographical locations of the first map point of interest and the second map point of interest, and the navigation subtask is used to determine the actual time consumed to travel along the travel route within the preset time period.

7. The method according to claim 4, wherein: The step of determining a target intelligent agent corresponding to each of the subtasks comprises: Obtaining task description information generated by the generative large language model for each of the subtasks; According to the task description information corresponding to each of the subtasks, a target intelligent agent corresponding to the corresponding subtask is determined.

8. The method according to claim 7, wherein: The step of determining a target agent corresponding to each subtask according to the task description information corresponding to each subtask includes: Extracting a target function name from the task description information corresponding to each of the subtasks; According to a preset function registration table, a registered agent having the same target function name is determined as the target agent corresponding to the corresponding subtask; wherein the function registration table records the correspondence between different function names and different registered agents.

9. The method according to claim 8, wherein: The step of determining, according to a preset function registration table, a registered agent having the same target function name as a target agent corresponding to a corresponding subtask includes: In response to the function registration table being a function routing registration table, determining a target routing address corresponding to the target function name according to the function routing registration table; wherein the function routing registration table records the correspondence between different function names and different routing addresses, and different routing addresses are used to call different registered agents; A registered agent that can be called through the target routing address is determined as a target agent corresponding to the corresponding subtask.

10. The method according to claim 9, wherein: The step of sending the task parameters corresponding to each of the subtasks to the corresponding target agent includes: Extracting corresponding task parameters from the task description information corresponding to each of the subtasks; The extracted task parameters are transmitted to the corresponding target agent through the corresponding target routing address.

11. The method according to claim 4, wherein: The controlling the target agent to retrieve the real-time information associated with the map point of interest to obtain supplementary information includes: Each of the target intelligent agents is controlled to retrieve real-time information of the map interest points contained in the received task parameters to obtain retrieval results; wherein the supplementary information includes the retrieval results.

12. The method according to claim 11, wherein: The respectively controlling each of the target intelligent agents to retrieve the real-time information of the map interest points contained in the received task parameters to obtain the retrieval results includes: For each of the target intelligent agents, the target intelligent agent is controlled to perform the following retrieval steps: Extracting the map points of interest from the received task parameters; Calling a preset search tool to search for a search statement constructed with the map interest point acting as a search keyword, and obtaining a real-time search result returned by the preset search tool; A supplementary prompt word is generated according to the real-time search result; wherein the supplementary information includes the supplementary prompt word.

13. The method according to claim 12, wherein: The preset search tool includes any of the following: Preset search engine, preset geographic knowledge graph, preset road administration information source, preset lane-level road database.

14. The method according to claim 11, wherein: The controlling the target agent to output a demand processing result corresponding to the supplementary information and the demand parameter as input information comprises: Control the target intelligent agent corresponding to the last subtask to output the demand processing result corresponding to the input information with the corresponding supplementary information and task parameters; wherein the last subtask is the subtask that is executed last in the execution sequence among the subtasks, the execution sequence is determined according to the execution dependency relationship between the subtasks, and the task parameters of the subtask executed later are determined based on the subtask processing results of the subtask executed earlier.

15. The method according to claim 6, wherein: The controlling the target agent to retrieve the real-time information associated with the map point of interest to obtain supplementary information includes: In response to the retrieval and positioning subtask being sent to the retrieval and positioning agent, controlling the retrieval and positioning agent to retrieve first real-time information associated with the names of the first map point of interest and the second map point of interest to obtain first supplementary information; In response to the path planning subtask being sent to the path planning agent, controlling the path planning agent to retrieve second real-time information associated with each actual road section covered by the travel route and the preset time period to obtain second supplementary information; In response to the navigation subtask being sent to the navigation agent, the navigation agent is controlled to retrieve third real-time information associated with traveling along the travel route using different means of transportation during the preset time period to obtain third supplementary information.

16. The method according to claim 15, wherein: The controlling the target agent to output a demand processing result corresponding to the supplementary information and the demand parameter as input information comprises: Control the navigation agent to output the predicted time corresponding to the third supplementary information and the corresponding task parameters as input information; wherein, the task parameters sent to the navigation agent are determined based on the task parameters of the navigation subtask and the subtask processing results of the path planning subtask, the subtask processing results of the path planning subtask are determined based on the task parameters of the path planning subtask, the second supplementary information and the subtask processing results of the retrieval and positioning subtask, and the subtask processing results of the retrieval and positioning subtask are determined based on the task parameters of the retrieval and positioning subtask and the first supplementary information.

17. A device for processing requirements related to map points of interest, comprising: A dynamic demand acquisition unit is configured to acquire dynamic demands related to a map point of interest; wherein the dynamic demands are demands that need to be processed in combination with real-time information associated with the map point of interest; A demand parameter sending unit is configured to send the demand parameters corresponding to the dynamic demand to a target intelligent agent with corresponding demand processing capability; wherein the target intelligent agent is pre-built based on the intelligent agent technology combining map interest point related services and retrieval enhancement generation technology; A real-time information retrieval unit, configured to control the target agent to retrieve real-time information associated with the map point of interest to obtain supplementary information; The demand processing result output unit is configured to control the target agent to output the demand processing result corresponding to the supplementary information and the demand parameter as input information.

18. The device according to claim 17, wherein: The dynamic demand acquisition unit is further configured to: Get any requirements related to map points of interest; In response to the arbitrary demand containing a preset keyword indicating that demand processing needs to be performed in combination with the real-time information associated with the map point of interest, the acquired arbitrary demand is determined to be the dynamic demand.

19. The device according to claim 17 or 18, wherein: The target agent includes at least one of the following: A retrieval and positioning agent corresponding to the retrieval and positioning service of the map point of interest; A path planning agent corresponding to the path planning service between different map points of interest; A navigation agent corresponding to navigation services between different map points of interest; An associated recommendation agent corresponding to the associated recommendation service for map points of interest.

20. The apparatus according to claim 19, further comprising: A demand splitting unit is configured to split the dynamic demand into at least two subtasks using a preset generative large language model; A matching agent determination unit, configured to determine a target agent corresponding to each of the subtasks; Correspondingly, the demand parameter issuing unit includes: The task parameter sending subunit is configured to send the task parameters corresponding to each of the subtasks to the corresponding target intelligent agent.

21. The device according to claim 20, wherein: The demand splitting unit comprises: The thought chain mode splitting sub-unit is configured to utilize the generative large language model to split the dynamic requirement into at least two sub-tasks in a thought chain mode.

22. The device according to claim 21, wherein The thought chain mode splitting subunit is further configured as follows: In response to the dynamic demand for determining the actual time consumed to travel from a first map point of interest to a second map point of interest within a preset time period, the generative large language model is used to split the dynamic demand into a retrieval and positioning subtask, a path planning subtask, and a navigation subtask that are executed sequentially in accordance with the thought chain method; wherein the retrieval and positioning subtask is used to locate the actual geographical locations of the first map point of interest and the second map point of interest, the path planning subtask is used to determine a travel route based on the actual geographical locations of the first map point of interest and the second map point of interest, and the navigation subtask is used to determine the actual time consumed to travel along the travel route within the preset time period.

23. The device according to claim 20, wherein: The matching agent determination unit comprises: A task description information acquisition subunit is configured to acquire task description information generated by the generative large language model for each of the subtasks; The matching agent determination subunit is configured to determine the target agent corresponding to the corresponding subtask based on the task description information corresponding to each of the subtasks.

24. The device according to claim 23, wherein: The matching agent determination subunit comprises: A function name extraction module is configured to extract a target function name from the task description information corresponding to each of the subtasks; The agent matching module is configured to determine, based on a preset function registration table, a registered agent with the same target function name as the target agent corresponding to the corresponding subtask; wherein the function registration table records the correspondence between different function names and different registered agents.

25. The device according to claim 24, wherein: The agent matching module is further configured to: In response to the function registration table being a function routing registration table, determining a target routing address corresponding to the target function name according to the function routing registration table; wherein the function routing registration table records the correspondence between different function names and different routing addresses, and different routing addresses are used to call different registered agents; A registered agent that can be called through the target routing address is determined as a target agent corresponding to the corresponding subtask.

26. The device according to claim 25, wherein The task parameter sending subunit is further configured as follows: Extracting corresponding task parameters from the task description information corresponding to each of the subtasks; The extracted task parameters are transmitted to the corresponding target agent through the corresponding target routing address.

27. The device according to claim 20, wherein: The real-time information retrieval unit comprises: The real-time information retrieval subunit is configured to control each of the target agents to retrieve real-time information on the map points of interest contained in the received task parameters to obtain retrieval results; wherein the supplementary information includes the retrieval results.

28. The device according to claim 27, wherein The sub-real-time information retrieval sub-unit is further configured to: For each of the target intelligent agents, the target intelligent agent is controlled to perform the following retrieval steps: Extracting the map points of interest from the received task parameters; Calling a preset search tool to search for a search statement constructed with the map interest point acting as a search keyword, and obtaining a real-time search result returned by the preset search tool; A supplementary prompt word is generated according to the real-time search result; wherein the supplementary information includes the supplementary prompt word.

29. The device according to claim 28, wherein The preset search tool includes any of the following: Preset search engine, preset geographic knowledge graph, preset road administration information source, preset lane-level road database.

30. The device according to claim 27, wherein: The demand processing result output unit is further configured to: Control the target intelligent agent corresponding to the last subtask to output the demand processing result corresponding to the corresponding supplementary information and task parameters as input information; wherein, the last subtask is the subtask that is executed last in the execution sequence among the subtasks, the execution sequence is determined according to the execution dependency relationship between the subtasks, and the task parameters of the subtask executed later are determined based on the subtask processing results of the subtask executed earlier.

31. The device according to claim 22, wherein: The real-time information retrieval unit includes a unit further configured to: In response to the retrieval and positioning subtask being sent to the retrieval and positioning agent, controlling the retrieval and positioning agent to retrieve first real-time information associated with the names of the first map point of interest and the second map point of interest to obtain first supplementary information; In response to the path planning subtask being sent to the path planning agent, controlling the path planning agent to retrieve second real-time information associated with each actual road section covered by the travel route and the preset time period to obtain second supplementary information; In response to the navigation subtask being sent to the navigation agent, the navigation agent is controlled to retrieve third real-time information associated with traveling along the travel route using different means of transportation during the preset time period to obtain third supplementary information.

32. The device according to claim 31, wherein The demand processing result output unit is further configured to: Control the navigation agent to output the predicted time corresponding to the third supplementary information and the corresponding task parameters as input information; wherein, the task parameters sent to the navigation agent are determined based on the task parameters of the navigation subtask and the subtask processing results of the path planning subtask, the subtask processing results of the path planning subtask are determined based on the task parameters of the path planning subtask, the second supplementary information and the subtask processing results of the retrieval and positioning subtask, and the subtask processing results of the retrieval and positioning subtask are determined based on the task parameters of the retrieval and positioning subtask and the first supplementary information.

33. An electronic device comprising: at least one processor; as well as 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 for processing requirements related to map points of interest described in any one of claims 1-16.

34. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method for processing requirements related to map points of interest as described in any one of claims 1-16.

35. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for processing requirements related to map points of interest according to any one of claims 1 to 16.

Images