Task scheduling method and device, storage medium and electronic equipment

Abstract

The invention provides a task scheduling method and device, a storage medium and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: constructing an ontology knowledge base of a target space; storing the ontology knowledge base in a graph database in the form of a target knowledge graph; the graph database updates the target knowledge graph along with the real-time change of the target space; according to a scheduling task, obtaining the latest updated target knowledge graph from the graph database, and determining a scheduling strategy; and scheduling a target robot in the target space to execute the scheduling task according to the scheduling strategy. A graph database is combined with a knowledge graph to store an ontology knowledge base, and a data set with a complex relation is efficiently expressed and queried. Complex relations and attributes between entities are expressed by utilizing the knowledge graph, so that data are not only isolated records, but are connected with semantic meanings.

Description

Background Art

[0002] With the continuous development of artificial intelligence technology, embodied intelligence has become one of the hot research directions. Embodied intelligence emphasizes that the intelligent agent learns and adapts through interaction with the environment to achieve more efficient and intelligent behavior.

[0003] In current technologies, templates (such as classes, attributes, and instances of the ontology) are usually used to build the ontology knowledge base, and task scheduling is achieved by the collaborative work of planning agents, behavioral agents, and robot ontology. This leads to problems such as incomplete knowledge base, low efficiency of information retrieval and update, etc.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a task scheduling method and device, a storage medium and an electronic device, which at least to a certain extent overcome the problems of an imperfect knowledge base and low efficiency of information retrieval and updating due to related technologies.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a task scheduling method is provided, comprising:

[0008] Construct the ontology knowledge base of the target space;

[0009] The ontology knowledge base is stored in a graph database in the form of a target knowledge graph; the graph database updates the target knowledge graph following the real-time changes of the target space;

[0010] According to the scheduling task, the latest updated target knowledge graph is obtained from the graph database to determine the scheduling strategy;

[0011] According to the scheduling strategy, the target robot in the target space is scheduled to perform the scheduling task.

[0012] In some embodiments, constructing an ontology knowledge base of a target space includes:

[0013] The elements in the target space are converted into instances and the relationships between the instances are established to construct an ontology knowledge base of the target space.

[0014] In some embodiments, converting elements in the target space into instances and establishing relationships between the instances to construct an ontology knowledge base of the target space includes:

[0015] Define concepts based on the structure and needs of the target space;

[0016] Connecting the concepts to each other through semantic relations to determine a concept network;

[0017] Perceiving the target space and acquiring elements and environment information of the target space;

[0018] Mapping the elements and environment information of the target space to corresponding concepts in the concept network to create instances; the instances have corresponding attribute values;

[0019] Establishing a relationship between the instances according to the environment information of the target space;

[0020] An ontology knowledge base of the target space is constructed according to the instances and the relationships between the instances.

[0021] In some embodiments, the ontology knowledge base is stored in a graph database in the form of a target knowledge graph, including:

[0022] Identify instances in the ontology knowledge base as entities, and extract relations between the instances as relations between entities;

[0023] Taking the entities as points of the knowledge graph and the relationships between the entities as edges of the knowledge graph, determining a target knowledge graph;

[0024] Establish spatial indexes in graph databases;

[0025] The target knowledge graph is stored in the graph database using the spatial index.

[0026] In some embodiments, the graph database updates the target knowledge graph following the real-time changes of the target space, including:

[0027] sensing the target space in real time, and if elements and / or environmental information of the target space change, determining an update priority according to the elements and / or environmental information sensed in real time;

[0028] According to the update priority, the target knowledge graph in the graph database is updated.

[0029] In some embodiments, determining the update priority according to the element and / or environmental information perceived in real time includes:

[0030] Determine the scope of impact of the state change and the urgency of the change based on the elements and / or environmental information perceived in real time;

[0031] Assign weights to the impact scope of the state change and the urgency of the change to determine a priority evaluation value;

[0032] Normalizing the priority evaluation value to determine a normalized priority;

[0033] The update priority is determined according to the priority level corresponding to the specification priority.

[0034] In some embodiments, the state change impact range is calculated by weighting direct relevance, indirect relevance, criticality, and complexity;

[0035] The urgency of the change is calculated by weighting time sensitivity, demand situation, security level and business impact.

[0036] In some embodiments, according to the scheduling task, the latest updated target knowledge graph is obtained from the graph database to determine the scheduling strategy, including:

[0037] In response to receiving the scheduling task, obtaining the most recently updated target knowledge graph from the graph database using the spatial index;

[0038] According to the newly updated target knowledge graph, obtaining elements and environment information corresponding to the scheduling task;

[0039] A scheduling strategy is determined according to the elements and environmental information corresponding to the scheduling task and the performance of the target robot in the target space.

[0040] In some embodiments, according to the scheduling strategy, scheduling the target robot in the target space to perform the scheduling task includes:

[0041] Determine a scheduling instruction according to the scheduling strategy;

[0042] The scheduling instruction is sent to the target robot in the target space to control the target robot to perform the scheduling task.

[0043] In some embodiments, if an emergency occurs during the process of the target robot executing the scheduling task, the scheduling strategy is adjusted according to the emergency; the emergency includes: environmental changes in the target space and state changes of the target robot.

[0044] According to another aspect of the present disclosure, there is also provided a task scheduling device, comprising:

[0045] Ontology knowledge graph construction module, used to build the ontology knowledge base of the target space;

[0046] An ontology knowledge base storage module is used to store the ontology knowledge base in the form of a target knowledge graph in a graph database; the graph database updates the target knowledge graph following the real-time changes of the target space;

[0047] A scheduling strategy determination module is used to obtain the latest updated target knowledge graph from the graph database according to the scheduling task and determine the scheduling strategy;

[0048] The scheduling task execution module is used to schedule the target robot in the target space to execute the scheduling task according to the scheduling strategy.

[0049] According to another aspect of the present disclosure, an electronic device is also provided, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned task scheduling methods by executing the executable instructions.

[0050] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the task scheduling method described in any one of the above is implemented.

[0051] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, any one of the above-mentioned task scheduling methods is implemented.

[0052] The task scheduling method and device, storage medium and electronic device provided in the embodiments of the present disclosure include: constructing an ontology knowledge base of the target space; storing the ontology knowledge base in the form of a target knowledge graph in a graph database; the graph database updates the target knowledge graph following the real-time changes of the target space; according to the scheduling task, obtaining the latest updated target knowledge graph from the graph database to determine the scheduling strategy; according to the scheduling strategy, scheduling the target robot in the target space to perform the scheduling task. The embodiments of the present disclosure utilize a graph database in combination with a knowledge graph to store an ontology knowledge base, thereby achieving efficient representation and query of data sets with complex relationships. The knowledge graph is used to express the complex relationships and attributes between entities, so that the data is not just an isolated record, but a connection with semantic meaning. The knowledge graph, graph database and query technology are combined and applied to the ontology knowledge base. This combination allows the data model to be flexibly expanded and adjusted to adapt to changes in business needs. By building an ontology knowledge base, the effective representation and management of intelligent space environment information is realized. The information is stored in a combination of graph database and knowledge graph, which improves the efficiency of information storage and retrieval. The changes in the target space are obtained in real time to update the target knowledge graph accordingly, thereby realizing the timely update of the ontology knowledge base and enhancing the adaptability to environmental changes. The robot's work efficiency and intelligence level are improved by using the information in the ontology knowledge base to schedule the robot. The scheduling strategy can be generated according to the environmental information and the performance characteristics of the robot; and the environment and robot status changes can be monitored in real time to ensure the completion of the task and improve the level of space intelligence.

[0053] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0055] Figure 1 A schematic diagram showing the system structure of a task scheduling method in an embodiment of the present disclosure.

[0056] Figure 2 A schematic diagram of a task scheduling method in an embodiment of the present disclosure is shown.

[0057] Figure 3 A schematic diagram showing entities and their relationships in a target space of a task scheduling method in an embodiment of the present disclosure.

[0058] Figure 4 A schematic diagram of a task scheduling system in an embodiment of the present disclosure is shown.

[0059] Figure 5 A workflow diagram showing a schematic diagram of a task scheduling system in an embodiment of the present disclosure.

[0060] Figure 6 A schematic diagram of a task scheduling device in an embodiment of the present disclosure is shown.

[0061] Figure 7 A structural block diagram of a computer device for a task scheduling method in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0062] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0063] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0064] For ease of understanding, before introducing the embodiments of the present disclosure, several terms involved in the embodiments of the present disclosure are first explained as follows:

[0065] OWL (Web Ontology Language), OWL is an RDF-based language used to define vocabularies (ontologies) and describe concepts in a domain and their relationships with each other. It provides a rich vocabulary to define classes, properties, and individuals, as well as the relationships between them. OWL is divided into several versions: OWL Lite, OWL DL, and OWL Full, of which OWL DL and OWL Full provide more complex logical expression capabilities. By using OWL, developers can create detailed ontologies that describe the types of entities in a specific domain, their properties, and the relationships between them. For example, you can define an ontology about the medical field, including diseases, symptoms, treatment plans, etc., and describe the logical relationships between them.

[0066] RDF (Resource Description Framework), RDF is a framework used to describe information about network resources and the relationships between these resources. It provides a standard way to represent data and allows the data to be read and processed by machines. In RDF, data is stored in the form of subject-predicate-object, which is called a "triplet". For example, "Alice has friend Bob" can be expressed as an RDF triple (Alice, hasFriend, Bob). RDF can use a variety of syntaxes to represent data, including but not limited to Turtle, N3, XMLSyntax, JSON-LD, etc. RDF data is usually stored in a database or exchanged as files, such as RDF / XML files.

[0067] Knowledge Graph is a data structure used to represent and organize knowledge. It displays entities and their relationships in a graphical way. Knowledge graph formalizes entities (such as people, places, events, etc.) and their attributes and relationships, allowing machines to understand and process this knowledge. Knowledge graphs are widely used in many fields, including search engine optimization, natural language processing, recommendation systems, intelligent question answering, etc.

[0068] Ontology Knowledge Base is a structured information collection used to represent and organize knowledge in a specific field. It is not just a simple data storage, but a framework that defines concepts, attributes, relationships, and rules to describe entities in a certain field and their connections.

[0069] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0070] Figure 1 FIG. 2 shows an exemplary application system architecture diagram to which the task scheduling method in the embodiment of the present disclosure can be applied. Figure 1 As shown, the system architecture may include a terminal device 101 , a network 102 and a server 103 .

[0071] The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103, and can be a wired network or a wireless network.

[0072] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged through the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0073] The terminal device 101 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, etc.

[0074] Optionally, the client of the application installed in different terminal devices 101 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0075] The server 103 may be a server that provides various services, such as a background management server that provides support for the device operated by the user using the terminal device 101. The background management server may analyze and process the received request and other data, and feed back the processing results to the terminal device.

[0076] Optionally, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The terminal can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in this application.

[0077] Those skilled in the art will know that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration, and any number of terminal devices, networks and servers may be provided according to actual needs, and the embodiments of the present disclosure do not limit this.

[0078] Under the above system architecture, a task scheduling method is provided in an embodiment of the present disclosure, and the method can be executed by any electronic device with computing and processing capabilities.

[0079] In some embodiments, the task scheduling method provided in the embodiments of the present disclosure can be executed by a terminal device of the above-mentioned system architecture; in other embodiments, the task scheduling method provided in the embodiments of the present disclosure can be executed by a server in the above-mentioned system architecture; in other embodiments, the task scheduling method provided in the embodiments of the present disclosure can be implemented by the terminal device and the server in the above-mentioned system architecture through interaction.

[0080] Embodied intelligence emphasizes that intelligent agents learn and adapt through interaction with the environment to achieve more efficient and intelligent behavior. In practical applications, how to build an intelligent system that can accurately perceive and understand the environment and schedule robots to work according to environmental information is a key issue. Although some intelligent systems have been able to achieve partial environmental perception and robot scheduling functions, these systems often have the following problems: the knowledge base is not well constructed and cannot fully and accurately represent environmental information; the information storage and update methods are not efficient enough to adapt to dynamically changing environments; the robot scheduling strategy is not intelligent enough to fully utilize the robot's performance.

[0081] Figure 2 A schematic diagram of a task scheduling method in an embodiment of the present disclosure is shown. Figure 2 As shown, the task scheduling method provided in the embodiment of the present disclosure includes the following steps:

[0082] Step S202: constructing an ontology knowledge base of the target space;

[0083] Step S204: storing the ontology knowledge base in the form of a target knowledge graph in a graph database; the graph database updates the target knowledge graph following the real-time changes of the target space;

[0084] Step S206: According to the scheduling task, the latest updated target knowledge graph is obtained from the graph database to determine the scheduling strategy;

[0085] Step S208: According to the scheduling strategy, the target robot in the target space is scheduled to perform the scheduling task.

[0086] The disclosed embodiment uses a graph database combined with a knowledge graph to store an ontology knowledge base, thereby realizing efficient representation and query of data sets with complex relationships. The knowledge graph is used to express the complex relationships and attributes between entities, so that the data is not just an isolated record, but a connection with semantic meaning. The knowledge graph, graph database and query technology are combined and applied to the ontology knowledge base. This combination allows the data model to be flexibly expanded and adjusted to adapt to changes in business needs. By constructing an ontology knowledge base, effective representation and management of intelligent space environment information is realized. The information storage is carried out in a way that combines the graph database with the knowledge graph, which improves the storage and retrieval efficiency of information, and obtains the changes in the target space in real time to update the target knowledge graph accordingly, thereby realizing timely update of the ontology knowledge base and enhancing the adaptability to environmental changes. The information in the ontology knowledge base is used to schedule the robot to work, thereby improving the work efficiency and intelligence level of the robot. It can generate a scheduling strategy based on environmental information and the performance characteristics of the robot; and monitor the changes in the environment and robot status in real time to ensure the completion of the task and improve the intelligence level of the space.

[0087] In the embodiment, constructing an ontology knowledge base of the target space includes:

[0088] The elements in the target space are converted into instances and the relationships between the instances are established to build the ontology knowledge base of the target space.

[0089] The target space can be an intelligent space, which includes many elements, such as objects, robots, etc. At the same time, the intelligent space also includes environmental information. The elements in the intelligent space establish associations through environmental information. Therefore, to build an ontology knowledge base is to convert the elements in the target space into instances and establish relationships between instances; the ontology knowledge base of the target space is constructed based on the instances and the relationships between instances.

[0090] In the embodiment, elements in the target space are converted into instances and relationships between the instances are established to construct an ontology knowledge base of the target space, including:

[0091] Define concepts based on the structure and needs of the target space;

[0092] Connect concepts to each other through semantic relations and determine the concept network;

[0093] Perceive the target space and obtain the elements and environment information of the target space;

[0094] Map the elements and environmental information of the target space to the corresponding concepts in the concept network and create instances; the instances have corresponding attribute values;

[0095] Establish relationships between instances based on the environment information of the target space;

[0096] According to the relationship between instances, the ontology knowledge base of the target space is constructed.

[0097] In the embodiment, the concept system is the knowledge structure of the ontology knowledge base, and the perfect concepts are defined according to the structural characteristics and requirements of the intelligent space. Such as spatial position, object type, robot task, etc., and these concepts are interconnected through semantic relationships to form a hierarchical concept network. For example, OWL (Web Ontology Language) or RDF (Resource Description Framework) can be used to describe the ontology knowledge base. Next, environmental information is collected and sorted. The intelligent space is perceived by various sensors (such as cameras, laser radars, infrared sensors, etc.), and the elements and environmental information in the target space are obtained. For example, the element is an object, and the environmental information is the object position, shape, color, etc. Further support is obtained by manual input or interaction with other systems. Additional information, such as the function and purpose of the object, is obtained. According to the concept network system, the collected elements and environmental information are mapped to the corresponding concepts to create specific instances. For example, a red box at a specific location is identified as an instance of the concept of "box" and its corresponding attribute values ​​are assigned, such as purpose function (storable), position coordinates, color, etc. According to the actual situation in the environment, determine the relationship between different instances, such as spatial position relationship, inclusion relationship, etc., in order to improve the content of the ontology knowledge base and enhance its ability to represent the environment.

[0098] In the embodiment, the ontology knowledge base is stored in the graph database in the form of a target knowledge graph, including:

[0099] Identify instances in the ontology knowledge base as entities, and extract relationships between instances as relationships between entities;

[0100] Taking the entities shown as points of the knowledge graph and the relationships between the entities as edges of the knowledge graph, determining the target knowledge graph;

[0101] Establish spatial indexes in graph databases;

[0102] The target knowledge graph is stored in the graph database using spatial index.

[0103] In the intelligent space, based on the conceptual system of the ontology knowledge base, the instances in the ontology knowledge base are identified as entities to complete entity recognition, and the relationships between instances are extracted as relationships between entities to complete relationship extraction. The obtained entities are used as points in the knowledge graph, and the relationships between entities are used as edges in the knowledge graph. The points and edges of the knowledge graph are used to establish the target knowledge graph.

[0104] Figure 3 A schematic diagram of entities and their relationships in the target space of an embodiment of the present disclosure is shown, such as Figure 3 As shown in the figure, the target space contains rooms, objects, devices, etc. Among them, rooms have attributes such as area and purpose; objects have attributes such as type and state (such as available, occupied); devices have attributes such as function and state (such as on, off). Relationships between entities: rooms can contain objects and connect devices; devices can act on objects; objects belong to rooms; devices can detect environmental conditions (temperature, humidity, etc.); device events can be on, off, etc. According to the entities in the space and their relationships, the nodes and edges of the target knowledge graph are constructed.

[0105] Based on the knowledge graph, the most suitable graph database is used for storage to complete the storage of information such as entities and entity relationships in the ontology knowledge base, with the function of efficient update, and lay the foundation for efficient retrieval. The information is stored in a combination of graph database and knowledge graph. The knowledge graph represents entities, attributes and relationships in the form of graphs, which can effectively integrate and represent multi-source heterogeneous knowledge. The concepts, instances and relationships in the ontology knowledge base are converted into nodes and edges in the knowledge graph and stored in the graph database. The information in the knowledge graph is quickly retrieved and updated using the efficient storage and query capabilities of the graph database. At the same time, through the semantic representation capabilities of the knowledge graph, the spatial elements, attributes and their relationships are stored using the triple storage mode to better understand and process environmental information. In order to realize the rapid retrieval capability of the graph database, a spatial index is established in the graph database; so as to quickly retrieve the elements and their states in the space, improve the scheduling and query efficiency of the intelligent space; and use the spatial index to store the target knowledge graph in the graph database. For large-scale ontology knowledge bases, distributed graph database technology can be used to store the knowledge graph on multiple nodes, and indexes can be created based on the graph database to improve storage capacity and access speed.

[0106] In the embodiment, the graph database updates the target knowledge graph following the real-time changes of the target space, including:

[0107] Real-time perception of the target space. If the elements and / or environmental information of the target space change, the update priority is determined according to the elements and / or environmental information perceived in real time.

[0108] Update the target knowledge graph in the graph database according to the update priority.

[0109] Since the target space is subject to change at any time, it is necessary to monitor the changes in the target space. Specifically, various sensors are continuously used to monitor the smart space in real time and collect various data. The camera captures the visual information in the space, the laser radar obtains the three-dimensional position and shape of the object, and the infrared sensor detects the temperature of the object. These sensors collect environmental status information and update the ontology knowledge base in real time through edge computing, providing rich environmental perception input. Preprocess the various data collected by the sensor to remove noise and outliers. Use data fusion technology to integrate data from different sensors to improve the accuracy and reliability of the data. For example, combine the visual information of the camera with the depth information of the laser radar to more accurately determine the position and shape of the object. Build a deep learning network for multi-task learning such as object recognition, relationship inference, and change detection, automatically identify new scenes and tasks from the robot's work feedback, and update the knowledge base. For example, by learning images and sensor data in different scenes, the network can identify various types of objects and infer the spatial position relationship and inclusion relationship between them. Specifically, machine learning algorithms can be used to analyze the data in the knowledge graph to find potential errors and inconsistencies and correct them. At the same time, the concept system can be adjusted and expanded according to the needs of actual applications to improve the adaptability of the ontology knowledge base.

[0110] In smart spaces, due to the large number of elements and frequent state changes, the state of the space may change rapidly, or even undergo significant changes rapidly. In order to ensure the accuracy and timeliness of the spatial brain scheduling, it is necessary to ensure that the ontology knowledge base can respond to and update these dynamic changes in real time.

[0111] If the elements and / or environmental information of the target space change, the update priority is determined based on the real-time perceived elements and / or environmental information, and the target knowledge graph in the graph database is updated based on the update priority. By designing a priority-based ontology knowledge base update method and updating in order from high to low priority, the timeliness and accuracy of the brain can be guaranteed to the greatest extent.

[0112] In the embodiment, determining the update priority according to the real-time perceived elements and / or environmental information includes:

[0113] Determine the scope of impact and urgency of status changes based on real-time perceived elements and / or environmental information;

[0114] Assign weights to the scope of impact of status changes and the urgency of changes to determine priority evaluation values;

[0115] Normalize the priority evaluation values ​​and determine the standard priority;

[0116] Determine the update priority based on the priority level corresponding to the specification priority.

[0117] In the embodiment, the evaluation factors of the update priority include: the impact scope of the state change and the urgency of the change; and the impact scope of the state change and the urgency of the change are determined by the real-time perceived elements and / or environmental information.

[0118] Specifically, the evaluation factors for update priority are defined as follows: the impact scope of state change (I) and the urgency of change (U). That is, P = f(I, U), where P is the priority, I is the impact scope of change, U is the urgency of change, and f is a function that comprehensively considers these two factors.

[0119] In the embodiment, the state change impact range is calculated by weighting direct relevance, indirect relevance, criticality, and complexity.

[0120] The impact scope (I) is defined as follows:

[0121] Direct relevance refers to the number of entities directly affected by the state change; the evaluation value is recorded as: D; indirect relevance refers to the number of entities indirectly affected through a series of relationships. The evaluation value is recorded as: I d ; Criticality refers to the criticality of the affected entity, for example, changes in safety-related equipment should have a higher weight; the evaluation value is recorded as: C; Complexity refers to the complexity involved in the update process, such as the amount of data and the amount of calculation; the evaluation value is recorded as: R.

[0122] The linear weighted method is used to combine the above dimensions to calculate the evaluation value of the impact range. The corresponding weights of each dimension are recorded as: w 1 ,w 2 ,w 3 ,w 4 ; The evaluation value of the state change impact range (I) is:

[0123] I=w 1 *D+w 2 *I d +w 3 *C+w 4 *R,

[0124] Among them, w 1 +w 2 +w 3 +w4 =1; w 1 is the weight of the direct correlation degree D; w 2 Indirect correlation I d The weight of 3 is the weight of criticality C; w 4 is the weight of complexity R; * is multiplication.

[0125] In the embodiment, the urgency of the change is calculated by weighting time sensitivity, demand situation, security level and business impact. The urgency (U) is evaluated from the following four dimensions by definition.

[0126] Time sensitivity refers to the update tasks that need to be completed within a specific time and the remaining time. The evaluation value is recorded as: T s ; Demand situation is the change that the user or system requires to be implemented as soon as possible. The evaluation value is recorded as: U r ; Security level refers to the criticality of the affected entity, for example, changes in security-related equipment should have a higher weight. The evaluation value is recorded as: S; Business impact refers to the complexity involved in the update process, such as the amount of data and the amount of calculation. The evaluation value is recorded as: B.

[0127] The linear weighted method is used to combine the above dimensions to calculate the evaluation value of the urgency. The corresponding weights of each dimension are recorded as: v 1 ,v 2 ,v 3 ,v 4 ; Then the evaluation value of the change urgency (U) is:

[0128] U=v 1 *T s +v 2 *U r +v 3 *S+v 4 *B,

[0129] where v 1 +v 2 +v 3 +v 4 =1;v 1 is the time sensitivity T s The weight of v 2 For demand situation U r The weight of v 3 is the weight of security level S; v 4 is the weight of business impact B.

[0130] In the embodiment, weights are assigned to the impact scope of the state change and the urgency of the change to determine the priority evaluation value, including:

[0131] According to the defined evaluation dimensions and their evaluation values, weights α and β are assigned respectively, α+β=1, which is used to define the relative importance of the two impact dimensions in the total priority evaluation value. They can be adjusted according to actual conditions. Determine the priority evaluation value and express it as follows:

[0132] P=f(I,U)=α*I+β*U

[0133] =α*(w 1 *D+w 2 *I d +w 3 *C+w 4 *R)

[0134] +β*(v 1 *T s +v 2 *U r +v 3 *S+v 4 *B)

[0135] Among them, P is the priority evaluation value; α is the weight of the impact range I of the state change; β is the weight of the change urgency U.

[0136] In the embodiment, the priority evaluation value is normalized to determine the normalized priority, including:

[0137] In order to ensure that the calculated priority value is within a reasonable range, the interval of 0 to 100 can be used, and the minimum-maximum normalization technology can be used to normalize the limited evaluation value; specifically, the update priority is determined and expressed as follows:

[0138]

[0139] Among them, P norm is the normative priority; P is the priority evaluation value; P min is the minimum value under the restricted evaluation value; P max It is the maximum value under the restricted evaluation value.

[0140] Set the priority threshold according to the actual needs. For example, set the priority level to high, medium, and low. norm Scores above 90 are high priority, scores between 80 and 90 are medium priority, and scores below 80 are low priority.

[0141] Due to the dynamic characteristics of smart space, the above weights and parameters should have a certain degree of flexibility and be able to make appropriate dynamic adjustments and optimizations according to actual conditions during operation. Feedback tuning can be performed based on the actual operation of the spatial brain, and the system can automatically learn and optimize these parameters through machine learning algorithms, thereby improving the accuracy of decision-making.

[0142] In the embodiment, according to the scheduling task, the latest updated target knowledge graph is obtained from the graph database to determine the scheduling strategy, including:

[0143] In response to receiving the scheduling task, the latest updated target knowledge graph is obtained from the graph database using the spatial index;

[0144] According to the newly updated target knowledge graph, the elements and environment information corresponding to the scheduling task are obtained;

[0145] The scheduling strategy is determined based on the elements and environmental information corresponding to the scheduling task and the performance of the target robot in the target space.

[0146] Establish an index based on the graph database itself to achieve fast retrieval of elements and their relationships. Establish a spatial index based on three-dimensional coordinates in the intelligent space to improve the retrieval efficiency of elements in the space: when receiving a robot scheduling task, obtain the task type and requirements in the scheduling task, use the spatial index to obtain the latest updated target knowledge graph from the graph database, and parse the newly updated target knowledge graph to obtain the elements and environmental information corresponding to the scheduling task; for example, if the task is to move an object, query the object's location, shape, weight and other information. Generate a scheduling algorithm based on environmental information and the performance characteristics of the robot, giving priority to task priority, spatial path and resource utilization. Formulate a reasonable scheduling strategy. For example, select a robot that is closest to the object and has sufficient load capacity to carry out the moving task, and plan the optimal path.

[0147] In an embodiment, according to a scheduling strategy, a target robot in a target space is scheduled to perform a scheduling task, including: determining a scheduling instruction according to the scheduling strategy; and sending the scheduling instruction to the target robot in the target space to control the target robot to perform the scheduling task.

[0148] After determining the scheduling strategy, a scheduling instruction corresponding to the target robot is generated according to the scheduling strategy, wherein the scheduling instruction instructs the robot to perform a corresponding action. The scheduling instruction is sent to the target robot in the target space to control the target robot to perform the scheduling task.

[0149] In the embodiment, if an emergency occurs during the execution of the scheduling task by the target robot, the scheduling strategy is adjusted according to the emergency; the emergency includes: environmental changes in the target space and state changes of the target robot.

[0150] When the robot is performing a task, it monitors the changes in the environment and the robot's status in real time. If any abnormal situation is found, such as obstacles or robot failures, the scheduling strategy will be adjusted in time to ensure the smooth completion of the task.

[0151] Figure 4 A schematic diagram of a task scheduling system according to an embodiment of the present disclosure is shown. Figure 4 As shown, the embodiment of the present disclosure also provides a task scheduling system, which mainly includes the following modules: a construction module, a storage module, a retrieval module, a perception module, an update module and a scheduling module.

[0152] The construction module realizes the construction of the ontology knowledge base; the storage module is responsible for storing information related to the ontology knowledge base; the retrieval module realizes the rapid retrieval of spatial elements; the perception module and the update module realize real-time monitoring of the intelligent space and dynamic updating of the knowledge base; the scheduling module formulates and adjusts strategies to realize the scheduling of robot tasks in the space.

[0153] Figure 5 A workflow diagram of a task scheduling system according to an embodiment of the present disclosure is shown. Figure 5 The modules shown interact with each other to form a closed loop of task scheduling based on the ontology knowledge base. When a new task comes, the system workflow is as follows:

[0154] The construction module completes the construction of the embodied intelligent ontology knowledge base, and the storage module completes the storage of the ontology knowledge base;

[0155] The perception module monitors the changes of elements and environment in the space in real time. When the information changes, the update module completes the update of the ontology knowledge base in real time.

[0156] The retrieval module retrieves the latest space status related information from the ontology knowledge base for the formulation of scheduling strategies;

[0157] The scheduling module generates the optimal scheduling strategy based on task information, robot characteristics, environmental information, etc. to execute and complete the task; and during the work process, it monitors changes in environmental status in real time to dynamically adjust the strategy to ensure efficient completion of the task.

[0158] The embodiment of the present disclosure also provides a specific design scheme of applying a task scheduling method to a factory, including:

[0159] Determine the concept system of the ontology knowledge base, including concepts such as factory layout, equipment type, product type, and robot tasks. Collect environmental information such as the location and status of equipment, the number and location of products, etc. through cameras, lidars, and infrared sensors installed throughout the factory. Convert this information into instances in the ontology knowledge base and establish relationships between instances. For example, identify a processing device at a specific location as an instance of the concept of "processing equipment" and establish a relationship with the corresponding location in the concept of "factory layout."

[0160] The information is stored in a combination of graph database and knowledge graph. Concepts, instances and relationships are converted into nodes and edges in the knowledge graph and stored in the graph database. The query language of the graph database can be used to easily perform complex queries and reasoning to obtain the required environmental information. At the same time, in order to improve storage efficiency and access speed, distributed graph database technology is used, and data compression and indexing technology are adopted.

[0161] Continuously use sensors to monitor the environment. Preprocess and fuse the data collected by the sensors, and then input them into the deep learning network for multi-task learning. When the network detects changes in the environment, such as the addition of new equipment or the change of product location, the system automatically updates the corresponding information in the knowledge graph.

[0162] When a robot receives a task request for transporting a product, it selects a suitable robot for the task based on the environmental information in the knowledge graph and the robot's performance characteristics. For example, it selects a robot that is closest to the product and has sufficient load capacity, and plans the optimal transport path. While the robot is performing the task, it monitors environmental changes and the robot's status in real time. If an obstacle is found, the system can adjust the path planning based on the feedback to ensure the smooth completion of the task.

[0163] The disclosed embodiment proposes a method for constructing, storing, updating and scheduling an ontology knowledge base that combines knowledge graphs, graph databases and spatial indexes, and updates information through sensor-based perception, data processing and multi-task learning based on deep learning networks, which improves the overall work efficiency and intelligence level of smart spaces. High efficiency is achieved: the graph database is used in combination with the knowledge graph to store the ontology knowledge base, so as to achieve efficient representation and query of data sets with complex relationships; a spatial index is established to achieve rapid retrieval of elements and their states in the space; high intelligence is achieved: the concept system of the ontology knowledge base of the smart space is constructed, and the complex relationships and attributes between entities are expressed using the knowledge graph, so that the data is not just an isolated record, but a connection with semantic meaning; and a priority-based ontology knowledge base update method is designed, and information is dynamically updated based on multi-task learning of deep learning networks, making the space more intelligent; flexibility and scalability are achieved: the knowledge graph, graph database and spatial index technology are combined and applied to the ontology knowledge base. This combination allows the data model to be flexibly expanded and adjusted to adapt to changes in business needs.

[0164] The system design architecture proposed in the disclosed embodiment utilizes the interaction between the various modules of the system to form a closed loop of task scheduling based on the ontology knowledge base. The proposed ontology knowledge base construction method defines the concept system of the ontology knowledge base, including elements such as spatial information, environmental information, objects and intelligent devices, establishes the association relationship between elements in the space, and constructs the ontology knowledge base; the proposed ontology knowledge base storage method implements the storage of the ontology knowledge base based on the graph database and knowledge graph, and combines the spatial index to achieve efficient retrieval of spatial information; the proposed priority-based ontology knowledge base update method designs a priority evaluation algorithm, and dynamically updates the ontology knowledge base through sensor-based perception, data processing and information update based on deep learning. The proposed ontology knowledge base scheduling method generates a scheduling algorithm based on environmental information and the performance characteristics of intelligent devices; and monitors the changes in the environment and robot status in real time to ensure the completion of tasks and improve the level of spatial intelligence.

[0165] With the rapid development of artificial intelligence, the application scenarios and user numbers of embodied intelligence are increasing. The embodied intelligence construction, storage, and scheduling solutions based on the local knowledge base are conducive to creating more efficient smart space applications. This method and system can be used in scenarios involving smart space. It is conducive to giving full play to the advantages of operators and developing more artificial intelligence business scenarios; it is conducive to the layout and development of related businesses in the field of artificial intelligence, and can activate businesses related to embodied intelligence applications.

[0166] It should be noted that the acquisition, storage, use, and processing of data in the technical solution disclosed in this disclosure are in compliance with the relevant provisions of national laws and regulations, and various types of data such as personal identity data, operation data, behavioral data, etc. related to individuals, customers, and groups obtained in the embodiments of this disclosure have all been authorized.

[0167] Based on the same inventive concept, the present disclosure also provides a task scheduling device, as described in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0168] Figure 6 A schematic diagram of a task scheduling device in an embodiment of the present disclosure is shown. Figure 6 As shown, the device comprises:

[0169] An ontology knowledge graph construction module 601 is used to construct an ontology knowledge base of a target space;

[0170] The ontology knowledge base storage module 602 is used to store the ontology knowledge base in the form of a target knowledge graph in a graph database; the graph database updates the target knowledge graph following the real-time changes of the target space;

[0171] The scheduling strategy determination module 603 is used to obtain the latest updated target knowledge graph from the graph database according to the scheduling task and determine the scheduling strategy;

[0172] The scheduling task execution module 604 is used to schedule the target robot in the target space to execute the scheduling task according to the scheduling strategy.

[0173] It should be noted that the above-mentioned ontology knowledge graph construction module 601, ontology knowledge base storage module 602, scheduling strategy determination module 603 and scheduling task execution module 604 correspond to S202 to S208 in the method embodiment, and the examples and application scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned method embodiment. It should be noted that the above-mentioned modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0174] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0175] Refer to the following Figure 7 An electronic device 700 according to this embodiment of the present disclosure is described. Figure 7 The electronic device 700 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0176] like Figure 7 As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include but are not limited to: at least one processing unit 710, at least one storage unit 720, and a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710).

[0177] Among them, the storage unit stores a program code, and the program code can be executed by the processing unit 710, so that the processing unit 710 executes the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 710 can execute the following steps of the above method embodiment: construct an ontology knowledge base of the target space; store the ontology knowledge base in the form of a target knowledge graph in a graph database; the graph database updates the target knowledge graph following the real-time changes of the target space; according to the scheduling task, obtain the latest updated target knowledge graph from the graph database and determine the scheduling strategy; according to the scheduling strategy, schedule the target robot in the target space to perform the scheduling task.

[0178] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 7201 and / or a cache storage unit 7202 , and may further include a read-only storage unit (ROM) 7203 .

[0179] The storage unit 720 may also include a program / utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0180] Bus 730 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0181] The electronic device 700 may also communicate with one or more external devices 740 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 750. Furthermore, the electronic device 700 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 760. As shown, the network adapter 760 communicates with other modules of the electronic device 700 via a bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0182] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0183] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer program product, which includes: a computer program, which implements the above-mentioned task scheduling method when executed by a processor.

[0184] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0185] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, 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), 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.

[0186] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0187] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0188] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0189] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0190] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0191] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0192] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A task scheduling method, characterized in that: include: Construct the ontology knowledge base of the target space; Storing the ontology knowledge base in a graph database in the form of a target knowledge graph; The graph database updates the target knowledge graph following the real-time changes of the target space; According to the scheduling task, the latest updated target knowledge graph is obtained from the graph database to determine the scheduling strategy; According to the scheduling strategy, the target robot in the target space is scheduled to perform the scheduling task.

2. The task scheduling method according to claim 1, characterized in that: Construct the ontology knowledge base of the target space, including: The elements in the target space are converted into instances and the relationships between the instances are established to construct an ontology knowledge base of the target space.

3. The task scheduling method according to claim 2, characterized in that: The elements in the target space are converted into instances and the relationships between the instances are established to construct an ontology knowledge base of the target space, including: Define concepts based on the structure and needs of the target space; Connecting the concepts to each other through semantic relations to determine a concept network; Perceiving the target space and acquiring elements and environment information of the target space; Mapping the elements and environment information of the target space to corresponding concepts in the concept network to create instances; the instances have corresponding attribute values; Establishing a relationship between the instances according to the environment information of the target space; An ontology knowledge base of the target space is constructed according to the instances and the relationships between the instances.

4. The task scheduling method according to claim 3, characterized in that: The ontology knowledge base is stored in the graph database in the form of a target knowledge graph, including: Identify instances in the ontology knowledge base as entities, and extract relations between the instances as relations between entities; Taking the entities as points of the knowledge graph and the relationships between the entities as edges of the knowledge graph, determining a target knowledge graph; Establish spatial indexes in graph databases; The target knowledge graph is stored in the graph database using the spatial index.

5. The task scheduling method according to claim 1, characterized in that: The graph database updates the target knowledge graph following the real-time changes of the target space, including: sensing the target space in real time, and if elements and / or environmental information of the target space change, determining an update priority according to the elements and / or environmental information sensed in real time; According to the update priority, the target knowledge graph in the graph database is updated.

6. The task scheduling method according to claim 5, characterized in that: Determine the update priority according to the elements and / or environmental information perceived in real time, including: Determine the scope of impact of the state change and the urgency of the change based on the elements and / or environmental information perceived in real time; Assign weights to the impact scope of the state change and the urgency of the change to determine a priority evaluation value; Normalizing the priority evaluation value to determine a normalized priority; The update priority is determined according to the priority level corresponding to the specification priority.

7. The task scheduling method according to claim 6, characterized in that: The state change impact range is calculated by weighting direct relevance, indirect relevance, criticality, and complexity; The urgency of the change is calculated by weighting time sensitivity, demand situation, security level and business impact.

8. The task scheduling method according to claim 4, characterized in that: According to the scheduling task, the latest updated target knowledge graph is obtained from the graph database, and a scheduling strategy is determined, including: In response to receiving the scheduling task, obtaining the most recently updated target knowledge graph from the graph database using the spatial index; According to the newly updated target knowledge graph, obtaining elements and environment information corresponding to the scheduling task; A scheduling strategy is determined according to the elements and environmental information corresponding to the scheduling task and the performance of the target robot in the target space.

9. The task scheduling method according to claim 8, characterized in that: Scheduling the target robot in the target space to perform the scheduling task according to the scheduling strategy includes: Determine a scheduling instruction according to the scheduling strategy; The scheduling instruction is sent to the target robot in the target space to control the target robot to perform the scheduling task.

10. The task scheduling method according to claim 9, characterized in that: If an emergency occurs during the execution of the scheduling task by the target robot, the scheduling strategy is adjusted according to the emergency; the emergency includes: environmental changes in the target space and state changes of the target robot.

11. A task scheduling device, characterized in that: include: Ontology knowledge graph construction module, used to build the ontology knowledge base of the target space; An ontology knowledge base storage module is used to store the ontology knowledge base in the form of a target knowledge graph in a graph database; the graph database updates the target knowledge graph following the real-time changes of the target space; A scheduling strategy determination module is used to obtain the latest updated target knowledge graph from the graph database according to the scheduling task and determine the scheduling strategy; The scheduling task execution module is used to schedule the target robot in the target space to execute the scheduling task according to the scheduling strategy.

12. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the task scheduling method according to any one of claims 1 to 10 by executing the executable instructions.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the task scheduling method according to any one of claims 1 to 10 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the task scheduling method according to any one of claims 1 to 10 is implemented.

Images