Method and system for intelligent agent task linkage execution based on navigation and life service
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING DAFANG YUNTU TECH CO LTD
- Filing Date
- 2026-03-05
- Publication Date
- 2026-06-16
Smart Images
Figure CN121787464B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent agent technology, and in particular to a method and system for intelligent agent task linkage execution based on navigation and life services. Background Technology
[0002] With the deep integration of smart business districts and urban life services, users are demanding more personalized and continuous service experiences during their travel and consumption processes. The system needs to be able to dynamically sense users' behavioral habits and real-time location, achieve seamless connections between multiple service nodes, and adjust subsequent action paths in real time based on service execution status, thereby improving overall service efficiency and user experience.
[0003] Current solutions construct task flows by integrating users' historical trajectories and preference information, and generate navigation guidance by combining indoor positioning and route planning. They also utilize service status feedback from IoT devices to locally optimize the task sequence, achieving a certain degree of service linkage and route adaptation. However, these solutions lack a multi-agent collaborative decision-making mechanism during task sequence generation and adjustment, making it difficult to efficiently model complex and dynamic service dependencies. This results in rigid task scheduling, delayed responses, and an inability to fully adapt to changes in user behavior and fluctuations in the service environment, thus hindering the level of intelligent integration between navigation and life services. Summary of the Invention
[0004] The purpose of this application is to provide a method and system for intelligent agent task linkage execution based on navigation and life services, so as to solve the problems of rigid task scheduling and delayed response caused by the lack of multi-agent collaborative decision-making in the existing technology.
[0005] To address the aforementioned technical problems, in a first aspect, this application provides a method for the coordinated execution of intelligent agent tasks based on navigation and life services, including:
[0006] Collect user-related data, including travel preference data and historical travel trajectory data;
[0007] The historical travel trajectory data is processed by multiple agents to perform time-series correlation processing, and combined with the travel preference data, a first task sequence is generated;
[0008] Obtain indoor positioning information of service points corresponding to each service link in the first task sequence, and generate a first navigation path based on the indoor positioning information using path planning technology;
[0009] Utilize IoT-based device collaborative control technology to construct a two-way communication channel between IoT devices and corresponding service links within the target business district;
[0010] The service status information of each service link fed back by each IoT device is obtained through the bidirectional communication channel, and the first task sequence is adjusted according to the service status information to generate a second task sequence and a second navigation path.
[0011] Navigation and life services are executed by multiple agents in a coordinated manner according to the second task sequence and the second navigation path.
[0012] Optionally, multi-agent processing is used to perform time-series correlation processing on the historical travel trajectory data, and combined with the travel preference data, a first task sequence is generated, including:
[0013] The multi-agent trajectory processing module extracts target trajectory data related to the target business district from the historical travel trajectory data.
[0014] Based on the location information of each trajectory node in the target trajectory data and the location coverage of each service type in the target business district and similar business districts, the service type corresponding to each trajectory node in the same historical travel process is analyzed by the multi-agent point matching module to generate analysis results.
[0015] The multi-agent preference parsing module extracts user preference features for each service type from the travel preference data;
[0016] The multi-agent data processing module compares the analysis results with the preference features to filter out the first service type combination that meets both the correlation features and the preference features. The correlation features are the correlation features between the second service type combinations in the same historical travel process extracted from the analysis results.
[0017] Based on the distribution of service points already open within the target business district, the multi-agent task orchestration module associates and matches the first service type with the corresponding service points according to the order of service steps in the user's historical travel process, generating the first task sequence.
[0018] Secondly, this application provides an intelligent agent task linkage execution system based on navigation and life services, including:
[0019] The data collection module is used to collect user-related data, including travel preference data and historical travel trajectory data.
[0020] The association module is used to perform time-series association processing on the historical travel trajectory data using multiple agents, and combine it with the travel preference data to generate a first task sequence;
[0021] The generation module is used to obtain indoor positioning information of service points corresponding to each service link in the first task sequence, and generate a first navigation path based on the indoor positioning information using path planning technology.
[0022] The module is used to build a two-way communication channel between IoT devices and various service links within the target business area using IoT-based device collaborative control technology.
[0023] The adjustment module is used to obtain service status information of each service link fed back by each IoT device through the bidirectional communication channel, and adjust the first task sequence and generate a second task sequence and a second navigation path according to the service status information.
[0024] The execution module is used to execute navigation and life services in a coordinated manner by multiple agents according to the second task sequence and the second navigation path.
[0025] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the steps of the intelligent agent task linkage execution method based on navigation and life services as described in the first aspect above.
[0026] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the steps of the intelligent agent task linkage execution method based on navigation and life services as described in the first aspect above.
[0027] The intelligent agent task linkage execution method based on navigation and life services provided in this application has the following beneficial effects: By collecting user travel preferences and historical trajectory data, multi-agents perform temporal correlation analysis on the trajectory and fuse preferences to generate an initial task sequence. Then, indoor positioning information is combined to plan the navigation path. At the same time, a two-way communication channel between IoT devices is built to obtain service status in real time, and the task sequence and navigation path are dynamically adjusted accordingly. Finally, the updated tasks and paths are executed collaboratively by multiple agents. This realizes an integrated linkage mechanism from user behavior understanding, intelligent task orchestration, dynamic path generation to closed-loop feedback of service status, improving the flexibility of service response, the adaptability of task scheduling, and the collaborative efficiency between navigation and life services.
[0028] Furthermore, this application utilizes a multi-agent architecture with modules for trajectory processing, location matching, preference parsing, and data processing to extract relevant behaviors of the target business district from historical trajectories, identify the service types corresponding to each trajectory node, and, combined with user preference features for service types, select service type combinations that conform to both historical behavioral correlation patterns and individual preferences. Based on the actual distribution of open service points within the business district, tasks are arranged according to historical service order. This enhances the personalization and contextual consistency of task sequence generation, making the initial tasks more closely aligned with the user's true intentions and the business district's service capabilities, laying a precise foundation for subsequent dynamic adjustments and efficient execution. Attached Figure Description
[0029] To more clearly illustrate the technical solutions of the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0030] Figure 1 A flowchart illustrating the intelligent agent task linkage execution method based on navigation and life services provided in this application embodiment;
[0031] Figure 2 A schematic diagram illustrating a specific implementation of the intelligent agent task linkage execution method based on navigation and life services provided in this application embodiment;
[0032] Figure 3 This is a schematic diagram of the structure of an intelligent agent task linkage execution system based on navigation and life services provided in an embodiment of this application. Detailed Implementation
[0033] To address the shortcomings of existing solutions in task scheduling, which struggle to handle dynamic changes in service dependencies and achieve multi-stage collaborative responses due to a single decision-making logic, this application provides a smart agent task linkage execution method based on navigation and life services. The core idea is to introduce a multi-agent architecture, perform time-series correlation modeling of user historical trajectories and preference data to generate an initial task sequence, integrate indoor positioning and path planning to form a navigation foundation, and establish a two-way communication channel for IoT devices to perceive service status in real time. Based on this, the task sequence and navigation path are adjusted in a coordinated manner, and finally, multiple smart agents collaboratively execute the updated task flow, thereby achieving rapid adaptation to changes in user behavior and fluctuations in the service environment at the system level.
[0034] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0035] The core of this application is to provide a method for intelligent agent task linkage execution based on navigation and life services. A flowchart of one specific implementation is shown below. Figure 1 As shown, the method includes:
[0036] Step 101: Collect user-related data, including travel preference data and historical travel trajectory data.
[0037] In this step, travel preference data refers to characteristic data obtained based on users' past choices, evaluations, feedback, and customized needs for various lifestyle services within the business district. This data includes users' preferred service types, service location selection tendencies, service consumption time preferences, and service experience standards.
[0038] Historical travel trajectory data refers to spatiotemporal data obtained based on users' past mobile location records in various business districts and surrounding areas. This data includes users' travel time, travel route, trajectory node location, dwell time at each trajectory node, and mode of transportation.
[0039] In this embodiment, the system first obtains the user's past mobile location records in various business districts through the user's mobile terminal positioning module and business district positioning sensing device. At the same time, it obtains the user's past service selections, evaluations, customizations, and other original information through the business district service platform and life service applications. Then, the system classifies and sorts the above two types of original data, extracts the effective information related to travel trajectory and the effective information related to service preferences, removes invalid and duplicate redundant data, and finally integrates them to form user-related data that includes travel preference data and historical travel trajectory data.
[0040] Step 102: Use multiple agents to perform time-series correlation processing on the historical travel trajectory data, and combine it with the travel preference data to generate a first task sequence.
[0041] In this step, the first task sequence refers to the list of executable tasks formed by combining the time-series correlation analysis results of the user's historical travel trajectory data and travel preference data with the service points that have been opened in the target business district, according to the order of service links in the user's historical travel process, and associating the preferred service types with the corresponding service points. The first task sequence includes the execution order of each service link, the corresponding service type, the service point, and the linkage requirements.
[0042] In the embodiments of this application, such as Figure 2 As shown, step 102 specifically includes the following steps:
[0043] Step 201: Extract target trajectory data related to the target business district from the historical travel trajectory data through the multi-agent trajectory processing module.
[0044] In this step, target trajectory data refers to trajectory information that is filtered from historical travel trajectory data and is associated with the geographical scope of the target business district. It may include the location of trajectory nodes, duration of stay, travel time, trajectory movement path, etc. of users in the past when they arrived at the target business district and surrounding areas, which is used to analyze the service demand correlation characteristics of users within the target business district.
[0045] For example, the trajectory processing module in this step can be composed of a boundary parsing submodule, a position matching submodule, an attribute extraction submodule, and a data processing submodule cascaded in sequence, with data transmission between the submodules through internal data interfaces or message middleware.
[0046] The boundary parsing submodule may include a geographic information parser and a range configurator, used to receive and process geographic range parameters; the location matching submodule may include a trajectory coordinate extractor and a spatial relationship determiner, used to perform the comparison between trajectory nodes and geographic ranges.
[0047] The attribute extraction submodule can include a trajectory attribute reader and a time series information extractor, used to extract attribute information of trajectory nodes; the data processing submodule can include a data cleaner and a structured integrator, used to clean, integrate and format the extracted data for output.
[0048] In this embodiment of the application, firstly, the range configurator in the boundary parsing submodule receives the geographic boundary parameters of the target business district. These parameters can be provided by a geographic information system or defined based on electronic map data. The geographic information parser converts them into spatial query conditions with a clear coordinate range and outputs them to the location matching submodule.
[0049] Subsequently, the trajectory coordinate extractor reads the location coordinates of trajectory nodes in the historical travel trajectory data one by one. The spatial relationship judge compares each coordinate with the aforementioned spatial query conditions, filters out trajectory nodes located within the geographical boundary of the target business district and the surrounding preset buffer area, and generates a list of trajectory node identifiers that meet the conditions. For example, the preset buffer area is an area within a radius of 500 meters.
[0050] Next, based on the list of trajectory node identifiers, the trajectory attribute reader extracts the travel time, stay duration, and movement path corresponding to each node from the historical trajectory database; the time sequence information extractor then recovers the movement path information between nodes from the trajectory sequence, forming a set of trajectory nodes with complete attributes.
[0051] Finally, the data cleaner performs deduplication, outlier removal, and format validation on the above set. The structure integrator organizes the cleaned data according to time series and spatial relationships and outputs it as a structured target trajectory dataset for use by the downstream point matching module.
[0052] Step 202: Based on the location information of each trajectory node in the target trajectory data and the location coverage of each service type in the target business district and similar business districts, the service type corresponding to each trajectory node in the same historical travel process is analyzed by the multi-agent point matching module to generate analysis results.
[0053] In this step, the location information of the trajectory nodes refers to the specific geographical coordinates, business district, and other location information corresponding to each trajectory node in the target trajectory data.
[0054] The location coverage of a service type refers to the geographical area covered by the service points corresponding to various services within the target business district and similar business districts.
[0055] The analysis results refer to the service types and service associations corresponding to each trajectory node passed by a user during the same historical trip, obtained through the matching analysis of trajectory nodes and service types.
[0056] For example, the point matching module can be composed of a service range management submodule, a spatial relationship calculation submodule, a type determination submodule, and a result aggregation submodule connected in sequence, and the submodules communicate with each other through a data bus or service call interface.
[0057] The service scope management submodule can include a scope data interface and a spatial index builder, which are used to access and store the coverage parameters of the storage service type.
[0058] The spatial relationship calculation submodule may include a node coordinate reader and a spatial relationship judgment engine, which are used to calculate the spatial relationship between trajectory nodes and service area;
[0059] The type determination submodule can include a matching rule base and a type binder, which are used to determine the service type corresponding to a node based on spatial relationships.
[0060] The results aggregation submodule can include a time series grouper and an analysis results generator, which are used to organize data by travel process and output structured analysis results.
[0061] In this embodiment, the service range management submodule first obtains the location coverage parameters of all service types within the target business district and similar business districts through its range data interface. These parameters include geographic coordinate boundaries and floor zoning information. The spatial index builder then organizes these parameters into a spatial index structure that can be queried efficiently.
[0062] Subsequently, the node coordinate reader reads the position information of each trajectory node sequentially from the target trajectory data; and the spatial relationship judgment engine quickly compares the coordinates of each node with the above spatial index structure, calculates the point-surface inclusion relationship, determines whether the node falls within the coverage of a certain type of service, and outputs the association pair between the node and the candidate service type.
[0063] Next, the matching rule base has preset judgment logic. For example, when a node falls into multiple service ranges, it is prioritized according to the closest distance or the main business type. The type binder determines one or more corresponding service types for each trajectory node based on the logic and the spatial relationship strength in the associated pair, and filters out nodes that have no service coverage.
[0064] Finally, the time-series grouper groups the trajectory nodes of the identified type according to the same historical travel process based on the timestamps and trip identifiers in the trajectory data; the analysis result generator sorts out the corresponding service type sequence of the nodes in each group according to their time order, integrates all groups, forms a structured analysis result, and outputs it to the data processing module.
[0065] Step 203: Extract user preference features for each service type from the travel preference data using the multi-agent preference parsing module.
[0066] In this step, preference features refer to the feature information extracted from travel preference data that can reflect users' subjective preference for various business district services. These preference features include the types of services users prefer, their acceptance of various services, and their preference patterns for service combinations.
[0067] For example, the preference parsing module consists of a data access and parsing submodule, a feature extraction and filtering submodule, a feature classification and quantization submodule, and a feature integration and output submodule, which are cascaded together. Each submodule transmits information through internal data pipelines or API calls.
[0068] The data access and parsing submodule can include multi-source data interfaces and structured parsers, used to access and parse raw travel preference data from different sources.
[0069] The feature extraction and filtering submodule may include a recognizer and a relevance filter to identify features relevant to the extracted service from the parsed data and filter out irrelevant noise;
[0070] The feature classification and quantization submodule can include a service type classifier and a feature quantifier, which are used to classify the extracted features into specific service types and calculate quantitative indicators such as selection frequency and average score.
[0071] The feature integration output submodule can contain a feature vector builder and a normalized output interface, which are used to organize the quantized features into structured feature vectors or datasets.
[0072] In this embodiment of the application, the data access and parsing submodule receives raw travel preference data through its multi-source data interface. This data may include user click records, order history, evaluation text, and actively set preference tags on the service platform. Then, the structured parser cleans, unifies the format, and performs preliminary structuring on this multi-source heterogeneous data. For example, it performs sentiment analysis on text evaluations and converts them into numerical scores, and maps unstructured preference tags to standardized service type codes.
[0073] Subsequently, the recognizer scans and identifies data entries that mention or are associated with specific service types from structured data based on a predefined service type keyword library or machine learning model; the relevance filter, according to preset rules, such as removing entries that only involve "mode of transportation" or "weather" and are unrelated to service provision, filters out noise information that is not directly related to service preferences, and outputs a preliminary set of feature entries.
[0074] Next, the service type classifier accurately classifies each feature item into one or more service types according to the standard service classification system; the feature quantifier then performs statistics and calculations on the feature items under each service type to generate quantitative indicators including but not limited to selection frequency, average rating, negative evaluation ratio, and frequency of customized requests.
[0075] Finally, the feature vector builder generates a multi-dimensional feature vector for each service type combination, where each dimension corresponds to a quantitative indicator; the standardized output interface encapsulates the feature vector sequence, or the dataset organized by user-service type matrix, into a standardized preference feature data format and transmits it to the data processing module for subsequent comparison and analysis.
[0076] Step 204: The analysis results and the preference features are compared by the multi-agent data processing module to filter out the first service type combination that meets the correlation features and the preference features. The correlation features are the correlation features between the second service type combinations in the same historical travel process extracted from the analysis results.
[0077] In this step, the association feature refers to the relationship between multiple combinations of second service types extracted from the analysis results during the same historical travel process. This feature includes the order in which the combinations appear, the frequency of pairing, and the degree of association.
[0078] The second service type combination refers to the combination of various service types that a user has encountered during the same historical trip, extracted from the analysis results and arranged in the order of their appearance.
[0079] The first service type combination refers to a combination of service types that is obtained by comparing and filtering related features and preference features, which not only conforms to the correlation patterns of users' historical travel services, but also matches users' subjective preferences.
[0080] In this embodiment of the application, step 204 specifically includes the following steps:
[0081] Step 211: Extract the associated features from the analysis results for all the same historical travel processes.
[0082] In this embodiment, the analysis results of the same historical travel process are first analyzed one by one to extract the order of occurrence and combination of each second service type combination in each group; then, the second service type combinations of all groups are summarized and analyzed to sort out the order of occurrence, combination frequency and degree of association between different combinations, and eliminate unrelated combinations; finally, the order of occurrence, combination of each second service type combination extracted above, as well as the order of occurrence, combination frequency and degree of association between combinations, are integrated to form the association features of all the same historical travel processes.
[0083] Step 212: Based on the aforementioned preference characteristics, determine the selection and combination preferences for each service type.
[0084] In this step, the selection tendency refers to the user's subjective acceptance of each service type based on preference characteristics. It is divided into two categories: preference and non-preference, and is used to determine whether the combination of the second service type matches the user's subjective preferences.
[0085] Combination tendency refers to the pattern of service type combinations that users prefer, determined based on preference characteristics and historical service combination patterns. This combination tendency includes the types and order of preferred service combinations.
[0086] In this embodiment of the application, step 212 specifically includes the following steps:
[0087] Step 221: Extract key information related to each service type from the preference features.
[0088] In this step, key information refers to the core feature information extracted from preference features that is related to each service type and can support the generation of subsequent selection patterns and the classification of selection tendencies. It is obtained based on users' subjective selection behavior and demand feedback on each service type. This information includes the frequency of users' selection of each service type, evaluation level, records of rejection selection, and details of customized needs.
[0089] In this embodiment, the preference features are first analyzed to extract key information directly related to each service type. The focus is on extracting information such as the frequency of user selection for each service type, rating level, records of rejection, and details of customized needs, while eliminating redundant content unrelated to the service type. Then, the key information is classified and labeled according to the service type to ensure that each service type has corresponding key information support.
[0090] Step 222: Based on the key information corresponding to each service type in the target business district and similar business districts, and the analysis results, generate the user's selection pattern for each service type.
[0091] In this step, the selection pattern refers to the patterns of user selection habits and preferences for each service type, which are derived from the key information and analysis results corresponding to each service type. This includes users' time preferences, frequency patterns, and related selection habits when selecting each service type, and is used to classify users' selection tendencies for each service type.
[0092] In this embodiment, key information corresponding to each service type within the target business district and similar business districts is linked and integrated with the analysis results. Combining the selection frequency and evaluation level in the key information, as well as the dwell time and occurrence frequency of the trajectory nodes corresponding to each service type in the analysis results, a comprehensive analysis is performed on each service type to generate the time pattern, selection frequency characteristics, and correlation selection habits of users in selecting this service type. The above information is integrated to form the user's selection pattern for each service type, ensuring that the selection pattern can accurately reflect the user's actual selection tendency for each service type.
[0093] Step 223: Based on the key information and selection patterns corresponding to each service type, classify users' selection tendencies for each service type, where the selection tendencies are either preferences or non-preferences.
[0094] In this embodiment, a selection preference classification standard is set based on the key information and selection patterns corresponding to each service type. The key information includes selection frequency, evaluation level, and records of rejection, while the selection patterns include selection habits. If a service type has a high selection frequency, a high evaluation level, no records of rejection, and conforms to the user's selection pattern, then the selection preference for that service type is classified as a preference. If a service type has a low selection frequency, a low evaluation level, clear records of rejection, and does not conform to the user's selection pattern, then the selection preference for that service type is classified as a non-preference. All service types are classified one by one to clarify the selection preference for each service type.
[0095] Step 224: Based on the preference characteristics, analyze all combinations of service types that the user tends to choose during the same historical travel process, and combine the second service type combinations corresponding to the same historical travel process in the analysis results to generate the combination rules of all combinations.
[0096] In this step, the combination form refers to the different combinations formed by the user's preferred service types in the order of their appearance during the same historical travel process.
[0097] Combination patterns refer to the patterns, frequency of combinations, and order of occurrence of user preferences for service types, which are derived from the analysis of all combination forms and the second service type combination in the analysis results.
[0098] In this embodiment, the user's preferred service type during the same historical travel process is first identified from the preference features. This service type is then combined into different combinations according to the travel order. The results are then combined with the second service type combination corresponding to the same historical travel process. All combinations are summarized and compared to analyze the frequency of occurrence, order of combination, and degree of correlation of each combination. Combinations with extremely low frequency or no correlation are eliminated. Finally, the core information such as the retained effective combinations, the frequency of occurrence, order of combination, and degree of correlation of each effective combination are classified and integrated to form a combination pattern that reflects the user's preferences and to clarify the user's commonly used preference combination patterns.
[0099] Step 225: Based on the combination patterns of all combination forms and the multi-service linkage needs of the target business district, determine the combination tendency of each service type.
[0100] In this step, the demand for multi-service linkage refers to the need for coordinated provision and seamless connection of various services within the target business district. This demand includes the rationality of the service combination and the feasibility of the execution sequence.
[0101] Combination preference refers to the preference and priority of each service type to other service types, determined based on combination rules and the need for multi-service linkage.
[0102] In this embodiment of the application, based on the combination rules of all combination forms, it is clear which service types are usually paired with each service type, the priority and order of the pairing, and then combined with the multi-service linkage needs of the target business district, the rationality and feasibility of each pairing combination are judged, and the pairing relationship that does not meet the linkage needs of the business district is eliminated. Finally, the combination tendency of each service type is determined to clarify which service types are suitable for pairing and the priority order of pairing.
[0103] Step 213: Establish comparison rules based on the multi-service linkage needs of the target business district.
[0104] In this step, the comparison rules refer to the rules set based on the multi-service linkage needs of the target business district, combined with the associated features, selection preferences, and combination preferences. These comparison rules include the standards for matching associated features, the standards for meeting selection preferences, and the standards for matching combination preferences. They are used to standardize the comparison process between the analysis results and the preference features, and to ensure that the selected first service type combination meets the needs of the business district and the user preferences.
[0105] In this embodiment, the multi-service linkage requirements of the target business district are first clarified. These requirements include the rationality of the service combination, the feasibility of the execution order, and the correlation of service locations. Then, based on the core requirements of the association features, the selection and combination tendencies of each service type, the specific content of the comparison rules is set. It is clarified that the second service type combination must simultaneously meet the conditions of association feature matching, the selection tendency of each service type being a preference, matching the combination tendency, and conforming to the multi-service linkage requirements of the business district in order to be selected as the first service type combination. The rule content is refined and standardized to form an executable comparison rule.
[0106] Step 214: According to the comparison rules, compare the second service type combination corresponding to the associated features with the selection tendency and combination tendency of each service type, and take the second service type combination with the selection tendency of each service type as a preference and the combination tendency as the first service type combination.
[0107] In this embodiment, firstly, all second service type combinations corresponding to the associated features are extracted. Then, according to the set comparison rules, each second service type combination is compared with the selection tendency and combination tendency of each service type one by one. It is determined whether the selection tendency of each service type in the combination is a preference, whether the combination as a whole matches the combination tendency of each service type, and whether it meets the multi-service linkage needs of the target business district. Finally, all second service type combinations that meet the comparison rules are selected and determined as the first service type combination, ensuring that the first service type combination not only conforms to the service association pattern of the user's historical travel, but also fits the user's subjective preferences and the service linkage needs of the business district.
[0108] The exemplary structure type and structure design of the data processing module are as follows: The data processing module adopts a comparison and filtering core structure, which mainly includes an association extraction unit, a tendency determination unit, a rule establishment unit, a comparison and filtering unit, and a combined output unit.
[0109] The association extraction unit is responsible for extracting association features and corresponding second service type combinations from the analysis results; the tendency determination unit is responsible for executing step 212; the rule establishment unit is responsible for establishing standardized comparison rules based on the multi-service linkage needs of the target business district; the comparison and screening unit is responsible for comparing the second service type combinations with the selection tendency and combination tendency one by one according to the comparison rules, and screening the combinations that meet the requirements; the combination output unit is responsible for determining the screened combinations as the first service type combinations and transmitting them to the task orchestration module.
[0110] Step 205: Based on the distribution of open service points within the target business district, the first service type combination is associated and matched with the corresponding service points according to the order of service links in the user's historical travel process through the multi-agent task orchestration module to generate the first task sequence.
[0111] In this step, the distribution of open service points refers to the spatial layout and supporting attributes of service points that are in normal operation within the target business district, based on the business format planning of the target business district, the geographic location information of the service points, and actual operation data.
[0112] This distribution includes the specific geographical coordinates of each open service point, the floor and zone location of the business district where it is located, the service type corresponding to each service point, the spatial distribution density of service points of different service types, the relative positional relationship between service points of the same type and different types, and also covers the real-time operational capacity and service provision range of each open service point, as well as other operational attribute information related to spatial distribution matching.
[0113] The service sequence refers to the order in which users select service types during the same historical trip, which aligns with users' travel habits and service needs.
[0114] In this embodiment, the distribution of all open service points within the target business district is first obtained, clarifying the location, service type, and operational status of each service point. Then, the service sequence of the user's historical travel process is extracted through the multi-agent task orchestration module. According to this sequence, each service type in the first service type combination is matched one by one with the corresponding open service points within the target business district, prioritizing service points that are closer to the user's historical trajectory nodes and match the user's preferences. Next, each service type is associated with the matched service points, and the sequence is organized to form a first task sequence containing the service sequence, service type, and corresponding service point.
[0115] The exemplary structure type and structure design of the task orchestration module are as follows: The task orchestration module adopts a sequence generation modular structure, which mainly includes a point acquisition unit, a sequence extraction unit, an association matching unit, and a sequence generation unit;
[0116] The system comprises the following components: a service point acquisition unit, a service point database, and a sequence extraction unit. The service point acquisition unit is responsible for acquiring information on the distribution, service types, and operational status of open service points within the target business district. The sequence extraction unit is responsible for extracting the order of service steps in a user's historical travel process from the analysis results, aligning with the user's travel habits. The association matching unit is responsible for matching each service type in the first service type combination with the corresponding service point in the service point database, prioritizing points that match user preferences and historical trajectories. The sequence generation unit is responsible for organizing the service types and corresponding service points according to the service step order, generating a standardized and executable first task sequence.
[0117] The embodiments of this application realize precise task orchestration based on user behavior and preferences, providing core support for subsequent navigation path generation and service linkage execution.
[0118] Step 103: Obtain the indoor positioning information of the service points corresponding to each service link in the first task sequence, and generate the first navigation path based on the indoor positioning information using path planning technology.
[0119] In this step, indoor positioning information refers to the precise indoor positioning data corresponding to each service point within the target business district. This information includes the floor where the service point is located, the specific zone coordinates, and the relative indoor position.
[0120] The first navigation path refers to the indoor movement path generated according to the service steps of the first task sequence based on the indoor positioning information, indoor access information and path connection rules of each service point. It is used to guide users to each service point in the order of service execution and connect the service execution and navigation guidance steps.
[0121] In this embodiment of the application, the indoor positioning raw data of the service points corresponding to each service link in the first task sequence are first obtained by the indoor positioning sensing device in the target business district; then the raw positioning data is denoised and calibrated to remove redundant data with large deviations and extract the accurate indoor positioning information of each service point to ensure that the positioning information can accurately reflect the specific indoor location of the service point.
[0122] Then, in this step, based on the indoor positioning information, a first navigation path is generated using path planning technology, which may specifically include the following steps:
[0123] Step 301: Obtain the location of access nodes in the indoor area of the target business district and the connectivity between each access node to form basic information.
[0124] In this step, access nodes refer to key points in the indoor area of the target business district that connect different areas and allow users to pass through. These access nodes include indoor stairwells, elevator entrances, corridor intersections, and passageway turning points.
[0125] The location of each access node refers to its precise indoor coordinates, floor level, and zone information. Connectivity refers to the passability status and connection method between access nodes, which can be direct connection, connection via corridor, bidirectional passage, or one-way passage.
[0126] Basic information refers to the basic indoor access data formed by integrating the locations and connectivity of all access nodes.
[0127] In this embodiment, a comprehensive survey of the indoor area of the target business district is first conducted to determine the specific location of each indoor access node. The precise indoor positioning coordinates, floor, and zone information of each access node are obtained through indoor positioning devices, and the location parameters of each access node are recorded one by one. Then, the actual connectivity between each access node is analyzed to determine whether any two access nodes can be directly connected, the type of connecting passage, and the direction of passage, and invalid connections that cannot be passed are eliminated. Finally, the location information of all access nodes and the analyzed connectivity are classified and integrated, and standardized by floor and zone to form complete basic information.
[0128] Step 302: Based on the correspondence between the execution order of each service link in the first task sequence and the indoor positioning information, the indoor positioning information of each service point is associated and matched with the basic information to obtain the association and matching results between each service point and the corresponding access node.
[0129] In this step, the execution order of the service links refers to the preset execution order of each service link in the first task sequence, which is consistent with the user's historical service selection habits.
[0130] The correspondence refers to the relationship between each service link in the first task sequence and the indoor positioning information of the corresponding service point. The association matching result refers to the matching data of the access nodes, association priorities and connection channels corresponding to each service point.
[0131] In this embodiment, the execution order of each service step in the first task sequence is first clarified, and the one-to-one correspondence between each service step and the indoor positioning information of the corresponding service point is sorted out to ensure that each service step can accurately correspond to the positioning information of its service point. Then, based on the location information of all access nodes in the basic information, the indoor positioning information of each service point is compared with the location information of each access node one by one, and the indoor straight-line distance and actual passage distance between the service point and each access node are calculated. The access node that is closest to the service point and has the most convenient passage is selected as the corresponding access node of the service point. If there are multiple access nodes that are close to each other, the node that is more in line with the passage direction of the next service point is selected based on the execution order of the service steps. Finally, the access node, association priority and connection channel corresponding to each service point are recorded and integrated to form an association matching result.
[0132] Step 303: Based on the layout characteristics of the indoor areas of the target business district, establish path connection rules between adjacent service points in the first task sequence.
[0133] In this step, the layout characteristics of the indoor area refer to the spatial distribution characteristics of the target business district, including the zoning layout of each floor, the width of passageways, the distribution of obstacles, the location of elevators / stairs, and the congestion situation in popular areas.
[0134] Adjacent service points refer to the service points corresponding to two adjacent service links arranged in the execution order in the first task sequence.
[0135] Path connection rules refer to the path selection criteria between access nodes corresponding to adjacent service points, based on indoor layout characteristics. These rules include priority access channels, congested areas to avoid, and priority use rules for elevators / stairs, which are used to standardize the path connection between adjacent service points and ensure that navigation paths are convenient and reasonable.
[0136] In this embodiment, the indoor layout characteristics of the target business district are first analyzed, and the zoning of each floor, the distribution of passages, the location of obstacles, the specific distribution and operation status of elevators and stairs are sorted out. At the same time, the regular traffic congestion in popular indoor areas is recorded, and the areas to be avoided and the preferred passages are identified in the route planning. Then, combined with the execution order of each service link in the first task sequence, the specific combination of adjacent service points and the corresponding passage nodes are determined.
[0137] Then, for each pair of adjacent service points, the access nodes are configured according to the indoor layout characteristics, and path connection rules are set. Priority is given to connecting two access nodes with short distances, smooth passage, and no obstacles, avoiding congested areas and impassable sections. If adjacent service points are on different floors, the nearest elevator or staircase is selected as the connecting passage, and the usage priority of elevators / staircases is clearly defined.
[0138] Step 304: Based on the path connection rules and the association matching results, and in accordance with the execution order of each service link, use path planning technology to connect the access nodes corresponding to each service point to generate the first navigation path.
[0139] In this embodiment of the application, firstly, based on the association matching results, according to the execution order of each service link in the first task sequence, the access nodes corresponding to adjacent service points are extracted in sequence. According to the corresponding path connection rules, the optimal connection path between two access nodes is determined, and the intermediate access nodes, channel types and access directions of the path are clarified.
[0140] Then, each adjacent service point is connected to the corresponding access nodes to form a continuous indoor movement path. At the same time, the path is optimized and adjusted to eliminate redundant access nodes and detours to ensure the convenience and continuity of the path. The path is also equipped with identification information for each service point, floor switching prompts, and access node guidance information. Finally, a complete first navigation path is generated to ensure that the navigation path can accurately guide users to the next service point in the order of service steps, achieving a seamless connection between navigation guidance and service execution.
[0141] This application embodiment achieves precise connection between the navigation path and the first task sequence service links, and ensures that the first navigation path is accurate, convenient and meets the user's service execution needs. At the same time, the modular design ensures the accuracy and efficiency of path planning, fills the gap of the disconnect between traditional navigation and life services, and provides core support for users to enjoy navigation guidance and life services in sequence.
[0142] Step 104: Utilize IoT-based device collaborative control technology to construct a two-way communication channel between IoT devices within the target business district and corresponding service links.
[0143] In this step, IoT devices refer to terminal devices within the target business district that are related to various service links and have IoT access capabilities. These IoT devices include control devices, status monitoring devices, and service execution devices at service points.
[0144] A two-way communication channel refers to a communication link built on Internet of Things (IoT) technology that enables bidirectional data transmission, allowing for the issuance of commands to IoT devices and the reception of device status information.
[0145] In this embodiment of the application, step 104 specifically includes the following steps:
[0146] Step 401: Construct basic communication links between IoT devices corresponding to each service link within the target business district, and configure communication access ports and device access protocols in the basic communication links to form target communication links.
[0147] In this step, the basic communication link refers to the initial communication connection link established between IoT devices, used to achieve basic interconnection and interoperability among various IoT devices. The communication access port refers to the dedicated port allocated to each IoT device for accessing the basic communication link, ensuring the uniqueness and stability of device access.
[0148] Device access protocols refer to the standards and rules that regulate the access communication links of IoT devices. They clarify the process of device access and the format requirements for data interaction, ensuring that different types of IoT devices can access the network compatiblely.
[0149] The target communication link refers to a standardized communication link formed by configuring access ports and access protocols on the basis of the basic communication link, which has the ability to enable device-compatible access and basic data transmission.
[0150] In this embodiment, the type, communication parameters, installation location, and corresponding service links of the IoT devices for each service link are first defined; then, based on IoT-based device collaborative control technology, a basic communication link covering the entire target business district is built according to the installation location and communication parameters of the IoT devices; then, wireless communication is used to achieve preliminary interconnection and interoperability of each IoT device, ensuring that the basic link can cover all relevant IoT devices.
[0151] Subsequently, a dedicated communication access port is assigned to each IoT device, and the correspondence between each device and the access port is recorded to avoid port conflicts. At the same time, a unified device access protocol is configured to standardize the access process, data interaction format, and identity authentication requirements of each device, ensuring that IoT devices of different types and brands can be compatible with the basic communication link. Finally, the access port and access protocol configuration information are integrated, and the basic communication link is optimized and debugged to solve problems such as unstable device access and abnormal data transmission, forming a standardized target communication link.
[0152] Step 402: Based on the target communication link, allocate communication access nodes to the IoT devices corresponding to each service link in the first task sequence.
[0153] In this step, the communication access node refers to the core node in the target communication link used to receive IoT device access requests and forward device data. It is equivalent to a relay station in the communication link and is responsible for coordinating the data transmission of devices in the corresponding area or service link.
[0154] The IoT devices corresponding to each service link in the first task sequence refer to the IoT devices directly related to each service link in the first task sequence, which are used to execute the service tasks of that service link and provide feedback on service status information.
[0155] Assigning communication access nodes refers to assigning dedicated communication access nodes to each IoT device based on its distribution location and corresponding service links.
[0156] In this embodiment of the application, the IoT devices corresponding to each service link in the first task sequence are first analyzed. The distribution location and communication requirements of each device are determined by combining the information of the IoT devices. At the same time, the coverage of the access nodes in the target communication link information is combined to initially match the candidate communication access nodes that each device can access.
[0157] Subsequently, based on the distribution location of the devices, the corresponding service links, and the coverage and data processing capabilities of the access nodes in the target communication link information, corresponding communication access nodes are assigned to each IoT device. Priority is given to assigning the same or adjacent communication access nodes to IoT devices in the same service link and the same area, which facilitates centralized management and data aggregation of devices in the same service link. In particular, the allocation process needs to reasonably allocate the number of devices to access based on the load of each communication access node in the target communication link information, so as to avoid problems such as data transmission delay and loss due to excessive load of a single node, and ensure that the load of each access node is balanced after allocation, so as to ensure the transmission stability of the target communication link. Finally, communication access nodes are assigned to the IoT devices corresponding to each service link in the first task sequence.
[0158] Next, based on the load status of each communication access node in the target communication link information, the number of devices connected is reasonably allocated to avoid problems such as data transmission delay and loss caused by excessive load on a single node. This ensures that the load of each access node is balanced after allocation, guaranteeing the transmission stability of the target communication link. Finally, the correspondence between each IoT device and the communication access node is recorded, and an access node allocation list is generated. This list clarifies the devices and service links corresponding to each access node, ensuring that each device can stably access the target communication link through its dedicated access node. This further verifies the compatibility between the access node allocation and the target communication link, providing stable access support and a link foundation for the subsequent setting of data transmission rules and the construction of bidirectional communication channels.
[0159] Step 403: Based on the data interaction requirements between IoT devices corresponding to each service link, set the data transmission rules for bidirectional communication.
[0160] In this step, data interaction requirements refer to the data transmission requirements between IoT devices and between IoT devices and communication access nodes corresponding to each service link. These requirements include the direction of data transmission, data type, transmission frequency, transmission priority, and data security requirements.
[0161] The data transmission rules for two-way communication refer to the standards and rules that regulate two-way data transmission between IoT devices and between devices and access nodes. These rules specify the data transmission process, frequency, priority, encryption method, and exception handling mechanism.
[0162] In this embodiment of the application, the data interaction requirements between devices in each service segment and between devices in different service segments are first analyzed based on the IoT devices corresponding to each service segment in the first task sequence. The data types, transmission directions, transmission frequencies and priorities that each device needs to transmit are then clarified. For devices in the same service segment, a higher data transmission priority is set to ensure that service status information can be fed back in a timely manner and control commands can be issued quickly.
[0163] Simultaneously, considering data security requirements, data encryption transmission rules are established to encrypt transmitted data and prevent data leakage or tampering. In addition, a data transmission anomaly handling mechanism is established to clarify remedial measures for data loss, delay, and errors, ensuring the stability of data transmission. Finally, the transmission standards corresponding to all data interaction requirements are summarized and organized to form a complete set of data transmission rules for two-way communication.
[0164] Step 404: Based on the target communication link, the communication access nodes of each IoT device, and the data transmission rules, construct a two-way communication channel.
[0165] In this embodiment, the IoT-based device collaborative control technology connects each IoT device to the target communication link through an assigned communication access node. Then, according to the data transmission rules, the data transmission parameters between the device and the access node, and between the access node and the target communication link, are configured to ensure that data can be transmitted bidirectionally according to the rules. At the same time, a data relay and management mechanism is established to coordinate the uplink feedback of device data and the downlink command issuance through the communication access node, so as to realize bidirectional data interaction between IoT devices and the communication link.
[0166] Finally, the constructed communication channel was debugged, data transmission scenarios were simulated, the accuracy, efficiency and security of data transmission were tested, the channel transmission performance was optimized, and problems such as data transmission delay, loss and encryption failure were solved, ultimately forming a stable, efficient and secure two-way communication channel.
[0167] This application embodiment achieves stable interconnection and bidirectional data transmission between IoT devices corresponding to various service links within the target business district, and ensures the stability, compatibility and security of the communication channel. It can accurately meet the needs of subsequent acquisition of service status information and adjustment of task sequences, and provides reliable communication support for the linkage execution of navigation and life services.
[0168] Step 105: Obtain the service status information of each service link fed back by each IoT device through the bidirectional communication channel, and adjust the first task sequence according to the service status information to generate a second task sequence and a second navigation path.
[0169] In this step, service status information refers to data fed back by IoT devices corresponding to each service link within the target business district through a two-way communication channel, reflecting the feasibility of service execution and the operating status of the devices. This information includes the operational status of the service points, device operating parameters, service carrying capacity, and service execution progress.
[0170] Preset execution conditions refer to pre-defined standards used to determine whether a service step can be executed normally. These conditions include normal equipment operation thresholds, service capacity thresholds, and operational status requirements. An abnormal service step refers to a service step whose service status information does not meet the preset execution conditions and therefore cannot be executed normally.
[0171] The second task sequence refers to a task sequence that can be executed normally after replacing the abnormal service links in the first task sequence. It retains the execution order of the normal service links in the first task sequence, and only replaces the service points corresponding to the abnormal links, which is in line with user preferences and the actual service situation of the business district.
[0172] The second navigation path refers to a new navigation path generated based on the indoor positioning information of each service point in the second task sequence, combined with indoor basic information and path connection rules. It is used to guide users to enjoy services according to the adjusted task sequence and connect the adjusted task execution with navigation guidance.
[0173] In this embodiment, firstly, a status query command is sent to the IoT devices corresponding to each service link in the first task sequence through a bidirectional communication channel, and the raw service status data fed back by each IoT device is received. The raw data is then subjected to noise reduction and verification processing to remove abnormal and distorted redundant data, and accurate service status information corresponding to each service link is extracted to ensure that the status information accurately reflects the actual executable status of the service link. Then, "based on the service status information, the first task sequence is adjusted to generate a second task sequence and a second navigation path." This step may specifically include the following steps:
[0174] Step 501: Identify abnormal service segments in the first task sequence whose service status information does not meet the preset execution conditions.
[0175] In this embodiment, the service status information of each service link is first compared with the corresponding preset execution conditions one by one. The operation status of the service point is checked one by one to verify whether the equipment operation parameters are within the preset threshold range and whether the service carrying capacity meets the user's needs. If any indicator in the service status information of a certain service link fails to meet the preset execution conditions, the service link is determined to be an abnormal service link. The specific information of the abnormal service link is recorded, including the corresponding service type, the original service point, and the reason for the abnormality.
[0176] Step 502: Select a target service point within the target business district that is already open and whose service status information meets the normal execution conditions, and replace the service point corresponding to the abnormal service link in the first task sequence with the target service point to obtain the second task sequence.
[0177] In this step, the target service point refers to a service point within the target business district that is open, whose service status information fully meets the preset execution conditions, and that can provide the same type of service as the abnormal service point. This service point is used to replace the original service point corresponding to the abnormal service point, ensuring that the service type does not change and the service demand is not disconnected.
[0178] The second task sequence refers to the complete task sequence formed after replacing the abnormal points. It retains the user's preferred service type and execution order while ensuring that all service links can be executed normally.
[0179] In this embodiment, firstly, based on the distribution of open service points within the target business district and the service status information of each service point, candidate service points that are consistent with the service type of each abnormal service link, are in an open state, and whose service status information fully meets the preset execution conditions are selected; then, combining the execution order of abnormal service links in the first task sequence, the location of the original service point, and the user's preference characteristics, service points that are closer to the original service point, fit the user's preferences, and do not affect the execution order of other normal service links are preferentially selected from the candidate service points as the target service point corresponding to the abnormal service link.
[0180] Then, for each abnormal service step, the original service point in the first task sequence is replaced with the selected target service point. The execution order, service type and related information of all normal service steps in the original task sequence are retained, without changing the core logic of the overall task sequence. Finally, the replaced task sequence is verified to confirm that the service status of all service steps meets the preset execution conditions, the service type is consistent, the execution order is reasonable, and there are no omissions or incorrect replacements. Finally, a second task sequence that can be executed normally is formed, ensuring that the second task sequence is both in line with user preferences and adapted to the actual service situation of the business district.
[0181] Step 503: Based on the indoor positioning information of the service points corresponding to each service link in the second task sequence, and combined with the basic information of the target business district and the path connection rules, generate a second navigation path using path planning technology.
[0182] In this embodiment, firstly, the execution order of each service link and the corresponding target service point are determined according to the second task sequence; then, the accurate indoor positioning information of each target service point is obtained through indoor positioning sensing devices in the target business district, and the indoor positioning information is subjected to noise reduction and calibration processing to ensure that the positioning information can accurately reflect the specific indoor location of the target service point; subsequently, the basic information and path connection rules of the target business district are retrieved, and the indoor positioning information of each target service point is associated and matched with the access nodes in the basic information according to the execution order of each service link in the second task sequence to determine the optimal access node corresponding to each target service point.
[0183] Then, according to the path connection rules, the optimal access nodes corresponding to adjacent service links are connected in sequence to determine the optimal connection path between each optimal access node, and to clarify the intermediate access nodes, channel types and directions of the path to form a preliminary path. After that, the preliminary path is optimized and adjusted to remove redundant access nodes and detours to ensure the convenience and continuity of the path. At the same time, identification information of each target service point, floor switching prompts and access node guidance information are added to maintain consistency with the guidance standards of the first navigation path.
[0184] Finally, the optimized path data is standardized and organized to generate a second navigation path. This ensures that the second navigation path can accurately guide users to each target service point according to the service steps of the second task sequence, achieving a seamless connection between navigation guidance and the execution of adjusted life services.
[0185] The embodiments of this application realize rapid adjustment and accurate adaptation after service anomalies; it not only preserves the user's preferred service types and execution order, but also ensures the feasibility of service execution and the accuracy of navigation paths, solving the problems of linkage interruption and inability to adapt quickly after service anomalies in traditional solutions, and ensuring the stability and continuity of navigation and life service linkage execution.
[0186] Step 106: Navigation and life services are executed in conjunction with multiple agents according to the second task sequence and the second navigation path.
[0187] In this embodiment, each service segment in the second task sequence and each navigation node in the second navigation path are first associated and bound together to clarify the execution responsibilities of each functional module in the multi-agent system. For example, the trajectory navigation module is responsible for providing real-time indoor navigation guidance to users according to the second navigation path, and the service execution module is responsible for connecting to the IoT devices at the corresponding service points in the target business district according to the service segment order of the second task sequence. Then, through the collaborative interaction between the modules of the multi-agent system, the execution actions of each service segment are triggered synchronously during the navigation guidance process to achieve synchronous linkage between navigation guidance and life service execution.
[0188] Figure 3 This is a schematic diagram of a specific implementation of the intelligent agent task linkage execution system based on navigation and life services provided in this application embodiment, with reference to... Figure 3 The system may include:
[0189] The data collection module 31 is used to collect user-related data, including travel preference data and historical travel trajectory data.
[0190] The association module 32 is used to perform time-series association processing on the historical travel trajectory data using multiple agents, and generate a first task sequence by combining the travel preference data;
[0191] The generation module 33 is used to obtain the indoor positioning information of the service points corresponding to each service link in the first task sequence, and generate a first navigation path based on the indoor positioning information using path planning technology.
[0192] Module 34 is used to build a two-way communication channel between IoT devices and various service links within the target business area using IoT-based device collaborative control technology.
[0193] The adjustment module 35 is used to obtain service status information of each service link fed back by each IoT device through the bidirectional communication channel, and adjust the first task sequence and generate a second task sequence and a second navigation path according to the service status information.
[0194] The execution module 36 is used to execute navigation and life services in a coordinated manner by multiple agents according to the second task sequence and the second navigation path.
[0195] The intelligent agent task linkage execution system based on navigation and life services in this application is used to implement the aforementioned intelligent agent task linkage execution method based on navigation and life services. Therefore, the specific implementation of the intelligent agent task linkage execution system based on navigation and life services can be found in the embodiment section of the intelligent agent task linkage execution method based on navigation and life services above. The specific implementation can be referred to the description of the corresponding embodiment, and will not be repeated here.
[0196] This application also provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the steps of any of the above-described intelligent agent task linkage execution methods based on navigation and life services.
[0197] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, implements the steps of any of the above-described intelligent agent task linkage execution methods based on navigation and life services.
[0198] In one exemplary embodiment, the computer storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory, random access memory, portable hard drives, magnetic disks, or optical disks.
[0199] The embodiments of this application also provide a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps in the embodiments of the intelligent agent task linkage execution method based on navigation and life services.
[0200] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0201] The above provides a detailed description of the intelligent agent task linkage execution method and system based on navigation and life services provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.
Claims
1. A method for coordinated execution of intelligent agent tasks based on navigation and life services, characterized in that, include: Collect user-related data, including travel preference data and historical travel trajectory data; The historical travel trajectory data is processed by multiple agents to perform time-series correlation processing, and combined with the travel preference data, a first task sequence is generated; Obtain indoor positioning information of service points corresponding to each service link in the first task sequence, and generate a first navigation path based on the indoor positioning information using path planning technology; Utilize IoT-based device collaborative control technology to construct a two-way communication channel between IoT devices and corresponding service links within the target business district; The service status information of each service link fed back by each IoT device is obtained through the bidirectional communication channel, and the first task sequence is adjusted according to the service status information to generate a second task sequence and a second navigation path. Navigation and life services are executed by multiple agents in coordination according to the second task sequence and the second navigation path. Based on the indoor positioning information, a first navigation path is generated using path planning technology, including: Obtain the locations of access nodes in the indoor areas within the target business district and the connectivity between these nodes to form basic information; Based on the correspondence between the execution order of each service link in the first task sequence and the indoor positioning information, the indoor positioning information of each service point is associated and matched with the basic information to obtain the association and matching results between each service point and the corresponding access node. Based on the layout characteristics of the indoor areas of the target business district, establish path connection rules between adjacent service points in the first task sequence; Based on the path connection rules and the association matching results, and in accordance with the execution order of each service link, the access nodes corresponding to each service point are connected using path planning technology to generate the first navigation path.
2. The method according to claim 1, characterized in that, Using multi-agent processing, the historical travel trajectory data is correlated over time. Combined with the travel preference data, a first task sequence is generated, including: The multi-agent trajectory processing module extracts target trajectory data related to the target business district from the historical travel trajectory data. Based on the location information of each trajectory node in the target trajectory data and the location coverage of each service type in the target business district and similar business districts, the service type corresponding to each trajectory node in the same historical travel process is analyzed by the multi-agent point matching module to generate analysis results. The multi-agent preference parsing module extracts user preference features for each service type from the travel preference data; The multi-agent data processing module compares the analysis results with the preference features to filter out the first service type combination that meets both the correlation features and the preference features. The correlation features are the correlation features between the second service type combinations in the same historical travel process extracted from the analysis results. Based on the distribution of service points already open within the target business district, the multi-agent task orchestration module associates and matches the first service type with the corresponding service points according to the order of service steps in the user's historical travel process, generating the first task sequence.
3. The method according to claim 2, characterized in that, The analysis results and the preference features are compared to filter out a first service type combination that meets both the correlation features and the preference features, including: Extract the associated features from all the same historical travel processes from the analysis results; Based on the aforementioned preference characteristics, determine the selection and combination tendencies for each service type; Establish comparison rules based on the multi-service linkage needs of the target business district; According to the comparison rules, the second service type combination corresponding to the associated features is compared with the selection tendency and combination tendency of each service type, and the second service type combination whose selection tendency of each service type is preferred and matches the combination tendency is taken as the first service type combination.
4. The method according to claim 3, characterized in that, Based on the aforementioned preference characteristics, the selection and combination tendencies for each service type are determined, including: Extract key information related to each service type from the aforementioned preference features; Based on the key information corresponding to each service type in the target business district and similar business districts, and the analysis results, the user's selection pattern for each service type is generated; Based on the key information and selection patterns corresponding to each service type, users' selection tendencies for each service type are classified, and the selection tendencies are either preferences or non-preferences. Based on the aforementioned preference characteristics, analyze all combinations of service types that users tend to choose during the same historical travel process. Combine this with the second service type combinations corresponding to the same historical travel process in the analysis results to generate the combination rules of all combinations. Based on the combination patterns of all combination forms and the multi-service linkage needs of the target business district, the combination tendency of each service type is determined.
5. The method according to claim 1, characterized in that, Utilizing IoT-based device collaborative control technology, a two-way communication channel is constructed between IoT devices within the target business district and corresponding service links, including: Construct basic communication links between IoT devices corresponding to each service link within the target business district, and configure communication access ports and device access protocols in the basic communication links to form target communication links; Based on the target communication link, a communication access node is allocated to the IoT device corresponding to each service link in the first task sequence; Based on the data interaction requirements between IoT devices in each service segment, set data transmission rules for bidirectional communication; Based on the target communication link, the communication access nodes of each IoT device, and the data transmission rules, a two-way communication channel is constructed.
6. The method according to claim 1, characterized in that, Based on the service status information, the first task sequence is adjusted to generate a second task sequence and a second navigation path, including: Identify abnormal service segments in the first task sequence where the service status information does not meet the preset execution conditions; Select a target service point that is open within the target business district and whose service status information meets the normal execution conditions, and replace the service point corresponding to the abnormal service link in the first task sequence with the target service point to obtain the second task sequence. Based on the indoor positioning information of the service points corresponding to each service link in the second task sequence, combined with the basic information of the target business district and the path connection rules, a second navigation path is generated using path planning technology.
7. A system for coordinated execution of intelligent agent tasks based on navigation and life services, used in the method for coordinated execution of intelligent agent tasks based on navigation and life services as described in any one of claims 1 to 6, characterized in that, include: The data collection module is used to collect user-related data, including travel preference data and historical travel trajectory data. The association module is used to perform time-series association processing on the historical travel trajectory data using multiple agents, and combine it with the travel preference data to generate a first task sequence; The generation module is used to obtain indoor positioning information of service points corresponding to each service link in the first task sequence, and generate a first navigation path based on the indoor positioning information using path planning technology. The module is used to build a two-way communication channel between IoT devices and various service links within the target business area using IoT-based device collaborative control technology. The adjustment module is used to obtain service status information of each service link fed back by each IoT device through the bidirectional communication channel, and adjust the first task sequence and generate a second task sequence and a second navigation path according to the service status information. The execution module is used to execute navigation and life services in a coordinated manner by multiple agents according to the second task sequence and the second navigation path.
8. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the intelligent agent task linkage execution method based on navigation and life services as described in any one of claims 1 to 6.
9. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements the intelligent agent task linkage execution method based on navigation and life services as described in any one of claims 1 to 6.